Skip to content

Instantly share code, notes, and snippets.

@hsanchez

hsanchez/factor_analysis_composite_index.ipynb

Forked from audhiaprilliant/factor_analysis_composite_index.ipynb
Created November 9, 2022 02:48
Show Gist options
  • Save hsanchez/cc3e4c8eb310e4fe931e80f942d721fb to your computer and use it in GitHub Desktop.
Save hsanchez/cc3e4c8eb310e4fe931e80f942d721fb to your computer and use it in GitHub Desktop.
Download ZIP
Display the source blob
Display the rendered blob
Raw
factor_analysis_composite_index.ipynb
{
"cells": [
{
"cell_type": "markdown",
"id": "polyphonic-arlington",
"metadata": {},
"source": [
"# Construct an Index Using the Factor Analysis"
]
},
{
"cell_type": "markdown",
"id": "further-portfolio",
"metadata": {},
"source": [
"Learn factor analysis by directly following this [**site**](https://www.datacamp.com/community/tutorials/introduction-factor-analysis)! Medium [**article**](https://medium.com/swlh/factor-analysis-characterising-companies-based-on-financial-metrics-3d5fcc4e8b6f)"
]
},
{
"cell_type": "markdown",
"id": "detected-spice",
"metadata": {},
"source": [
"---"
]
},
{
"cell_type": "markdown",
"id": "animal-collect",
"metadata": {},
"source": [
"### Import modules"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "structural-understanding",
"metadata": {},
"outputs": [],
"source": [
"# Module for data manipulation\n",
"import pandas as pd\n",
"# Module for linear algebra calculation\n",
"import numpy as np\n",
"# Module for constructing the data\n",
"from sklearn.datasets import make_regression\n",
"# Module for factor analysis\n",
"from factor_analyzer import FactorAnalyzer\n",
"# Module for adequacy test\n",
"from factor_analyzer.factor_analyzer import calculate_bartlett_sphericity\n",
"from factor_analyzer.factor_analyzer import calculate_kmo\n",
"# Module for standardization\n",
"from sklearn.preprocessing import MinMaxScaler\n",
"# Module for data viz\n",
"from plotnine import *\n",
"import plotnine"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "attempted-definition",
"metadata": {},
"outputs": [],
"source": [
"# Functions\n",
"def highlightLoadings(x):\n",
" '''\n",
" highlight the values if they are greater than 0.5 in a Series yellow.\n",
" '''\n",
" return ['background-color: yellow' if abs(v) > 0.5 else '' for v in x]\n",
"\n",
"def highlightCommunalities(x):\n",
" '''\n",
" highlight the values if they are greater than 0.5 in a Series yellow.\n",
" '''\n",
" return ['background-color: yellow' if v > 0.5 else '' for v in x]\n",
"\n",
"def highlightEigenvalue(x):\n",
" '''\n",
" highlight the values if they are greater than 1 in a Series yellow.\n",
" '''\n",
" return ['background-color: yellow' if v > 1 else '' for v in x]"
]
},
{
"cell_type": "markdown",
"id": "further-convergence",
"metadata": {},
"source": [
"> # Simulation"
]
},
{
"cell_type": "markdown",
"id": "shared-comedy",
"metadata": {},
"source": [
"### Create a dataframe"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "willing-jacket",
"metadata": {},
"outputs": [],
"source": [
"# Create a dataframe\n",
"features, output = make_regression(n_samples = 100, n_features = 10, noise = 0.5, random_state = 1725)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "imposed-hungary",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['Column 1', 'Column 2', 'Column 3', 'Column 4', 'Column 5', 'Column 6', 'Column 7', 'Column 8', 'Column 9', 'Column 10']\n"
]
}
],
"source": [
"# Create a column's names\n",
"cols = ['Column' + ' ' + str(i + 1) for i in range(10)]\n",
"print(cols)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "perceived-defeat",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Column 1</th>\n",
" <th>Column 2</th>\n",
" <th>Column 3</th>\n",
" <th>Column 4</th>\n",
" <th>Column 5</th>\n",
" <th>Column 6</th>\n",
" <th>Column 7</th>\n",
" <th>Column 8</th>\n",
" <th>Column 9</th>\n",
" <th>Column 10</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>-0.697062</td>\n",
" <td>0.459241</td>\n",
" <td>-1.005742</td>\n",
" <td>-0.507787</td>\n",
" <td>-1.236139</td>\n",
" <td>0.688517</td>\n",
" <td>-0.588681</td>\n",
" <td>2.014447</td>\n",
" <td>1.330914</td>\n",
" <td>0.759752</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0.355132</td>\n",
" <td>0.626574</td>\n",
" <td>-0.071070</td>\n",
" <td>-0.328714</td>\n",
" <td>1.361401</td>\n",
" <td>-1.105292</td>\n",
" <td>0.514255</td>\n",
" <td>0.258649</td>\n",
" <td>1.790521</td>\n",
" <td>-0.299009</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>-1.038471</td>\n",
" <td>-0.266067</td>\n",
" <td>-0.811032</td>\n",
" <td>-0.604647</td>\n",
" <td>-0.420145</td>\n",
" <td>1.973308</td>\n",
" <td>-0.221848</td>\n",
" <td>0.255416</td>\n",
" <td>-0.538983</td>\n",
" <td>1.170527</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>-0.941241</td>\n",
" <td>0.562763</td>\n",
" <td>1.521282</td>\n",
" <td>1.342270</td>\n",
" <td>-0.404714</td>\n",
" <td>0.489614</td>\n",
" <td>0.756517</td>\n",
" <td>0.064853</td>\n",
" <td>-0.387161</td>\n",
" <td>0.785146</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>-0.287042</td>\n",
" <td>1.076180</td>\n",
" <td>0.002398</td>\n",
" <td>0.765508</td>\n",
" <td>-0.694746</td>\n",
" <td>-0.011508</td>\n",
" <td>0.887498</td>\n",
" <td>-0.269613</td>\n",
" <td>-1.272851</td>\n",
" <td>-0.043677</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Column 1 Column 2 Column 3 Column 4 Column 5 Column 6 Column 7 \\\n",
"0 -0.697062 0.459241 -1.005742 -0.507787 -1.236139 0.688517 -0.588681 \n",
"1 0.355132 0.626574 -0.071070 -0.328714 1.361401 -1.105292 0.514255 \n",
"2 -1.038471 -0.266067 -0.811032 -0.604647 -0.420145 1.973308 -0.221848 \n",
"3 -0.941241 0.562763 1.521282 1.342270 -0.404714 0.489614 0.756517 \n",
"4 -0.287042 1.076180 0.002398 0.765508 -0.694746 -0.011508 0.887498 \n",
"\n",
" Column 8 Column 9 Column 10 \n",
"0 2.014447 1.330914 0.759752 \n",
"1 0.258649 1.790521 -0.299009 \n",
"2 0.255416 -0.538983 1.170527 \n",
"3 0.064853 -0.387161 0.785146 \n",
"4 -0.269613 -1.272851 -0.043677 "
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Dataframe\n",
"df = pd.DataFrame(data = features, columns = cols)\n",
"df.head()"
]
},
{
"cell_type": "markdown",
"id": "purple-induction",
"metadata": {},
"source": [
"### Adequacy test"
]
},
{
"cell_type": "markdown",
"id": "colored-bridge",
"metadata": {},
"source": [
"#### 1 Bartlett’s test"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "lightweight-laser",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Chi-square value : 73.3\n",
"p-value : 0.001\n"
]
}
],
"source": [
"chiSquareValue, pValue = calculate_bartlett_sphericity(df)\n",
"print('Chi-square value : {}'.format(round(chiSquareValue, ndigits = 3)))\n",
"print('p-value : {}'.format(round(pValue, ndigits = 3)))"
]
},
{
"cell_type": "markdown",
"id": "pleasant-diversity",
"metadata": {},
"source": [
"#### 2 Kaiser-Meyer-Olkin test"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "coastal-instrumentation",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"KMO value : 0.407\n"
]
}
],
"source": [
"KMO, KMO_model = calculate_kmo(df)\n",
"print('KMO value : {}'.format(round(KMO_model, ndigits = 3)))"
]
},
{
"cell_type": "markdown",
"id": "gross-catalyst",
"metadata": {},
"source": [
"### Initial factor analysis"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "different-denver",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"FactorAnalyzer(n_factors=25, rotation=None, rotation_kwargs={})"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Create factor analysis object and perform factor analysis\n",
"fa = FactorAnalyzer(n_factors = 25, rotation = None)\n",
"fa.fit(df)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "afraid-adaptation",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
"#T_2ff26c74_e56c_11eb_8e72_5065f309ee96row1_col1,#T_2ff26c74_e56c_11eb_8e72_5065f309ee96row5_col1,#T_2ff26c74_e56c_11eb_8e72_5065f309ee96row8_col1,#T_2ff26c74_e56c_11eb_8e72_5065f309ee96row9_col1{\n",
" background-color: yellow;\n",
" }</style><table id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96\" ><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >Column</th> <th class=\"col_heading level0 col1\" >Communality</th> </tr></thead><tbody>\n",
" <tr>\n",
" <th id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
" <td id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96row0_col0\" class=\"data row0 col0\" >1</td>\n",
" <td id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96row0_col1\" class=\"data row0 col1\" >0.374590</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
" <td id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96row1_col0\" class=\"data row1 col0\" >2</td>\n",
" <td id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96row1_col1\" class=\"data row1 col1\" >0.529073</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
" <td id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96row2_col0\" class=\"data row2 col0\" >3</td>\n",
" <td id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96row2_col1\" class=\"data row2 col1\" >0.323547</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
" <td id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96row3_col0\" class=\"data row3 col0\" >4</td>\n",
" <td id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96row3_col1\" class=\"data row3 col1\" >0.267157</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
" <td id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96row4_col0\" class=\"data row4 col0\" >5</td>\n",
" <td id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96row4_col1\" class=\"data row4 col1\" >0.324842</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96level0_row5\" class=\"row_heading level0 row5\" >5</th>\n",
" <td id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96row5_col0\" class=\"data row5 col0\" >6</td>\n",
" <td id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96row5_col1\" class=\"data row5 col1\" >0.719005</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96level0_row6\" class=\"row_heading level0 row6\" >6</th>\n",
" <td id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96row6_col0\" class=\"data row6 col0\" >7</td>\n",
" <td id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96row6_col1\" class=\"data row6 col1\" >0.393029</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96level0_row7\" class=\"row_heading level0 row7\" >7</th>\n",
" <td id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96row7_col0\" class=\"data row7 col0\" >8</td>\n",
" <td id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96row7_col1\" class=\"data row7 col1\" >0.443964</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96level0_row8\" class=\"row_heading level0 row8\" >8</th>\n",
" <td id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96row8_col0\" class=\"data row8 col0\" >9</td>\n",
" <td id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96row8_col1\" class=\"data row8 col1\" >0.564001</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96level0_row9\" class=\"row_heading level0 row9\" >9</th>\n",
" <td id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96row9_col0\" class=\"data row9 col0\" >10</td>\n",
" <td id=\"T_2ff26c74_e56c_11eb_8e72_5065f309ee96row9_col1\" class=\"data row9 col1\" >0.727110</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x1827c587070>"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# The communalities\n",
"df_communalities = pd.DataFrame(data = {'Column': [str(i + 1) for i in range(10)], 'Communality': fa.get_communalities()})\n",
"df_communalities.style.apply(highlightCommunalities, subset = ['Communality'])"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "rapid-launch",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 800x480 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"<ggplot: (103746558055)>"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"plotnine.options.figure_size = (8, 4.8)\n",
"(\n",
" ggplot(data = df_communalities)+\n",
" geom_bar(aes(x = 'Column',\n",
" y = 'Communality'),\n",
" stat = 'identity')+\n",
" geom_hline(yintercept = 0.5)+\n",
" scale_x_discrete(limits = df_communalities['Column'].tolist())+\n",
" labs(title = 'Communalitites of factor analysis')+\n",
" xlab('Columns')+\n",
" ylab('Communalities')+\n",
" theme_minimal()\n",
")"
]
},
{
"cell_type": "markdown",
"id": "complicated-chapter",
"metadata": {},
"source": [
"### Choose the number of factors"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "lightweight-arrival",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([1.58328914, 1.35434375, 1.26875433, 1.17454385, 1.1185727 ,\n",
" 0.92121728, 0.78222803, 0.72146015, 0.65831422, 0.41727655])"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Check Eigenvalues\n",
"eigenValue, value = fa.get_eigenvalues()\n",
"eigenValue"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "functioning-custom",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
"#T_307d6a84_e56c_11eb_9efc_5065f309ee96row0_col1,#T_307d6a84_e56c_11eb_9efc_5065f309ee96row1_col1,#T_307d6a84_e56c_11eb_9efc_5065f309ee96row2_col1,#T_307d6a84_e56c_11eb_9efc_5065f309ee96row3_col1,#T_307d6a84_e56c_11eb_9efc_5065f309ee96row4_col1{\n",
" background-color: yellow;\n",
" }</style><table id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96\" ><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >Factor</th> <th class=\"col_heading level0 col1\" >Eigen value</th> </tr></thead><tbody>\n",
" <tr>\n",
" <th id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
" <td id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96row0_col0\" class=\"data row0 col0\" >1</td>\n",
" <td id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96row0_col1\" class=\"data row0 col1\" >1.583289</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
" <td id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96row1_col0\" class=\"data row1 col0\" >2</td>\n",
" <td id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96row1_col1\" class=\"data row1 col1\" >1.354344</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
" <td id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96row2_col0\" class=\"data row2 col0\" >3</td>\n",
" <td id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96row2_col1\" class=\"data row2 col1\" >1.268754</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
" <td id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96row3_col0\" class=\"data row3 col0\" >4</td>\n",
" <td id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96row3_col1\" class=\"data row3 col1\" >1.174544</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
" <td id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96row4_col0\" class=\"data row4 col0\" >5</td>\n",
" <td id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96row4_col1\" class=\"data row4 col1\" >1.118573</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96level0_row5\" class=\"row_heading level0 row5\" >5</th>\n",
" <td id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96row5_col0\" class=\"data row5 col0\" >6</td>\n",
" <td id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96row5_col1\" class=\"data row5 col1\" >0.921217</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96level0_row6\" class=\"row_heading level0 row6\" >6</th>\n",
" <td id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96row6_col0\" class=\"data row6 col0\" >7</td>\n",
" <td id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96row6_col1\" class=\"data row6 col1\" >0.782228</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96level0_row7\" class=\"row_heading level0 row7\" >7</th>\n",
" <td id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96row7_col0\" class=\"data row7 col0\" >8</td>\n",
" <td id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96row7_col1\" class=\"data row7 col1\" >0.721460</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96level0_row8\" class=\"row_heading level0 row8\" >8</th>\n",
" <td id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96row8_col0\" class=\"data row8 col0\" >9</td>\n",
" <td id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96row8_col1\" class=\"data row8 col1\" >0.658314</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96level0_row9\" class=\"row_heading level0 row9\" >9</th>\n",
" <td id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96row9_col0\" class=\"data row9 col0\" >10</td>\n",
" <td id=\"T_307d6a84_e56c_11eb_9efc_5065f309ee96row9_col1\" class=\"data row9 col1\" >0.417277</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x1827b5c6910>"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Convert the results into a dataframe\n",
"df_eigen = pd.DataFrame({'Factor': range(1, len(eigenValue) + 1), 'Eigen value': eigenValue})\n",
"df_eigen.style.apply(highlightEigenvalue, subset = ['Eigen value'])"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "eastern-practice",
"metadata": {
"scrolled": false
},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 800x480 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"<ggplot: (103746932625)>"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"plotnine.options.figure_size = (8, 4.8)\n",
"(\n",
" ggplot(data = df_eigen)+\n",
" geom_hline(yintercept = 1)+\n",
" geom_line(aes(x = 'Factor',\n",
" y = 'Eigen value'))+\n",
" geom_point(aes(x = 'Factor',\n",
" y = 'Eigen value'),\n",
" size = 2)+\n",
" geom_label(aes(x = 'Factor',\n",
" y = 'Eigen value',\n",
" label = 'Factor'),\n",
" size = 10,\n",
" nudge_y = 0.07) +\n",
" labs(title = 'Scree plot of eigen value from factor analysis')+\n",
" xlab('Factors')+\n",
" ylab('Eigenvalue')+\n",
" theme_minimal()\n",
")"
]
},
{
"cell_type": "markdown",
"id": "structured-tractor",
"metadata": {},
"source": [
"### Perform factor analysis"
]
},
{
"cell_type": "markdown",
"id": "bound-portable",
"metadata": {},
"source": [
"#### 1 Without rotation"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "unlikely-suspect",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"FactorAnalyzer(n_factors=5, rotation=None, rotation_kwargs={})"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"fa = FactorAnalyzer(n_factors = 5, rotation = None)\n",
"fa.fit(df)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "fewer-trauma",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['Factors 1', 'Factors 2', 'Factors 3', 'Factors 4', 'Factors 5']\n"
]
}
],
"source": [
"# Create a factor's names\n",
"facs = ['Factors' + ' ' + str(i + 1) for i in range(5)]\n",
"print(facs)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "running-russell",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
"#T_3129378f_e56c_11eb_a230_5065f309ee96row1_col0,#T_3129378f_e56c_11eb_a230_5065f309ee96row1_col2,#T_3129378f_e56c_11eb_a230_5065f309ee96row2_col3,#T_3129378f_e56c_11eb_a230_5065f309ee96row5_col1,#T_3129378f_e56c_11eb_a230_5065f309ee96row8_col0,#T_3129378f_e56c_11eb_a230_5065f309ee96row8_col2{\n",
" background-color: yellow;\n",
" }</style><table id=\"T_3129378f_e56c_11eb_a230_5065f309ee96\" ><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >Factors 1</th> <th class=\"col_heading level0 col1\" >Factors 2</th> <th class=\"col_heading level0 col2\" >Factors 3</th> <th class=\"col_heading level0 col3\" >Factors 4</th> <th class=\"col_heading level0 col4\" >Factors 5</th> </tr></thead><tbody>\n",
" <tr>\n",
" <th id=\"T_3129378f_e56c_11eb_a230_5065f309ee96level0_row0\" class=\"row_heading level0 row0\" >Column 1</th>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row0_col0\" class=\"data row0 col0\" >-0.026499</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row0_col1\" class=\"data row0 col1\" >-0.017275</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row0_col2\" class=\"data row0 col2\" >0.253280</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row0_col3\" class=\"data row0 col3\" >-0.009292</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row0_col4\" class=\"data row0 col4\" >-0.182496</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3129378f_e56c_11eb_a230_5065f309ee96level0_row1\" class=\"row_heading level0 row1\" >Column 2</th>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row1_col0\" class=\"data row1 col0\" >0.643712</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row1_col1\" class=\"data row1 col1\" >-0.495083</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row1_col2\" class=\"data row1 col2\" >0.508308</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row1_col3\" class=\"data row1 col3\" >0.182928</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row1_col4\" class=\"data row1 col4\" >0.209636</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3129378f_e56c_11eb_a230_5065f309ee96level0_row2\" class=\"row_heading level0 row2\" >Column 3</th>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row2_col0\" class=\"data row2 col0\" >-0.295380</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row2_col1\" class=\"data row2 col1\" >0.001251</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row2_col2\" class=\"data row2 col2\" >0.047693</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row2_col3\" class=\"data row2 col3\" >0.783351</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row2_col4\" class=\"data row2 col4\" >-0.035701</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3129378f_e56c_11eb_a230_5065f309ee96level0_row3\" class=\"row_heading level0 row3\" >Column 4</th>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row3_col0\" class=\"data row3 col0\" >-0.206686</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row3_col1\" class=\"data row3 col1\" >0.032892</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row3_col2\" class=\"data row3 col2\" >0.005789</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row3_col3\" class=\"data row3 col3\" >0.235071</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row3_col4\" class=\"data row3 col4\" >0.102755</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3129378f_e56c_11eb_a230_5065f309ee96level0_row4\" class=\"row_heading level0 row4\" >Column 5</th>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row4_col0\" class=\"data row4 col0\" >0.080732</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row4_col1\" class=\"data row4 col1\" >-0.013165</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row4_col2\" class=\"data row4 col2\" >0.069969</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row4_col3\" class=\"data row4 col3\" >-0.013437</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row4_col4\" class=\"data row4 col4\" >0.265401</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3129378f_e56c_11eb_a230_5065f309ee96level0_row5\" class=\"row_heading level0 row5\" >Column 6</th>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row5_col0\" class=\"data row5 col0\" >0.480599</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row5_col1\" class=\"data row5 col1\" >0.868042</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row5_col2\" class=\"data row5 col2\" >0.088369</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row5_col3\" class=\"data row5 col3\" >0.079708</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row5_col4\" class=\"data row5 col4\" >0.078758</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3129378f_e56c_11eb_a230_5065f309ee96level0_row6\" class=\"row_heading level0 row6\" >Column 7</th>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row6_col0\" class=\"data row6 col0\" >0.152650</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row6_col1\" class=\"data row6 col1\" >-0.245053</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row6_col2\" class=\"data row6 col2\" >-0.062942</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row6_col3\" class=\"data row6 col3\" >-0.179507</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row6_col4\" class=\"data row6 col4\" >-0.072423</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3129378f_e56c_11eb_a230_5065f309ee96level0_row7\" class=\"row_heading level0 row7\" >Column 8</th>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row7_col0\" class=\"data row7 col0\" >-0.131120</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row7_col1\" class=\"data row7 col1\" >0.151689</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row7_col2\" class=\"data row7 col2\" >0.061944</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row7_col3\" class=\"data row7 col3\" >-0.069523</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row7_col4\" class=\"data row7 col4\" >0.436576</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3129378f_e56c_11eb_a230_5065f309ee96level0_row8\" class=\"row_heading level0 row8\" >Column 9</th>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row8_col0\" class=\"data row8 col0\" >-0.551202</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row8_col1\" class=\"data row8 col1\" >0.152355</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row8_col2\" class=\"data row8 col2\" >0.790675</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row8_col3\" class=\"data row8 col3\" >-0.205840</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row8_col4\" class=\"data row8 col4\" >-0.029024</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3129378f_e56c_11eb_a230_5065f309ee96level0_row9\" class=\"row_heading level0 row9\" >Column 10</th>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row9_col0\" class=\"data row9 col0\" >0.382085</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row9_col1\" class=\"data row9 col1\" >0.132322</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row9_col2\" class=\"data row9 col2\" >0.262311</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row9_col3\" class=\"data row9 col3\" >0.077410</td>\n",
" <td id=\"T_3129378f_e56c_11eb_a230_5065f309ee96row9_col4\" class=\"data row9 col4\" >-0.356111</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x1827c68d6a0>"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Loading factors\n",
"pd.DataFrame(data = fa.loadings_, index = df.columns, columns = facs).style.apply(highlightLoadings)"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "damaged-capacity",
"metadata": {
"scrolled": false
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Factors 1</th>\n",
" <th>Factors 2</th>\n",
" <th>Factors 3</th>\n",
" <th>Factors 4</th>\n",
" <th>Factors 5</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>SS Loadings</th>\n",
" <td>1.272836</td>\n",
" <td>1.123941</td>\n",
" <td>1.039314</td>\n",
" <td>0.794399</td>\n",
" <td>0.489227</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Proportion Variance</th>\n",
" <td>0.127284</td>\n",
" <td>0.112394</td>\n",
" <td>0.103931</td>\n",
" <td>0.079440</td>\n",
" <td>0.048923</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Cumulative Variance</th>\n",
" <td>0.127284</td>\n",
" <td>0.239678</td>\n",
" <td>0.343609</td>\n",
" <td>0.423049</td>\n",
" <td>0.471972</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Factors 1 Factors 2 Factors 3 Factors 4 Factors 5\n",
"SS Loadings 1.272836 1.123941 1.039314 0.794399 0.489227\n",
"Proportion Variance 0.127284 0.112394 0.103931 0.079440 0.048923\n",
"Cumulative Variance 0.127284 0.239678 0.343609 0.423049 0.471972"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Explained variance\n",
"idx = ['SS Loadings', 'Proportion Variance', 'Cumulative Variance']\n",
"df_variance = pd.DataFrame(data = fa.get_factor_variance(), index = idx, columns = facs)\n",
"df_variance"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "proud-calvin",
"metadata": {
"scrolled": false
},
"outputs": [
{
"data": {
"text/plain": [
"(array([1.27283642, 1.12394089, 1.0393142 , 0.79439864, 0.48922663]),\n",
" array([0.12728364, 0.11239409, 0.10393142, 0.07943986, 0.04892266]),\n",
" array([0.12728364, 0.23967773, 0.34360915, 0.42304901, 0.47197168]))"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"fa.get_factor_variance()"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "featured-hometown",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Factors 1</th>\n",
" <th>Factors 2</th>\n",
" <th>Factors 3</th>\n",
" <th>Factors 4</th>\n",
" <th>Factors 5</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>Ratio Variance</th>\n",
" <td>0.269685</td>\n",
" <td>0.238137</td>\n",
" <td>0.220207</td>\n",
" <td>0.168315</td>\n",
" <td>0.103656</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Factors 1 Factors 2 Factors 3 Factors 4 Factors 5\n",
"Ratio Variance 0.269685 0.238137 0.220207 0.168315 0.103656"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Ratio of variance\n",
"ratioVariance = fa.get_factor_variance()[1] / fa.get_factor_variance()[1].sum()\n",
"df_ratio_var = pd.DataFrame(data = ratioVariance.reshape((1, 5)), index = ['Ratio Variance'], columns = facs)\n",
"df_ratio_var"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "looking-literacy",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Factors 1</th>\n",
" <th>Factors 2</th>\n",
" <th>Factors 3</th>\n",
" <th>Factors 4</th>\n",
" <th>Factors 5</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>SS Loadings</th>\n",
" <td>1.272836</td>\n",
" <td>1.123941</td>\n",
" <td>1.039314</td>\n",
" <td>0.794399</td>\n",
" <td>0.489227</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Proportion Variance</th>\n",
" <td>0.127284</td>\n",
" <td>0.112394</td>\n",
" <td>0.103931</td>\n",
" <td>0.079440</td>\n",
" <td>0.048923</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Cumulative Variance</th>\n",
" <td>0.127284</td>\n",
" <td>0.239678</td>\n",
" <td>0.343609</td>\n",
" <td>0.423049</td>\n",
" <td>0.471972</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Ratio Variance</th>\n",
" <td>0.269685</td>\n",
" <td>0.238137</td>\n",
" <td>0.220207</td>\n",
" <td>0.168315</td>\n",
" <td>0.103656</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Factors 1 Factors 2 Factors 3 Factors 4 Factors 5\n",
"SS Loadings 1.272836 1.123941 1.039314 0.794399 0.489227\n",
"Proportion Variance 0.127284 0.112394 0.103931 0.079440 0.048923\n",
"Cumulative Variance 0.127284 0.239678 0.343609 0.423049 0.471972\n",
"Ratio Variance 0.269685 0.238137 0.220207 0.168315 0.103656"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# New completed dataframe\n",
"df_variance.append(df_ratio_var)"
]
},
{
"cell_type": "markdown",
"id": "coupled-sampling",
"metadata": {},
"source": [
"#### 2 With rotation"
]
},
{
"cell_type": "code",
"execution_count": 21,
"id": "everyday-illinois",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"FactorAnalyzer(n_factors=5, rotation='varimax', rotation_kwargs={})"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"fa = FactorAnalyzer(n_factors = 5, rotation = 'varimax')\n",
"fa.fit(df)"
]
},
{
"cell_type": "code",
"execution_count": 22,
"id": "numerical-marijuana",
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['Factors 1', 'Factors 2', 'Factors 3', 'Factors 4', 'Factors 5']\n"
]
}
],
"source": [
"# Create a factor's names\n",
"facs = ['Factors' + ' ' + str(i + 1) for i in range(5)]\n",
"print(facs)"
]
},
{
"cell_type": "code",
"execution_count": 23,
"id": "clear-vegetation",
"metadata": {
"scrolled": false
},
"outputs": [
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
"#T_3203f188_e56c_11eb_a663_5065f309ee96row1_col1,#T_3203f188_e56c_11eb_a663_5065f309ee96row2_col3,#T_3203f188_e56c_11eb_a663_5065f309ee96row5_col0,#T_3203f188_e56c_11eb_a663_5065f309ee96row8_col2{\n",
" background-color: yellow;\n",
" }</style><table id=\"T_3203f188_e56c_11eb_a663_5065f309ee96\" ><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >Factors 1</th> <th class=\"col_heading level0 col1\" >Factors 2</th> <th class=\"col_heading level0 col2\" >Factors 3</th> <th class=\"col_heading level0 col3\" >Factors 4</th> <th class=\"col_heading level0 col4\" >Factors 5</th> </tr></thead><tbody>\n",
" <tr>\n",
" <th id=\"T_3203f188_e56c_11eb_a663_5065f309ee96level0_row0\" class=\"row_heading level0 row0\" >Column 1</th>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row0_col0\" class=\"data row0 col0\" >0.019434</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row0_col1\" class=\"data row0 col1\" >0.076962</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row0_col2\" class=\"data row0 col2\" >0.269297</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row0_col3\" class=\"data row0 col3\" >-0.004579</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row0_col4\" class=\"data row0 col4\" >-0.140355</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3203f188_e56c_11eb_a663_5065f309ee96level0_row1\" class=\"row_heading level0 row1\" >Column 2</th>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row1_col0\" class=\"data row1 col0\" >-0.012188</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row1_col1\" class=\"data row1 col1\" >0.989177</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row1_col2\" class=\"data row1 col2\" >0.042635</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row1_col3\" class=\"data row1 col3\" >-0.109073</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row1_col4\" class=\"data row1 col4\" >0.054085</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3203f188_e56c_11eb_a663_5065f309ee96level0_row2\" class=\"row_heading level0 row2\" >Column 3</th>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row2_col0\" class=\"data row2 col0\" >-0.041225</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row2_col1\" class=\"data row2 col1\" >0.067977</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row2_col2\" class=\"data row2 col2\" >-0.012261</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row2_col3\" class=\"data row2 col3\" >0.820945</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row2_col4\" class=\"data row2 col4\" >-0.154976</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3203f188_e56c_11eb_a663_5065f309ee96level0_row3\" class=\"row_heading level0 row3\" >Column 4</th>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row3_col0\" class=\"data row3 col0\" >-0.050081</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row3_col1\" class=\"data row3 col1\" >-0.053950</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row3_col2\" class=\"data row3 col2\" >0.012760</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row3_col3\" class=\"data row3 col3\" >0.312125</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row3_col4\" class=\"data row3 col4\" >0.081533</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3203f188_e56c_11eb_a663_5065f309ee96level0_row4\" class=\"row_heading level0 row4\" >Column 5</th>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row4_col0\" class=\"data row4 col0\" >0.024365</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row4_col1\" class=\"data row4 col1\" >0.135464</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row4_col2\" class=\"data row4 col2\" >-0.031487</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row4_col3\" class=\"data row4 col3\" >-0.012785</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row4_col4\" class=\"data row4 col4\" >0.249211</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3203f188_e56c_11eb_a663_5065f309ee96level0_row5\" class=\"row_heading level0 row5\" >Column 6</th>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row5_col0\" class=\"data row5 col0\" >0.990772</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row5_col1\" class=\"data row5 col1\" >-0.038628</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row5_col2\" class=\"data row5 col2\" >-0.069693</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row5_col3\" class=\"data row5 col3\" >-0.017637</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row5_col4\" class=\"data row5 col4\" >0.128644</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3203f188_e56c_11eb_a663_5065f309ee96level0_row6\" class=\"row_heading level0 row6\" >Column 7</th>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row6_col0\" class=\"data row6 col0\" >-0.159783</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row6_col1\" class=\"data row6 col1\" >0.118650</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row6_col2\" class=\"data row6 col2\" >-0.079723</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row6_col3\" class=\"data row6 col3\" >-0.264106</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row6_col4\" class=\"data row6 col4\" >-0.095219</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3203f188_e56c_11eb_a663_5065f309ee96level0_row7\" class=\"row_heading level0 row7\" >Column 8</th>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row7_col0\" class=\"data row7 col0\" >0.042854</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row7_col1\" class=\"data row7 col1\" >-0.069710</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row7_col2\" class=\"data row7 col2\" >0.034471</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row7_col3\" class=\"data row7 col3\" >0.064157</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row7_col4\" class=\"data row7 col4\" >0.476939</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3203f188_e56c_11eb_a663_5065f309ee96level0_row8\" class=\"row_heading level0 row8\" >Column 9</th>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row8_col0\" class=\"data row8 col0\" >-0.044232</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row8_col1\" class=\"data row8 col1\" >-0.114111</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row8_col2\" class=\"data row8 col2\" >0.961530</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row8_col3\" class=\"data row8 col3\" >0.110397</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row8_col4\" class=\"data row8 col4\" >0.209072</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3203f188_e56c_11eb_a663_5065f309ee96level0_row9\" class=\"row_heading level0 row9\" >Column 10</th>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row9_col0\" class=\"data row9 col0\" >0.368012</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row9_col1\" class=\"data row9 col1\" >0.262556</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row9_col2\" class=\"data row9 col2\" >0.149376</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row9_col3\" class=\"data row9 col3\" >-0.101297</td>\n",
" <td id=\"T_3203f188_e56c_11eb_a663_5065f309ee96row9_col4\" class=\"data row9 col4\" >-0.358008</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x1827c821f70>"
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Loading factors\n",
"pd.DataFrame(data = fa.loadings_, index = df.columns, columns = facs).style.apply(highlightLoadings)"
]
},
{
"cell_type": "code",
"execution_count": 24,
"id": "handed-saskatchewan",
"metadata": {
"scrolled": false
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Factors 1</th>\n",
" <th>Factors 2</th>\n",
" <th>Factors 3</th>\n",
" <th>Factors 4</th>\n",
" <th>Factors 5</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>SS Loadings</th>\n",
" <td>1.151712</td>\n",
" <td>1.112662</td>\n",
" <td>1.034897</td>\n",
" <td>0.880082</td>\n",
" <td>0.540363</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Proportion Variance</th>\n",
" <td>0.115171</td>\n",
" <td>0.111266</td>\n",
" <td>0.103490</td>\n",
" <td>0.088008</td>\n",
" <td>0.054036</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Cumulative Variance</th>\n",
" <td>0.115171</td>\n",
" <td>0.226437</td>\n",
" <td>0.329927</td>\n",
" <td>0.417935</td>\n",
" <td>0.471972</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Factors 1 Factors 2 Factors 3 Factors 4 Factors 5\n",
"SS Loadings 1.151712 1.112662 1.034897 0.880082 0.540363\n",
"Proportion Variance 0.115171 0.111266 0.103490 0.088008 0.054036\n",
"Cumulative Variance 0.115171 0.226437 0.329927 0.417935 0.471972"
]
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Explained variance\n",
"idx = ['SS Loadings', 'Proportion Variance', 'Cumulative Variance']\n",
"df_variance = pd.DataFrame(data = fa.get_factor_variance(), index = idx, columns = facs)\n",
"df_variance"
]
},
{
"cell_type": "code",
"execution_count": 25,
"id": "prime-honey",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"(array([1.15171229, 1.11266206, 1.03489709, 0.88008217, 0.54036316]),\n",
" array([0.11517123, 0.11126621, 0.10348971, 0.08800822, 0.05403632]),\n",
" array([0.11517123, 0.22643743, 0.32992714, 0.41793536, 0.47197168]))"
]
},
"execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"fa.get_factor_variance()"
]
},
{
"cell_type": "code",
"execution_count": 26,
"id": "micro-eagle",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Factors 1</th>\n",
" <th>Factors 2</th>\n",
" <th>Factors 3</th>\n",
" <th>Factors 4</th>\n",
" <th>Factors 5</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>Ratio Variance</th>\n",
" <td>0.244021</td>\n",
" <td>0.235748</td>\n",
" <td>0.219271</td>\n",
" <td>0.186469</td>\n",
" <td>0.114491</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Factors 1 Factors 2 Factors 3 Factors 4 Factors 5\n",
"Ratio Variance 0.244021 0.235748 0.219271 0.186469 0.114491"
]
},
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Ratio of variance\n",
"ratioVariance = fa.get_factor_variance()[1] / fa.get_factor_variance()[1].sum()\n",
"df_ratio_var = pd.DataFrame(data = ratioVariance.reshape((1, 5)), index = ['Ratio Variance'], columns = facs)\n",
"df_ratio_var"
]
},
{
"cell_type": "code",
"execution_count": 27,
"id": "ignored-rochester",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Factors 1</th>\n",
" <th>Factors 2</th>\n",
" <th>Factors 3</th>\n",
" <th>Factors 4</th>\n",
" <th>Factors 5</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>SS Loadings</th>\n",
" <td>1.151712</td>\n",
" <td>1.112662</td>\n",
" <td>1.034897</td>\n",
" <td>0.880082</td>\n",
" <td>0.540363</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Proportion Variance</th>\n",
" <td>0.115171</td>\n",
" <td>0.111266</td>\n",
" <td>0.103490</td>\n",
" <td>0.088008</td>\n",
" <td>0.054036</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Cumulative Variance</th>\n",
" <td>0.115171</td>\n",
" <td>0.226437</td>\n",
" <td>0.329927</td>\n",
" <td>0.417935</td>\n",
" <td>0.471972</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Ratio Variance</th>\n",
" <td>0.244021</td>\n",
" <td>0.235748</td>\n",
" <td>0.219271</td>\n",
" <td>0.186469</td>\n",
" <td>0.114491</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Factors 1 Factors 2 Factors 3 Factors 4 Factors 5\n",
"SS Loadings 1.151712 1.112662 1.034897 0.880082 0.540363\n",
"Proportion Variance 0.115171 0.111266 0.103490 0.088008 0.054036\n",
"Cumulative Variance 0.115171 0.226437 0.329927 0.417935 0.471972\n",
"Ratio Variance 0.244021 0.235748 0.219271 0.186469 0.114491"
]
},
"execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# New completed dataframe\n",
"df_variance.append(df_ratio_var)"
]
},
{
"cell_type": "markdown",
"id": "operational-feelings",
"metadata": {},
"source": [
"> # Factor analysis"
]
},
{
"cell_type": "markdown",
"id": "amended-courtesy",
"metadata": {},
"source": [
"### Read a dataframe"
]
},
{
"cell_type": "code",
"execution_count": 28,
"id": "charged-castle",
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_excel('datasets/3 BPS Indonesia Education Index - Processed.xlsx', engine = 'openpyxl', sheet_name = 'Data')\n",
"# Drop NaN\n",
"df.dropna(inplace = True, axis = 1)"
]
},
{
"cell_type": "code",
"execution_count": 29,
"id": "large-fisher",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Dimension of data: 34 rows and 30 columns\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Province</th>\n",
" <th>Code</th>\n",
" <th>Region</th>\n",
" <th>Population</th>\n",
" <th>HDI</th>\n",
" <th>X1</th>\n",
" <th>X2</th>\n",
" <th>X3</th>\n",
" <th>X4</th>\n",
" <th>X5</th>\n",
" <th>...</th>\n",
" <th>X16</th>\n",
" <th>X17</th>\n",
" <th>X18</th>\n",
" <th>X19</th>\n",
" <th>X20</th>\n",
" <th>X21</th>\n",
" <th>X22</th>\n",
" <th>X23</th>\n",
" <th>X24</th>\n",
" <th>X25</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>ACEH</td>\n",
" <td>11</td>\n",
" <td>West</td>\n",
" <td>5388.1</td>\n",
" <td>71.99</td>\n",
" <td>0.051321</td>\n",
" <td>0.049048</td>\n",
" <td>0.046932</td>\n",
" <td>0.040260</td>\n",
" <td>10.72</td>\n",
" <td>...</td>\n",
" <td>32.50</td>\n",
" <td>108.70</td>\n",
" <td>97.79</td>\n",
" <td>90.90</td>\n",
" <td>37.15</td>\n",
" <td>99.03</td>\n",
" <td>86.87</td>\n",
" <td>70.70</td>\n",
" <td>27.34</td>\n",
" <td>9.71</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>NORTH SUMATERA</td>\n",
" <td>12</td>\n",
" <td>West</td>\n",
" <td>14798.4</td>\n",
" <td>71.77</td>\n",
" <td>0.044705</td>\n",
" <td>0.037903</td>\n",
" <td>0.034175</td>\n",
" <td>0.038862</td>\n",
" <td>16.07</td>\n",
" <td>...</td>\n",
" <td>26.98</td>\n",
" <td>108.53</td>\n",
" <td>91.68</td>\n",
" <td>94.68</td>\n",
" <td>25.76</td>\n",
" <td>97.73</td>\n",
" <td>80.56</td>\n",
" <td>68.00</td>\n",
" <td>19.67</td>\n",
" <td>9.83</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>WEST SUMATERA</td>\n",
" <td>13</td>\n",
" <td>West</td>\n",
" <td>5545.7</td>\n",
" <td>72.38</td>\n",
" <td>0.049760</td>\n",
" <td>0.041749</td>\n",
" <td>0.035463</td>\n",
" <td>0.033911</td>\n",
" <td>13.06</td>\n",
" <td>...</td>\n",
" <td>35.96</td>\n",
" <td>108.68</td>\n",
" <td>92.33</td>\n",
" <td>90.01</td>\n",
" <td>36.56</td>\n",
" <td>98.80</td>\n",
" <td>78.41</td>\n",
" <td>68.90</td>\n",
" <td>28.55</td>\n",
" <td>9.34</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>RIAU</td>\n",
" <td>14</td>\n",
" <td>West</td>\n",
" <td>6951.2</td>\n",
" <td>72.71</td>\n",
" <td>0.041208</td>\n",
" <td>0.039844</td>\n",
" <td>0.035384</td>\n",
" <td>0.038516</td>\n",
" <td>16.84</td>\n",
" <td>...</td>\n",
" <td>28.35</td>\n",
" <td>105.89</td>\n",
" <td>94.89</td>\n",
" <td>84.61</td>\n",
" <td>28.74</td>\n",
" <td>97.73</td>\n",
" <td>80.48</td>\n",
" <td>64.01</td>\n",
" <td>23.06</td>\n",
" <td>9.47</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>JAMBI</td>\n",
" <td>15</td>\n",
" <td>West</td>\n",
" <td>3604.2</td>\n",
" <td>71.29</td>\n",
" <td>0.047939</td>\n",
" <td>0.043825</td>\n",
" <td>0.036182</td>\n",
" <td>0.039739</td>\n",
" <td>10.29</td>\n",
" <td>...</td>\n",
" <td>23.75</td>\n",
" <td>109.39</td>\n",
" <td>88.91</td>\n",
" <td>83.71</td>\n",
" <td>25.69</td>\n",
" <td>99.11</td>\n",
" <td>79.93</td>\n",
" <td>61.38</td>\n",
" <td>18.71</td>\n",
" <td>8.97</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 30 columns</p>\n",
"</div>"
],
"text/plain": [
" Province Code Region Population HDI X1 X2 \\\n",
"0 ACEH 11 West 5388.1 71.99 0.051321 0.049048 \n",
"1 NORTH SUMATERA 12 West 14798.4 71.77 0.044705 0.037903 \n",
"2 WEST SUMATERA 13 West 5545.7 72.38 0.049760 0.041749 \n",
"3 RIAU 14 West 6951.2 72.71 0.041208 0.039844 \n",
"4 JAMBI 15 West 3604.2 71.29 0.047939 0.043825 \n",
"\n",
" X3 X4 X5 ... X16 X17 X18 X19 X20 X21 \\\n",
"0 0.046932 0.040260 10.72 ... 32.50 108.70 97.79 90.90 37.15 99.03 \n",
"1 0.034175 0.038862 16.07 ... 26.98 108.53 91.68 94.68 25.76 97.73 \n",
"2 0.035463 0.033911 13.06 ... 35.96 108.68 92.33 90.01 36.56 98.80 \n",
"3 0.035384 0.038516 16.84 ... 28.35 105.89 94.89 84.61 28.74 97.73 \n",
"4 0.036182 0.039739 10.29 ... 23.75 109.39 88.91 83.71 25.69 99.11 \n",
"\n",
" X22 X23 X24 X25 \n",
"0 86.87 70.70 27.34 9.71 \n",
"1 80.56 68.00 19.67 9.83 \n",
"2 78.41 68.90 28.55 9.34 \n",
"3 80.48 64.01 23.06 9.47 \n",
"4 79.93 61.38 18.71 8.97 \n",
"\n",
"[5 rows x 30 columns]"
]
},
"execution_count": 29,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"print('Dimension of data: {} rows and {} columns'.format(len(df), len(df.columns)))\n",
"df.head()"
]
},
{
"cell_type": "markdown",
"id": "simplified-plate",
"metadata": {},
"source": [
"### Data standarization"
]
},
{
"cell_type": "code",
"execution_count": 30,
"id": "saving-range",
"metadata": {},
"outputs": [],
"source": [
"df_fix = df[[col for col in list(df.columns) if col not in ['Province', 'Code', 'Region', 'Population', 'HDI']]]"
]
},
{
"cell_type": "code",
"execution_count": 31,
"id": "composed-holder",
"metadata": {},
"outputs": [],
"source": [
"# Standardize the factors\n",
"scaler = MinMaxScaler()\n",
"df_scaled = pd.DataFrame(data = scaler.fit_transform(df_fix),\n",
" columns = df_fix.columns)"
]
},
{
"cell_type": "code",
"execution_count": 32,
"id": "aerial-straight",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>X1</th>\n",
" <th>X2</th>\n",
" <th>X3</th>\n",
" <th>X4</th>\n",
" <th>X5</th>\n",
" <th>X6</th>\n",
" <th>X7</th>\n",
" <th>X8</th>\n",
" <th>X9</th>\n",
" <th>X10</th>\n",
" <th>...</th>\n",
" <th>X16</th>\n",
" <th>X17</th>\n",
" <th>X18</th>\n",
" <th>X19</th>\n",
" <th>X20</th>\n",
" <th>X21</th>\n",
" <th>X22</th>\n",
" <th>X23</th>\n",
" <th>X24</th>\n",
" <th>X25</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.547020</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>0.454429</td>\n",
" <td>0.086659</td>\n",
" <td>0.104676</td>\n",
" <td>0.056815</td>\n",
" <td>0.150266</td>\n",
" <td>0.806622</td>\n",
" <td>0.879837</td>\n",
" <td>...</td>\n",
" <td>0.437682</td>\n",
" <td>0.787619</td>\n",
" <td>0.834383</td>\n",
" <td>0.703125</td>\n",
" <td>0.495894</td>\n",
" <td>0.972346</td>\n",
" <td>0.994967</td>\n",
" <td>0.904248</td>\n",
" <td>0.446814</td>\n",
" <td>0.653207</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0.353110</td>\n",
" <td>0.378600</td>\n",
" <td>0.197898</td>\n",
" <td>0.400034</td>\n",
" <td>0.239168</td>\n",
" <td>0.322795</td>\n",
" <td>0.432890</td>\n",
" <td>0.462434</td>\n",
" <td>0.937923</td>\n",
" <td>0.865580</td>\n",
" <td>...</td>\n",
" <td>0.276937</td>\n",
" <td>0.779937</td>\n",
" <td>0.559406</td>\n",
" <td>0.854567</td>\n",
" <td>0.267775</td>\n",
" <td>0.908148</td>\n",
" <td>0.913537</td>\n",
" <td>0.810237</td>\n",
" <td>0.242335</td>\n",
" <td>0.681710</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0.501272</td>\n",
" <td>0.593056</td>\n",
" <td>0.278911</td>\n",
" <td>0.207457</td>\n",
" <td>0.153364</td>\n",
" <td>0.274708</td>\n",
" <td>0.371905</td>\n",
" <td>0.768285</td>\n",
" <td>0.822047</td>\n",
" <td>0.754582</td>\n",
" <td>...</td>\n",
" <td>0.538439</td>\n",
" <td>0.786715</td>\n",
" <td>0.588659</td>\n",
" <td>0.667468</td>\n",
" <td>0.484078</td>\n",
" <td>0.960988</td>\n",
" <td>0.885792</td>\n",
" <td>0.841574</td>\n",
" <td>0.479072</td>\n",
" <td>0.565321</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0.250608</td>\n",
" <td>0.486813</td>\n",
" <td>0.273924</td>\n",
" <td>0.386593</td>\n",
" <td>0.261117</td>\n",
" <td>0.326514</td>\n",
" <td>0.481366</td>\n",
" <td>0.685505</td>\n",
" <td>0.846125</td>\n",
" <td>0.776986</td>\n",
" <td>...</td>\n",
" <td>0.316832</td>\n",
" <td>0.660642</td>\n",
" <td>0.703870</td>\n",
" <td>0.451122</td>\n",
" <td>0.327458</td>\n",
" <td>0.908148</td>\n",
" <td>0.912505</td>\n",
" <td>0.671309</td>\n",
" <td>0.332711</td>\n",
" <td>0.596200</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0.447906</td>\n",
" <td>0.708768</td>\n",
" <td>0.324114</td>\n",
" <td>0.434177</td>\n",
" <td>0.074401</td>\n",
" <td>0.088735</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.830700</td>\n",
" <td>0.885947</td>\n",
" <td>...</td>\n",
" <td>0.182877</td>\n",
" <td>0.818798</td>\n",
" <td>0.434743</td>\n",
" <td>0.415064</td>\n",
" <td>0.266373</td>\n",
" <td>0.976296</td>\n",
" <td>0.905407</td>\n",
" <td>0.579735</td>\n",
" <td>0.216742</td>\n",
" <td>0.477435</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 25 columns</p>\n",
"</div>"
],
"text/plain": [
" X1 X2 X3 X4 X5 X6 X7 \\\n",
"0 0.547020 1.000000 1.000000 0.454429 0.086659 0.104676 0.056815 \n",
"1 0.353110 0.378600 0.197898 0.400034 0.239168 0.322795 0.432890 \n",
"2 0.501272 0.593056 0.278911 0.207457 0.153364 0.274708 0.371905 \n",
"3 0.250608 0.486813 0.273924 0.386593 0.261117 0.326514 0.481366 \n",
"4 0.447906 0.708768 0.324114 0.434177 0.074401 0.088735 0.000000 \n",
"\n",
" X8 X9 X10 ... X16 X17 X18 X19 \\\n",
"0 0.150266 0.806622 0.879837 ... 0.437682 0.787619 0.834383 0.703125 \n",
"1 0.462434 0.937923 0.865580 ... 0.276937 0.779937 0.559406 0.854567 \n",
"2 0.768285 0.822047 0.754582 ... 0.538439 0.786715 0.588659 0.667468 \n",
"3 0.685505 0.846125 0.776986 ... 0.316832 0.660642 0.703870 0.451122 \n",
"4 0.000000 0.830700 0.885947 ... 0.182877 0.818798 0.434743 0.415064 \n",
"\n",
" X20 X21 X22 X23 X24 X25 \n",
"0 0.495894 0.972346 0.994967 0.904248 0.446814 0.653207 \n",
"1 0.267775 0.908148 0.913537 0.810237 0.242335 0.681710 \n",
"2 0.484078 0.960988 0.885792 0.841574 0.479072 0.565321 \n",
"3 0.327458 0.908148 0.912505 0.671309 0.332711 0.596200 \n",
"4 0.266373 0.976296 0.905407 0.579735 0.216742 0.477435 \n",
"\n",
"[5 rows x 25 columns]"
]
},
"execution_count": 32,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_scaled.head()"
]
},
{
"cell_type": "markdown",
"id": "perfect-harvey",
"metadata": {},
"source": [
"### Adequacy test"
]
},
{
"cell_type": "code",
"execution_count": 33,
"id": "hispanic-killer",
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"# Correlation\n",
"df_corr = df_scaled.corr()\n",
"df_scaled.to_csv('datasets/4 Data Correlation.csv', index = True)"
]
},
{
"cell_type": "markdown",
"id": "graduate-melissa",
"metadata": {},
"source": [
"#### 1 Bartlett’s test"
]
},
{
"cell_type": "code",
"execution_count": 34,
"id": "personal-pitch",
"metadata": {
"scrolled": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Chi-square value : 1045.341\n",
"p-value : 0.0\n"
]
}
],
"source": [
"chiSquareValue, pValue = calculate_bartlett_sphericity(df_scaled)\n",
"print('Chi-square value : {}'.format(round(chiSquareValue, ndigits = 3)))\n",
"print('p-value : {}'.format(round(pValue, ndigits = 3)))"
]
},
{
"cell_type": "markdown",
"id": "unavailable-manhattan",
"metadata": {},
"source": [
"#### 2 Kaiser-Meyer-Olkin test"
]
},
{
"cell_type": "code",
"execution_count": 35,
"id": "subsequent-genetics",
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"KMO value : 0.364\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\ProgramData\\Anaconda3\\lib\\site-packages\\factor_analyzer\\utils.py:248: UserWarning: The inverse of the variance-covariance matrix was calculated using the Moore-Penrose generalized matrix inversion, due to its determinant being at or very close to zero.\n"
]
}
],
"source": [
"KMO, KMO_model = calculate_kmo(df_scaled)\n",
"print('KMO value : {}'.format(round(KMO_model, ndigits = 3)))"
]
},
{
"cell_type": "markdown",
"id": "extreme-fellowship",
"metadata": {},
"source": [
"### Initial factor analysis"
]
},
{
"cell_type": "code",
"execution_count": 36,
"id": "dress-jackson",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"FactorAnalyzer(n_factors=25, rotation=None, rotation_kwargs={})"
]
},
"execution_count": 36,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Create factor analysis object and perform factor analysis\n",
"fa = FactorAnalyzer(n_factors = 25, rotation = None)\n",
"fa.fit(df_scaled)"
]
},
{
"cell_type": "code",
"execution_count": 37,
"id": "sapphire-blood",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
"#T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row0_col1,#T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row1_col1,#T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row2_col1,#T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row3_col1,#T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row4_col1,#T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row5_col1,#T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row6_col1,#T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row7_col1,#T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row8_col1,#T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row9_col1,#T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row10_col1,#T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row11_col1,#T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row12_col1,#T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row13_col1,#T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row14_col1,#T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row15_col1,#T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row16_col1,#T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row17_col1,#T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row18_col1,#T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row19_col1,#T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row20_col1,#T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row21_col1,#T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row22_col1,#T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row23_col1,#T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row24_col1{\n",
" background-color: yellow;\n",
" }</style><table id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96\" ><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >Column</th> <th class=\"col_heading level0 col1\" >Communality</th> </tr></thead><tbody>\n",
" <tr>\n",
" <th id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row0_col0\" class=\"data row0 col0\" >X1</td>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row0_col1\" class=\"data row0 col1\" >0.995006</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row1_col0\" class=\"data row1 col0\" >X2</td>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row1_col1\" class=\"data row1 col1\" >0.995029</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row2_col0\" class=\"data row2 col0\" >X3</td>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row2_col1\" class=\"data row2 col1\" >0.995004</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row3_col0\" class=\"data row3 col0\" >X4</td>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row3_col1\" class=\"data row3 col1\" >0.995007</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row4_col0\" class=\"data row4 col0\" >X5</td>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row4_col1\" class=\"data row4 col1\" >0.995109</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96level0_row5\" class=\"row_heading level0 row5\" >5</th>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row5_col0\" class=\"data row5 col0\" >X6</td>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row5_col1\" class=\"data row5 col1\" >0.995190</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96level0_row6\" class=\"row_heading level0 row6\" >6</th>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row6_col0\" class=\"data row6 col0\" >X7</td>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row6_col1\" class=\"data row6 col1\" >0.995008</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96level0_row7\" class=\"row_heading level0 row7\" >7</th>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row7_col0\" class=\"data row7 col0\" >X8</td>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row7_col1\" class=\"data row7 col1\" >0.995025</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96level0_row8\" class=\"row_heading level0 row8\" >8</th>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row8_col0\" class=\"data row8 col0\" >X9</td>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row8_col1\" class=\"data row8 col1\" >0.995053</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96level0_row9\" class=\"row_heading level0 row9\" >9</th>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row9_col0\" class=\"data row9 col0\" >X10</td>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row9_col1\" class=\"data row9 col1\" >0.995008</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96level0_row10\" class=\"row_heading level0 row10\" >10</th>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row10_col0\" class=\"data row10 col0\" >X11</td>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row10_col1\" class=\"data row10 col1\" >0.995015</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96level0_row11\" class=\"row_heading level0 row11\" >11</th>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row11_col0\" class=\"data row11 col0\" >X12</td>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row11_col1\" class=\"data row11 col1\" >0.940341</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96level0_row12\" class=\"row_heading level0 row12\" >12</th>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row12_col0\" class=\"data row12 col0\" >X13</td>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row12_col1\" class=\"data row12 col1\" >0.995336</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96level0_row13\" class=\"row_heading level0 row13\" >13</th>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row13_col0\" class=\"data row13 col0\" >X14</td>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row13_col1\" class=\"data row13 col1\" >0.995010</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96level0_row14\" class=\"row_heading level0 row14\" >14</th>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row14_col0\" class=\"data row14 col0\" >X15</td>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row14_col1\" class=\"data row14 col1\" >0.995083</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96level0_row15\" class=\"row_heading level0 row15\" >15</th>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row15_col0\" class=\"data row15 col0\" >X16</td>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row15_col1\" class=\"data row15 col1\" >0.996411</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96level0_row16\" class=\"row_heading level0 row16\" >16</th>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row16_col0\" class=\"data row16 col0\" >X17</td>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row16_col1\" class=\"data row16 col1\" >0.995040</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96level0_row17\" class=\"row_heading level0 row17\" >17</th>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row17_col0\" class=\"data row17 col0\" >X18</td>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row17_col1\" class=\"data row17 col1\" >0.995141</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96level0_row18\" class=\"row_heading level0 row18\" >18</th>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row18_col0\" class=\"data row18 col0\" >X19</td>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row18_col1\" class=\"data row18 col1\" >0.995253</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96level0_row19\" class=\"row_heading level0 row19\" >19</th>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row19_col0\" class=\"data row19 col0\" >X20</td>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row19_col1\" class=\"data row19 col1\" >0.995041</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96level0_row20\" class=\"row_heading level0 row20\" >20</th>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row20_col0\" class=\"data row20 col0\" >X21</td>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row20_col1\" class=\"data row20 col1\" >0.995032</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96level0_row21\" class=\"row_heading level0 row21\" >21</th>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row21_col0\" class=\"data row21 col0\" >X22</td>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row21_col1\" class=\"data row21 col1\" >0.995011</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96level0_row22\" class=\"row_heading level0 row22\" >22</th>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row22_col0\" class=\"data row22 col0\" >X23</td>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row22_col1\" class=\"data row22 col1\" >0.995533</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96level0_row23\" class=\"row_heading level0 row23\" >23</th>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row23_col0\" class=\"data row23 col0\" >X24</td>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row23_col1\" class=\"data row23 col1\" >0.996191</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96level0_row24\" class=\"row_heading level0 row24\" >24</th>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row24_col0\" class=\"data row24 col0\" >X25</td>\n",
" <td id=\"T_35f6e6b9_e56c_11eb_bea6_5065f309ee96row24_col1\" class=\"data row24 col1\" >0.995002</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x1827cb25b20>"
]
},
"execution_count": 37,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# The communalities\n",
"df_communalities = pd.DataFrame(data = {'Column': df_scaled.columns, 'Communality': fa.get_communalities()})\n",
"df_communalities.style.apply(highlightCommunalities, subset = ['Communality'])"
]
},
{
"cell_type": "code",
"execution_count": 38,
"id": "solar-sperm",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 1200x900 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"<ggplot: (103746863924)>"
]
},
"execution_count": 38,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Data viz\n",
"plotnine.options.figure_size = (12, 9)\n",
"communality_bar = (\n",
" ggplot(data = df_communalities)+\n",
" geom_bar(aes(x = 'Column',\n",
" y = 'Communality'),\n",
" width = 0.75,\n",
" stat = 'identity')+\n",
" geom_hline(yintercept = 0.5)+\n",
" scale_x_discrete(limits = df_communalities['Column'].tolist())+\n",
" labs(title = 'Communalitites of factor analysis')+\n",
" xlab('Columns')+\n",
" ylab('Communalities')+\n",
" theme_minimal()\n",
")\n",
"# Display the viz\n",
"communality_bar"
]
},
{
"cell_type": "code",
"execution_count": 39,
"id": "directed-glasgow",
"metadata": {},
"outputs": [],
"source": [
"# Save the graph\n",
"communality_bar.save(filename = 'img/communality_bar.png',\n",
" dpi = 1000,\n",
" verbose = False)"
]
},
{
"cell_type": "markdown",
"id": "accurate-queensland",
"metadata": {},
"source": [
"### Choose the number of factors"
]
},
{
"cell_type": "code",
"execution_count": 40,
"id": "guilty-acrobat",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([7.08937021e+00, 5.43716636e+00, 3.16822002e+00, 1.70856516e+00,\n",
" 1.54548873e+00, 1.41838147e+00, 9.61205005e-01, 8.75131668e-01,\n",
" 7.28919455e-01, 5.29027173e-01, 4.24890455e-01, 2.88490634e-01,\n",
" 2.17630337e-01, 1.49947052e-01, 1.11817362e-01, 9.55623077e-02,\n",
" 8.18211212e-02, 5.75573589e-02, 4.71429794e-02, 2.06933743e-02,\n",
" 1.63697890e-02, 1.19162444e-02, 9.10243768e-03, 4.82771425e-03,\n",
" 7.55573850e-04])"
]
},
"execution_count": 40,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Check Eigenvalues\n",
"eigenValue, value = fa.get_eigenvalues()\n",
"eigenValue"
]
},
{
"cell_type": "code",
"execution_count": 41,
"id": "distributed-moses",
"metadata": {
"scrolled": false
},
"outputs": [
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
"#T_3a383004_e56c_11eb_a92f_5065f309ee96row0_col1,#T_3a383004_e56c_11eb_a92f_5065f309ee96row1_col1,#T_3a383004_e56c_11eb_a92f_5065f309ee96row2_col1,#T_3a383004_e56c_11eb_a92f_5065f309ee96row3_col1,#T_3a383004_e56c_11eb_a92f_5065f309ee96row4_col1,#T_3a383004_e56c_11eb_a92f_5065f309ee96row5_col1{\n",
" background-color: yellow;\n",
" }</style><table id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96\" ><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >Factor</th> <th class=\"col_heading level0 col1\" >Eigen value</th> </tr></thead><tbody>\n",
" <tr>\n",
" <th id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row0_col0\" class=\"data row0 col0\" >1</td>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row0_col1\" class=\"data row0 col1\" >7.089370</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row1_col0\" class=\"data row1 col0\" >2</td>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row1_col1\" class=\"data row1 col1\" >5.437166</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row2_col0\" class=\"data row2 col0\" >3</td>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row2_col1\" class=\"data row2 col1\" >3.168220</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row3_col0\" class=\"data row3 col0\" >4</td>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row3_col1\" class=\"data row3 col1\" >1.708565</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row4_col0\" class=\"data row4 col0\" >5</td>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row4_col1\" class=\"data row4 col1\" >1.545489</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96level0_row5\" class=\"row_heading level0 row5\" >5</th>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row5_col0\" class=\"data row5 col0\" >6</td>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row5_col1\" class=\"data row5 col1\" >1.418381</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96level0_row6\" class=\"row_heading level0 row6\" >6</th>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row6_col0\" class=\"data row6 col0\" >7</td>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row6_col1\" class=\"data row6 col1\" >0.961205</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96level0_row7\" class=\"row_heading level0 row7\" >7</th>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row7_col0\" class=\"data row7 col0\" >8</td>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row7_col1\" class=\"data row7 col1\" >0.875132</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96level0_row8\" class=\"row_heading level0 row8\" >8</th>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row8_col0\" class=\"data row8 col0\" >9</td>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row8_col1\" class=\"data row8 col1\" >0.728919</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96level0_row9\" class=\"row_heading level0 row9\" >9</th>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row9_col0\" class=\"data row9 col0\" >10</td>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row9_col1\" class=\"data row9 col1\" >0.529027</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96level0_row10\" class=\"row_heading level0 row10\" >10</th>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row10_col0\" class=\"data row10 col0\" >11</td>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row10_col1\" class=\"data row10 col1\" >0.424890</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96level0_row11\" class=\"row_heading level0 row11\" >11</th>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row11_col0\" class=\"data row11 col0\" >12</td>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row11_col1\" class=\"data row11 col1\" >0.288491</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96level0_row12\" class=\"row_heading level0 row12\" >12</th>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row12_col0\" class=\"data row12 col0\" >13</td>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row12_col1\" class=\"data row12 col1\" >0.217630</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96level0_row13\" class=\"row_heading level0 row13\" >13</th>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row13_col0\" class=\"data row13 col0\" >14</td>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row13_col1\" class=\"data row13 col1\" >0.149947</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96level0_row14\" class=\"row_heading level0 row14\" >14</th>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row14_col0\" class=\"data row14 col0\" >15</td>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row14_col1\" class=\"data row14 col1\" >0.111817</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96level0_row15\" class=\"row_heading level0 row15\" >15</th>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row15_col0\" class=\"data row15 col0\" >16</td>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row15_col1\" class=\"data row15 col1\" >0.095562</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96level0_row16\" class=\"row_heading level0 row16\" >16</th>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row16_col0\" class=\"data row16 col0\" >17</td>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row16_col1\" class=\"data row16 col1\" >0.081821</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96level0_row17\" class=\"row_heading level0 row17\" >17</th>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row17_col0\" class=\"data row17 col0\" >18</td>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row17_col1\" class=\"data row17 col1\" >0.057557</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96level0_row18\" class=\"row_heading level0 row18\" >18</th>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row18_col0\" class=\"data row18 col0\" >19</td>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row18_col1\" class=\"data row18 col1\" >0.047143</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96level0_row19\" class=\"row_heading level0 row19\" >19</th>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row19_col0\" class=\"data row19 col0\" >20</td>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row19_col1\" class=\"data row19 col1\" >0.020693</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96level0_row20\" class=\"row_heading level0 row20\" >20</th>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row20_col0\" class=\"data row20 col0\" >21</td>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row20_col1\" class=\"data row20 col1\" >0.016370</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96level0_row21\" class=\"row_heading level0 row21\" >21</th>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row21_col0\" class=\"data row21 col0\" >22</td>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row21_col1\" class=\"data row21 col1\" >0.011916</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96level0_row22\" class=\"row_heading level0 row22\" >22</th>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row22_col0\" class=\"data row22 col0\" >23</td>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row22_col1\" class=\"data row22 col1\" >0.009102</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96level0_row23\" class=\"row_heading level0 row23\" >23</th>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row23_col0\" class=\"data row23 col0\" >24</td>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row23_col1\" class=\"data row23 col1\" >0.004828</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96level0_row24\" class=\"row_heading level0 row24\" >24</th>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row24_col0\" class=\"data row24 col0\" >25</td>\n",
" <td id=\"T_3a383004_e56c_11eb_a92f_5065f309ee96row24_col1\" class=\"data row24 col1\" >0.000756</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x1827cc31790>"
]
},
"execution_count": 41,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Convert the results into a dataframe\n",
"df_eigen = pd.DataFrame({'Factor': range(1, len(eigenValue) + 1), 'Eigen value': eigenValue})\n",
"df_eigen.style.apply(highlightEigenvalue, subset = ['Eigen value'])"
]
},
{
"cell_type": "code",
"execution_count": 42,
"id": "operational-heather",
"metadata": {
"scrolled": false
},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 800x480 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"<ggplot: (103746906802)>"
]
},
"execution_count": 42,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Data viz\n",
"plotnine.options.figure_size = (8, 4.8)\n",
"scree_eigenvalue = (\n",
" ggplot(data = df_eigen)+\n",
" geom_hline(yintercept = 1)+\n",
" geom_line(aes(x = 'Factor',\n",
" y = 'Eigen value'))+\n",
" geom_point(aes(x = 'Factor',\n",
" y = 'Eigen value'),\n",
" size = 2)+\n",
" labs(title = 'Scree plot of eigen value from factor analysis')+\n",
" xlab('Factors')+\n",
" ylab('Eigenvalue')+\n",
" theme_minimal()\n",
")\n",
"# Display the viz\n",
"scree_eigenvalue"
]
},
{
"cell_type": "code",
"execution_count": 43,
"id": "brazilian-emission",
"metadata": {},
"outputs": [],
"source": [
"# Save the graph\n",
"scree_eigenvalue.save(filename = 'img/scree_eigenvalue.png',\n",
" dpi = 1000,\n",
" verbose = False)"
]
},
{
"cell_type": "markdown",
"id": "closed-indonesian",
"metadata": {},
"source": [
"### Perform factor analysis"
]
},
{
"cell_type": "code",
"execution_count": 44,
"id": "metropolitan-judges",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Number of factors: 6\n"
]
}
],
"source": [
"# Number of factors\n",
"n_factor = len(df_eigen[df_eigen['Eigen value'] > 1])\n",
"print('Number of factors: {}'.format(n_factor))"
]
},
{
"cell_type": "markdown",
"id": "blocked-bearing",
"metadata": {},
"source": [
"#### 1 Without rotation"
]
},
{
"cell_type": "code",
"execution_count": 45,
"id": "revised-phoenix",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"FactorAnalyzer(n_factors=6, rotation=None, rotation_kwargs={})"
]
},
"execution_count": 45,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"fa = FactorAnalyzer(n_factors = n_factor, rotation = None)\n",
"fa.fit(df_scaled)"
]
},
{
"cell_type": "code",
"execution_count": 46,
"id": "existing-vehicle",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['Factors 1', 'Factors 2', 'Factors 3', 'Factors 4', 'Factors 5', 'Factors 6']\n"
]
}
],
"source": [
"# Create a factor's names\n",
"facs = ['Factors' + ' ' + str(i + 1) for i in range(n_factor)]\n",
"print(facs)"
]
},
{
"cell_type": "code",
"execution_count": 47,
"id": "increasing-customer",
"metadata": {
"scrolled": false
},
"outputs": [
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
"#T_3c9a49d5_e56c_11eb_8161_5065f309ee96row0_col1,#T_3c9a49d5_e56c_11eb_8161_5065f309ee96row1_col1,#T_3c9a49d5_e56c_11eb_8161_5065f309ee96row2_col1,#T_3c9a49d5_e56c_11eb_8161_5065f309ee96row3_col1,#T_3c9a49d5_e56c_11eb_8161_5065f309ee96row4_col1,#T_3c9a49d5_e56c_11eb_8161_5065f309ee96row5_col1,#T_3c9a49d5_e56c_11eb_8161_5065f309ee96row6_col1,#T_3c9a49d5_e56c_11eb_8161_5065f309ee96row8_col0,#T_3c9a49d5_e56c_11eb_8161_5065f309ee96row8_col2,#T_3c9a49d5_e56c_11eb_8161_5065f309ee96row9_col0,#T_3c9a49d5_e56c_11eb_8161_5065f309ee96row9_col2,#T_3c9a49d5_e56c_11eb_8161_5065f309ee96row12_col0,#T_3c9a49d5_e56c_11eb_8161_5065f309ee96row12_col2,#T_3c9a49d5_e56c_11eb_8161_5065f309ee96row13_col0,#T_3c9a49d5_e56c_11eb_8161_5065f309ee96row14_col0,#T_3c9a49d5_e56c_11eb_8161_5065f309ee96row15_col1,#T_3c9a49d5_e56c_11eb_8161_5065f309ee96row16_col2,#T_3c9a49d5_e56c_11eb_8161_5065f309ee96row17_col0,#T_3c9a49d5_e56c_11eb_8161_5065f309ee96row17_col3,#T_3c9a49d5_e56c_11eb_8161_5065f309ee96row18_col1,#T_3c9a49d5_e56c_11eb_8161_5065f309ee96row19_col0,#T_3c9a49d5_e56c_11eb_8161_5065f309ee96row19_col1,#T_3c9a49d5_e56c_11eb_8161_5065f309ee96row20_col0,#T_3c9a49d5_e56c_11eb_8161_5065f309ee96row20_col2,#T_3c9a49d5_e56c_11eb_8161_5065f309ee96row22_col0,#T_3c9a49d5_e56c_11eb_8161_5065f309ee96row23_col0,#T_3c9a49d5_e56c_11eb_8161_5065f309ee96row24_col0{\n",
" background-color: yellow;\n",
" }</style><table id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96\" ><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >Factors 1</th> <th class=\"col_heading level0 col1\" >Factors 2</th> <th class=\"col_heading level0 col2\" >Factors 3</th> <th class=\"col_heading level0 col3\" >Factors 4</th> <th class=\"col_heading level0 col4\" >Factors 5</th> <th class=\"col_heading level0 col5\" >Factors 6</th> </tr></thead><tbody>\n",
" <tr>\n",
" <th id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96level0_row0\" class=\"row_heading level0 row0\" >X1</th>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row0_col0\" class=\"data row0 col0\" >-0.088154</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row0_col1\" class=\"data row0 col1\" >0.645762</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row0_col2\" class=\"data row0 col2\" >0.201730</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row0_col3\" class=\"data row0 col3\" >0.192564</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row0_col4\" class=\"data row0 col4\" >0.158142</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row0_col5\" class=\"data row0 col5\" >-0.051111</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96level0_row1\" class=\"row_heading level0 row1\" >X2</th>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row1_col0\" class=\"data row1 col0\" >-0.106023</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row1_col1\" class=\"data row1 col1\" >0.776502</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row1_col2\" class=\"data row1 col2\" >0.232927</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row1_col3\" class=\"data row1 col3\" >0.168349</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row1_col4\" class=\"data row1 col4\" >0.253025</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row1_col5\" class=\"data row1 col5\" >0.178572</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96level0_row2\" class=\"row_heading level0 row2\" >X3</th>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row2_col0\" class=\"data row2 col0\" >0.215744</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row2_col1\" class=\"data row2 col1\" >0.567222</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row2_col2\" class=\"data row2 col2\" >-0.125862</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row2_col3\" class=\"data row2 col3\" >-0.115621</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row2_col4\" class=\"data row2 col4\" >0.286634</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row2_col5\" class=\"data row2 col5\" >0.269899</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96level0_row3\" class=\"row_heading level0 row3\" >X4</th>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row3_col0\" class=\"data row3 col0\" >-0.154060</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row3_col1\" class=\"data row3 col1\" >0.691620</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row3_col2\" class=\"data row3 col2\" >-0.195333</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row3_col3\" class=\"data row3 col3\" >0.133001</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row3_col4\" class=\"data row3 col4\" >0.429184</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row3_col5\" class=\"data row3 col5\" >0.112041</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96level0_row4\" class=\"row_heading level0 row4\" >X5</th>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row4_col0\" class=\"data row4 col0\" >0.345182</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row4_col1\" class=\"data row4 col1\" >-0.587718</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row4_col2\" class=\"data row4 col2\" >-0.487819</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row4_col3\" class=\"data row4 col3\" >0.193630</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row4_col4\" class=\"data row4 col4\" >0.375371</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row4_col5\" class=\"data row4 col5\" >0.096973</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96level0_row5\" class=\"row_heading level0 row5\" >X6</th>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row5_col0\" class=\"data row5 col0\" >0.450933</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row5_col1\" class=\"data row5 col1\" >-0.713172</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row5_col2\" class=\"data row5 col2\" >-0.401999</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row5_col3\" class=\"data row5 col3\" >0.213098</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row5_col4\" class=\"data row5 col4\" >0.287999</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row5_col5\" class=\"data row5 col5\" >-0.044280</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96level0_row6\" class=\"row_heading level0 row6\" >X7</th>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row6_col0\" class=\"data row6 col0\" >0.397190</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row6_col1\" class=\"data row6 col1\" >-0.782536</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row6_col2\" class=\"data row6 col2\" >-0.149440</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row6_col3\" class=\"data row6 col3\" >0.268428</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row6_col4\" class=\"data row6 col4\" >0.103330</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row6_col5\" class=\"data row6 col5\" >0.020780</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96level0_row7\" class=\"row_heading level0 row7\" >X8</th>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row7_col0\" class=\"data row7 col0\" >0.367294</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row7_col1\" class=\"data row7 col1\" >-0.458908</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row7_col2\" class=\"data row7 col2\" >-0.121690</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row7_col3\" class=\"data row7 col3\" >0.183385</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row7_col4\" class=\"data row7 col4\" >0.040418</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row7_col5\" class=\"data row7 col5\" >-0.349634</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96level0_row8\" class=\"row_heading level0 row8\" >X9</th>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row8_col0\" class=\"data row8 col0\" >0.635399</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row8_col1\" class=\"data row8 col1\" >-0.386708</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row8_col2\" class=\"data row8 col2\" >0.519768</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row8_col3\" class=\"data row8 col3\" >0.133266</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row8_col4\" class=\"data row8 col4\" >-0.183094</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row8_col5\" class=\"data row8 col5\" >0.106667</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96level0_row9\" class=\"row_heading level0 row9\" >X10</th>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row9_col0\" class=\"data row9 col0\" >0.612005</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row9_col1\" class=\"data row9 col1\" >-0.123334</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row9_col2\" class=\"data row9 col2\" >0.573455</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row9_col3\" class=\"data row9 col3\" >0.185857</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row9_col4\" class=\"data row9 col4\" >-0.133716</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row9_col5\" class=\"data row9 col5\" >0.156792</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96level0_row10\" class=\"row_heading level0 row10\" >X11</th>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row10_col0\" class=\"data row10 col0\" >0.012558</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row10_col1\" class=\"data row10 col1\" >0.199377</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row10_col2\" class=\"data row10 col2\" >0.249540</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row10_col3\" class=\"data row10 col3\" >0.114430</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row10_col4\" class=\"data row10 col4\" >0.374921</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row10_col5\" class=\"data row10 col5\" >-0.271090</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96level0_row11\" class=\"row_heading level0 row11\" >X12</th>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row11_col0\" class=\"data row11 col0\" >0.048660</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row11_col1\" class=\"data row11 col1\" >0.072049</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row11_col2\" class=\"data row11 col2\" >0.207142</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row11_col3\" class=\"data row11 col3\" >-0.150678</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row11_col4\" class=\"data row11 col4\" >-0.032443</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row11_col5\" class=\"data row11 col5\" >0.488003</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96level0_row12\" class=\"row_heading level0 row12\" >X13</th>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row12_col0\" class=\"data row12 col0\" >0.797047</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row12_col1\" class=\"data row12 col1\" >-0.006274</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row12_col2\" class=\"data row12 col2\" >0.563040</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row12_col3\" class=\"data row12 col3\" >0.035232</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row12_col4\" class=\"data row12 col4\" >0.145936</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row12_col5\" class=\"data row12 col5\" >-0.008000</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96level0_row13\" class=\"row_heading level0 row13\" >X14</th>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row13_col0\" class=\"data row13 col0\" >0.911274</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row13_col1\" class=\"data row13 col1\" >0.055360</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row13_col2\" class=\"data row13 col2\" >0.124333</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row13_col3\" class=\"data row13 col3\" >-0.260718</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row13_col4\" class=\"data row13 col4\" >0.105122</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row13_col5\" class=\"data row13 col5\" >-0.060276</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96level0_row14\" class=\"row_heading level0 row14\" >X15</th>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row14_col0\" class=\"data row14 col0\" >0.726539</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row14_col1\" class=\"data row14 col1\" >0.342477</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row14_col2\" class=\"data row14 col2\" >-0.396861</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row14_col3\" class=\"data row14 col3\" >-0.279164</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row14_col4\" class=\"data row14 col4\" >-0.145204</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row14_col5\" class=\"data row14 col5\" >-0.257999</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96level0_row15\" class=\"row_heading level0 row15\" >X16</th>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row15_col0\" class=\"data row15 col0\" >0.451087</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row15_col1\" class=\"data row15 col1\" >0.604331</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row15_col2\" class=\"data row15 col2\" >-0.356666</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row15_col3\" class=\"data row15 col3\" >0.281549</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row15_col4\" class=\"data row15 col4\" >-0.357808</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row15_col5\" class=\"data row15 col5\" >-0.065954</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96level0_row16\" class=\"row_heading level0 row16\" >X17</th>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row16_col0\" class=\"data row16 col0\" >0.378617</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row16_col1\" class=\"data row16 col1\" >0.309256</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row16_col2\" class=\"data row16 col2\" >0.567772</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row16_col3\" class=\"data row16 col3\" >0.153644</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row16_col4\" class=\"data row16 col4\" >0.127390</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row16_col5\" class=\"data row16 col5\" >-0.273424</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96level0_row17\" class=\"row_heading level0 row17\" >X18</th>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row17_col0\" class=\"data row17 col0\" >0.613925</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row17_col1\" class=\"data row17 col1\" >-0.120687</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row17_col2\" class=\"data row17 col2\" >-0.084043</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row17_col3\" class=\"data row17 col3\" >-0.574590</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row17_col4\" class=\"data row17 col4\" >-0.085834</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row17_col5\" class=\"data row17 col5\" >0.185631</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96level0_row18\" class=\"row_heading level0 row18\" >X19</th>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row18_col0\" class=\"data row18 col0\" >0.377495</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row18_col1\" class=\"data row18 col1\" >0.513654</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row18_col2\" class=\"data row18 col2\" >-0.071146</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row18_col3\" class=\"data row18 col3\" >-0.352236</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row18_col4\" class=\"data row18 col4\" >0.127376</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row18_col5\" class=\"data row18 col5\" >-0.324992</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96level0_row19\" class=\"row_heading level0 row19\" >X20</th>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row19_col0\" class=\"data row19 col0\" >0.563857</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row19_col1\" class=\"data row19 col1\" >0.542168</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row19_col2\" class=\"data row19 col2\" >-0.382742</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row19_col3\" class=\"data row19 col3\" >0.379917</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row19_col4\" class=\"data row19 col4\" >-0.244513</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row19_col5\" class=\"data row19 col5\" >0.085886</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96level0_row20\" class=\"row_heading level0 row20\" >X21</th>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row20_col0\" class=\"data row20 col0\" >0.745290</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row20_col1\" class=\"data row20 col1\" >-0.031225</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row20_col2\" class=\"data row20 col2\" >0.568783</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row20_col3\" class=\"data row20 col3\" >0.121427</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row20_col4\" class=\"data row20 col4\" >0.009228</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row20_col5\" class=\"data row20 col5\" >0.006297</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96level0_row21\" class=\"row_heading level0 row21\" >X22</th>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row21_col0\" class=\"data row21 col0\" >0.346377</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row21_col1\" class=\"data row21 col1\" >-0.309739</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row21_col2\" class=\"data row21 col2\" >-0.041371</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row21_col3\" class=\"data row21 col3\" >-0.005655</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row21_col4\" class=\"data row21 col4\" >-0.042872</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row21_col5\" class=\"data row21 col5\" >0.206373</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96level0_row22\" class=\"row_heading level0 row22\" >X23</th>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row22_col0\" class=\"data row22 col0\" >0.829641</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row22_col1\" class=\"data row22 col1\" >0.138744</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row22_col2\" class=\"data row22 col2\" >-0.180656</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row22_col3\" class=\"data row22 col3\" >-0.307207</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row22_col4\" class=\"data row22 col4\" >-0.028329</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row22_col5\" class=\"data row22 col5\" >-0.040880</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96level0_row23\" class=\"row_heading level0 row23\" >X24</th>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row23_col0\" class=\"data row23 col0\" >0.611698</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row23_col1\" class=\"data row23 col1\" >0.489015</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row23_col2\" class=\"data row23 col2\" >-0.376315</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row23_col3\" class=\"data row23 col3\" >0.378883</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row23_col4\" class=\"data row23 col4\" >-0.303911</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row23_col5\" class=\"data row23 col5\" >0.082253</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96level0_row24\" class=\"row_heading level0 row24\" >X25</th>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row24_col0\" class=\"data row24 col0\" >0.747430</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row24_col1\" class=\"data row24 col1\" >0.065944</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row24_col2\" class=\"data row24 col2\" >-0.353527</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row24_col3\" class=\"data row24 col3\" >-0.021335</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row24_col4\" class=\"data row24 col4\" >0.389572</td>\n",
" <td id=\"T_3c9a49d5_e56c_11eb_8161_5065f309ee96row24_col5\" class=\"data row24 col5\" >0.195047</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x1827c882130>"
]
},
"execution_count": 47,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Loading factors\n",
"pd.DataFrame(data = fa.loadings_, index = df_scaled.columns, columns = facs).style.apply(highlightLoadings)"
]
},
{
"cell_type": "code",
"execution_count": 48,
"id": "chinese-tomato",
"metadata": {
"scrolled": false
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Factors 1</th>\n",
" <th>Factors 2</th>\n",
" <th>Factors 3</th>\n",
" <th>Factors 4</th>\n",
" <th>Factors 5</th>\n",
" <th>Factors 6</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>SS Loadings</th>\n",
" <td>6.959552</td>\n",
" <td>5.219973</td>\n",
" <td>3.012464</td>\n",
" <td>1.474913</td>\n",
" <td>1.312487</td>\n",
" <td>0.987474</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Proportion Variance</th>\n",
" <td>0.278382</td>\n",
" <td>0.208799</td>\n",
" <td>0.120499</td>\n",
" <td>0.058997</td>\n",
" <td>0.052499</td>\n",
" <td>0.039499</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Cumulative Variance</th>\n",
" <td>0.278382</td>\n",
" <td>0.487181</td>\n",
" <td>0.607680</td>\n",
" <td>0.666676</td>\n",
" <td>0.719176</td>\n",
" <td>0.758675</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Factors 1 Factors 2 Factors 3 Factors 4 Factors 5 \\\n",
"SS Loadings 6.959552 5.219973 3.012464 1.474913 1.312487 \n",
"Proportion Variance 0.278382 0.208799 0.120499 0.058997 0.052499 \n",
"Cumulative Variance 0.278382 0.487181 0.607680 0.666676 0.719176 \n",
"\n",
" Factors 6 \n",
"SS Loadings 0.987474 \n",
"Proportion Variance 0.039499 \n",
"Cumulative Variance 0.758675 "
]
},
"execution_count": 48,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Explained variance\n",
"idx = ['SS Loadings', 'Proportion Variance', 'Cumulative Variance']\n",
"df_variance = pd.DataFrame(data = fa.get_factor_variance(), index = idx, columns = facs)\n",
"df_variance"
]
},
{
"cell_type": "code",
"execution_count": 49,
"id": "hairy-laundry",
"metadata": {
"scrolled": false
},
"outputs": [
{
"data": {
"text/plain": [
"(array([6.95955237, 5.21997293, 3.01246372, 1.47491307, 1.31248724,\n",
" 0.98747442]),\n",
" array([0.27838209, 0.20879892, 0.12049855, 0.05899652, 0.05249949,\n",
" 0.03949898]),\n",
" array([0.27838209, 0.48718101, 0.60767956, 0.66667608, 0.71917557,\n",
" 0.75867455]))"
]
},
"execution_count": 49,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"fa.get_factor_variance()"
]
},
{
"cell_type": "code",
"execution_count": 50,
"id": "scheduled-orleans",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Factors 1</th>\n",
" <th>Factors 2</th>\n",
" <th>Factors 3</th>\n",
" <th>Factors 4</th>\n",
" <th>Factors 5</th>\n",
" <th>Factors 6</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>Ratio Variance</th>\n",
" <td>0.366932</td>\n",
" <td>0.275215</td>\n",
" <td>0.158828</td>\n",
" <td>0.077763</td>\n",
" <td>0.069199</td>\n",
" <td>0.052063</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Factors 1 Factors 2 Factors 3 Factors 4 Factors 5 \\\n",
"Ratio Variance 0.366932 0.275215 0.158828 0.077763 0.069199 \n",
"\n",
" Factors 6 \n",
"Ratio Variance 0.052063 "
]
},
"execution_count": 50,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Ratio of variance\n",
"ratioVariance = fa.get_factor_variance()[1] / fa.get_factor_variance()[1].sum()\n",
"df_ratio_var = pd.DataFrame(data = ratioVariance.reshape((1, n_factor)), index = ['Ratio Variance'], columns = facs)\n",
"df_ratio_var"
]
},
{
"cell_type": "code",
"execution_count": 51,
"id": "pregnant-divide",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Factors 1</th>\n",
" <th>Factors 2</th>\n",
" <th>Factors 3</th>\n",
" <th>Factors 4</th>\n",
" <th>Factors 5</th>\n",
" <th>Factors 6</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>SS Loadings</th>\n",
" <td>6.959552</td>\n",
" <td>5.219973</td>\n",
" <td>3.012464</td>\n",
" <td>1.474913</td>\n",
" <td>1.312487</td>\n",
" <td>0.987474</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Proportion Variance</th>\n",
" <td>0.278382</td>\n",
" <td>0.208799</td>\n",
" <td>0.120499</td>\n",
" <td>0.058997</td>\n",
" <td>0.052499</td>\n",
" <td>0.039499</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Cumulative Variance</th>\n",
" <td>0.278382</td>\n",
" <td>0.487181</td>\n",
" <td>0.607680</td>\n",
" <td>0.666676</td>\n",
" <td>0.719176</td>\n",
" <td>0.758675</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Ratio Variance</th>\n",
" <td>0.366932</td>\n",
" <td>0.275215</td>\n",
" <td>0.158828</td>\n",
" <td>0.077763</td>\n",
" <td>0.069199</td>\n",
" <td>0.052063</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Factors 1 Factors 2 Factors 3 Factors 4 Factors 5 \\\n",
"SS Loadings 6.959552 5.219973 3.012464 1.474913 1.312487 \n",
"Proportion Variance 0.278382 0.208799 0.120499 0.058997 0.052499 \n",
"Cumulative Variance 0.278382 0.487181 0.607680 0.666676 0.719176 \n",
"Ratio Variance 0.366932 0.275215 0.158828 0.077763 0.069199 \n",
"\n",
" Factors 6 \n",
"SS Loadings 0.987474 \n",
"Proportion Variance 0.039499 \n",
"Cumulative Variance 0.758675 \n",
"Ratio Variance 0.052063 "
]
},
"execution_count": 51,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# New completed dataframe\n",
"df_variance.append(df_ratio_var)"
]
},
{
"cell_type": "markdown",
"id": "close-township",
"metadata": {},
"source": [
"#### 2 With rotation"
]
},
{
"cell_type": "code",
"execution_count": 52,
"id": "joined-tampa",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"FactorAnalyzer(n_factors=6, rotation='varimax', rotation_kwargs={})"
]
},
"execution_count": 52,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"fa = FactorAnalyzer(n_factors = n_factor, rotation = 'varimax')\n",
"fa.fit(df_scaled)"
]
},
{
"cell_type": "code",
"execution_count": 53,
"id": "sacred-bracket",
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['Factors 1', 'Factors 2', 'Factors 3', 'Factors 4', 'Factors 5', 'Factors 6']\n"
]
}
],
"source": [
"# Create a factor's names\n",
"facs = ['Factors' + ' ' + str(i + 1) for i in range(n_factor)]\n",
"print(facs)"
]
},
{
"cell_type": "code",
"execution_count": 54,
"id": "bacterial-fifth",
"metadata": {
"scrolled": false
},
"outputs": [
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
"#T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row0_col4,#T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row1_col4,#T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row2_col4,#T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row3_col4,#T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row4_col1,#T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row5_col1,#T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row6_col1,#T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row8_col0,#T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row9_col0,#T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row11_col5,#T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row12_col0,#T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row13_col0,#T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row13_col2,#T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row14_col2,#T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row14_col3,#T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row15_col3,#T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row16_col0,#T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row17_col2,#T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row18_col2,#T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row19_col3,#T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row20_col0,#T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row22_col2,#T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row23_col3,#T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row24_col1,#T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row24_col2{\n",
" background-color: yellow;\n",
" }</style><table id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96\" ><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >Factors 1</th> <th class=\"col_heading level0 col1\" >Factors 2</th> <th class=\"col_heading level0 col2\" >Factors 3</th> <th class=\"col_heading level0 col3\" >Factors 4</th> <th class=\"col_heading level0 col4\" >Factors 5</th> <th class=\"col_heading level0 col5\" >Factors 6</th> </tr></thead><tbody>\n",
" <tr>\n",
" <th id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96level0_row0\" class=\"row_heading level0 row0\" >X1</th>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row0_col0\" class=\"data row0 col0\" >0.086515</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row0_col1\" class=\"data row0 col1\" >-0.385899</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row0_col2\" class=\"data row0 col2\" >-0.077736</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row0_col3\" class=\"data row0 col3\" >0.184285</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row0_col4\" class=\"data row0 col4\" >0.571311</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row0_col5\" class=\"data row0 col5\" >-0.085869</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96level0_row1\" class=\"row_heading level0 row1\" >X2</th>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row1_col0\" class=\"data row1 col0\" >0.079639</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row1_col1\" class=\"data row1 col1\" >-0.414097</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row1_col2\" class=\"data row1 col2\" >-0.081965</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row1_col3\" class=\"data row1 col3\" >0.183481</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row1_col4\" class=\"data row1 col4\" >0.745538</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row1_col5\" class=\"data row1 col5\" >0.136647</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96level0_row2\" class=\"row_heading level0 row2\" >X3</th>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row2_col0\" class=\"data row2 col0\" >-0.045179</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row2_col1\" class=\"data row2 col1\" >-0.066811</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row2_col2\" class=\"data row2 col2\" >0.334558</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row2_col3\" class=\"data row2 col3\" >0.224066</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row2_col4\" class=\"data row2 col4\" >0.555754</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row2_col5\" class=\"data row2 col5\" >0.273859</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96level0_row3\" class=\"row_heading level0 row3\" >X4</th>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row3_col0\" class=\"data row3 col0\" >-0.278431</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row3_col1\" class=\"data row3 col1\" >-0.134528</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row3_col2\" class=\"data row3 col2\" >0.024528</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row3_col3\" class=\"data row3 col3\" >0.203735</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row3_col4\" class=\"data row3 col4\" >0.784594</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row3_col5\" class=\"data row3 col5\" >0.036758</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96level0_row4\" class=\"row_heading level0 row4\" >X5</th>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row4_col0\" class=\"data row4 col0\" >-0.077399</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row4_col1\" class=\"data row4 col1\" >0.934030</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row4_col2\" class=\"data row4 col2\" >0.068199</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row4_col3\" class=\"data row4 col3\" >0.006447</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row4_col4\" class=\"data row4 col4\" >-0.082567</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row4_col5\" class=\"data row4 col5\" >-0.020397</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96level0_row5\" class=\"row_heading level0 row5\" >X6</th>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row5_col0\" class=\"data row5 col0\" >0.069244</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row5_col1\" class=\"data row5 col1\" >0.956030</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row5_col2\" class=\"data row5 col2\" >0.086516</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row5_col3\" class=\"data row5 col3\" >-0.004298</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row5_col4\" class=\"data row5 col4\" >-0.235941</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row5_col5\" class=\"data row5 col5\" >-0.148027</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96level0_row6\" class=\"row_heading level0 row6\" >X7</th>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row6_col0\" class=\"data row6 col0\" >0.249757</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row6_col1\" class=\"data row6 col1\" >0.808739</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row6_col2\" class=\"data row6 col2\" >-0.086514</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row6_col3\" class=\"data row6 col3\" >-0.046177</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row6_col4\" class=\"data row6 col4\" >-0.380317</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row6_col5\" class=\"data row6 col5\" >-0.070150</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96level0_row7\" class=\"row_heading level0 row7\" >X8</th>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row7_col0\" class=\"data row7 col0\" >0.210711</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row7_col1\" class=\"data row7 col1\" >0.484274</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row7_col2\" class=\"data row7 col2\" >0.078680</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row7_col3\" class=\"data row7 col3\" >0.036182</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row7_col4\" class=\"data row7 col4\" >-0.278764</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row7_col5\" class=\"data row7 col5\" >-0.392031</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96level0_row8\" class=\"row_heading level0 row8\" >X9</th>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row8_col0\" class=\"data row8 col0\" >0.844127</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row8_col1\" class=\"data row8 col1\" >0.212339</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row8_col2\" class=\"data row8 col2\" >0.036031</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row8_col3\" class=\"data row8 col3\" >0.017154</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row8_col4\" class=\"data row8 col4\" >-0.332927</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row8_col5\" class=\"data row8 col5\" >0.126583</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96level0_row9\" class=\"row_heading level0 row9\" >X10</th>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row9_col0\" class=\"data row9 col0\" >0.859366</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row9_col1\" class=\"data row9 col1\" >0.067980</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row9_col2\" class=\"data row9 col2\" >0.022386</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row9_col3\" class=\"data row9 col3\" >0.109262</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row9_col4\" class=\"data row9 col4\" >-0.111154</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row9_col5\" class=\"data row9 col5\" >0.166412</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96level0_row10\" class=\"row_heading level0 row10\" >X11</th>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row10_col0\" class=\"data row10 col0\" >0.200106</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row10_col1\" class=\"data row10 col1\" >-0.057394</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row10_col2\" class=\"data row10 col2\" >-0.001726</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row10_col3\" class=\"data row10 col3\" >-0.151791</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row10_col4\" class=\"data row10 col4\" >0.411883</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row10_col5\" class=\"data row10 col5\" >-0.305452</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96level0_row11\" class=\"row_heading level0 row11\" >X12</th>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row11_col0\" class=\"data row11 col0\" >0.144320</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row11_col1\" class=\"data row11 col1\" >-0.101795</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row11_col2\" class=\"data row11 col2\" >0.015053</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row11_col3\" class=\"data row11 col3\" >-0.057810</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row11_col4\" class=\"data row11 col4\" >0.052525</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row11_col5\" class=\"data row11 col5\" >0.524264</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96level0_row12\" class=\"row_heading level0 row12\" >X13</th>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row12_col0\" class=\"data row12 col0\" >0.915493</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row12_col1\" class=\"data row12 col1\" >0.132017</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row12_col2\" class=\"data row12 col2\" >0.324901</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row12_col3\" class=\"data row12 col3\" >0.024059</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row12_col4\" class=\"data row12 col4\" >0.112408</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row12_col5\" class=\"data row12 col5\" >0.024654</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96level0_row13\" class=\"row_heading level0 row13\" >X14</th>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row13_col0\" class=\"data row13 col0\" >0.581759</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row13_col1\" class=\"data row13 col1\" >0.216035</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row13_col2\" class=\"data row13 col2\" >0.721682</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row13_col3\" class=\"data row13 col3\" >0.155784</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row13_col4\" class=\"data row13 col4\" >0.022703</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row13_col5\" class=\"data row13 col5\" >0.029618</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96level0_row14\" class=\"row_heading level0 row14\" >X15</th>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row14_col0\" class=\"data row14 col0\" >0.053177</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row14_col1\" class=\"data row14 col1\" >0.052412</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row14_col2\" class=\"data row14 col2\" >0.812018</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row14_col3\" class=\"data row14 col3\" >0.526034</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row14_col4\" class=\"data row14 col4\" >-0.032195</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row14_col5\" class=\"data row14 col5\" >-0.159783</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96level0_row15\" class=\"row_heading level0 row15\" >X16</th>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row15_col0\" class=\"data row15 col0\" >0.023890</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row15_col1\" class=\"data row15 col1\" >-0.131640</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row15_col2\" class=\"data row15 col2\" >0.231400</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row15_col3\" class=\"data row15 col3\" >0.901634</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row15_col4\" class=\"data row15 col4\" >0.124190</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row15_col5\" class=\"data row15 col5\" >-0.087971</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96level0_row16\" class=\"row_heading level0 row16\" >X17</th>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row16_col0\" class=\"data row16 col0\" >0.668175</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row16_col1\" class=\"data row16 col1\" >-0.227632</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row16_col2\" class=\"data row16 col2\" >0.106761</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row16_col3\" class=\"data row16 col3\" >0.043001</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row16_col4\" class=\"data row16 col4\" >0.309456</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row16_col5\" class=\"data row16 col5\" >-0.262042</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96level0_row17\" class=\"row_heading level0 row17\" >X18</th>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row17_col0\" class=\"data row17 col0\" >0.190047</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row17_col1\" class=\"data row17 col1\" >0.158830</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row17_col2\" class=\"data row17 col2\" >0.724447</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row17_col3\" class=\"data row17 col3\" >0.002439</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row17_col4\" class=\"data row17 col4\" >-0.268170</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row17_col5\" class=\"data row17 col5\" >0.335296</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96level0_row18\" class=\"row_heading level0 row18\" >X19</th>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row18_col0\" class=\"data row18 col0\" >0.053021</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row18_col1\" class=\"data row18 col1\" >-0.226903</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row18_col2\" class=\"data row18 col2\" >0.667994</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row18_col3\" class=\"data row18 col3\" >0.157247</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row18_col4\" class=\"data row18 col4\" >0.288484</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row18_col5\" class=\"data row18 col5\" >-0.221038</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96level0_row19\" class=\"row_heading level0 row19\" >X20</th>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row19_col0\" class=\"data row19 col0\" >0.096251</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row19_col1\" class=\"data row19 col1\" >0.061464</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row19_col2\" class=\"data row19 col2\" >0.202360</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row19_col3\" class=\"data row19 col3\" >0.935638</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row19_col4\" class=\"data row19 col4\" >0.199681</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row19_col5\" class=\"data row19 col5\" >0.024300</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96level0_row20\" class=\"row_heading level0 row20\" >X21</th>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row20_col0\" class=\"data row20 col0\" >0.912595</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row20_col1\" class=\"data row20 col1\" >0.089441</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row20_col2\" class=\"data row20 col2\" >0.208626</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row20_col3\" class=\"data row20 col3\" >0.096525</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row20_col4\" class=\"data row20 col4\" >0.017300</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row20_col5\" class=\"data row20 col5\" >0.029073</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96level0_row21\" class=\"row_heading level0 row21\" >X22</th>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row21_col0\" class=\"data row21 col0\" >0.202316</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row21_col1\" class=\"data row21 col1\" >0.341006</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row21_col2\" class=\"data row21 col2\" >0.107772</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row21_col3\" class=\"data row21 col3\" >0.049406</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row21_col4\" class=\"data row21 col4\" >-0.221209</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row21_col5\" class=\"data row21 col5\" >0.204648</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96level0_row22\" class=\"row_heading level0 row22\" >X23</th>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row22_col0\" class=\"data row22 col0\" >0.286301</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row22_col1\" class=\"data row22 col1\" >0.196221</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row22_col2\" class=\"data row22 col2\" >0.775474</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row22_col3\" class=\"data row22 col3\" >0.331669</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row22_col4\" class=\"data row22 col4\" >-0.046733</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row22_col5\" class=\"data row22 col5\" >0.054964</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96level0_row23\" class=\"row_heading level0 row23\" >X24</th>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row23_col0\" class=\"data row23 col0\" >0.135526</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row23_col1\" class=\"data row23 col1\" >0.080176</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row23_col2\" class=\"data row23 col2\" >0.212725</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row23_col3\" class=\"data row23 col3\" >0.955172</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row23_col4\" class=\"data row23 col4\" >0.120261</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row23_col5\" class=\"data row23 col5\" >0.027201</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96level0_row24\" class=\"row_heading level0 row24\" >X25</th>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row24_col0\" class=\"data row24 col0\" >0.165173</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row24_col1\" class=\"data row24 col1\" >0.593129</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row24_col2\" class=\"data row24 col2\" >0.544837</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row24_col3\" class=\"data row24 col3\" >0.299869</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row24_col4\" class=\"data row24 col4\" >0.294641</td>\n",
" <td id=\"T_3d4b14b3_e56c_11eb_9a3a_5065f309ee96row24_col5\" class=\"data row24 col5\" >0.159936</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x1820006f670>"
]
},
"execution_count": 54,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Loading factors\n",
"pd.DataFrame(data = fa.loadings_, index = df_scaled.columns, columns = facs).style.apply(highlightLoadings)"
]
},
{
"cell_type": "code",
"execution_count": 55,
"id": "coral-detection",
"metadata": {
"scrolled": false
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Factors 1</th>\n",
" <th>Factors 2</th>\n",
" <th>Factors 3</th>\n",
" <th>Factors 4</th>\n",
" <th>Factors 5</th>\n",
" <th>Factors 6</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>SS Loadings</th>\n",
" <td>4.398885</td>\n",
" <td>3.818808</td>\n",
" <td>3.514422</td>\n",
" <td>3.341996</td>\n",
" <td>2.860190</td>\n",
" <td>1.032562</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Proportion Variance</th>\n",
" <td>0.175955</td>\n",
" <td>0.152752</td>\n",
" <td>0.140577</td>\n",
" <td>0.133680</td>\n",
" <td>0.114408</td>\n",
" <td>0.041302</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Cumulative Variance</th>\n",
" <td>0.175955</td>\n",
" <td>0.328708</td>\n",
" <td>0.469285</td>\n",
" <td>0.602964</td>\n",
" <td>0.717372</td>\n",
" <td>0.758675</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Factors 1 Factors 2 Factors 3 Factors 4 Factors 5 \\\n",
"SS Loadings 4.398885 3.818808 3.514422 3.341996 2.860190 \n",
"Proportion Variance 0.175955 0.152752 0.140577 0.133680 0.114408 \n",
"Cumulative Variance 0.175955 0.328708 0.469285 0.602964 0.717372 \n",
"\n",
" Factors 6 \n",
"SS Loadings 1.032562 \n",
"Proportion Variance 0.041302 \n",
"Cumulative Variance 0.758675 "
]
},
"execution_count": 55,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Explained variance\n",
"idx = ['SS Loadings', 'Proportion Variance', 'Cumulative Variance']\n",
"df_variance = pd.DataFrame(data = fa.get_factor_variance(), index = idx, columns = facs)\n",
"df_variance"
]
},
{
"cell_type": "code",
"execution_count": 56,
"id": "secret-softball",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"(array([4.3988852 , 3.81880796, 3.5144225 , 3.34199639, 2.86018972,\n",
" 1.03256198]),\n",
" array([0.17595541, 0.15275232, 0.1405769 , 0.13367986, 0.11440759,\n",
" 0.04130248]),\n",
" array([0.17595541, 0.32870773, 0.46928463, 0.60296448, 0.71737207,\n",
" 0.75867455]))"
]
},
"execution_count": 56,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"fa.get_factor_variance()"
]
},
{
"cell_type": "code",
"execution_count": 57,
"id": "controlling-tiger",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Factors 1</th>\n",
" <th>Factors 2</th>\n",
" <th>Factors 3</th>\n",
" <th>Factors 4</th>\n",
" <th>Factors 5</th>\n",
" <th>Factors 6</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>Ratio Variance</th>\n",
" <td>0.231925</td>\n",
" <td>0.201341</td>\n",
" <td>0.185293</td>\n",
" <td>0.176202</td>\n",
" <td>0.150799</td>\n",
" <td>0.05444</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Factors 1 Factors 2 Factors 3 Factors 4 Factors 5 \\\n",
"Ratio Variance 0.231925 0.201341 0.185293 0.176202 0.150799 \n",
"\n",
" Factors 6 \n",
"Ratio Variance 0.05444 "
]
},
"execution_count": 57,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Ratio of variance\n",
"ratioVariance = fa.get_factor_variance()[1] / fa.get_factor_variance()[1].sum()\n",
"df_ratio_var = pd.DataFrame(data = ratioVariance.reshape((1, n_factor)), index = ['Ratio Variance'], columns = facs)\n",
"df_ratio_var"
]
},
{
"cell_type": "code",
"execution_count": 58,
"id": "fantastic-humidity",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Factors 1</th>\n",
" <th>Factors 2</th>\n",
" <th>Factors 3</th>\n",
" <th>Factors 4</th>\n",
" <th>Factors 5</th>\n",
" <th>Factors 6</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>SS Loadings</th>\n",
" <td>4.398885</td>\n",
" <td>3.818808</td>\n",
" <td>3.514422</td>\n",
" <td>3.341996</td>\n",
" <td>2.860190</td>\n",
" <td>1.032562</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Proportion Variance</th>\n",
" <td>0.175955</td>\n",
" <td>0.152752</td>\n",
" <td>0.140577</td>\n",
" <td>0.133680</td>\n",
" <td>0.114408</td>\n",
" <td>0.041302</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Cumulative Variance</th>\n",
" <td>0.175955</td>\n",
" <td>0.328708</td>\n",
" <td>0.469285</td>\n",
" <td>0.602964</td>\n",
" <td>0.717372</td>\n",
" <td>0.758675</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Ratio Variance</th>\n",
" <td>0.231925</td>\n",
" <td>0.201341</td>\n",
" <td>0.185293</td>\n",
" <td>0.176202</td>\n",
" <td>0.150799</td>\n",
" <td>0.054440</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Factors 1 Factors 2 Factors 3 Factors 4 Factors 5 \\\n",
"SS Loadings 4.398885 3.818808 3.514422 3.341996 2.860190 \n",
"Proportion Variance 0.175955 0.152752 0.140577 0.133680 0.114408 \n",
"Cumulative Variance 0.175955 0.328708 0.469285 0.602964 0.717372 \n",
"Ratio Variance 0.231925 0.201341 0.185293 0.176202 0.150799 \n",
"\n",
" Factors 6 \n",
"SS Loadings 1.032562 \n",
"Proportion Variance 0.041302 \n",
"Cumulative Variance 0.758675 \n",
"Ratio Variance 0.054440 "
]
},
"execution_count": 58,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# New completed dataframe\n",
"df_variance.append(df_ratio_var)"
]
},
{
"cell_type": "markdown",
"id": "acute-support",
"metadata": {},
"source": [
"#### Standardize the factors"
]
},
{
"cell_type": "code",
"execution_count": 59,
"id": "professional-connectivity",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th></th>\n",
" <th>Factors 1</th>\n",
" <th>Factors 2</th>\n",
" <th>Factors 3</th>\n",
" <th>Factors 4</th>\n",
" <th>Factors 5</th>\n",
" <th>Factors 6</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Province</th>\n",
" <th>Region</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>ACEH</th>\n",
" <th>West</th>\n",
" <td>0.213151</td>\n",
" <td>-0.181858</td>\n",
" <td>0.527530</td>\n",
" <td>1.128943</td>\n",
" <td>0.788172</td>\n",
" <td>1.702225</td>\n",
" </tr>\n",
" <tr>\n",
" <th>NORTH SUMATERA</th>\n",
" <th>West</th>\n",
" <td>-0.447379</td>\n",
" <td>-0.341386</td>\n",
" <td>1.361850</td>\n",
" <td>-1.108200</td>\n",
" <td>-0.665725</td>\n",
" <td>0.635541</td>\n",
" </tr>\n",
" <tr>\n",
" <th>WEST SUMATERA</th>\n",
" <th>West</th>\n",
" <td>0.320698</td>\n",
" <td>-1.232980</td>\n",
" <td>1.886044</td>\n",
" <td>-0.360122</td>\n",
" <td>-0.926783</td>\n",
" <td>-1.116187</td>\n",
" </tr>\n",
" <tr>\n",
" <th>RIAU</th>\n",
" <th>West</th>\n",
" <td>-0.066843</td>\n",
" <td>0.959367</td>\n",
" <td>-1.119813</td>\n",
" <td>1.548194</td>\n",
" <td>0.048667</td>\n",
" <td>1.492447</td>\n",
" </tr>\n",
" <tr>\n",
" <th>JAMBI</th>\n",
" <th>West</th>\n",
" <td>0.789713</td>\n",
" <td>-1.075963</td>\n",
" <td>1.069349</td>\n",
" <td>-1.614698</td>\n",
" <td>1.224877</td>\n",
" <td>0.684390</td>\n",
" </tr>\n",
" <tr>\n",
" <th>SOUTH SUMATERA</th>\n",
" <th>West</th>\n",
" <td>0.228829</td>\n",
" <td>-0.567252</td>\n",
" <td>-0.492303</td>\n",
" <td>0.030032</td>\n",
" <td>-1.071543</td>\n",
" <td>-0.437447</td>\n",
" </tr>\n",
" <tr>\n",
" <th>BENGKULU</th>\n",
" <th>West</th>\n",
" <td>0.252115</td>\n",
" <td>-1.363703</td>\n",
" <td>0.954648</td>\n",
" <td>-0.097229</td>\n",
" <td>0.633134</td>\n",
" <td>-0.307455</td>\n",
" </tr>\n",
" <tr>\n",
" <th>LAMPUNG</th>\n",
" <th>West</th>\n",
" <td>0.687480</td>\n",
" <td>-2.861992</td>\n",
" <td>2.931481</td>\n",
" <td>-3.058802</td>\n",
" <td>-1.144177</td>\n",
" <td>-1.304143</td>\n",
" </tr>\n",
" <tr>\n",
" <th>BANGKA BELITUNG ISLAND</th>\n",
" <th>West</th>\n",
" <td>0.837486</td>\n",
" <td>0.928729</td>\n",
" <td>-1.751948</td>\n",
" <td>-1.553879</td>\n",
" <td>0.076898</td>\n",
" <td>-0.052605</td>\n",
" </tr>\n",
" <tr>\n",
" <th>RIAU ISLAND</th>\n",
" <th>West</th>\n",
" <td>-0.508374</td>\n",
" <td>1.742409</td>\n",
" <td>1.912176</td>\n",
" <td>-0.841399</td>\n",
" <td>-0.789010</td>\n",
" <td>-0.586194</td>\n",
" </tr>\n",
" <tr>\n",
" <th>DKI JAKARTA</th>\n",
" <th>West</th>\n",
" <td>0.170310</td>\n",
" <td>3.266037</td>\n",
" <td>0.669947</td>\n",
" <td>-1.128038</td>\n",
" <td>0.648238</td>\n",
" <td>-0.624196</td>\n",
" </tr>\n",
" <tr>\n",
" <th>WEST JAVA</th>\n",
" <th>West</th>\n",
" <td>0.553373</td>\n",
" <td>0.091768</td>\n",
" <td>-0.638877</td>\n",
" <td>-0.038492</td>\n",
" <td>-1.157643</td>\n",
" <td>0.849553</td>\n",
" </tr>\n",
" <tr>\n",
" <th>CENTRAL JAVA</th>\n",
" <th>West</th>\n",
" <td>0.547894</td>\n",
" <td>-0.400094</td>\n",
" <td>-0.673137</td>\n",
" <td>-0.337820</td>\n",
" <td>-1.415012</td>\n",
" <td>0.208667</td>\n",
" </tr>\n",
" <tr>\n",
" <th>DI YOGYAKARTA</th>\n",
" <th>West</th>\n",
" <td>0.237828</td>\n",
" <td>0.266943</td>\n",
" <td>-0.214521</td>\n",
" <td>4.690676</td>\n",
" <td>-1.274001</td>\n",
" <td>0.520238</td>\n",
" </tr>\n",
" <tr>\n",
" <th>EAST JAVA</th>\n",
" <th>West</th>\n",
" <td>0.573270</td>\n",
" <td>-1.770365</td>\n",
" <td>1.738095</td>\n",
" <td>-1.477722</td>\n",
" <td>-1.869037</td>\n",
" <td>-0.162133</td>\n",
" </tr>\n",
" <tr>\n",
" <th>BANTEN</th>\n",
" <th>West</th>\n",
" <td>0.201589</td>\n",
" <td>1.636382</td>\n",
" <td>-1.682450</td>\n",
" <td>-0.105598</td>\n",
" <td>-0.551341</td>\n",
" <td>1.544308</td>\n",
" </tr>\n",
" <tr>\n",
" <th>BALI</th>\n",
" <th>Central</th>\n",
" <td>-0.124501</td>\n",
" <td>1.773795</td>\n",
" <td>0.715277</td>\n",
" <td>0.484883</td>\n",
" <td>-1.731976</td>\n",
" <td>-0.865438</td>\n",
" </tr>\n",
" <tr>\n",
" <th>WEST NUSA TENGGARA</th>\n",
" <th>Central</th>\n",
" <td>0.345893</td>\n",
" <td>-0.761601</td>\n",
" <td>0.182316</td>\n",
" <td>-0.056937</td>\n",
" <td>0.024782</td>\n",
" <td>0.268018</td>\n",
" </tr>\n",
" <tr>\n",
" <th>EAST NUSA TENGGARA</th>\n",
" <th>Central</th>\n",
" <td>0.345532</td>\n",
" <td>-1.739352</td>\n",
" <td>1.224085</td>\n",
" <td>-1.165089</td>\n",
" <td>-0.411580</td>\n",
" <td>-2.549342</td>\n",
" </tr>\n",
" <tr>\n",
" <th>WEST KALIMANTAN</th>\n",
" <th>West</th>\n",
" <td>0.255196</td>\n",
" <td>0.750499</td>\n",
" <td>-3.104979</td>\n",
" <td>1.003659</td>\n",
" <td>0.060603</td>\n",
" <td>-0.451072</td>\n",
" </tr>\n",
" <tr>\n",
" <th>CENTRAL KALIMANTAN</th>\n",
" <th>West</th>\n",
" <td>-0.038564</td>\n",
" <td>0.618968</td>\n",
" <td>-2.227896</td>\n",
" <td>0.078942</td>\n",
" <td>1.207622</td>\n",
" <td>2.439636</td>\n",
" </tr>\n",
" <tr>\n",
" <th>SOUTH KALIMANTAN</th>\n",
" <th>Central</th>\n",
" <td>0.716767</td>\n",
" <td>0.584312</td>\n",
" <td>-1.274741</td>\n",
" <td>0.523116</td>\n",
" <td>-0.227285</td>\n",
" <td>-0.289499</td>\n",
" </tr>\n",
" <tr>\n",
" <th>EAST KALIMANTAN</th>\n",
" <th>Central</th>\n",
" <td>-0.010683</td>\n",
" <td>1.364138</td>\n",
" <td>-0.324912</td>\n",
" <td>2.054904</td>\n",
" <td>-0.565893</td>\n",
" <td>0.308872</td>\n",
" </tr>\n",
" <tr>\n",
" <th>NORTH KALIMANTAN</th>\n",
" <th>Central</th>\n",
" <td>-0.394177</td>\n",
" <td>0.932103</td>\n",
" <td>1.230990</td>\n",
" <td>-1.273467</td>\n",
" <td>0.460739</td>\n",
" <td>0.604457</td>\n",
" </tr>\n",
" <tr>\n",
" <th>NORTH SULAWESI</th>\n",
" <th>Central</th>\n",
" <td>-0.013015</td>\n",
" <td>0.653074</td>\n",
" <td>-0.634037</td>\n",
" <td>0.471395</td>\n",
" <td>1.478582</td>\n",
" <td>1.229851</td>\n",
" </tr>\n",
" <tr>\n",
" <th>CENTRAL SULAWESI</th>\n",
" <th>Central</th>\n",
" <td>-0.266392</td>\n",
" <td>-0.966007</td>\n",
" <td>0.866090</td>\n",
" <td>-0.130028</td>\n",
" <td>0.443012</td>\n",
" <td>0.026746</td>\n",
" </tr>\n",
" <tr>\n",
" <th>SOUTH SULAWESI</th>\n",
" <th>Central</th>\n",
" <td>0.813912</td>\n",
" <td>-0.473556</td>\n",
" <td>-1.214740</td>\n",
" <td>0.233033</td>\n",
" <td>0.622401</td>\n",
" <td>0.990557</td>\n",
" </tr>\n",
" <tr>\n",
" <th>SOUTHEAST SULAWESI</th>\n",
" <th>Central</th>\n",
" <td>0.146140</td>\n",
" <td>0.085434</td>\n",
" <td>-0.814991</td>\n",
" <td>0.805546</td>\n",
" <td>1.415224</td>\n",
" <td>0.743209</td>\n",
" </tr>\n",
" <tr>\n",
" <th>GORONTALO</th>\n",
" <th>Central</th>\n",
" <td>1.013529</td>\n",
" <td>-0.161450</td>\n",
" <td>-1.011981</td>\n",
" <td>0.368327</td>\n",
" <td>0.526117</td>\n",
" <td>-2.967429</td>\n",
" </tr>\n",
" <tr>\n",
" <th>WEST SULAWESI</th>\n",
" <th>Central</th>\n",
" <td>0.005677</td>\n",
" <td>-0.593116</td>\n",
" <td>-1.500844</td>\n",
" <td>-0.361320</td>\n",
" <td>0.412945</td>\n",
" <td>0.129086</td>\n",
" </tr>\n",
" <tr>\n",
" <th>MALUKU</th>\n",
" <th>East</th>\n",
" <td>-0.734740</td>\n",
" <td>-0.342158</td>\n",
" <td>1.003453</td>\n",
" <td>1.748197</td>\n",
" <td>1.011289</td>\n",
" <td>-0.169695</td>\n",
" </tr>\n",
" <tr>\n",
" <th>NORTH MALUKU</th>\n",
" <th>East</th>\n",
" <td>-0.530875</td>\n",
" <td>0.391949</td>\n",
" <td>0.175645</td>\n",
" <td>0.631005</td>\n",
" <td>2.352812</td>\n",
" <td>-1.016838</td>\n",
" </tr>\n",
" <tr>\n",
" <th>WEST PAPUA</th>\n",
" <th>East</th>\n",
" <td>-0.933099</td>\n",
" <td>-0.651113</td>\n",
" <td>2.076139</td>\n",
" <td>-1.159579</td>\n",
" <td>1.382128</td>\n",
" <td>-1.750588</td>\n",
" </tr>\n",
" <tr>\n",
" <th>PAPUA</th>\n",
" <th>East</th>\n",
" <td>-5.187740</td>\n",
" <td>-0.561962</td>\n",
" <td>-1.842944</td>\n",
" <td>0.067567</td>\n",
" <td>-1.017236</td>\n",
" <td>0.272463</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Factors 1 Factors 2 Factors 3 Factors 4 \\\n",
"Province Region \n",
"ACEH West 0.213151 -0.181858 0.527530 1.128943 \n",
"NORTH SUMATERA West -0.447379 -0.341386 1.361850 -1.108200 \n",
"WEST SUMATERA West 0.320698 -1.232980 1.886044 -0.360122 \n",
"RIAU West -0.066843 0.959367 -1.119813 1.548194 \n",
"JAMBI West 0.789713 -1.075963 1.069349 -1.614698 \n",
"SOUTH SUMATERA West 0.228829 -0.567252 -0.492303 0.030032 \n",
"BENGKULU West 0.252115 -1.363703 0.954648 -0.097229 \n",
"LAMPUNG West 0.687480 -2.861992 2.931481 -3.058802 \n",
"BANGKA BELITUNG ISLAND West 0.837486 0.928729 -1.751948 -1.553879 \n",
"RIAU ISLAND West -0.508374 1.742409 1.912176 -0.841399 \n",
"DKI JAKARTA West 0.170310 3.266037 0.669947 -1.128038 \n",
"WEST JAVA West 0.553373 0.091768 -0.638877 -0.038492 \n",
"CENTRAL JAVA West 0.547894 -0.400094 -0.673137 -0.337820 \n",
"DI YOGYAKARTA West 0.237828 0.266943 -0.214521 4.690676 \n",
"EAST JAVA West 0.573270 -1.770365 1.738095 -1.477722 \n",
"BANTEN West 0.201589 1.636382 -1.682450 -0.105598 \n",
"BALI Central -0.124501 1.773795 0.715277 0.484883 \n",
"WEST NUSA TENGGARA Central 0.345893 -0.761601 0.182316 -0.056937 \n",
"EAST NUSA TENGGARA Central 0.345532 -1.739352 1.224085 -1.165089 \n",
"WEST KALIMANTAN West 0.255196 0.750499 -3.104979 1.003659 \n",
"CENTRAL KALIMANTAN West -0.038564 0.618968 -2.227896 0.078942 \n",
"SOUTH KALIMANTAN Central 0.716767 0.584312 -1.274741 0.523116 \n",
"EAST KALIMANTAN Central -0.010683 1.364138 -0.324912 2.054904 \n",
"NORTH KALIMANTAN Central -0.394177 0.932103 1.230990 -1.273467 \n",
"NORTH SULAWESI Central -0.013015 0.653074 -0.634037 0.471395 \n",
"CENTRAL SULAWESI Central -0.266392 -0.966007 0.866090 -0.130028 \n",
"SOUTH SULAWESI Central 0.813912 -0.473556 -1.214740 0.233033 \n",
"SOUTHEAST SULAWESI Central 0.146140 0.085434 -0.814991 0.805546 \n",
"GORONTALO Central 1.013529 -0.161450 -1.011981 0.368327 \n",
"WEST SULAWESI Central 0.005677 -0.593116 -1.500844 -0.361320 \n",
"MALUKU East -0.734740 -0.342158 1.003453 1.748197 \n",
"NORTH MALUKU East -0.530875 0.391949 0.175645 0.631005 \n",
"WEST PAPUA East -0.933099 -0.651113 2.076139 -1.159579 \n",
"PAPUA East -5.187740 -0.561962 -1.842944 0.067567 \n",
"\n",
" Factors 5 Factors 6 \n",
"Province Region \n",
"ACEH West 0.788172 1.702225 \n",
"NORTH SUMATERA West -0.665725 0.635541 \n",
"WEST SUMATERA West -0.926783 -1.116187 \n",
"RIAU West 0.048667 1.492447 \n",
"JAMBI West 1.224877 0.684390 \n",
"SOUTH SUMATERA West -1.071543 -0.437447 \n",
"BENGKULU West 0.633134 -0.307455 \n",
"LAMPUNG West -1.144177 -1.304143 \n",
"BANGKA BELITUNG ISLAND West 0.076898 -0.052605 \n",
"RIAU ISLAND West -0.789010 -0.586194 \n",
"DKI JAKARTA West 0.648238 -0.624196 \n",
"WEST JAVA West -1.157643 0.849553 \n",
"CENTRAL JAVA West -1.415012 0.208667 \n",
"DI YOGYAKARTA West -1.274001 0.520238 \n",
"EAST JAVA West -1.869037 -0.162133 \n",
"BANTEN West -0.551341 1.544308 \n",
"BALI Central -1.731976 -0.865438 \n",
"WEST NUSA TENGGARA Central 0.024782 0.268018 \n",
"EAST NUSA TENGGARA Central -0.411580 -2.549342 \n",
"WEST KALIMANTAN West 0.060603 -0.451072 \n",
"CENTRAL KALIMANTAN West 1.207622 2.439636 \n",
"SOUTH KALIMANTAN Central -0.227285 -0.289499 \n",
"EAST KALIMANTAN Central -0.565893 0.308872 \n",
"NORTH KALIMANTAN Central 0.460739 0.604457 \n",
"NORTH SULAWESI Central 1.478582 1.229851 \n",
"CENTRAL SULAWESI Central 0.443012 0.026746 \n",
"SOUTH SULAWESI Central 0.622401 0.990557 \n",
"SOUTHEAST SULAWESI Central 1.415224 0.743209 \n",
"GORONTALO Central 0.526117 -2.967429 \n",
"WEST SULAWESI Central 0.412945 0.129086 \n",
"MALUKU East 1.011289 -0.169695 \n",
"NORTH MALUKU East 2.352812 -1.016838 \n",
"WEST PAPUA East 1.382128 -1.750588 \n",
"PAPUA East -1.017236 0.272463 "
]
},
"execution_count": 59,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# The factor scores\n",
"df_factors = pd.DataFrame(data = fa.fit_transform(df_scaled),\n",
" index = pd.MultiIndex.from_frame(df[['Province', 'Region']]),\n",
" columns = facs)\n",
"df_factors"
]
},
{
"cell_type": "code",
"execution_count": 60,
"id": "conditional-visiting",
"metadata": {},
"outputs": [],
"source": [
"# Standardize the factors\n",
"scaler = MinMaxScaler()\n",
"df_factors_scaled = pd.DataFrame(data = scaler.fit_transform(df_factors),\n",
" index = pd.MultiIndex.from_frame(df[['Province', 'Region']]),\n",
" columns = facs)"
]
},
{
"cell_type": "code",
"execution_count": 61,
"id": "colonial-print",
"metadata": {
"scrolled": false
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th></th>\n",
" <th>Factors 1</th>\n",
" <th>Factors 2</th>\n",
" <th>Factors 3</th>\n",
" <th>Factors 4</th>\n",
" <th>Factors 5</th>\n",
" <th>Factors 6</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Province</th>\n",
" <th>Region</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>ACEH</th>\n",
" <th>West</th>\n",
" <td>0.870933</td>\n",
" <td>0.437357</td>\n",
" <td>0.601761</td>\n",
" <td>0.540391</td>\n",
" <td>0.629395</td>\n",
" <td>0.863621</td>\n",
" </tr>\n",
" <tr>\n",
" <th>NORTH SUMATERA</th>\n",
" <th>West</th>\n",
" <td>0.764418</td>\n",
" <td>0.411324</td>\n",
" <td>0.739975</td>\n",
" <td>0.251708</td>\n",
" <td>0.285020</td>\n",
" <td>0.666345</td>\n",
" </tr>\n",
" <tr>\n",
" <th>WEST SUMATERA</th>\n",
" <th>West</th>\n",
" <td>0.888276</td>\n",
" <td>0.265830</td>\n",
" <td>0.826813</td>\n",
" <td>0.348240</td>\n",
" <td>0.223185</td>\n",
" <td>0.342375</td>\n",
" </tr>\n",
" <tr>\n",
" <th>RIAU</th>\n",
" <th>West</th>\n",
" <td>0.825782</td>\n",
" <td>0.623587</td>\n",
" <td>0.328863</td>\n",
" <td>0.594491</td>\n",
" <td>0.454233</td>\n",
" <td>0.824824</td>\n",
" </tr>\n",
" <tr>\n",
" <th>JAMBI</th>\n",
" <th>West</th>\n",
" <td>0.963908</td>\n",
" <td>0.291452</td>\n",
" <td>0.691519</td>\n",
" <td>0.186349</td>\n",
" <td>0.732834</td>\n",
" <td>0.675379</td>\n",
" </tr>\n",
" <tr>\n",
" <th>SOUTH SUMATERA</th>\n",
" <th>West</th>\n",
" <td>0.873461</td>\n",
" <td>0.374466</td>\n",
" <td>0.432816</td>\n",
" <td>0.398586</td>\n",
" <td>0.188897</td>\n",
" <td>0.467903</td>\n",
" </tr>\n",
" <tr>\n",
" <th>BENGKULU</th>\n",
" <th>West</th>\n",
" <td>0.877216</td>\n",
" <td>0.244498</td>\n",
" <td>0.672518</td>\n",
" <td>0.382164</td>\n",
" <td>0.592672</td>\n",
" <td>0.491944</td>\n",
" </tr>\n",
" <tr>\n",
" <th>LAMPUNG</th>\n",
" <th>West</th>\n",
" <td>0.947422</td>\n",
" <td>0.000000</td>\n",
" <td>1.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.171692</td>\n",
" <td>0.307613</td>\n",
" </tr>\n",
" <tr>\n",
" <th>BANGKA BELITUNG ISLAND</th>\n",
" <th>West</th>\n",
" <td>0.971612</td>\n",
" <td>0.618587</td>\n",
" <td>0.224143</td>\n",
" <td>0.194197</td>\n",
" <td>0.460920</td>\n",
" <td>0.539077</td>\n",
" </tr>\n",
" <tr>\n",
" <th>RIAU ISLAND</th>\n",
" <th>West</th>\n",
" <td>0.754582</td>\n",
" <td>0.751367</td>\n",
" <td>0.831142</td>\n",
" <td>0.286136</td>\n",
" <td>0.255819</td>\n",
" <td>0.440393</td>\n",
" </tr>\n",
" <tr>\n",
" <th>DKI JAKARTA</th>\n",
" <th>West</th>\n",
" <td>0.864025</td>\n",
" <td>1.000000</td>\n",
" <td>0.625354</td>\n",
" <td>0.249148</td>\n",
" <td>0.596249</td>\n",
" <td>0.433365</td>\n",
" </tr>\n",
" <tr>\n",
" <th>WEST JAVA</th>\n",
" <th>West</th>\n",
" <td>0.925796</td>\n",
" <td>0.482008</td>\n",
" <td>0.408534</td>\n",
" <td>0.389744</td>\n",
" <td>0.168503</td>\n",
" <td>0.705925</td>\n",
" </tr>\n",
" <tr>\n",
" <th>CENTRAL JAVA</th>\n",
" <th>West</th>\n",
" <td>0.924913</td>\n",
" <td>0.401744</td>\n",
" <td>0.402859</td>\n",
" <td>0.351118</td>\n",
" <td>0.107542</td>\n",
" <td>0.587397</td>\n",
" </tr>\n",
" <tr>\n",
" <th>DI YOGYAKARTA</th>\n",
" <th>West</th>\n",
" <td>0.874913</td>\n",
" <td>0.510594</td>\n",
" <td>0.478833</td>\n",
" <td>1.000000</td>\n",
" <td>0.140942</td>\n",
" <td>0.645020</td>\n",
" </tr>\n",
" <tr>\n",
" <th>EAST JAVA</th>\n",
" <th>West</th>\n",
" <td>0.929005</td>\n",
" <td>0.178137</td>\n",
" <td>0.802304</td>\n",
" <td>0.204024</td>\n",
" <td>0.000000</td>\n",
" <td>0.518821</td>\n",
" </tr>\n",
" <tr>\n",
" <th>BANTEN</th>\n",
" <th>West</th>\n",
" <td>0.869069</td>\n",
" <td>0.734065</td>\n",
" <td>0.235656</td>\n",
" <td>0.381084</td>\n",
" <td>0.312114</td>\n",
" <td>0.834415</td>\n",
" </tr>\n",
" <tr>\n",
" <th>BALI</th>\n",
" <th>Central</th>\n",
" <td>0.816484</td>\n",
" <td>0.756489</td>\n",
" <td>0.632864</td>\n",
" <td>0.457280</td>\n",
" <td>0.032465</td>\n",
" <td>0.388749</td>\n",
" </tr>\n",
" <tr>\n",
" <th>WEST NUSA TENGGARA</th>\n",
" <th>Central</th>\n",
" <td>0.892339</td>\n",
" <td>0.342751</td>\n",
" <td>0.544573</td>\n",
" <td>0.387364</td>\n",
" <td>0.448576</td>\n",
" <td>0.598374</td>\n",
" </tr>\n",
" <tr>\n",
" <th>EAST NUSA TENGGARA</th>\n",
" <th>Central</th>\n",
" <td>0.892280</td>\n",
" <td>0.183198</td>\n",
" <td>0.717153</td>\n",
" <td>0.244367</td>\n",
" <td>0.345218</td>\n",
" <td>0.077322</td>\n",
" </tr>\n",
" <tr>\n",
" <th>WEST KALIMANTAN</th>\n",
" <th>West</th>\n",
" <td>0.877713</td>\n",
" <td>0.589503</td>\n",
" <td>0.000000</td>\n",
" <td>0.524224</td>\n",
" <td>0.457060</td>\n",
" <td>0.465383</td>\n",
" </tr>\n",
" <tr>\n",
" <th>CENTRAL KALIMANTAN</th>\n",
" <th>West</th>\n",
" <td>0.830342</td>\n",
" <td>0.568039</td>\n",
" <td>0.145297</td>\n",
" <td>0.404897</td>\n",
" <td>0.728747</td>\n",
" <td>1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>SOUTH KALIMANTAN</th>\n",
" <th>Central</th>\n",
" <td>0.952145</td>\n",
" <td>0.562384</td>\n",
" <td>0.303197</td>\n",
" <td>0.462214</td>\n",
" <td>0.388870</td>\n",
" <td>0.495265</td>\n",
" </tr>\n",
" <tr>\n",
" <th>EAST KALIMANTAN</th>\n",
" <th>Central</th>\n",
" <td>0.834838</td>\n",
" <td>0.689639</td>\n",
" <td>0.460546</td>\n",
" <td>0.659877</td>\n",
" <td>0.308667</td>\n",
" <td>0.605930</td>\n",
" </tr>\n",
" <tr>\n",
" <th>NORTH KALIMANTAN</th>\n",
" <th>Central</th>\n",
" <td>0.772997</td>\n",
" <td>0.619138</td>\n",
" <td>0.718297</td>\n",
" <td>0.230381</td>\n",
" <td>0.551838</td>\n",
" <td>0.660596</td>\n",
" </tr>\n",
" <tr>\n",
" <th>NORTH SULAWESI</th>\n",
" <th>Central</th>\n",
" <td>0.834462</td>\n",
" <td>0.573605</td>\n",
" <td>0.409336</td>\n",
" <td>0.455540</td>\n",
" <td>0.792927</td>\n",
" <td>0.776259</td>\n",
" </tr>\n",
" <tr>\n",
" <th>CENTRAL SULAWESI</th>\n",
" <th>Central</th>\n",
" <td>0.793603</td>\n",
" <td>0.309396</td>\n",
" <td>0.657847</td>\n",
" <td>0.377932</td>\n",
" <td>0.547639</td>\n",
" <td>0.553752</td>\n",
" </tr>\n",
" <tr>\n",
" <th>SOUTH SULAWESI</th>\n",
" <th>Central</th>\n",
" <td>0.967810</td>\n",
" <td>0.389756</td>\n",
" <td>0.313137</td>\n",
" <td>0.424782</td>\n",
" <td>0.590130</td>\n",
" <td>0.732003</td>\n",
" </tr>\n",
" <tr>\n",
" <th>SOUTHEAST SULAWESI</th>\n",
" <th>Central</th>\n",
" <td>0.860127</td>\n",
" <td>0.480975</td>\n",
" <td>0.379359</td>\n",
" <td>0.498659</td>\n",
" <td>0.777920</td>\n",
" <td>0.686257</td>\n",
" </tr>\n",
" <tr>\n",
" <th>GORONTALO</th>\n",
" <th>Central</th>\n",
" <td>1.000000</td>\n",
" <td>0.440687</td>\n",
" <td>0.346726</td>\n",
" <td>0.442240</td>\n",
" <td>0.567323</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>WEST SULAWESI</th>\n",
" <th>Central</th>\n",
" <td>0.837476</td>\n",
" <td>0.370246</td>\n",
" <td>0.265741</td>\n",
" <td>0.348086</td>\n",
" <td>0.540517</td>\n",
" <td>0.572680</td>\n",
" </tr>\n",
" <tr>\n",
" <th>MALUKU</th>\n",
" <th>East</th>\n",
" <td>0.718079</td>\n",
" <td>0.411198</td>\n",
" <td>0.680603</td>\n",
" <td>0.620300</td>\n",
" <td>0.682243</td>\n",
" <td>0.517422</td>\n",
" </tr>\n",
" <tr>\n",
" <th>NORTH MALUKU</th>\n",
" <th>East</th>\n",
" <td>0.750954</td>\n",
" <td>0.530993</td>\n",
" <td>0.543468</td>\n",
" <td>0.476136</td>\n",
" <td>1.000000</td>\n",
" <td>0.360749</td>\n",
" </tr>\n",
" <tr>\n",
" <th>WEST PAPUA</th>\n",
" <th>East</th>\n",
" <td>0.686092</td>\n",
" <td>0.360781</td>\n",
" <td>0.858304</td>\n",
" <td>0.245078</td>\n",
" <td>0.770081</td>\n",
" <td>0.225046</td>\n",
" </tr>\n",
" <tr>\n",
" <th>PAPUA</th>\n",
" <th>East</th>\n",
" <td>0.000000</td>\n",
" <td>0.375330</td>\n",
" <td>0.209069</td>\n",
" <td>0.403430</td>\n",
" <td>0.201760</td>\n",
" <td>0.599196</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Factors 1 Factors 2 Factors 3 Factors 4 \\\n",
"Province Region \n",
"ACEH West 0.870933 0.437357 0.601761 0.540391 \n",
"NORTH SUMATERA West 0.764418 0.411324 0.739975 0.251708 \n",
"WEST SUMATERA West 0.888276 0.265830 0.826813 0.348240 \n",
"RIAU West 0.825782 0.623587 0.328863 0.594491 \n",
"JAMBI West 0.963908 0.291452 0.691519 0.186349 \n",
"SOUTH SUMATERA West 0.873461 0.374466 0.432816 0.398586 \n",
"BENGKULU West 0.877216 0.244498 0.672518 0.382164 \n",
"LAMPUNG West 0.947422 0.000000 1.000000 0.000000 \n",
"BANGKA BELITUNG ISLAND West 0.971612 0.618587 0.224143 0.194197 \n",
"RIAU ISLAND West 0.754582 0.751367 0.831142 0.286136 \n",
"DKI JAKARTA West 0.864025 1.000000 0.625354 0.249148 \n",
"WEST JAVA West 0.925796 0.482008 0.408534 0.389744 \n",
"CENTRAL JAVA West 0.924913 0.401744 0.402859 0.351118 \n",
"DI YOGYAKARTA West 0.874913 0.510594 0.478833 1.000000 \n",
"EAST JAVA West 0.929005 0.178137 0.802304 0.204024 \n",
"BANTEN West 0.869069 0.734065 0.235656 0.381084 \n",
"BALI Central 0.816484 0.756489 0.632864 0.457280 \n",
"WEST NUSA TENGGARA Central 0.892339 0.342751 0.544573 0.387364 \n",
"EAST NUSA TENGGARA Central 0.892280 0.183198 0.717153 0.244367 \n",
"WEST KALIMANTAN West 0.877713 0.589503 0.000000 0.524224 \n",
"CENTRAL KALIMANTAN West 0.830342 0.568039 0.145297 0.404897 \n",
"SOUTH KALIMANTAN Central 0.952145 0.562384 0.303197 0.462214 \n",
"EAST KALIMANTAN Central 0.834838 0.689639 0.460546 0.659877 \n",
"NORTH KALIMANTAN Central 0.772997 0.619138 0.718297 0.230381 \n",
"NORTH SULAWESI Central 0.834462 0.573605 0.409336 0.455540 \n",
"CENTRAL SULAWESI Central 0.793603 0.309396 0.657847 0.377932 \n",
"SOUTH SULAWESI Central 0.967810 0.389756 0.313137 0.424782 \n",
"SOUTHEAST SULAWESI Central 0.860127 0.480975 0.379359 0.498659 \n",
"GORONTALO Central 1.000000 0.440687 0.346726 0.442240 \n",
"WEST SULAWESI Central 0.837476 0.370246 0.265741 0.348086 \n",
"MALUKU East 0.718079 0.411198 0.680603 0.620300 \n",
"NORTH MALUKU East 0.750954 0.530993 0.543468 0.476136 \n",
"WEST PAPUA East 0.686092 0.360781 0.858304 0.245078 \n",
"PAPUA East 0.000000 0.375330 0.209069 0.403430 \n",
"\n",
" Factors 5 Factors 6 \n",
"Province Region \n",
"ACEH West 0.629395 0.863621 \n",
"NORTH SUMATERA West 0.285020 0.666345 \n",
"WEST SUMATERA West 0.223185 0.342375 \n",
"RIAU West 0.454233 0.824824 \n",
"JAMBI West 0.732834 0.675379 \n",
"SOUTH SUMATERA West 0.188897 0.467903 \n",
"BENGKULU West 0.592672 0.491944 \n",
"LAMPUNG West 0.171692 0.307613 \n",
"BANGKA BELITUNG ISLAND West 0.460920 0.539077 \n",
"RIAU ISLAND West 0.255819 0.440393 \n",
"DKI JAKARTA West 0.596249 0.433365 \n",
"WEST JAVA West 0.168503 0.705925 \n",
"CENTRAL JAVA West 0.107542 0.587397 \n",
"DI YOGYAKARTA West 0.140942 0.645020 \n",
"EAST JAVA West 0.000000 0.518821 \n",
"BANTEN West 0.312114 0.834415 \n",
"BALI Central 0.032465 0.388749 \n",
"WEST NUSA TENGGARA Central 0.448576 0.598374 \n",
"EAST NUSA TENGGARA Central 0.345218 0.077322 \n",
"WEST KALIMANTAN West 0.457060 0.465383 \n",
"CENTRAL KALIMANTAN West 0.728747 1.000000 \n",
"SOUTH KALIMANTAN Central 0.388870 0.495265 \n",
"EAST KALIMANTAN Central 0.308667 0.605930 \n",
"NORTH KALIMANTAN Central 0.551838 0.660596 \n",
"NORTH SULAWESI Central 0.792927 0.776259 \n",
"CENTRAL SULAWESI Central 0.547639 0.553752 \n",
"SOUTH SULAWESI Central 0.590130 0.732003 \n",
"SOUTHEAST SULAWESI Central 0.777920 0.686257 \n",
"GORONTALO Central 0.567323 0.000000 \n",
"WEST SULAWESI Central 0.540517 0.572680 \n",
"MALUKU East 0.682243 0.517422 \n",
"NORTH MALUKU East 1.000000 0.360749 \n",
"WEST PAPUA East 0.770081 0.225046 \n",
"PAPUA East 0.201760 0.599196 "
]
},
"execution_count": 61,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_factors_scaled"
]
},
{
"cell_type": "markdown",
"id": "inappropriate-telling",
"metadata": {},
"source": [
"#### Create a composite index"
]
},
{
"cell_type": "code",
"execution_count": 62,
"id": "hispanic-globe",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Factors 1</th>\n",
" <th>Factors 2</th>\n",
" <th>Factors 3</th>\n",
" <th>Factors 4</th>\n",
" <th>Factors 5</th>\n",
" <th>Factors 6</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>Ratio Variance</th>\n",
" <td>0.231925</td>\n",
" <td>0.201341</td>\n",
" <td>0.185293</td>\n",
" <td>0.176202</td>\n",
" <td>0.150799</td>\n",
" <td>0.05444</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Factors 1 Factors 2 Factors 3 Factors 4 Factors 5 \\\n",
"Ratio Variance 0.231925 0.201341 0.185293 0.176202 0.150799 \n",
"\n",
" Factors 6 \n",
"Ratio Variance 0.05444 "
]
},
"execution_count": 62,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Ratio of variance\n",
"df_ratio_var"
]
},
{
"cell_type": "code",
"execution_count": 63,
"id": "explicit-madagascar",
"metadata": {
"scrolled": false
},
"outputs": [],
"source": [
"# Perform aggregation\n",
"dict_index = {}\n",
"for i in range(n_factor):\n",
" key = df_factors_scaled.columns[i]\n",
" value = df_factors_scaled.iloc[:,i].values * df_ratio_var.iloc[:,i].values\n",
" dict_index.update({key:value})"
]
},
{
"cell_type": "code",
"execution_count": 64,
"id": "portuguese-plane",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th></th>\n",
" <th>Factors 1</th>\n",
" <th>Factors 2</th>\n",
" <th>Factors 3</th>\n",
" <th>Factors 4</th>\n",
" <th>Factors 5</th>\n",
" <th>Factors 6</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Province</th>\n",
" <th>Region</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>ACEH</th>\n",
" <th>West</th>\n",
" <td>0.201991</td>\n",
" <td>0.088058</td>\n",
" <td>0.111502</td>\n",
" <td>0.095218</td>\n",
" <td>0.094912</td>\n",
" <td>0.047016</td>\n",
" </tr>\n",
" <tr>\n",
" <th>NORTH SUMATERA</th>\n",
" <th>West</th>\n",
" <td>0.177287</td>\n",
" <td>0.082816</td>\n",
" <td>0.137112</td>\n",
" <td>0.044351</td>\n",
" <td>0.042981</td>\n",
" <td>0.036276</td>\n",
" </tr>\n",
" <tr>\n",
" <th>WEST SUMATERA</th>\n",
" <th>West</th>\n",
" <td>0.206013</td>\n",
" <td>0.053522</td>\n",
" <td>0.153202</td>\n",
" <td>0.061361</td>\n",
" <td>0.033656</td>\n",
" <td>0.018639</td>\n",
" </tr>\n",
" <tr>\n",
" <th>RIAU</th>\n",
" <th>West</th>\n",
" <td>0.191519</td>\n",
" <td>0.125554</td>\n",
" <td>0.060936</td>\n",
" <td>0.104750</td>\n",
" <td>0.068498</td>\n",
" <td>0.044904</td>\n",
" </tr>\n",
" <tr>\n",
" <th>JAMBI</th>\n",
" <th>West</th>\n",
" <td>0.223554</td>\n",
" <td>0.058681</td>\n",
" <td>0.128134</td>\n",
" <td>0.032835</td>\n",
" <td>0.110511</td>\n",
" <td>0.036768</td>\n",
" </tr>\n",
" <tr>\n",
" <th>SOUTH SUMATERA</th>\n",
" <th>West</th>\n",
" <td>0.202577</td>\n",
" <td>0.075395</td>\n",
" <td>0.080198</td>\n",
" <td>0.070232</td>\n",
" <td>0.028486</td>\n",
" <td>0.025473</td>\n",
" </tr>\n",
" <tr>\n",
" <th>BENGKULU</th>\n",
" <th>West</th>\n",
" <td>0.203448</td>\n",
" <td>0.049227</td>\n",
" <td>0.124613</td>\n",
" <td>0.067338</td>\n",
" <td>0.089375</td>\n",
" <td>0.026782</td>\n",
" </tr>\n",
" <tr>\n",
" <th>LAMPUNG</th>\n",
" <th>West</th>\n",
" <td>0.219731</td>\n",
" <td>0.000000</td>\n",
" <td>0.185293</td>\n",
" <td>0.000000</td>\n",
" <td>0.025891</td>\n",
" <td>0.016747</td>\n",
" </tr>\n",
" <tr>\n",
" <th>BANGKA BELITUNG ISLAND</th>\n",
" <th>West</th>\n",
" <td>0.225341</td>\n",
" <td>0.124547</td>\n",
" <td>0.041532</td>\n",
" <td>0.034218</td>\n",
" <td>0.069506</td>\n",
" <td>0.029348</td>\n",
" </tr>\n",
" <tr>\n",
" <th>RIAU ISLAND</th>\n",
" <th>West</th>\n",
" <td>0.175006</td>\n",
" <td>0.151281</td>\n",
" <td>0.154005</td>\n",
" <td>0.050418</td>\n",
" <td>0.038577</td>\n",
" <td>0.023975</td>\n",
" </tr>\n",
" <tr>\n",
" <th>DKI JAKARTA</th>\n",
" <th>West</th>\n",
" <td>0.200389</td>\n",
" <td>0.201341</td>\n",
" <td>0.115874</td>\n",
" <td>0.043900</td>\n",
" <td>0.089914</td>\n",
" <td>0.023593</td>\n",
" </tr>\n",
" <tr>\n",
" <th>WEST JAVA</th>\n",
" <th>West</th>\n",
" <td>0.214715</td>\n",
" <td>0.097048</td>\n",
" <td>0.075698</td>\n",
" <td>0.068674</td>\n",
" <td>0.025410</td>\n",
" <td>0.038431</td>\n",
" </tr>\n",
" <tr>\n",
" <th>CENTRAL JAVA</th>\n",
" <th>West</th>\n",
" <td>0.214510</td>\n",
" <td>0.080888</td>\n",
" <td>0.074647</td>\n",
" <td>0.061868</td>\n",
" <td>0.016217</td>\n",
" <td>0.031978</td>\n",
" </tr>\n",
" <tr>\n",
" <th>DI YOGYAKARTA</th>\n",
" <th>West</th>\n",
" <td>0.202914</td>\n",
" <td>0.102804</td>\n",
" <td>0.088724</td>\n",
" <td>0.176202</td>\n",
" <td>0.021254</td>\n",
" <td>0.035115</td>\n",
" </tr>\n",
" <tr>\n",
" <th>EAST JAVA</th>\n",
" <th>West</th>\n",
" <td>0.215459</td>\n",
" <td>0.035866</td>\n",
" <td>0.148661</td>\n",
" <td>0.035949</td>\n",
" <td>0.000000</td>\n",
" <td>0.028245</td>\n",
" </tr>\n",
" <tr>\n",
" <th>BANTEN</th>\n",
" <th>West</th>\n",
" <td>0.201559</td>\n",
" <td>0.147797</td>\n",
" <td>0.043665</td>\n",
" <td>0.067148</td>\n",
" <td>0.047066</td>\n",
" <td>0.045426</td>\n",
" </tr>\n",
" <tr>\n",
" <th>BALI</th>\n",
" <th>Central</th>\n",
" <td>0.189363</td>\n",
" <td>0.152312</td>\n",
" <td>0.117265</td>\n",
" <td>0.080574</td>\n",
" <td>0.004896</td>\n",
" <td>0.021164</td>\n",
" </tr>\n",
" <tr>\n",
" <th>WEST NUSA TENGGARA</th>\n",
" <th>Central</th>\n",
" <td>0.206955</td>\n",
" <td>0.069010</td>\n",
" <td>0.100905</td>\n",
" <td>0.068254</td>\n",
" <td>0.067645</td>\n",
" <td>0.032576</td>\n",
" </tr>\n",
" <tr>\n",
" <th>EAST NUSA TENGGARA</th>\n",
" <th>Central</th>\n",
" <td>0.206942</td>\n",
" <td>0.036885</td>\n",
" <td>0.132883</td>\n",
" <td>0.043058</td>\n",
" <td>0.052059</td>\n",
" <td>0.004209</td>\n",
" </tr>\n",
" <tr>\n",
" <th>WEST KALIMANTAN</th>\n",
" <th>West</th>\n",
" <td>0.203563</td>\n",
" <td>0.118691</td>\n",
" <td>0.000000</td>\n",
" <td>0.092369</td>\n",
" <td>0.068924</td>\n",
" <td>0.025336</td>\n",
" </tr>\n",
" <tr>\n",
" <th>CENTRAL KALIMANTAN</th>\n",
" <th>West</th>\n",
" <td>0.192577</td>\n",
" <td>0.114370</td>\n",
" <td>0.026923</td>\n",
" <td>0.071344</td>\n",
" <td>0.109895</td>\n",
" <td>0.054440</td>\n",
" </tr>\n",
" <tr>\n",
" <th>SOUTH KALIMANTAN</th>\n",
" <th>Central</th>\n",
" <td>0.220826</td>\n",
" <td>0.113231</td>\n",
" <td>0.056180</td>\n",
" <td>0.081443</td>\n",
" <td>0.058641</td>\n",
" <td>0.026962</td>\n",
" </tr>\n",
" <tr>\n",
" <th>EAST KALIMANTAN</th>\n",
" <th>Central</th>\n",
" <td>0.193620</td>\n",
" <td>0.138853</td>\n",
" <td>0.085336</td>\n",
" <td>0.116272</td>\n",
" <td>0.046547</td>\n",
" <td>0.032987</td>\n",
" </tr>\n",
" <tr>\n",
" <th>NORTH KALIMANTAN</th>\n",
" <th>Central</th>\n",
" <td>0.179277</td>\n",
" <td>0.124658</td>\n",
" <td>0.133095</td>\n",
" <td>0.040594</td>\n",
" <td>0.083217</td>\n",
" <td>0.035963</td>\n",
" </tr>\n",
" <tr>\n",
" <th>NORTH SULAWESI</th>\n",
" <th>Central</th>\n",
" <td>0.193532</td>\n",
" <td>0.115490</td>\n",
" <td>0.075847</td>\n",
" <td>0.080267</td>\n",
" <td>0.119573</td>\n",
" <td>0.042260</td>\n",
" </tr>\n",
" <tr>\n",
" <th>CENTRAL SULAWESI</th>\n",
" <th>Central</th>\n",
" <td>0.184056</td>\n",
" <td>0.062294</td>\n",
" <td>0.121894</td>\n",
" <td>0.066592</td>\n",
" <td>0.082584</td>\n",
" <td>0.030146</td>\n",
" </tr>\n",
" <tr>\n",
" <th>SOUTH SULAWESI</th>\n",
" <th>Central</th>\n",
" <td>0.224459</td>\n",
" <td>0.078474</td>\n",
" <td>0.058022</td>\n",
" <td>0.074847</td>\n",
" <td>0.088991</td>\n",
" <td>0.039850</td>\n",
" </tr>\n",
" <tr>\n",
" <th>SOUTHEAST SULAWESI</th>\n",
" <th>Central</th>\n",
" <td>0.199485</td>\n",
" <td>0.096840</td>\n",
" <td>0.070293</td>\n",
" <td>0.087865</td>\n",
" <td>0.117310</td>\n",
" <td>0.037360</td>\n",
" </tr>\n",
" <tr>\n",
" <th>GORONTALO</th>\n",
" <th>Central</th>\n",
" <td>0.231925</td>\n",
" <td>0.088728</td>\n",
" <td>0.064246</td>\n",
" <td>0.077924</td>\n",
" <td>0.085552</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>WEST SULAWESI</th>\n",
" <th>Central</th>\n",
" <td>0.194232</td>\n",
" <td>0.074546</td>\n",
" <td>0.049240</td>\n",
" <td>0.061333</td>\n",
" <td>0.081510</td>\n",
" <td>0.031177</td>\n",
" </tr>\n",
" <tr>\n",
" <th>MALUKU</th>\n",
" <th>East</th>\n",
" <td>0.166540</td>\n",
" <td>0.082791</td>\n",
" <td>0.126111</td>\n",
" <td>0.109298</td>\n",
" <td>0.102882</td>\n",
" <td>0.028169</td>\n",
" </tr>\n",
" <tr>\n",
" <th>NORTH MALUKU</th>\n",
" <th>East</th>\n",
" <td>0.174165</td>\n",
" <td>0.106911</td>\n",
" <td>0.100701</td>\n",
" <td>0.083896</td>\n",
" <td>0.150799</td>\n",
" <td>0.019639</td>\n",
" </tr>\n",
" <tr>\n",
" <th>WEST PAPUA</th>\n",
" <th>East</th>\n",
" <td>0.159122</td>\n",
" <td>0.072640</td>\n",
" <td>0.159038</td>\n",
" <td>0.043183</td>\n",
" <td>0.116128</td>\n",
" <td>0.012252</td>\n",
" </tr>\n",
" <tr>\n",
" <th>PAPUA</th>\n",
" <th>East</th>\n",
" <td>0.000000</td>\n",
" <td>0.075569</td>\n",
" <td>0.038739</td>\n",
" <td>0.071085</td>\n",
" <td>0.030425</td>\n",
" <td>0.032620</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Factors 1 Factors 2 Factors 3 Factors 4 \\\n",
"Province Region \n",
"ACEH West 0.201991 0.088058 0.111502 0.095218 \n",
"NORTH SUMATERA West 0.177287 0.082816 0.137112 0.044351 \n",
"WEST SUMATERA West 0.206013 0.053522 0.153202 0.061361 \n",
"RIAU West 0.191519 0.125554 0.060936 0.104750 \n",
"JAMBI West 0.223554 0.058681 0.128134 0.032835 \n",
"SOUTH SUMATERA West 0.202577 0.075395 0.080198 0.070232 \n",
"BENGKULU West 0.203448 0.049227 0.124613 0.067338 \n",
"LAMPUNG West 0.219731 0.000000 0.185293 0.000000 \n",
"BANGKA BELITUNG ISLAND West 0.225341 0.124547 0.041532 0.034218 \n",
"RIAU ISLAND West 0.175006 0.151281 0.154005 0.050418 \n",
"DKI JAKARTA West 0.200389 0.201341 0.115874 0.043900 \n",
"WEST JAVA West 0.214715 0.097048 0.075698 0.068674 \n",
"CENTRAL JAVA West 0.214510 0.080888 0.074647 0.061868 \n",
"DI YOGYAKARTA West 0.202914 0.102804 0.088724 0.176202 \n",
"EAST JAVA West 0.215459 0.035866 0.148661 0.035949 \n",
"BANTEN West 0.201559 0.147797 0.043665 0.067148 \n",
"BALI Central 0.189363 0.152312 0.117265 0.080574 \n",
"WEST NUSA TENGGARA Central 0.206955 0.069010 0.100905 0.068254 \n",
"EAST NUSA TENGGARA Central 0.206942 0.036885 0.132883 0.043058 \n",
"WEST KALIMANTAN West 0.203563 0.118691 0.000000 0.092369 \n",
"CENTRAL KALIMANTAN West 0.192577 0.114370 0.026923 0.071344 \n",
"SOUTH KALIMANTAN Central 0.220826 0.113231 0.056180 0.081443 \n",
"EAST KALIMANTAN Central 0.193620 0.138853 0.085336 0.116272 \n",
"NORTH KALIMANTAN Central 0.179277 0.124658 0.133095 0.040594 \n",
"NORTH SULAWESI Central 0.193532 0.115490 0.075847 0.080267 \n",
"CENTRAL SULAWESI Central 0.184056 0.062294 0.121894 0.066592 \n",
"SOUTH SULAWESI Central 0.224459 0.078474 0.058022 0.074847 \n",
"SOUTHEAST SULAWESI Central 0.199485 0.096840 0.070293 0.087865 \n",
"GORONTALO Central 0.231925 0.088728 0.064246 0.077924 \n",
"WEST SULAWESI Central 0.194232 0.074546 0.049240 0.061333 \n",
"MALUKU East 0.166540 0.082791 0.126111 0.109298 \n",
"NORTH MALUKU East 0.174165 0.106911 0.100701 0.083896 \n",
"WEST PAPUA East 0.159122 0.072640 0.159038 0.043183 \n",
"PAPUA East 0.000000 0.075569 0.038739 0.071085 \n",
"\n",
" Factors 5 Factors 6 \n",
"Province Region \n",
"ACEH West 0.094912 0.047016 \n",
"NORTH SUMATERA West 0.042981 0.036276 \n",
"WEST SUMATERA West 0.033656 0.018639 \n",
"RIAU West 0.068498 0.044904 \n",
"JAMBI West 0.110511 0.036768 \n",
"SOUTH SUMATERA West 0.028486 0.025473 \n",
"BENGKULU West 0.089375 0.026782 \n",
"LAMPUNG West 0.025891 0.016747 \n",
"BANGKA BELITUNG ISLAND West 0.069506 0.029348 \n",
"RIAU ISLAND West 0.038577 0.023975 \n",
"DKI JAKARTA West 0.089914 0.023593 \n",
"WEST JAVA West 0.025410 0.038431 \n",
"CENTRAL JAVA West 0.016217 0.031978 \n",
"DI YOGYAKARTA West 0.021254 0.035115 \n",
"EAST JAVA West 0.000000 0.028245 \n",
"BANTEN West 0.047066 0.045426 \n",
"BALI Central 0.004896 0.021164 \n",
"WEST NUSA TENGGARA Central 0.067645 0.032576 \n",
"EAST NUSA TENGGARA Central 0.052059 0.004209 \n",
"WEST KALIMANTAN West 0.068924 0.025336 \n",
"CENTRAL KALIMANTAN West 0.109895 0.054440 \n",
"SOUTH KALIMANTAN Central 0.058641 0.026962 \n",
"EAST KALIMANTAN Central 0.046547 0.032987 \n",
"NORTH KALIMANTAN Central 0.083217 0.035963 \n",
"NORTH SULAWESI Central 0.119573 0.042260 \n",
"CENTRAL SULAWESI Central 0.082584 0.030146 \n",
"SOUTH SULAWESI Central 0.088991 0.039850 \n",
"SOUTHEAST SULAWESI Central 0.117310 0.037360 \n",
"GORONTALO Central 0.085552 0.000000 \n",
"WEST SULAWESI Central 0.081510 0.031177 \n",
"MALUKU East 0.102882 0.028169 \n",
"NORTH MALUKU East 0.150799 0.019639 \n",
"WEST PAPUA East 0.116128 0.012252 \n",
"PAPUA East 0.030425 0.032620 "
]
},
"execution_count": 64,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Create a dataframe\n",
"df_index = pd.DataFrame(dict_index,\n",
" index = pd.MultiIndex.from_frame(df[['Province', 'Region']]))\n",
"df_index"
]
},
{
"cell_type": "code",
"execution_count": 65,
"id": "immune-lottery",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Province</th>\n",
" <th>Region</th>\n",
" <th>Factors 1</th>\n",
" <th>Factors 2</th>\n",
" <th>Factors 3</th>\n",
" <th>Factors 4</th>\n",
" <th>Factors 5</th>\n",
" <th>Factors 6</th>\n",
" <th>Composite Index</th>\n",
" <th>Rank</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>DKI JAKARTA</td>\n",
" <td>West</td>\n",
" <td>0.200389</td>\n",
" <td>0.201341</td>\n",
" <td>0.115874</td>\n",
" <td>0.043900</td>\n",
" <td>0.089914</td>\n",
" <td>0.023593</td>\n",
" <td>0.675010</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>ACEH</td>\n",
" <td>West</td>\n",
" <td>0.201991</td>\n",
" <td>0.088058</td>\n",
" <td>0.111502</td>\n",
" <td>0.095218</td>\n",
" <td>0.094912</td>\n",
" <td>0.047016</td>\n",
" <td>0.638697</td>\n",
" <td>2.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>NORTH MALUKU</td>\n",
" <td>East</td>\n",
" <td>0.174165</td>\n",
" <td>0.106911</td>\n",
" <td>0.100701</td>\n",
" <td>0.083896</td>\n",
" <td>0.150799</td>\n",
" <td>0.019639</td>\n",
" <td>0.636111</td>\n",
" <td>3.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>DI YOGYAKARTA</td>\n",
" <td>West</td>\n",
" <td>0.202914</td>\n",
" <td>0.102804</td>\n",
" <td>0.088724</td>\n",
" <td>0.176202</td>\n",
" <td>0.021254</td>\n",
" <td>0.035115</td>\n",
" <td>0.627013</td>\n",
" <td>4.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>NORTH SULAWESI</td>\n",
" <td>Central</td>\n",
" <td>0.193532</td>\n",
" <td>0.115490</td>\n",
" <td>0.075847</td>\n",
" <td>0.080267</td>\n",
" <td>0.119573</td>\n",
" <td>0.042260</td>\n",
" <td>0.626969</td>\n",
" <td>5.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>MALUKU</td>\n",
" <td>East</td>\n",
" <td>0.166540</td>\n",
" <td>0.082791</td>\n",
" <td>0.126111</td>\n",
" <td>0.109298</td>\n",
" <td>0.102882</td>\n",
" <td>0.028169</td>\n",
" <td>0.615790</td>\n",
" <td>6.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>EAST KALIMANTAN</td>\n",
" <td>Central</td>\n",
" <td>0.193620</td>\n",
" <td>0.138853</td>\n",
" <td>0.085336</td>\n",
" <td>0.116272</td>\n",
" <td>0.046547</td>\n",
" <td>0.032987</td>\n",
" <td>0.613614</td>\n",
" <td>7.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>SOUTHEAST SULAWESI</td>\n",
" <td>Central</td>\n",
" <td>0.199485</td>\n",
" <td>0.096840</td>\n",
" <td>0.070293</td>\n",
" <td>0.087865</td>\n",
" <td>0.117310</td>\n",
" <td>0.037360</td>\n",
" <td>0.609152</td>\n",
" <td>8.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>NORTH KALIMANTAN</td>\n",
" <td>Central</td>\n",
" <td>0.179277</td>\n",
" <td>0.124658</td>\n",
" <td>0.133095</td>\n",
" <td>0.040594</td>\n",
" <td>0.083217</td>\n",
" <td>0.035963</td>\n",
" <td>0.596804</td>\n",
" <td>9.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>RIAU</td>\n",
" <td>West</td>\n",
" <td>0.191519</td>\n",
" <td>0.125554</td>\n",
" <td>0.060936</td>\n",
" <td>0.104750</td>\n",
" <td>0.068498</td>\n",
" <td>0.044904</td>\n",
" <td>0.596161</td>\n",
" <td>10.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>RIAU ISLAND</td>\n",
" <td>West</td>\n",
" <td>0.175006</td>\n",
" <td>0.151281</td>\n",
" <td>0.154005</td>\n",
" <td>0.050418</td>\n",
" <td>0.038577</td>\n",
" <td>0.023975</td>\n",
" <td>0.593262</td>\n",
" <td>11.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>JAMBI</td>\n",
" <td>West</td>\n",
" <td>0.223554</td>\n",
" <td>0.058681</td>\n",
" <td>0.128134</td>\n",
" <td>0.032835</td>\n",
" <td>0.110511</td>\n",
" <td>0.036768</td>\n",
" <td>0.590483</td>\n",
" <td>12.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>CENTRAL KALIMANTAN</td>\n",
" <td>West</td>\n",
" <td>0.192577</td>\n",
" <td>0.114370</td>\n",
" <td>0.026923</td>\n",
" <td>0.071344</td>\n",
" <td>0.109895</td>\n",
" <td>0.054440</td>\n",
" <td>0.569548</td>\n",
" <td>13.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>BALI</td>\n",
" <td>Central</td>\n",
" <td>0.189363</td>\n",
" <td>0.152312</td>\n",
" <td>0.117265</td>\n",
" <td>0.080574</td>\n",
" <td>0.004896</td>\n",
" <td>0.021164</td>\n",
" <td>0.565573</td>\n",
" <td>14.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>SOUTH SULAWESI</td>\n",
" <td>Central</td>\n",
" <td>0.224459</td>\n",
" <td>0.078474</td>\n",
" <td>0.058022</td>\n",
" <td>0.074847</td>\n",
" <td>0.088991</td>\n",
" <td>0.039850</td>\n",
" <td>0.564644</td>\n",
" <td>15.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>WEST PAPUA</td>\n",
" <td>East</td>\n",
" <td>0.159122</td>\n",
" <td>0.072640</td>\n",
" <td>0.159038</td>\n",
" <td>0.043183</td>\n",
" <td>0.116128</td>\n",
" <td>0.012252</td>\n",
" <td>0.562362</td>\n",
" <td>16.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>BENGKULU</td>\n",
" <td>West</td>\n",
" <td>0.203448</td>\n",
" <td>0.049227</td>\n",
" <td>0.124613</td>\n",
" <td>0.067338</td>\n",
" <td>0.089375</td>\n",
" <td>0.026782</td>\n",
" <td>0.560782</td>\n",
" <td>17.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>SOUTH KALIMANTAN</td>\n",
" <td>Central</td>\n",
" <td>0.220826</td>\n",
" <td>0.113231</td>\n",
" <td>0.056180</td>\n",
" <td>0.081443</td>\n",
" <td>0.058641</td>\n",
" <td>0.026962</td>\n",
" <td>0.557284</td>\n",
" <td>18.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>BANTEN</td>\n",
" <td>West</td>\n",
" <td>0.201559</td>\n",
" <td>0.147797</td>\n",
" <td>0.043665</td>\n",
" <td>0.067148</td>\n",
" <td>0.047066</td>\n",
" <td>0.045426</td>\n",
" <td>0.552661</td>\n",
" <td>19.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>GORONTALO</td>\n",
" <td>Central</td>\n",
" <td>0.231925</td>\n",
" <td>0.088728</td>\n",
" <td>0.064246</td>\n",
" <td>0.077924</td>\n",
" <td>0.085552</td>\n",
" <td>0.000000</td>\n",
" <td>0.548374</td>\n",
" <td>20.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>CENTRAL SULAWESI</td>\n",
" <td>Central</td>\n",
" <td>0.184056</td>\n",
" <td>0.062294</td>\n",
" <td>0.121894</td>\n",
" <td>0.066592</td>\n",
" <td>0.082584</td>\n",
" <td>0.030146</td>\n",
" <td>0.547567</td>\n",
" <td>21.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>WEST NUSA TENGGARA</td>\n",
" <td>Central</td>\n",
" <td>0.206955</td>\n",
" <td>0.069010</td>\n",
" <td>0.100905</td>\n",
" <td>0.068254</td>\n",
" <td>0.067645</td>\n",
" <td>0.032576</td>\n",
" <td>0.545346</td>\n",
" <td>22.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>WEST SUMATERA</td>\n",
" <td>West</td>\n",
" <td>0.206013</td>\n",
" <td>0.053522</td>\n",
" <td>0.153202</td>\n",
" <td>0.061361</td>\n",
" <td>0.033656</td>\n",
" <td>0.018639</td>\n",
" <td>0.526394</td>\n",
" <td>23.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>BANGKA BELITUNG ISLAND</td>\n",
" <td>West</td>\n",
" <td>0.225341</td>\n",
" <td>0.124547</td>\n",
" <td>0.041532</td>\n",
" <td>0.034218</td>\n",
" <td>0.069506</td>\n",
" <td>0.029348</td>\n",
" <td>0.524492</td>\n",
" <td>24.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>NORTH SUMATERA</td>\n",
" <td>West</td>\n",
" <td>0.177287</td>\n",
" <td>0.082816</td>\n",
" <td>0.137112</td>\n",
" <td>0.044351</td>\n",
" <td>0.042981</td>\n",
" <td>0.036276</td>\n",
" <td>0.520824</td>\n",
" <td>25.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>WEST JAVA</td>\n",
" <td>West</td>\n",
" <td>0.214715</td>\n",
" <td>0.097048</td>\n",
" <td>0.075698</td>\n",
" <td>0.068674</td>\n",
" <td>0.025410</td>\n",
" <td>0.038431</td>\n",
" <td>0.519976</td>\n",
" <td>26.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>WEST KALIMANTAN</td>\n",
" <td>West</td>\n",
" <td>0.203563</td>\n",
" <td>0.118691</td>\n",
" <td>0.000000</td>\n",
" <td>0.092369</td>\n",
" <td>0.068924</td>\n",
" <td>0.025336</td>\n",
" <td>0.508884</td>\n",
" <td>27.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>WEST SULAWESI</td>\n",
" <td>Central</td>\n",
" <td>0.194232</td>\n",
" <td>0.074546</td>\n",
" <td>0.049240</td>\n",
" <td>0.061333</td>\n",
" <td>0.081510</td>\n",
" <td>0.031177</td>\n",
" <td>0.492037</td>\n",
" <td>28.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>SOUTH SUMATERA</td>\n",
" <td>West</td>\n",
" <td>0.202577</td>\n",
" <td>0.075395</td>\n",
" <td>0.080198</td>\n",
" <td>0.070232</td>\n",
" <td>0.028486</td>\n",
" <td>0.025473</td>\n",
" <td>0.482360</td>\n",
" <td>29.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>CENTRAL JAVA</td>\n",
" <td>West</td>\n",
" <td>0.214510</td>\n",
" <td>0.080888</td>\n",
" <td>0.074647</td>\n",
" <td>0.061868</td>\n",
" <td>0.016217</td>\n",
" <td>0.031978</td>\n",
" <td>0.480108</td>\n",
" <td>30.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>30</th>\n",
" <td>EAST NUSA TENGGARA</td>\n",
" <td>Central</td>\n",
" <td>0.206942</td>\n",
" <td>0.036885</td>\n",
" <td>0.132883</td>\n",
" <td>0.043058</td>\n",
" <td>0.052059</td>\n",
" <td>0.004209</td>\n",
" <td>0.476036</td>\n",
" <td>31.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>31</th>\n",
" <td>EAST JAVA</td>\n",
" <td>West</td>\n",
" <td>0.215459</td>\n",
" <td>0.035866</td>\n",
" <td>0.148661</td>\n",
" <td>0.035949</td>\n",
" <td>0.000000</td>\n",
" <td>0.028245</td>\n",
" <td>0.464181</td>\n",
" <td>32.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>32</th>\n",
" <td>LAMPUNG</td>\n",
" <td>West</td>\n",
" <td>0.219731</td>\n",
" <td>0.000000</td>\n",
" <td>0.185293</td>\n",
" <td>0.000000</td>\n",
" <td>0.025891</td>\n",
" <td>0.016747</td>\n",
" <td>0.447661</td>\n",
" <td>33.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>33</th>\n",
" <td>PAPUA</td>\n",
" <td>East</td>\n",
" <td>0.000000</td>\n",
" <td>0.075569</td>\n",
" <td>0.038739</td>\n",
" <td>0.071085</td>\n",
" <td>0.030425</td>\n",
" <td>0.032620</td>\n",
" <td>0.248439</td>\n",
" <td>34.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Province Region Factors 1 Factors 2 Factors 3 \\\n",
"0 DKI JAKARTA West 0.200389 0.201341 0.115874 \n",
"1 ACEH West 0.201991 0.088058 0.111502 \n",
"2 NORTH MALUKU East 0.174165 0.106911 0.100701 \n",
"3 DI YOGYAKARTA West 0.202914 0.102804 0.088724 \n",
"4 NORTH SULAWESI Central 0.193532 0.115490 0.075847 \n",
"5 MALUKU East 0.166540 0.082791 0.126111 \n",
"6 EAST KALIMANTAN Central 0.193620 0.138853 0.085336 \n",
"7 SOUTHEAST SULAWESI Central 0.199485 0.096840 0.070293 \n",
"8 NORTH KALIMANTAN Central 0.179277 0.124658 0.133095 \n",
"9 RIAU West 0.191519 0.125554 0.060936 \n",
"10 RIAU ISLAND West 0.175006 0.151281 0.154005 \n",
"11 JAMBI West 0.223554 0.058681 0.128134 \n",
"12 CENTRAL KALIMANTAN West 0.192577 0.114370 0.026923 \n",
"13 BALI Central 0.189363 0.152312 0.117265 \n",
"14 SOUTH SULAWESI Central 0.224459 0.078474 0.058022 \n",
"15 WEST PAPUA East 0.159122 0.072640 0.159038 \n",
"16 BENGKULU West 0.203448 0.049227 0.124613 \n",
"17 SOUTH KALIMANTAN Central 0.220826 0.113231 0.056180 \n",
"18 BANTEN West 0.201559 0.147797 0.043665 \n",
"19 GORONTALO Central 0.231925 0.088728 0.064246 \n",
"20 CENTRAL SULAWESI Central 0.184056 0.062294 0.121894 \n",
"21 WEST NUSA TENGGARA Central 0.206955 0.069010 0.100905 \n",
"22 WEST SUMATERA West 0.206013 0.053522 0.153202 \n",
"23 BANGKA BELITUNG ISLAND West 0.225341 0.124547 0.041532 \n",
"24 NORTH SUMATERA West 0.177287 0.082816 0.137112 \n",
"25 WEST JAVA West 0.214715 0.097048 0.075698 \n",
"26 WEST KALIMANTAN West 0.203563 0.118691 0.000000 \n",
"27 WEST SULAWESI Central 0.194232 0.074546 0.049240 \n",
"28 SOUTH SUMATERA West 0.202577 0.075395 0.080198 \n",
"29 CENTRAL JAVA West 0.214510 0.080888 0.074647 \n",
"30 EAST NUSA TENGGARA Central 0.206942 0.036885 0.132883 \n",
"31 EAST JAVA West 0.215459 0.035866 0.148661 \n",
"32 LAMPUNG West 0.219731 0.000000 0.185293 \n",
"33 PAPUA East 0.000000 0.075569 0.038739 \n",
"\n",
" Factors 4 Factors 5 Factors 6 Composite Index Rank \n",
"0 0.043900 0.089914 0.023593 0.675010 1.0 \n",
"1 0.095218 0.094912 0.047016 0.638697 2.0 \n",
"2 0.083896 0.150799 0.019639 0.636111 3.0 \n",
"3 0.176202 0.021254 0.035115 0.627013 4.0 \n",
"4 0.080267 0.119573 0.042260 0.626969 5.0 \n",
"5 0.109298 0.102882 0.028169 0.615790 6.0 \n",
"6 0.116272 0.046547 0.032987 0.613614 7.0 \n",
"7 0.087865 0.117310 0.037360 0.609152 8.0 \n",
"8 0.040594 0.083217 0.035963 0.596804 9.0 \n",
"9 0.104750 0.068498 0.044904 0.596161 10.0 \n",
"10 0.050418 0.038577 0.023975 0.593262 11.0 \n",
"11 0.032835 0.110511 0.036768 0.590483 12.0 \n",
"12 0.071344 0.109895 0.054440 0.569548 13.0 \n",
"13 0.080574 0.004896 0.021164 0.565573 14.0 \n",
"14 0.074847 0.088991 0.039850 0.564644 15.0 \n",
"15 0.043183 0.116128 0.012252 0.562362 16.0 \n",
"16 0.067338 0.089375 0.026782 0.560782 17.0 \n",
"17 0.081443 0.058641 0.026962 0.557284 18.0 \n",
"18 0.067148 0.047066 0.045426 0.552661 19.0 \n",
"19 0.077924 0.085552 0.000000 0.548374 20.0 \n",
"20 0.066592 0.082584 0.030146 0.547567 21.0 \n",
"21 0.068254 0.067645 0.032576 0.545346 22.0 \n",
"22 0.061361 0.033656 0.018639 0.526394 23.0 \n",
"23 0.034218 0.069506 0.029348 0.524492 24.0 \n",
"24 0.044351 0.042981 0.036276 0.520824 25.0 \n",
"25 0.068674 0.025410 0.038431 0.519976 26.0 \n",
"26 0.092369 0.068924 0.025336 0.508884 27.0 \n",
"27 0.061333 0.081510 0.031177 0.492037 28.0 \n",
"28 0.070232 0.028486 0.025473 0.482360 29.0 \n",
"29 0.061868 0.016217 0.031978 0.480108 30.0 \n",
"30 0.043058 0.052059 0.004209 0.476036 31.0 \n",
"31 0.035949 0.000000 0.028245 0.464181 32.0 \n",
"32 0.000000 0.025891 0.016747 0.447661 33.0 \n",
"33 0.071085 0.030425 0.032620 0.248439 34.0 "
]
},
"execution_count": 65,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Assign the composite index and ranking\n",
"df_index['Composite Index'] = df_index.sum(axis = 1).values\n",
"df_index['Rank'] = df_index['Composite Index'].rank(ascending = False)\n",
"df_index = df_index.sort_values(by = 'Rank').reset_index()\n",
"df_index"
]
},
{
"cell_type": "code",
"execution_count": 66,
"id": "warming-overhead",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Province</th>\n",
" <th>Region</th>\n",
" <th>Factors 1</th>\n",
" <th>Factors 2</th>\n",
" <th>Factors 3</th>\n",
" <th>Factors 4</th>\n",
" <th>Factors 5</th>\n",
" <th>Factors 6</th>\n",
" <th>Composite Index</th>\n",
" <th>Rank</th>\n",
" <th>Status</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>DKI JAKARTA</td>\n",
" <td>West</td>\n",
" <td>0.200389</td>\n",
" <td>0.201341</td>\n",
" <td>0.115874</td>\n",
" <td>0.043900</td>\n",
" <td>0.089914</td>\n",
" <td>0.023593</td>\n",
" <td>0.675010</td>\n",
" <td>1.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>ACEH</td>\n",
" <td>West</td>\n",
" <td>0.201991</td>\n",
" <td>0.088058</td>\n",
" <td>0.111502</td>\n",
" <td>0.095218</td>\n",
" <td>0.094912</td>\n",
" <td>0.047016</td>\n",
" <td>0.638697</td>\n",
" <td>2.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>NORTH MALUKU</td>\n",
" <td>East</td>\n",
" <td>0.174165</td>\n",
" <td>0.106911</td>\n",
" <td>0.100701</td>\n",
" <td>0.083896</td>\n",
" <td>0.150799</td>\n",
" <td>0.019639</td>\n",
" <td>0.636111</td>\n",
" <td>3.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>DI YOGYAKARTA</td>\n",
" <td>West</td>\n",
" <td>0.202914</td>\n",
" <td>0.102804</td>\n",
" <td>0.088724</td>\n",
" <td>0.176202</td>\n",
" <td>0.021254</td>\n",
" <td>0.035115</td>\n",
" <td>0.627013</td>\n",
" <td>4.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>NORTH SULAWESI</td>\n",
" <td>Central</td>\n",
" <td>0.193532</td>\n",
" <td>0.115490</td>\n",
" <td>0.075847</td>\n",
" <td>0.080267</td>\n",
" <td>0.119573</td>\n",
" <td>0.042260</td>\n",
" <td>0.626969</td>\n",
" <td>5.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>MALUKU</td>\n",
" <td>East</td>\n",
" <td>0.166540</td>\n",
" <td>0.082791</td>\n",
" <td>0.126111</td>\n",
" <td>0.109298</td>\n",
" <td>0.102882</td>\n",
" <td>0.028169</td>\n",
" <td>0.615790</td>\n",
" <td>6.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>EAST KALIMANTAN</td>\n",
" <td>Central</td>\n",
" <td>0.193620</td>\n",
" <td>0.138853</td>\n",
" <td>0.085336</td>\n",
" <td>0.116272</td>\n",
" <td>0.046547</td>\n",
" <td>0.032987</td>\n",
" <td>0.613614</td>\n",
" <td>7.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>SOUTHEAST SULAWESI</td>\n",
" <td>Central</td>\n",
" <td>0.199485</td>\n",
" <td>0.096840</td>\n",
" <td>0.070293</td>\n",
" <td>0.087865</td>\n",
" <td>0.117310</td>\n",
" <td>0.037360</td>\n",
" <td>0.609152</td>\n",
" <td>8.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>NORTH KALIMANTAN</td>\n",
" <td>Central</td>\n",
" <td>0.179277</td>\n",
" <td>0.124658</td>\n",
" <td>0.133095</td>\n",
" <td>0.040594</td>\n",
" <td>0.083217</td>\n",
" <td>0.035963</td>\n",
" <td>0.596804</td>\n",
" <td>9.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>RIAU</td>\n",
" <td>West</td>\n",
" <td>0.191519</td>\n",
" <td>0.125554</td>\n",
" <td>0.060936</td>\n",
" <td>0.104750</td>\n",
" <td>0.068498</td>\n",
" <td>0.044904</td>\n",
" <td>0.596161</td>\n",
" <td>10.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>RIAU ISLAND</td>\n",
" <td>West</td>\n",
" <td>0.175006</td>\n",
" <td>0.151281</td>\n",
" <td>0.154005</td>\n",
" <td>0.050418</td>\n",
" <td>0.038577</td>\n",
" <td>0.023975</td>\n",
" <td>0.593262</td>\n",
" <td>11.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>JAMBI</td>\n",
" <td>West</td>\n",
" <td>0.223554</td>\n",
" <td>0.058681</td>\n",
" <td>0.128134</td>\n",
" <td>0.032835</td>\n",
" <td>0.110511</td>\n",
" <td>0.036768</td>\n",
" <td>0.590483</td>\n",
" <td>12.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>CENTRAL KALIMANTAN</td>\n",
" <td>West</td>\n",
" <td>0.192577</td>\n",
" <td>0.114370</td>\n",
" <td>0.026923</td>\n",
" <td>0.071344</td>\n",
" <td>0.109895</td>\n",
" <td>0.054440</td>\n",
" <td>0.569548</td>\n",
" <td>13.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>BALI</td>\n",
" <td>Central</td>\n",
" <td>0.189363</td>\n",
" <td>0.152312</td>\n",
" <td>0.117265</td>\n",
" <td>0.080574</td>\n",
" <td>0.004896</td>\n",
" <td>0.021164</td>\n",
" <td>0.565573</td>\n",
" <td>14.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>SOUTH SULAWESI</td>\n",
" <td>Central</td>\n",
" <td>0.224459</td>\n",
" <td>0.078474</td>\n",
" <td>0.058022</td>\n",
" <td>0.074847</td>\n",
" <td>0.088991</td>\n",
" <td>0.039850</td>\n",
" <td>0.564644</td>\n",
" <td>15.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>WEST PAPUA</td>\n",
" <td>East</td>\n",
" <td>0.159122</td>\n",
" <td>0.072640</td>\n",
" <td>0.159038</td>\n",
" <td>0.043183</td>\n",
" <td>0.116128</td>\n",
" <td>0.012252</td>\n",
" <td>0.562362</td>\n",
" <td>16.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>BENGKULU</td>\n",
" <td>West</td>\n",
" <td>0.203448</td>\n",
" <td>0.049227</td>\n",
" <td>0.124613</td>\n",
" <td>0.067338</td>\n",
" <td>0.089375</td>\n",
" <td>0.026782</td>\n",
" <td>0.560782</td>\n",
" <td>17.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>SOUTH KALIMANTAN</td>\n",
" <td>Central</td>\n",
" <td>0.220826</td>\n",
" <td>0.113231</td>\n",
" <td>0.056180</td>\n",
" <td>0.081443</td>\n",
" <td>0.058641</td>\n",
" <td>0.026962</td>\n",
" <td>0.557284</td>\n",
" <td>18.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>BANTEN</td>\n",
" <td>West</td>\n",
" <td>0.201559</td>\n",
" <td>0.147797</td>\n",
" <td>0.043665</td>\n",
" <td>0.067148</td>\n",
" <td>0.047066</td>\n",
" <td>0.045426</td>\n",
" <td>0.552661</td>\n",
" <td>19.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>GORONTALO</td>\n",
" <td>Central</td>\n",
" <td>0.231925</td>\n",
" <td>0.088728</td>\n",
" <td>0.064246</td>\n",
" <td>0.077924</td>\n",
" <td>0.085552</td>\n",
" <td>0.000000</td>\n",
" <td>0.548374</td>\n",
" <td>20.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>CENTRAL SULAWESI</td>\n",
" <td>Central</td>\n",
" <td>0.184056</td>\n",
" <td>0.062294</td>\n",
" <td>0.121894</td>\n",
" <td>0.066592</td>\n",
" <td>0.082584</td>\n",
" <td>0.030146</td>\n",
" <td>0.547567</td>\n",
" <td>21.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>WEST NUSA TENGGARA</td>\n",
" <td>Central</td>\n",
" <td>0.206955</td>\n",
" <td>0.069010</td>\n",
" <td>0.100905</td>\n",
" <td>0.068254</td>\n",
" <td>0.067645</td>\n",
" <td>0.032576</td>\n",
" <td>0.545346</td>\n",
" <td>22.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>WEST SUMATERA</td>\n",
" <td>West</td>\n",
" <td>0.206013</td>\n",
" <td>0.053522</td>\n",
" <td>0.153202</td>\n",
" <td>0.061361</td>\n",
" <td>0.033656</td>\n",
" <td>0.018639</td>\n",
" <td>0.526394</td>\n",
" <td>23.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>BANGKA BELITUNG ISLAND</td>\n",
" <td>West</td>\n",
" <td>0.225341</td>\n",
" <td>0.124547</td>\n",
" <td>0.041532</td>\n",
" <td>0.034218</td>\n",
" <td>0.069506</td>\n",
" <td>0.029348</td>\n",
" <td>0.524492</td>\n",
" <td>24.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>NORTH SUMATERA</td>\n",
" <td>West</td>\n",
" <td>0.177287</td>\n",
" <td>0.082816</td>\n",
" <td>0.137112</td>\n",
" <td>0.044351</td>\n",
" <td>0.042981</td>\n",
" <td>0.036276</td>\n",
" <td>0.520824</td>\n",
" <td>25.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>WEST JAVA</td>\n",
" <td>West</td>\n",
" <td>0.214715</td>\n",
" <td>0.097048</td>\n",
" <td>0.075698</td>\n",
" <td>0.068674</td>\n",
" <td>0.025410</td>\n",
" <td>0.038431</td>\n",
" <td>0.519976</td>\n",
" <td>26.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>WEST KALIMANTAN</td>\n",
" <td>West</td>\n",
" <td>0.203563</td>\n",
" <td>0.118691</td>\n",
" <td>0.000000</td>\n",
" <td>0.092369</td>\n",
" <td>0.068924</td>\n",
" <td>0.025336</td>\n",
" <td>0.508884</td>\n",
" <td>27.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>WEST SULAWESI</td>\n",
" <td>Central</td>\n",
" <td>0.194232</td>\n",
" <td>0.074546</td>\n",
" <td>0.049240</td>\n",
" <td>0.061333</td>\n",
" <td>0.081510</td>\n",
" <td>0.031177</td>\n",
" <td>0.492037</td>\n",
" <td>28.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>SOUTH SUMATERA</td>\n",
" <td>West</td>\n",
" <td>0.202577</td>\n",
" <td>0.075395</td>\n",
" <td>0.080198</td>\n",
" <td>0.070232</td>\n",
" <td>0.028486</td>\n",
" <td>0.025473</td>\n",
" <td>0.482360</td>\n",
" <td>29.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>CENTRAL JAVA</td>\n",
" <td>West</td>\n",
" <td>0.214510</td>\n",
" <td>0.080888</td>\n",
" <td>0.074647</td>\n",
" <td>0.061868</td>\n",
" <td>0.016217</td>\n",
" <td>0.031978</td>\n",
" <td>0.480108</td>\n",
" <td>30.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>30</th>\n",
" <td>EAST NUSA TENGGARA</td>\n",
" <td>Central</td>\n",
" <td>0.206942</td>\n",
" <td>0.036885</td>\n",
" <td>0.132883</td>\n",
" <td>0.043058</td>\n",
" <td>0.052059</td>\n",
" <td>0.004209</td>\n",
" <td>0.476036</td>\n",
" <td>31.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>31</th>\n",
" <td>EAST JAVA</td>\n",
" <td>West</td>\n",
" <td>0.215459</td>\n",
" <td>0.035866</td>\n",
" <td>0.148661</td>\n",
" <td>0.035949</td>\n",
" <td>0.000000</td>\n",
" <td>0.028245</td>\n",
" <td>0.464181</td>\n",
" <td>32.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>32</th>\n",
" <td>LAMPUNG</td>\n",
" <td>West</td>\n",
" <td>0.219731</td>\n",
" <td>0.000000</td>\n",
" <td>0.185293</td>\n",
" <td>0.000000</td>\n",
" <td>0.025891</td>\n",
" <td>0.016747</td>\n",
" <td>0.447661</td>\n",
" <td>33.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>33</th>\n",
" <td>PAPUA</td>\n",
" <td>East</td>\n",
" <td>0.000000</td>\n",
" <td>0.075569</td>\n",
" <td>0.038739</td>\n",
" <td>0.071085</td>\n",
" <td>0.030425</td>\n",
" <td>0.032620</td>\n",
" <td>0.248439</td>\n",
" <td>34.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Province Region Factors 1 Factors 2 Factors 3 \\\n",
"0 DKI JAKARTA West 0.200389 0.201341 0.115874 \n",
"1 ACEH West 0.201991 0.088058 0.111502 \n",
"2 NORTH MALUKU East 0.174165 0.106911 0.100701 \n",
"3 DI YOGYAKARTA West 0.202914 0.102804 0.088724 \n",
"4 NORTH SULAWESI Central 0.193532 0.115490 0.075847 \n",
"5 MALUKU East 0.166540 0.082791 0.126111 \n",
"6 EAST KALIMANTAN Central 0.193620 0.138853 0.085336 \n",
"7 SOUTHEAST SULAWESI Central 0.199485 0.096840 0.070293 \n",
"8 NORTH KALIMANTAN Central 0.179277 0.124658 0.133095 \n",
"9 RIAU West 0.191519 0.125554 0.060936 \n",
"10 RIAU ISLAND West 0.175006 0.151281 0.154005 \n",
"11 JAMBI West 0.223554 0.058681 0.128134 \n",
"12 CENTRAL KALIMANTAN West 0.192577 0.114370 0.026923 \n",
"13 BALI Central 0.189363 0.152312 0.117265 \n",
"14 SOUTH SULAWESI Central 0.224459 0.078474 0.058022 \n",
"15 WEST PAPUA East 0.159122 0.072640 0.159038 \n",
"16 BENGKULU West 0.203448 0.049227 0.124613 \n",
"17 SOUTH KALIMANTAN Central 0.220826 0.113231 0.056180 \n",
"18 BANTEN West 0.201559 0.147797 0.043665 \n",
"19 GORONTALO Central 0.231925 0.088728 0.064246 \n",
"20 CENTRAL SULAWESI Central 0.184056 0.062294 0.121894 \n",
"21 WEST NUSA TENGGARA Central 0.206955 0.069010 0.100905 \n",
"22 WEST SUMATERA West 0.206013 0.053522 0.153202 \n",
"23 BANGKA BELITUNG ISLAND West 0.225341 0.124547 0.041532 \n",
"24 NORTH SUMATERA West 0.177287 0.082816 0.137112 \n",
"25 WEST JAVA West 0.214715 0.097048 0.075698 \n",
"26 WEST KALIMANTAN West 0.203563 0.118691 0.000000 \n",
"27 WEST SULAWESI Central 0.194232 0.074546 0.049240 \n",
"28 SOUTH SUMATERA West 0.202577 0.075395 0.080198 \n",
"29 CENTRAL JAVA West 0.214510 0.080888 0.074647 \n",
"30 EAST NUSA TENGGARA Central 0.206942 0.036885 0.132883 \n",
"31 EAST JAVA West 0.215459 0.035866 0.148661 \n",
"32 LAMPUNG West 0.219731 0.000000 0.185293 \n",
"33 PAPUA East 0.000000 0.075569 0.038739 \n",
"\n",
" Factors 4 Factors 5 Factors 6 Composite Index Rank Status \n",
"0 0.043900 0.089914 0.023593 0.675010 1.0 Above \n",
"1 0.095218 0.094912 0.047016 0.638697 2.0 Above \n",
"2 0.083896 0.150799 0.019639 0.636111 3.0 Above \n",
"3 0.176202 0.021254 0.035115 0.627013 4.0 Above \n",
"4 0.080267 0.119573 0.042260 0.626969 5.0 Above \n",
"5 0.109298 0.102882 0.028169 0.615790 6.0 Above \n",
"6 0.116272 0.046547 0.032987 0.613614 7.0 Above \n",
"7 0.087865 0.117310 0.037360 0.609152 8.0 Above \n",
"8 0.040594 0.083217 0.035963 0.596804 9.0 Above \n",
"9 0.104750 0.068498 0.044904 0.596161 10.0 Above \n",
"10 0.050418 0.038577 0.023975 0.593262 11.0 Above \n",
"11 0.032835 0.110511 0.036768 0.590483 12.0 Above \n",
"12 0.071344 0.109895 0.054440 0.569548 13.0 Above \n",
"13 0.080574 0.004896 0.021164 0.565573 14.0 Above \n",
"14 0.074847 0.088991 0.039850 0.564644 15.0 Above \n",
"15 0.043183 0.116128 0.012252 0.562362 16.0 Above \n",
"16 0.067338 0.089375 0.026782 0.560782 17.0 Above \n",
"17 0.081443 0.058641 0.026962 0.557284 18.0 Above \n",
"18 0.067148 0.047066 0.045426 0.552661 19.0 Above \n",
"19 0.077924 0.085552 0.000000 0.548374 20.0 Below \n",
"20 0.066592 0.082584 0.030146 0.547567 21.0 Below \n",
"21 0.068254 0.067645 0.032576 0.545346 22.0 Below \n",
"22 0.061361 0.033656 0.018639 0.526394 23.0 Below \n",
"23 0.034218 0.069506 0.029348 0.524492 24.0 Below \n",
"24 0.044351 0.042981 0.036276 0.520824 25.0 Below \n",
"25 0.068674 0.025410 0.038431 0.519976 26.0 Below \n",
"26 0.092369 0.068924 0.025336 0.508884 27.0 Below \n",
"27 0.061333 0.081510 0.031177 0.492037 28.0 Below \n",
"28 0.070232 0.028486 0.025473 0.482360 29.0 Below \n",
"29 0.061868 0.016217 0.031978 0.480108 30.0 Below \n",
"30 0.043058 0.052059 0.004209 0.476036 31.0 Below \n",
"31 0.035949 0.000000 0.028245 0.464181 32.0 Below \n",
"32 0.000000 0.025891 0.016747 0.447661 33.0 Below \n",
"33 0.071085 0.030425 0.032620 0.248439 34.0 Below "
]
},
"execution_count": 66,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Above and below the average\n",
"stat = ['Above' if i > df_index['Composite Index'].mean() else 'Below' for i in df_index['Composite Index']]\n",
"df_index['Status'] = stat\n",
"df_index"
]
},
{
"cell_type": "markdown",
"id": "material-housing",
"metadata": {},
"source": [
"### Data visualization"
]
},
{
"cell_type": "markdown",
"id": "incorporated-catering",
"metadata": {},
"source": [
"#### 1 Composite index distribution"
]
},
{
"cell_type": "code",
"execution_count": 67,
"id": "interesting-stone",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"count 34.000000\n",
"mean 0.549547\n",
"std 0.076946\n",
"min 0.248439\n",
"25% 0.520188\n",
"50% 0.559033\n",
"75% 0.596643\n",
"max 0.675010\n",
"Name: Composite Index, dtype: float64"
]
},
"execution_count": 67,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Summary statistic\n",
"df_index['Composite Index'].describe()"
]
},
{
"cell_type": "code",
"execution_count": 68,
"id": "continuous-rally",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 800x480 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"<ggplot: (103746906588)>"
]
},
"execution_count": 68,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"plotnine.options.figure_size = (8, 4.8)\n",
"composite_index_distribution = (\n",
" ggplot(data = df_index)+\n",
" geom_density(aes(x = 'Composite Index'),\n",
" color = 'white',\n",
" fill = '#c22d6d')+\n",
" labs(title = 'Education Index Indonesia 2020')+\n",
" xlab('Composite Index')+\n",
" ylab('Density')+\n",
" theme_minimal()\n",
")\n",
"# Display the viz\n",
"composite_index_distribution"
]
},
{
"cell_type": "code",
"execution_count": 69,
"id": "incoming-murray",
"metadata": {},
"outputs": [],
"source": [
"# Save the graph\n",
"composite_index_distribution.save(filename = 'img/composite_index_distribution.png',\n",
" dpi = 1000,\n",
" verbose = False)"
]
},
{
"cell_type": "markdown",
"id": "loved-trinity",
"metadata": {},
"source": [
"#### 2 Composite index by province"
]
},
{
"cell_type": "code",
"execution_count": 70,
"id": "cheap-central",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Above 19\n",
"Below 15\n",
"Name: Status, dtype: int64"
]
},
"execution_count": 70,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Number of index status\n",
"df_index['Status'].value_counts()"
]
},
{
"cell_type": "code",
"execution_count": 71,
"id": "challenging-belize",
"metadata": {
"scrolled": false
},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 900x1200 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"<ggplot: (103616142963)>"
]
},
"execution_count": 71,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Redefine the data\n",
"df_index_reverse = df_index.sort_values(by = 'Rank', ascending = False).reset_index(drop = True)\n",
"# Data viz\n",
"plotnine.options.figure_size = (9, 12)\n",
"composite_index_province = (\n",
" ggplot(data = df_index_reverse)+\n",
" geom_bar(aes(x = 'Province',\n",
" y = 'Composite Index'),\n",
" width = 0.75,\n",
" fill = np.where(df_index_reverse['Status'] == 'Above','#c22d6d','#80797c'),\n",
" stat = 'identity')+\n",
" geom_hline(yintercept = df_index_reverse['Composite Index'].mean())+\n",
" scale_x_discrete(limits = df_index_reverse['Province'].tolist())+\n",
" labs(title = 'Education Index by Province in Indonesia 2020')+\n",
" xlab('Province')+\n",
" ylab('Composite Index')+\n",
" coord_flip()+\n",
" theme_minimal()\n",
")\n",
"# Display the viz\n",
"composite_index_province"
]
},
{
"cell_type": "code",
"execution_count": 72,
"id": "weighted-original",
"metadata": {},
"outputs": [],
"source": [
"# Save the graph\n",
"composite_index_province.save(filename = 'img/composite_index_province.png',\n",
" dpi = 1000,\n",
" verbose = False)"
]
},
{
"cell_type": "markdown",
"id": "coated-equation",
"metadata": {},
"source": [
"#### 3 Contribution of factors for composite index"
]
},
{
"cell_type": "code",
"execution_count": 73,
"id": "iraqi-timer",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Province</th>\n",
" <th>Factor</th>\n",
" <th>Factor Value</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>PAPUA</td>\n",
" <td>Factors 1</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>LAMPUNG</td>\n",
" <td>Factors 1</td>\n",
" <td>0.219731</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>EAST JAVA</td>\n",
" <td>Factors 1</td>\n",
" <td>0.215459</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>EAST NUSA TENGGARA</td>\n",
" <td>Factors 1</td>\n",
" <td>0.206942</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>CENTRAL JAVA</td>\n",
" <td>Factors 1</td>\n",
" <td>0.214510</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>199</th>\n",
" <td>NORTH SULAWESI</td>\n",
" <td>Factors 6</td>\n",
" <td>0.042260</td>\n",
" </tr>\n",
" <tr>\n",
" <th>200</th>\n",
" <td>DI YOGYAKARTA</td>\n",
" <td>Factors 6</td>\n",
" <td>0.035115</td>\n",
" </tr>\n",
" <tr>\n",
" <th>201</th>\n",
" <td>NORTH MALUKU</td>\n",
" <td>Factors 6</td>\n",
" <td>0.019639</td>\n",
" </tr>\n",
" <tr>\n",
" <th>202</th>\n",
" <td>ACEH</td>\n",
" <td>Factors 6</td>\n",
" <td>0.047016</td>\n",
" </tr>\n",
" <tr>\n",
" <th>203</th>\n",
" <td>DKI JAKARTA</td>\n",
" <td>Factors 6</td>\n",
" <td>0.023593</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>204 rows × 3 columns</p>\n",
"</div>"
],
"text/plain": [
" Province Factor Factor Value\n",
"0 PAPUA Factors 1 0.000000\n",
"1 LAMPUNG Factors 1 0.219731\n",
"2 EAST JAVA Factors 1 0.215459\n",
"3 EAST NUSA TENGGARA Factors 1 0.206942\n",
"4 CENTRAL JAVA Factors 1 0.214510\n",
".. ... ... ...\n",
"199 NORTH SULAWESI Factors 6 0.042260\n",
"200 DI YOGYAKARTA Factors 6 0.035115\n",
"201 NORTH MALUKU Factors 6 0.019639\n",
"202 ACEH Factors 6 0.047016\n",
"203 DKI JAKARTA Factors 6 0.023593\n",
"\n",
"[204 rows x 3 columns]"
]
},
"execution_count": 73,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Redefine the data\n",
"df_contribution = pd.melt(frame = df_index_reverse,\n",
" id_vars = 'Province',\n",
" value_vars = facs,\n",
" var_name = 'Factor',\n",
" value_name = 'Factor Value')\n",
"df_contribution"
]
},
{
"cell_type": "code",
"execution_count": 74,
"id": "sexual-insertion",
"metadata": {
"scrolled": false
},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAABBoAAAQACAYAAABPkTqiAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuNCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8QVMy6AAAACXBIWXMAAA9hAAAPYQGoP6dpAAEAAElEQVR4nOzde5xcdX34/9cnSyQSElYRwfWGFi3WO6igVcR6+aHCu9pq6yXUpPWC31pFFBFJFW28oSCItlgrRgGNN4Q3VfFGY1BULCitVkVEQBmQSNgACYnLcn5/nLM6DLObzWZ2J5t9PR+PeWTncz7nc95n9uxkzns+l1JVFZIkSZIkSb0wr98BSJIkSZKkHYeJBkmSJEmS1DMmGiRJkiRJUs+YaJAkSZIkST1jokGSJEmSJPWMiQZJkiRJktQzJhokSZIkSVLPmGiQJEmSJEk9Y6JBkiRJkiT1jIkGSdoOlVL2LqVUpZTj+x3L1mhiXtnvOKZTKeWqUsrqPh5/afM6H9yvGLY3/f6dbK3Z+HcyW9+T2pVSVpZSqn7HIUlzgYkGSeqhUsrBzYfxiR579zvOqWpuNo4vpTym37GMp+13sLzfsewomhv59mt4pJTym1LKWaWUffsdn2rN32ZVSnlyv2OZS0op+5VSTiilXFJKWVdKWV9K+WEp5ZhSyi7j7LN7KeXfSimtUsrmUsrPm/o7ddS7bynlzaWU1U3djaWUn5VS/rWUct9x2t6paevnTdut5li7T8f5S1I3O225iiRpCj4PnDvOtrUzGUiP7Q28DbgK+FGX7XcHRmcuHM2g3wJvbH5eCBwILAEOLaU8vqqqy/sWGfwpMJu+qfbvpD9eARwxDe2+CXgWcA7wMeov8g4F3gO8qJTypKqqbhurXEpZBKyhvm7/Ffgf4ClN/UcAh7e1fRjwduB84ETgZuAJzbm8uGn7px3xfJz6b/M/gfdTv28fCRxUSjmwqqpbenTekjQuEw2SND0uq6rqzH4HMdOqqtrU7xg0bW7tuKY/Ukr5P+AE4HXAP3bbqZRSgF2qqtowXYFVVbV5utqeDv6d9EdVVSPAyDQ0fSqwrD2ZAHyolHIm8FLg74EPt207Gvgz4A1VVZ3UlP1HKWUdcGQp5fSqqv6rKb8Q2Luqquva9v9oKeX7wEeBdwAvHNtQSvkL6iRDVlX1l23lF1MnQt5InSyWpGnl0AlJ6rNSyotLKZeVUjaVUq4tpZwE3KW77URj88cbe1xKeVAp5aOllKubLrS/LaV8rZTyzLY6+5ZSPlxK+XHT5fe2Usr/llLeWEoZaKt3PDD24ffjbd3oV7fV6Tr2vJTy0lLK90spt5ZSNpRSvldKeVGXequbbvpDpZRPNd2QbyulfKuUsv/Er+T42seXl1IOLaVc3LR7QynltG7dm0sp+5dSvtHEe1Mp5QsTDXsppTytlPKVpu7mUspPm+7L7a/hO5s4/l/Hvvdpfje/LKXsNsnT2qmU8tZSyq+a4/2sS7sfbo73Z13iXdC8vt+e5PG6+Urz7z5Nm2PX6DNKKceWUi4HNlPfWFFKmVdKeW1zvd9WSrm5lHJB+/XY1PtOcy3evUvc+zTH+Ghb2V3maBgra67v/2zau7WU8qVSyp90aXd+KeX1pe7+vqGUcksp5X9KKW/vqFdKKa9orqENzeOiUsrzJvuidfs7GSsrpTyxiXtDKWW4lPLpUsoek227y7HGfid/0fxN/6K5Xq4spbx+nH0m9Z7U1F1QSnlbc/1taq6p80opjxvvvCd7jqWURc3fzNgQgHWllHNKKY/qqFdKKf9U6uEK65t2r2ra3bOt3l3eJ8sk3/8mUlXVdzqSDGM+2/z7yI7yvwNuA/6to/zEtu1jbf+kI8kwmbYBTmovrKrqXOCK9rYlaTrZo0GSpscupZR7dSm/vaqq4bEnpZQjqD9sXk7dPXaE+huwg7Y1gFLKfsA3qW8QTgcuAxZTd3l/BvD1purBwFOB84Crqbt1Pwd4H/BgYOzm9WxgPvAW4N+pv2mDukv9RHG8A/hn6u7B/9IULwE+XUp5cFVV7+rYZSF1t+L/BpYDewKvB85v6m9Lt99nA68BPkL9mjwdeFWz7Q9dqpvXbg119/YPAr+h7hq9uomv8xz/HvgP4IfU3Z+HgT8H3g08FhhLqryVuov0SaWU71ZV9cNSyjzgU8Ag8NyqqtZP8lzeS/37/Cj1zfxLgA+XUu5dVdXxTZ3TqH9/LweO6tj/r4F7NPtP1UObfzuHA72P+nX6JHAD8OumfCV1t/BvA8cCi5rYvlpK+bu2HhMrqa+x51O/Nu1e1lZnS+4LfIt6GNMxwEOAfwKylPLIqqrugDrJQJ00eTr17/jtwK3AvtTfFrd/A/xx6pu1c4GzmrK/Ar5YSnl1VVWnTSKu8TwG+BLwCeDTwP7Ur889gEO2oV2Ad1G/3qdTn9vfUV+H11VVtWqs0ta8JzU34l8GnkbdTf9DwF7Aq4Fvl1Ke3fbN/FadYyllMfV1sk9T97KmziuA75ZSnlJV1aVN9bcAK5p2/6OJ+f7Uf+97MfF71MFM7v1vKsbmULih7bz2BB4IXNSZnKiq6jellF8DB0yl7cYBwB3A97rs813g8OY9onM/Seqtqqp8+PDhw0ePHtQfWqsJHj9rq7sbcAv1h9vd2srvTn3DWgHHt5UvbcoO7nLclfVb+h+eF+B/qT9wP65L/XltPy8c51zOAm4H7tPl/JaOs08FrGx7/hDqm/VLgLu3H7OJ73bqbsFj5aubNo7taPdFTfkrt+J3sLytbO+mbCPw4I765wO/b38d+GOSYb+Ouqc17axuK9uL+tvJLwKlo/4bmvpPbSu7L/XNwS+ob/ze3tQ5cpLX2Nh18GtgsK18AXVypvM1/Q51IuBuHe2spk6I7DKJY14FXAncq3k8APgb4Nomlv+vI7YrgF072viLZtt5wEBb+R7UN4I3je1DnUDZCHyto43SxHJ5l/hWdymrgBd3lL+5KX9WW9kbm7KTtvC38rym3uu71EtgPbBoEq/nnf5O2sruAP58nGvuoZNo9/im7pO7XC+XATt3/A3+jvqGd6rvSX/flP1rRxwPBTZRJyvmTeUcgZOp/y4P6Kg7SH3t/1db2aXA/03i9VlJ2/vk2OswTt27vP9tzaN5fX9J/R78p23l+zfn+plx9rsIuHkS7a9q2vn7jvJbgN+Os8+7mn32m8w5+PDhw8e2PBw6IUnTYyXwzC6PZW11ngXsCnyoavsWu6q/5Xr/Nh7/0dSTip1ZVdV/d26smm9ym5//MHa+lLJzKeWeTW+M84EB6g/GU/U86mF6J1Rt3941x3xf0/5fduxzB/CBjrKx3hcPZdt8saqqK7u0PR94EEDThfspwPnVH78xHfMv3NULqG/y/wPYvZRyr7EH9be8AP/fWOWqqq6l/lb/T6hf4+XU46lP3spz+deqrXdMVY/7P4m7vqanUScHnj9WUEp5KPW3uGdWVbVxksd7EHXCYi31jehnqG/8l1ZV9dWOuh+qqurWjrK/bv5dUVXVHyZCrKpqLfX49UHqHgVUVXUzdeLm6aWU+7W18TTqb4NXTjLmVlVVn+4o63YtLQE2UPe8uZP2v5Wm3m3AZ9p/z83v+hzqBMkTJxlbN9+tquo7k4h3Kj5Utc1l0fwNfrej3a19Txr7nb6jvbCqJwb9FHWisbNr/xbPsZRSqHtRfBf4ZcfrvBPwNeAp5Y9Da24C7ldKeep4Jz+e6Xj/a3p6fIq6R8Q/V1X187bNY0NQxptXZBPjDFNpa/9o4G+bGD/esXmXLbTdHoMkTRuHTkjS9PhlVVXf2EKdsXHi/9dl20+28fhjNw8/3FLFUs9P8M/UvQb27lLlntsQx4Obf7udz/82/3aOl29VHZPlVVV1Y33vwbYuz9aZZAC4sfl3rO1xfy9VVV1bSukc2vCw5t//7KzfZs/2J1VVfbWUcirwWqDFnRNQk9Xtuhkr26et7HPUiZuXUycHaH6GrRs20eKPwxZGgOuBX3TciI/ptgLF1l4LK6mHgyyhHo5Cc/w7qIdkTMZkft9Q/738rNryhJUPo/52/9oJ6uw5wbYtmWy8vWy7vd2tfU96MHBjVVXXd9nW/ju9bBJx0BbLWM+Zg5h4lZ57UfdueDN1omd1KeW31MO6vgl8utrCUKRev/81Q6FOBwI4taqq93RUGUvs7TxOE3dvq9Ot/VdQD5u6CHhhVVVVl/Ynars9BkmaNiYaJGn7VLqUdX6gbNf5ft5t//F8ivpD8X9QDxn4HXWX4f2pb/C2pffbWBwTxd5pomX/tua8Zqrtsdfn5dTf9HfTutOB6pubZzRPd6ceirBuisfv5g+vd1VVm0opnwBeX0p5EPV8Ey8DLq6q6rLxGujitkkkz8Z0u5HZ2tf3m9Q3kS8D3lNK2ZX6G/RvVFX1m0m20evf9zzq4REvmKDOtiQJ+3XtT0a34xe2flnRyZzj2N/UGrr3IhqzFqCqqh+UUh5C3WvsadS9dV4AvKOZy+HnE7TRs/e/pifGf1DPf3FqVVWv7VJt7Nq9X5dtUA+t6np9N3PBfIS6p8chXXoNjbX/0FLKztVdV2O5b1sdSZpWJhokqX9+2fz7Z9STmLW7yyoB/PFGtNs3bA/ueD72wfqxEwVQ6hUOgroL/Ss7tj2kyy5be1NxRfPvI7jrDdgjmn9/yfal/fdyJ6WU+1KPY2839u39TVtxI/6hpv2jqL9N/UwpZf9xbhzG82fUExJ2lsFdX9OPNMf6B+BHwL2B47biWL1wBfUQkocD3+/YdpdroaqqO0opZwBvKaUcQN2bYCGTHzaxNS6nvjlbuIVeDZdTTxD5w6qqbpyg3my1te9JVwB/WkrZs6qqzgkXt+Xvey31cIh7TPZvqhkCdG7zoJRyKPV8IG+ivu7vYgrvf+NqSzIsA06pqurIceL8bSnlGuCxpZS7tw8pa4YJ3Z968svO9pdR90C6CHh2Nf6kuBdTX6MHUk+E2u5JwNWVE0FKmgHO0SBJ/fM16nHhryltSxqWUhZQT07XaSx58Iz2wlLKU6g/VLa7DPgxsGScZebG3v/Hur2Xju2LuOsqBVDPVg+T7058TnOMNzbnNdb+LtRLHo5y15vlvmrmDPg2cEiz+kS75V12+Sz12Ofjm2/d76SUcvfm9Rx7voT6ZuTDVVV9oPn5ocC/bmWo/6+UMtjW7s7Uv7NR6okJ28/pcuqlSZdSr65xC/VkcjPp7Obft7RdfzTj4f+RemLKb3bss7L592XNYz313A29diZ1EuMu3563x8ofbwBPaG4sO+tuy7CJ7cHWvieN/U7vNLdFKWUf6mEvv6BebWarNMNxzgQeWUp5Wbc6HctWdlv+85Lm34neq7b2/a+r5lr4KPXkmCeNl2Rocwb1MIZXd5Qf1ba9vf2l1EmMb1P3ZJho5Z2xfe8UfyklqIexnHGXPSRpGtijQZKmx6ObG8puvllV1XVVVa0vpRxD/e32xaWUj1OPfV9Cl+7FVVVdXkr5KnBEM9nYJdTf8r6M+sP8o9vqVs2H0wuA75RSxpa3XEi9/NmvgGOqqrqllHI+8NJSymbqb5rvQ/0NYLcl4f6P+ib1/5VSNlLfHN5QVdUF3U60qqorSinvpL4R+V4p5SzqD/VLqCeJO66qqqvGeZ366fXU3ahXl1I+zB+Xt3wMddfqP2jmbXgV9bjsnzfDFK6kvsF5GPUkjM9r2noo9dKBP6RekYKqqs4tpXwQeG0p5ZtVVd3l28xx3AD8oPnd/p76xm4/6skWf9Wl/mnUczTcF/j3rew9sc2qqrqg6aFwOPBfpZQvUk88+HLqHhZ/1xlTVVW/KKVcRH297NrEvYneOwV4LvXwksdSL9l4C3UC6Fk0385XVXV2KeWj1EssPqqUcg7138kQ8Djq5RTnT0N8M2Jr35OoEy9LgH8spTwA+Cp/XN6yAK/qMofAZC2nXiJ2ZSnlL6lvsjdSDzN6evPz05q6Py2lfJ/6/eta6uFIS6l7YI379zSF97/xvK/Z53+AH3Z57/9tVVVfb3t+AvXQjhNKKXtTvzc/hfq9/NNVVf0h4dYkCD4G3Ey9EsbzOnNc1R+XhaWqqm+UUj4NvLiUch51Indv6ve0nzWxStL0m6nlLXz48OFjLjzY8vKWFfU3Uu37vJT6A+pm6rH8J1F3U77TUnJN3XtTrz0/TP3N47eoZ7lfSceybU39fZptLeqb0eupZyp/elude1LfhP6G+pv5n1H3Nng6XZaypF5j/tKmbsWdl3q8y7J9TfkS6g/xG5vH9+hYdrCptxq4apzXtmvbE/wOui1veXyX+kvpsmwo8HjqRM2G5vX+QtPOVXQspdjUP4B64sXr217ri6hvmO5JvTLFj6hvGPbp2Pdu1EtT3grsu4XzG4v3GcDbmng2U/d4+acJ9pvfxFQB+2/ldX0VcMUk6nV9Ldu2zwNeR329b6K+mb+AtqUmu+zzcv74t3PgBPGt3lLZRNdC8zt4UxPbbc3v6TLgbV3aeBF1D5Hh5rW/hjo5ccQkX8+7XMvjXd9sYUnZjrrHM/7ylnf5nTD++8bWvCctaI7786b+TdRDFh4/mfOe6Bypv/U/lvrvZiP13+IvqHs7tC9P+mbq947fUv/ttZrfx9O3dL5s5fvfOK/7asZ/v7/Te2TbPntQD2m6rnndLm/Odf44v9NxH+P8rR/btLm5OcZHgD225u/ehw8fPrblUapqqolmSZI0WzS9YK6m7oHSOSREkiSpZ5yjQZKkueGF1MMm/q3fgUiSpB2bPRokSdqBlVIOox7X/s/UXcP/tLrrsneSJEk9Y6JBkqQdWCnlKurJCn9EPYfApX0NSJIk7fBMNEiSJEmSpJ5xjgZJkiRJktQzJhokSZIkSVLPmGiQJEmSJEk9Y6JBkiRJkiT1jIkGSZIkSZLUMyYaJEmSJElSz5hokCRJkiRJPWOiQdqBtVqtnVut1vGtVmvnfscyl4yMjNxnZGTk+JGRkfv0O5a5xOt95nmt94fXen94vfeH13t/eL1rW5lokHZsOwNva/7VzLkP9evuf84zy+t95nmt94fXen94vfeH13t/eL1rm5hokCRJkiRJPWOiQZIkSZIk9YyJBkmSJEmS1DMmGiRJkiRJUs+Uqqr6HYOkadJqtRZvPGrd+uloewULpqPZOWvT8n5HMEkLVvQ7Am2F5WzqdwjSjPNtSnPJPitXlelod2RkZD/gEmD/+fPnXzodx9COzR4NkiRJkiSpZ0w0SJIkSZKknjHRIEmSJEmSesZEgyRJkiRJ6pmd+h2AZk5ErAYOBEaAO4CrgAROyMxbmjoHA6syc6/m+Tzg35v9ngHs2759nGOsyszT2sqeD5wNvCYzP9xRvwIelpk/a54vA04EIjO/3ZQ9Bvgh8P7MPLpj/6uAPYFRYCPwLeA1wD8Ab2mqDQA7N9sByMxdm/3PBQ4B7pOZ6yZ6/SRJkiRJW2aPhrnnyMxcBNwDWAocAHwnInbprBgROwFnAY8BnpqZ10/xmEuBm4BlE1WKiNcCJwDPHEsyNJY1+x/exNTp+U3iYF/q8zoxM9+Vmbs25c8Hrhl73pZkuDfwbGAD8JIpnpskSZIkqY2JhjkqM+/IzB8CLwDuTUcSICJ2pu6FcD/gLzLzxqkcJyL2BJ4DvBLYLyIeOU69twBvBg7OzEvayu8GvBR4PbCQOjEw3jmtA74IPHaS4S0BfgF8gC0kQSRJkiRJk2OiYY7LzJuBrwMHtRXPB74ELAD+v6bOVC0BrszMzwMX0v2G/h3Aq4CDMvMnHdsOa+L5DHXiY9yEQETsAfw1cMUkY1tG3WPjTOokyKMmuZ8kSZIkaRzO0SCAFrBf2/NdgacAL8/Mjd13mbSl1DfzAGcA74qIYzJzpK3OIcDnMrNbgmAZ8IXM3BQRZwBfjog9MnNtW53PR8QdwCLgUuBlWwoqIh4HPBw4KzOvjojvNMd6/Vae3xa1Wq2dqeeI6IdFfTquJEmSplmr1Vo8He0ODg4uHBgYYHR0dOHatWu7HmNoaGhbvozUDs4eDQIYAtonQryJumfAaRHxgqk2GhGPBx7BHxMNn6O+8X1uR9UXA8+KiA907H8f6iTEmU3RBcAN1EMp2r0gMxdTJ0vuDdx3EuEtA76dmVc3z88AlkTE/Ensu7WOBdb36fGbaTgfSZIkbR+m5TPk8PDwmhtvvJHh4eE1E9STxmWiYY6LiMXUq0msaS/PzP+kTgB8IiL+aorNLwMq6skmrwd+Tt2LpnP4wy+BpwF/ExEntpUfTr1ixKeb/VvAvbrsPxbzD4F3Af8aEWW8oJr5J14M7B8R1zdtv7Np+9CtPsstezewW58e95uG85EkSdL2YVo+Qw4ODh60++67Mzg4eNAE9aRxOXRijmpuxB8FvAe4Efh4Z53MzIhYApwZEXdk5jlb0f4C4EXUS02e3bbpicBnI2LPzPxt27GuiIinAaubYx1NPeziPcApbfvfH/h+ROyXmZd2OfTpwFuBvwTGi/d51Nf+I4Db2spPpk5ifHFyZzk5Q0NDm4HNvWxzslqtVj8OK0mSpBkwXcMXRkZGNgDMmzdvg0MkNBUmGuaekyPifcAdwNXAecCLxpuLITO/GBF/B5wVES8GJvNGU1HfzN8BnJ6Zm9q2fTEiLqeeJLK99wKZeXlbsuGRwEOAUzuW1bw+Ir5KnRC4S6IhMzdHxCnA2yLi3MysusS3DDgjM3/VXtgM3fh2ZxJEkiRJkjR5paq63YdJUxMRlwLvalaZUJ+1Wq3FG49aNy1j6FawYDqanbM2Le93BJO0YEW/I9BWWM6mLVeSdjC+TWku2WflqnGHC2+LkZGR/YBLgP3nz5/frRexNCHnaFDPRMTDgT+jS08DSZIkSdLcYKJBPRER7wW+DrwlM6/sdzySJEmSpP5wjgb1RGYeAxzT7zgkSZIkSf1ljwZJkiRJktQzJhokSZIkSVLPmGiQJEmSJEk94/KW0g6s1WotBtYDuw0NDd3c73jmCpeE6g+v95nntd4fXuv94fXeH17v/eH1rm1ljwZJkiRJktQzJhokSZIkSVLPmGiQJEmSJEk9Y6JBkiRJkiT1jIkGSZIkSZLUM646Ie3AWq3W4o1HrVvf7zi2xgoW9DuEHd6m5f2OYA5YsKLfEWgLlrOp3yHsMLzcNRfts3JV6XcM08lVJ7St7NEgSZIkSZJ6xkSDJEmSJEnqGRMNkiRJkiSpZ0w0SJIkSZKkntmp3wFI44mIc4FDgPtk5rq28r8AlgOPA0aAK4B/y8yVEbE38CtgQ0dzb83MkyJiKXBEZh7YcazvAadl5sppOh1JkiRJmhNMNGi7FBH3Bp4N3Aq8BPhQU/584JPA0cBfA8PA44E3ASvbmrhXZjqluCRJkiTNMBMN2l4tAX4BrAKWAR+KiAKcDKzIzNPa6l4MvGDGI5QkSZIk3YVzNGh7tQw4CzgT2C8iHgX8KfAA4HP9DEySJEmSND57NGi7ExGPAx4OnJWZV0fEd6gTD59vqrQm0cz1EdH+/K8z85vNz4+LiOGO+rtuQ8gTarVaOwM7T1f7W7CoT8eVJEnaYbVarcX9jmE6DQ4OLhwYGGB0dHTh2rVru57r0NDQzTMdl2YPEw3aHi0Dvp2ZVzfPzwBWAKc3z4eAK7fQxl4TzNHw3+NMBjldjgXeNo3tS5IkaWat73cA02l4eHjsxzUTVCvTH4lmKxMN2q5ExM7Ai4GdI+L6pngnYHdgH+Aa6vkYTuhPhFPybuCkPh17EfCbPh1bkiRpR7VbvwOYToODg48eGBhYMzo6etDw8PBl/Y5Hs4+JBm1vnkd9XT4CuK2t/GTqng6vB1Y2Qx8+S51NfixwTGb+7UwGOllDQ0Obgc39OHarNZlRJpIkSdoaO/qwgZGRkQ0A8+bN27Cjn6umh4kGbW+WAWdk5q/aCyPiA8C3gVcAzweOA04Efk+9OsWHO9r5XcccDR/OzGOmK2hJkiRJUq1UVdXvGCRNk1artXjjUetm1RjCFSzodwg7vE3L+x3BHLBgRb8j0BYsZ7xpfLS1vNw1F+2zctUOPT/ByMjIfsAlwP7z58+/tN/xaPZxeUtJkiRJktQzJhokSZIkSVLPmGiQJEmSJEk9Y6JBkiRJkiT1jIkGSZIkSZLUMyYaJEmSJElSz7i8pbQDa7Vai4H1wG5DQ0M39zueucIlofrD633mea33h9d6f3i994fXe394vWtb2aNBkiRJkiT1jIkGSZIkSZLUMyYaJEmSJElSz5hokCRJkiRJPWOiQZIkSZIk9YyrTkg7sFartXjjUevW96KtFSzoRTOaYzYt73cEs9iCFf2OYE5azqZ+h6AO/iloe7HPylWl3zHMFFed0LayR4MkSZIkSeoZEw2SJEmSJKlnTDRIkiRJkqSeMdEgSZIkSZJ6Zqd+B6C7iojVwJ8DD8vMK5qyfYGfZmZpq/cE4J3AAUABvgccl5kXt9WpgI1ABdwCfAl4HXAisKSpthMwH7iteX51Zj48Iq4CjsjM89vaOwQ4LTP3niD2pwJPzszvtJWfArwWeHVmntZWvgdwLXBuZr6wS1ur2us35d3iOripu1e3fSNiP+B8YAVwc7P/gZM5niRJkiRp8uzRsP26GXjHeBsj4gDgAuBrwP2B+zU/X9Bsa7d/Zu4KPA54AnBsZh6Rmbs25UcCF449z8yHb2PslwMva4t1PvC3wBVd6i4Bbq2rxe7beNyuIuLPgW8Ab87MD07HMSRJkiRJNRMN269TgcMi4jHjbH8f8KnMfF9mrm8e7wM+DZzQbYfMvBb4KvDY6Qi4zVnAX0XE3ZvnhwKXUfdc6LQMeA/wa+AlvQ4kIp5J3Yvj1Zl5eq/blyRJkiTdmYmG7df1wAeph0bcSUTsQj20YlWX/T4NPLntJr99vwcAz6F7z4JeugG4CHhe83wpsLJLPPsDDwc+RZ2cWNbjOJ4NfA44PDM/0+O2JUmSJEldOEfD9u0E4MqIeAqwtq38HtRJolaXfa5rtt2TP/YguDgi5gELga8Db9uKGD4fEbe3Pd8J+N0k9lsJvDIivgE8iXroxKs66iwDvpWZv4mIM4C3RsSjM/OyrYhvIk8DrgRW96i9KWm1WjsDO/fp8Iv6dFxJkqQdSqvVWtzvGGbK4ODgwoGBAUZHRxeuXbu263kPDQ3dPNNxafYw0bAdy8z1EfFe4N3Ay9s23QTcAQwBP+vY7T7Ntpvayp4A/Bx4BnUC4J7A8CTDeEG3ySAnsd95wL8CxwBnZ+amiPjDxojYGXgxcDRAZl4REd+jTj4cuYW2R6gnr2w3vylv9zbqYRtfiYhDMvPWCfYfr41eOJatS+5IkiRp+7O+3wHMlOHh4bEf10xQrUywTXOcQye2f6cCD6K+YQYgMzdSD034my71/xa4qKlD2z5VZn4dOJN6xYlplZkjwGeBo+gybAL4S+qExwkRcX1EXA88CnhpM3nkRK6hfk3aPRi4uqPsNuAw6uTBlyNiYdv+D4iIgbGKEVGAvbu00QvvBnbr0+N+03A+kiRJc1G/Ps/N+GNwcPCg3XffncHBwYMmqCeNyx4N27nMvC0i3sFd52o4Bvh6RPwC+Ch1RvEfqFdxeMYETZ4E/CoiHpuZP5yOmNusAM7JzO922baMel6GN7aV7QL8D3Vy4OymbKeIWNBW545mv+Mi4gLgJ8C+1AmNUzoPkpkbI+JQ4MvAlyLiOcDF1D063tr0GLmj2X8E+E5nG9tqaGhoM7C51+1ORqvVbXSNJEmSttZcGiowMjKyAWDevHkb5tJ5q3fs0TA7fIw7D4UgMy8Cnk494eG1wG+oJ3p8+jg39mP7/Rb4JDPQlT8zb8jMCzrLI2IIeCZwSmZe3/a4EjiDO08KeSp1z4Sxx9eAjwMfBr5AvQzoucDpjDOkIzM3AM8FBoD/bP59LrA/dQ+GXwNPAZ6Tmbdt63lLkiRJ0lxWqqrqdwySpkmr1Vq88ah1PRlPuIIFW64kddi0vN8RzGILVvQ7gjlpOZv6HYI6+Keg7cU+K1fNmTkJRkZG9gMuAfafP3/+pf2OR7OPPRokSZIkSVLPmGiQJEmSJEk9Y6JBkiRJkiT1jIkGSZIkSZLUMyYaJEmSJElSz5hokCRJkiRJPePyltIOrNVqLQbWA7sNDQ3d3O945gqXhOoPr/eZ57XeH17r/eH13h9e7/3h9a5tZY8GSZIkSZLUMyYaJEmSJElSz5hokCRJkiRJPWOiQZIkSZIk9YyJBkmSJEmS1DOuOiHtwFqt1uKNR61b3+84VrCgp+1tWt7T5qRtt2BFvyPYYSxnU79DmPO8nDVX7bNyVel3DNsLV53QtrJHgyRJkiRJ6hkTDZIkSZIkqWdMNEiSJEmSpJ4x0SBJkiRJknpmp34HoPFFxGrgQGAEuAO4CkjghMy8palzMLAqM/fqsn8Crcw8oq1sf+ACYH/gGuCfgSXAXsD1wJnAv2Tm79v2eSxwPPAU6mvmeuDLwPuBf53oGJl5RUQ8HzgbeE1mfrgjxgp4WGb+rHm+DDgRiMz8dlP2GOCHwPsz8+iO/a8C9gRGgY3At4DXAP8AvKWpNgDs3GwHIDN3bfY/FzgEuE9mrut8DSVJkiRJW8ceDdu/IzNzEXAPYClwAPCdiNhlEvu+CnhhRDwdICLmA6cD/5yZVwCrgMOA5wOLmn8Pbcpp9jkQWAP8N/DwzFwMPBX4NfDkSRyDJu6bgGUTBRsRrwVOAJ45lmRoLGv2PzwiuiXHnt8kDvalfp1OzMx3ZeauTfnzgWvGnrclGe4NPBvYALxkotgkSZIkSZNjomGWyMw7MvOHwAuAe7OFm/Zmn+uA1wH/ERG7Un/Dvx44NSL+Angu8LzM/FFm3p6ZP6K+KX9uRDytaeZ9wCcz81+a9sjM6zLzxMxcNdExACJiT+A5wCuB/SLikd1ijYi3AG8GDs7MS9rK7wa8FHg9sJA6MTDe+a4Dvgg8dkuvTWMJ8AvgA0zi9ZQkSZIkbZmJhlkmM28Gvg4cNMn6ZwL/A3wKOBJYlpkV8Ezg+5l5VUf9q4DvA8+KiIXAk4DPT/EYUN/MX5mZnwcupPsN/Tuoe0YclJk/6dh2GDAf+Az18ItxEwIRsQfw18AV49XpsAw4i3q4yH4R8ahJ7idJkiRJGodzNMxOLWC/raj/Kuqb7+Mz85dN2b2adrq5rtl+D+pk1HVjGyLiOOBo6mvn05n5igmOAfWwibOan88A3hURx2TmSFudQ4DPtQ21aLcM+EJmboqIM4AvR8Qembm2rc7nI+IO6uEflwIvG+e8/iAiHgc8HDgrM6+OiO80x3r9lvbdWq1Wa2fqOSL6YVGfjitJkjSrtFqtxf2OYXsxODi4cGBggNHR0YVr167t+roMDQ3dPNNxafawR8PsNARMeuLCzLwe+B3w47bi3zXtdHOfZvtN1JNQ/qFeZr4zMweBD1H3NBj3GBHxeOAR/DHR8DnqG9/ndhzvxdQ9KD7QXhgR96FOQpzZFF0A3EA9lKLdC5q5I/ajHlZy33HOq90y4NuZeXXz/AxgSTPHRK8dSz2cpB+P30zD+UiSJO2I+vV5bbt7DA8Pr7nxxhsZHh5eM0E9aVz2aJhlImIx8AxgxTY29Q3gqIh4YNvNNhHxQOoJJ9+emRsi4nvUwxEumMIxlgEV9eSVY2U7NeXntNX7JfA04FsRcUdmvqEpP5x6xYhPN6tTAAw2+5/cebDM/GFEvAv414jYv234xp1ExM7UyY2dI+L6trh2p54M84tbfaYTezdwUo/bnKxFmGyQJEmajN36HcD2YnBw8NEDAwNrRkdHDxoeHr6s3/Fo9jHRMEtERAEeBbwHuBH4+La0l5nfjIivAmdHxN9T90R4eNPuVzPzm03Vo4GvNzfkH83M65vVGvYFhieIdwHwIuqlJs9u2/RE4LMRsWdm/rYtniuaCShXN8mGo6mHXbwHOKVt//sD34+I/TLz0i6HPh14K/CX3DmZ0e551Nf+I4Db2spPpk5i9DTRMDQ0tBnY3Ms2J6vVGm90jCRJkto5FOCPRkZGNgDMmzdvg6+LpsKhE9u/kyPiFuqb+jOo5yD488zc2IO2XwicDyT1Eo/nNc9fOFYhMy+iXs7yCcBPI+Jm6uUurwKWT9D286iHXZyemde3Pb4IXE49SeSdZObl1D0blkTE+cBDgFM79v8B8FXGmRQyMzdTJybe1iRnulkGnJGZv2pvm3r1iWc3K2VIkiRJkqagVFXX3uWSdgCtVmvxxqPW9X0M3QoW9LS9TROluKR+WLCto9k0Zjmb+h3CnOflrLlqn5WrxvuSas4ZGRnZD7gE2H/+/PndehFLE7JHgyRJkiRJ6hkTDZIkSZIkqWdMNEiSJEmSpJ4x0SBJkiRJknrGRIMkSZIkSeoZEw2SJEmSJKlnXN5S2oG1Wq3FwHpgt6GhoZv7Hc9c4ZJQ/eH1PvO81vvDa70/vN77w+u9P7zeta3s0SBJkiRJknrGRIMkSZIkSeoZEw2SJEmSJKlnTDRIkiRJkqSeMdEgSZIkSZJ6xlUnpB1Yq9VavPGodev7Hcd4VrCg3yFoG21a3u8IZpEFK/odwXZrOZv6HYK2kpezdkT7rFxV+h3D9sJVJ7St7NEgSZIkSZJ6xkSDJEmSJEnqGRMNkiRJkiSpZ0w0SJIkSZKkntmp3wHMBRGxGvhz4GGZeUVTti/w08wsbfWeALwTOAAowPeA4zLz4rY6FbARqIBbgC8BrwNOBJY01XYC5gO3Nc+vzsyHR8RVwBGZeX5be4cAp2Xm3uPE/iTgvcAjm6IrgLdm5pcjYmnT3oFdzndVZp4WEQc3P+81wevzGOCHwPsz8+im7InABcBgZm5uylYAxwF7ZeZvm7LXAP+QmY9t4vlY23mPeVpm/iAiHgacBDyheY2uAU7MzJVNWxX17+hn48UqSZIkSZqYiYaZczPwDuAl3TZGxAHAN4G3Ay9oil8JXBART8/M77dV3z8zfxYR9wW+AhybmUcARzRtHQG8KDMP3paAI2IxdSLjSOAs6uTFAcDotrTbxTLgJuDwiDg2M28HftAc5wBgTVPvIOCnwFOBz7aVfautrR90Jj7a/CdwOvB84A7gMcC9encakiRJkiQTDTPnVOANEfGYzPxRl+3vAz6Vme9rL4uIhwInUN9c30lmXhsRXwUeOx0BAw8F5mfmJ5rntwOre3mAiLgb8FLg9cCHgGcD52Xm7RHxHerzXhMRC4CHU/do6Ew0HDGJ49wLeDDw75k5to7axRPsIkmSJEmaAudomDnXAx+kHhpxJxGxC/XQilVd9vs08OSIuHuX/R4APId6OMN0uBzYHBFnRcShEbHHNBzjMOqeEp8Bzqbu3TDmW/wxwXIA9fCKb46VRcSfAvcGLpzEcW4EfgF8MiL+uukNIkmSJEnqMXs0zKwTgCsj4inA2rbye1AnfVpd9rmu2XZP4Nqm7OKImAcsBL4OvG0rYvh8RNze9nwn4HfdKmbmzRHxZOBo4MPA/SLiW8ArMvOXW3HMiSwDvpCZmyLiDODLEbFHZq6l7j1xXETMp+nZkJm/iIh7ND0Ungr8b2be2Nbe4yJiuOMYe2bm5oj4C+AY4N3APhFxKfCqzLykR+fSVavV2hnYeTqPMYFFfTquJEnSrNJqtRb3O4btxeDg4MKBgQFGR0cXrl27tuvrMjQ0dPNMx6XZw0TDDMrM9RHxXuob3Ze3bbqJes6AIaBzIsL7NNtuait7AvBz4BnASuokxPAkw3hBt8kgJ4j5p8DfN3X3Bj4CnAE8CRih7o3QaX6zbUIRcR/gEOBZTdEFwA3UQylOpp6nAeDx1EMkVjTPv90875yfAeC/x5ujITN/A/xTc+w9gfcD50bE/TOz2lK82+BYti4ZJEmSpJm3vt8BbC+Gh4fHflwzQbUywTbNcQ6dmHmnAg8CDh0ryMyNwEXA33Sp/7fARU0d2vapMvPrwJnUK05Mu8y8ijr+sRUorgEeEBEDY3UiogB7A1dPosnDgQHg0xFxPXWPjnvRDJ/IzBHq1+UZwH7A2ISYa6h7MxzEFOeMaFateC9wX+pEzXR6N7Bbnx73m+ZzkyRJ2lH06/PadvcYHBw8aPfdd2dwcPCgCepJ47JHwwzLzNsi4h3cda6GY4CvR8QvgI9SZwj/gXrJymdM0ORJwK8i4rGZ+cNextoswXkY9fwJvwb2oO6J8d2mysXUPSne2vTUuAM4iro3w3c62lrQ0fzvgaXAe4BT2srvD3w/IvbLzEupeyy8Bvi/zBxbtnIN8M/U8zNMlGVtP/49mtjOAH4J7Nq0+4uOoRc9NzQ0tBnYPJ3HGE+r1W00jiRJkjo5FOCPRkZGNgDMmzdvg6+LpsJEQ398DHgjsPtYQWZeFBFPpx4ecHxT/H3g6Zn5vfEayszfRsQnqbvmP6/Hcd4CPA54HTBIvUTnBcCrm2NvjojnUic7xnow/DfwnLakAMCeQPtzqIcTPAQ4NTOvbyu/vllJYxlwKXWPhX+hXpZyzI+ph2f8JDM755d4fETc2lH2IuC/qJMYX6VOmGykTpgcNuErIEmSJEnaKqWqpnNouqR+arVaizcetW67HW+4gs6OLpptNi3vdwSzyIIVW64zRy1n05Yrabvi5awd0T4rVznnQGNkZGQ/4BJg//nz51/a73g0+zhHgyRJkiRJ6hkTDZIkSZIkqWdMNEiSJEmSpJ4x0SBJkiRJknrGRIMkSZIkSeoZEw2SJEmSJKlnXN5S2oG1Wq3FwHpgt6GhoZv7Hc9c4ZJQ/eH1PvO81vvDa70/vN77w+u9P7zeta3s0SBJkiRJknrGRIMkSZIkSeoZEw2SJEmSJKlnTDRIkiRJkqSeMdEgSZIkSZJ6xlUnpB1Yq9VavPGodetn4lgrWDATh9EENi3vdwTqasGKfkegabKcTf0OYVbyT0IzaZ+Vq0q/Y5iNXHVC28oeDZIkSZIkqWdMNEiSJEmSpJ4x0SBJkiRJknrGRIMkSZIkSeqZnfodgHYsEbEaeCrw5Mz8Tlv5KcBrgVdn5mlN2R7AtcC5mfnCLu2sGqvbVn4VcERmnt9WdnBTd69u+0bEfsD5wArg5mb/AydzPEmSJEnS1rFHg6bD5cDLxp5ExHzgb4ErOuotAW6tq8Tu0xFIRPw58A3gzZn5wek4hiRJkiTpj0w0aDqcBfxVRNy9eX4ocBl174V2y4D3AL8GXtLrICLimcCXqHtRnN7r9iVJkiRJd2WiQdPhBuAi4HnN86XAyvYKEbE/8HDgU9SJiWU9juHZwOeAwzPzMz1uW5IkSZI0Dudo0HRZCbwyIr4BPIl66MSr2rYvA76Vmb+JiDOAt0bEozPzsh4d/2nAlcDqHrU3Za1Wa2dg5z4dflGfjitJktR3rVZrcb9jmI0GBwcXDgwMMDo6unDt2rVdX8OhoaGbZzouzR4mGjRdzgP+FTgGODszN0UEABGxM/Bi4GiAzLwiIr5HnXw4cgvtjgDzO8rmN+Xt3kY9ZOMrEXFIZt46wf7jtdErxzbxSJIkaWat73cAs9Hw8PDYj2smqFamPxLNViYaNC0ycyQiPgscBfx5x+a/BO4JnBAR72rKFgH7RMTRmTnRDf81wIM6yh4MXN1RdhtwGPUcDV+OiGdn5oZm/wdExEBmjgJERAH27tJGr7wbOGma2t6SRcBv+nRsSZKkftut3wHMRoODg48eGBhYMzo6etDw8HCvehxrDjHRoOm0AjgnM7/bUb6Mel6GN7aV7QL8D3Vy4OymbKeIWNBW545mv+Mi4gLgJ8C+1MmMUzoPnpkbI+JQ4MvAlyLiOcDFwDD1UI33Nm0eRd2b4TudbfTC0NDQZmDzdLS9Ja1Wqx+HlSRJ2i7YvX9qRkZGNgDMmzdvg6+hpsJEg6ZNZt4AXNBRfE/gmcATM/P69g3NXA3L+GOi4dTmMeZb1HMvDAJfAIaA64CPAaeNE8OGiHgu8BXgP6mHUzyXuofBWA+G/waek5m3bfVJSpIkSZLupFRV1e8YJE2TVqu1eONR62ZkbOIKFmy5kqbVpuX9jkBdLVjR7wg0TZazqd8hzEr+SWgm7bNylfMITMHIyMh+wCXA/vPnz7+03/Fo9nF5S0mSJEmS1DMmGiRJkiRJUs+YaJAkSZIkST1jokGSJEmSJPWMiQZJkiRJktQzJhokSZIkSVLPuLyltANrtVqLgfXAbkNDQzf3O565wiWh+sPrfeZ5rfeH13p/eL33h9d7f3i9a1vZo0GSJEmSJPWMiQZJkiRJktQzJhokSZIkSVLPmGiQJEmSJEk9Y6JBkiRJkiT1jKtOSDuwVqu1eONR69b36/grWNCvQ2+1Tcv7HYGmZMGKfkcwqy1nU79D0HbAPyPtiPZZuar0O4bZzFUntK3s0SBJkiRJknrGRIMkSZIkSeoZEw2SJEmSJKlnTDRIkiRJkqSe2anfAexoImI1cCBwe1vxzzNz/7Y684EWcFVmPr5j/4cBJwFPoP79XAOcCPwS+Epb1YXARmBsNs9nZ+aFHW2tBK7PzDc3z/cGvgl8MTPf2FbvR8CewP0z8/a28uOBfTPzReOc56rMPK1p91fALzLzoR3neS2wB3D3zNzUtu31zXkemplfaisfa2t1Zj6trfw9wF7AW4H/awtlF2AzMNo8f1VmnhURzwfOBl6TmR/uiL0CfgH82dj5RsQRwIsy8+DOc5UkSZIkTZ6JhulxZGaeNsH2Q4H5wH4R8YjM/HHbtv8ETgeeD9wBPAa4V5NE2BUgIhYAtwEPz8yrJhNQROwLfAP4j8w8vq38scDDm/YOaY4/VVVEPCkzL2qeHwqso040dFoK3AQsA77UZfujIuJZmfm19sLMvIbmdWjiv546QbB6gvY/zF3tDvw98O8Tn5IkSZIkaWs4dKI/lgFnAaubnwGIiHsBDwb+PTM3ZebvM/PizPzythwsIh4DfAv4QHuSoS2WrwGfa49lij5BfYM/ZmlT1hnPftTJjSOAwyJi9y5tvQd4V0Rs9dJEEbEn8BzgldTJnEeO0/5bI+LuW9u+JEmSJGl8JhpmWHMT/GzqRMOZwJJmiAHAjdRd+j8ZEX8dEfftwSH3ox4u8dbMPLEjlrsBL2mL5bAm2TFVZwLPj4gFEbEH8CTgi13qLQMuoE5utICXdqnzEepeBy+YQhxLgCsz8/PAhXRPoJwHXA28ZgrtS5IkSZLG4dCJ6XFSM6fAmC9k5j80Px8OXJOZF0XE/1J3638OcG5mVhHxF8AxwLuBfSLiUup5By6ZYiwHAjcD2WVbADsD51APnbie+qb/lCke6wbgu8DzgPtQz5Gwqb1CW3Lj9c35nkWdCPhgR1u/B94G/EtEnL2VcSylTp4AnEHdM+KYzBzpqHcs8MWImNbhE61Wa2fq17kfFvXpuJIkSX3TarUW9zuG2WxwcHDhwMAAo6OjC9euXdv1tRwaGrp5puPS7GGiYXocNcEcDUtpboIz85aIOJf6Rvvcpuw3wD/BH3o/vB84NyLun5lV1xYndhowBPxXRBycmde3bVtGPTHkxuZ4Yzf9U000AKykHrKwF/DqLtv/ElhAnYSAOhFwXEQ8JjN/1FH3TOBotmJIR0Q8HngEdbID6l4TpwLPpU6o/EFmromI7zfH+M1kjzEFx1InTSRJkjQz1vc7gNlseHh47Mc1E1Tb6iHOmjtMNMygiHgC9dwE942IVzbFuwB3j4h7Z+YN7fUz87cR8V7qoQD3pB5asbXuAF5GfUN/QUQ8rWn3PsD/B2xsJlSE+lv3wYh4bGb+cArHgnpIwmnAusz8brOKRLtlwN2AKyJirKxqyl/XXjEz74iI5cCHgC9M8vjLmva+09b+Tk35OV3qv4X6DfTELtt65d3UK2z0wyKmN4kiSZK0Pdqt3wHMZoODg48eGBhYMzo6etDw8PBl/Y5Hs4+Jhpm1jPqm9m/bygr1cIMlEfFx4CjqpMAvqVdXeA31spFTSTIAkJmjEXE4dU+KCyLiacDfUS+d+aSO6l9o4hxLNMxrVrlob28T48jMkYh4FvWSk3cSEUPAs6hX1PhB26a/oZ6Y8egu7Z0bEW+mTrZMuCJGE+eLqF+z9uEWTwQ+GxF7ZuZvO9r/UUR8iboXSfvqHz0zNDS0mS6vx0xotVr9OKwkSVJf2a1/24yMjGwAmDdv3gZfS02FiYbpcXJEvL/t+TCwD/VN8Cs7hi8QEf9GfXP/EeD+wFepl4TcSJ2EOGxbA2qSDUuAT1FPDrkT8G9dYvkg8OGIeGNT9MLm0W7CblJdhkCM+Tvg55l5XscxP0o9tOAwoNtcFMcC/zXRMRvPo+7BcXpHMuSLEXE5dbKiW8+Ff2Zqk05KkiRJkjqUqprKsH9Js0Gr1Vq88ah1fRujuIIFW660ndi0vN8RaEoWrOh3BLPacsbtoKY5xD8j7Yj2WbnK+QO2wcjIyH7UXwDuP3/+/Ev7HY9mH5e3lCRJkiRJPWOiQZIkSZIk9YyJBkmSJEmS1DMmGiRJkiRJUs+YaJAkSZIkST1jokGSJEmSJPWMy1tKO7BWq7UYWA/sNjQ0dHO/45krXBKqP7zeZ57Xen94rfeH13t/eL33h9e7tpU9GiRJkiRJUs+YaJAkSZIkST1jokGSJEmSJPWMiQZJkiRJktQzJhokSZIkSVLPuOqEtANrtVqLNx61bn2/4xizggX9DkFTsGl5vyPYQSxY0e8IthvL2dTvEOYELznNJfusXFX6HcOOxFUntK3s0SBJkiRJknrGRIMkSZIkSeoZEw2SJEmSJKlnTDRIkiRJkqSe2anfAcyUiHgS8F7gkU3RFcBbM/PLzfbFwDuBvwYGgWuA04BTMrNq6lwFHJGZ57e1ezCwKjP3iohb2w55d2AEuL15/i7gorG6HbGtAn6Wmcc3zytgI9A+U+d/ZOaRbfs8Bvgh8P7MPLqjvUOBtwP7AKPA/wGvB54JvKWpNgDs3BwHgMzctcvr1rWtzPxBRBwP7JuZL+rY5w+vU0QsbX4+sLPttvrPB84GXpOZH27KXgy8KzMf1FbvTCCAe2bm7U3Z+4E/ycznN/EcB2zuOMSDM/OGia6BiNgb+BVw98x0ljJJkiRJmqI5kWhokghfAo4EzgLmAwdQ3zgTEXcDvg7cAjyV+obzicAngQdS36RvUfuNekR8DzgtM1e2lR28FWHvn5k/m2D7MuAm4PCIOLbtxvtPgE8BfwN8DdiF+pw2Z+a7qBMeRMQhTXx7j3eAidraivOYjKXNuSwDPtyUrQb2jogHZOY1TdlTgGuB/YCLm7KDmhjHfKEz8QFbvgYkSZIkSb0xJxINwEOB+Zn5ieb57dQ3smOWAH9C/c33zU3ZhRGxBFgTER/KzF/OWLRb0CRGXkqdAPkQ8GzgvGbzY4Fft/W6uJX6BnsqetlWVxGxJ/Ac4MXAZyPikZn5v5l5XURcTp3YOCMiHkSd4Ph8U3ZxROzaxPjKSRxqS9eAJEmSJKkH5socDZcDmyPirIg4NCL26Nj+TODLbUkGADLzO9TfoD9jhuKcrMOov5H/DPWQg2Vt2y4F/iQiPhgRz4yI3bbhOL1sazxLgCsz8/PAhdz5XL5FnVSAuufCmuYxVvbn1L1Q/mcSx9nSNSBJkiRJ6oE5kWhoEghPpv5G/MPA9RFxQTM0AOBeQGuc3a9rtvfKvSNiuP0B/FWXehd31Gu/AV9GPURgE3AG8Icb58y8EjgYuDf10I/fRcTZU7mx7mVbE1hKPZQB6nNZEhHzm+er+WNS4anUSYaLgAMjYl5TdmFm3tHW3l91vG4/b85lS9eAJEmSJKkH5srQCTLzp8DfAzQT/32E+sb2ScDvgKFxdr1Psx3qyR3nd2yf35RP1g3jTAbZ6Qnd5miIiPsAhwDPaoouAG6gHkpxMkBmfg94UVP/EdRJglOAl2xFnEyirW6vB0zyNYmIxwOPAJ7XFH0OOBV4LnAOdY+GfSJiiLpHwzsyc0NE/BJ4TFN2dkezZ3ebo6E5l4mugWnTarV2pp54sx8W9em4kiRJM6bVai3udww7ksHBwYUDAwOMjo4uXLt2bdfXdmho6OZu5RLMoURDu8y8KiJOBT7dFH0DeE9ELMrMW8bqRcQTgfsC32yKrgEexJ09GLh6mkNudzj1ihGfblangHqVjGU0iYZ2mfnjiDgdeNW2HrhLW9dQr9LxBxGxC7Ank3tNllGvrPGdiBgr26kpPyczr42IK6iTGnfLzKuaOmuoky2PB147xXPpvAam07HA22bgOJIkSXPV+n4HsCMZHh4e+3HNBNXK9Eei2WpOJBoiYl/qeQ0+A/wa2AN4OfDdpsoZwKuBL0TEq6lvkg8EPgF8ODOvaOqdBRwXERcAPwH2BY6i/oZ/piwF3tNxzPsD34+I/ahXhngEcG4zoeIDqXs7fLezoS2JiCdvoa2vAKdExMupezrs3MT230D75JklIhZ0NF+oe0q8hjv3Sngi9aSQe2bmb6l7NbyROhk0Zg3wUeA24EeTPJctXQPT6d3ASTNwnG4WAb/p07ElSZJmynTMJTZnDQ4OPnpgYGDN6OjoQcPDw5f1Ox7NPnMi0UA9YeDjgNdRf/t/M/WQg1cDZObvI+IZwDuBbzd1rgH+lTvfIH682fYF6qEW1wEfA06bhpgvaeuxAPWqEqcADwFOzczr27ZdHxFfpe4J8BHqVRyOj4hFwLpm32OmEMPwRG1l5u+aZTJPaB6/p04CvCAz22N/AnVSoN2xwB3A6c1cE2O+2Kw2sQQ4kXqehn/gztnUb1MnCr7cMT8DwF9HxK0dZU9sYh/3GphOQ0NDm+n9kqCT0mqNN/WIJEnSjsNu/L01MjKyAWDevHkbfG01FaWqqi3XkjQrtVqtxRuPWrfddCVcQWfHFs0Gm5b3O4IdxIIV/Y5gu7GcTVuupG3mJae5ZJ+Vq+zG30MjIyP7AZcA+8+fP//Sfsej2WdOrDohSZIkSZJmhokGSZIkSZLUMyYaJEmSJElSz5hokCRJkiRJPWOiQZIkSZIk9YyJBkmSJEmS1DMubyntwFqt1mJgPbCbayDPHJeE6g+v95nntd4fXuv94fXeH17v/eH1rm1ljwZJkiRJktQzJhokSZIkSVLPmGiQJEmSJEk9Y6JBkiRJkiT1jIkGSZIkSZLUMzv1OwBJ02vjUesA1l/Bur7FsIIFfTt2n12yrQ1sWt6LMKbBghX9jmAi67mi3yHseJazaaLN23yta0rWr9uGa337/jPernm9z4B9Vq4q/Y5B0tTZo0GSJEmSJPWMiQZJkiRJktQzJhokSZIkSVLPmGiQJEmSJEk942SQWxARq4E/Bx6WmVc0ZfsCP83M0lbvCcA7gQOAAnwPOC4zL26rUwEbgQq4BfgS8DrgRGBJU20nYD5wW/P86sx8eERcBRyRmee3tXcIcFpm7j1B7Ksy87Tm+X7A+cCKzPxgUzYfaAFXZebjO/ZfCVyfmW/u0vYf4omIg4H/Ar6Rmc9sq7MHcC2wLjP36tj/FOC1wCMz88dt5WNtrczMZW3lq4CfAd8EvtLW1EL++JoCPDszL4yI1wMnAYdm5pfa2tkb+BWwOjOf1lb+HmCvzFzaea6SJEmSpMmzR8Pk3Ay8Y7yNEXEAcAHwNeD+wP2any9otrXbPzN3BR4HPAE4NjOPyMxdm/IjgQvHnmfmw3txAhHx58A3gDePJRkah1InNvaLiEdswyHWAY+KiPu1lS0BruwSy3zgJcBNwNIubW0EXhgRD+vckJkXtr1W92qKH972el3YlC1t2l/W2UbjURHxrC2fliRJkiRpa5homJxTgcMi4jHjbH8f8KnMfF9mrm8e7wM+DZzQbYfMvBb4KvDY6Qi4XUQ8k7r3xKsz8/SOzcuAs4DVjH9TPhkjwGeAv2srexnwiS51DwMGgDcBh0dEZ8+aW4CPUPcQ2WpNz42HA0dQ/95271LtPcC7IsKlkyRJkiSph0w0TM71wAfpcuMbEbtQD61Y1WW/TwNPjoi7d9nvAcBzYNpXe3828Dng8Mz8TEcMezbbzwLOBJY0vQ2maiV1coEmKbMA+G6XesuAz1O/PgupX4dO7wKe3gxJ2VrLqHuYfI56WMhLu9T5CLA78IIptC9JkiRJGoeJhsk7ATgwIp7SUX4P6tex1WWf65pt92wruzgibgWupp6/4G1bEcPnI2J47EF9s74lTwOuou6x0Olw4JrMvKhpaxHdb/onJTMvBTZFxIHUN/t36c0QEXsBhwBnZuYG4By69KTIzBup565499bEEBF3ox6WcWZmVtRJlG49NX5P/dr/S0QMbM0xJEmSJEnjczLIScrM9RHxXuob35e3bboJuAMYop6ssN19mm03tZU9Afg58AzqHgD3BIYnGcYLuk0GuYV93kY9D8NXIuKQzLy1bdtS6htxMvOWiDiX+qb83EnG080ngFcAzwX2Bx7Ssf1w6gTL2FwKZwDnRcQembm2o+5JwGsi4hlbcfy/pO5JcXZb+8dFxGMy80cddc8EjmbbhoxsUavV2hnYeTqPMYFFfTquJEnSlLVarcXNj2OfZRa1Wt2+19N0GBwcXDgwMMDo6OjCtWvXLu5WZ2ho6OaZjkuzh4mGrXMq9SoRh44VZObGiLgI+Bvq7vrt/ha4KDM3thc237R/PSLOpP7W/vnTGPNt1HMifAn4ckQ8OzM3NEMSHg7cNyJe2dTdBbh7RNw7M2+Y4vHOBH5NvarDtRHRmWhYCuwFXBcRUK/QMZ964sgPtFfMzFsj4p3UyZ1fTvL4y4C7AVc07UO9IsUy6t9de/t3RMRy4EPAFybZ/lQcy9b1XJEkSZrr1nc8/01fopijhoeHx35cM0E15zrTuEw0bIXMvC0i3sFd52o4hjpx8Avgo9R/dP9AffM80bfxJwG/iojHZuYPpyNm+EMy5FDgy8CXIuI51Dfea6iTIWMK9ZwKS5rYAAYiYkFbnSozN09wrBsi4qnAbzu3NStw7Evdq+Patk1vaOL5QOc+wL8BrwcexF17jHS2PwQ8izpx84O2TX8DvDUiju4S77kR8Wbqc/7PidrfBu/mj6/nTFuE/zFLkqTZZ7fm37HPMvejnjBcM2BwcPDRAwMDa0ZHRw8aHh6+rN/xaPYx0bD1Pga8kXoiQQAy86KIeDqwAji+Kf4+8PTM/N54DWXmbyPik9Tfdj9vugJujrUhIp4LfIX6hvqxwCsz8/r2ehHxb9Q3/WM3xm9sHmOuBvbewrHGO+dlwPmZeUnHMU8GjoyI/bu09fuIOB74+ETHbPwd8PPMPK+j/Y9Sv8aHAZd02e9Y4L8m0f6UDA0NbQbGTc5MJ7sYSpKk2WisW37bZ5lb7Ko/c0ZGRjYAzJs3b4Ovu6aiVFXV7xgkTZNWq7V441HrOrsezrgVLNhyJXW1aXm/IxjHghX9jkAzbDmb+h2Cesw/Y23P9lm5qsAf5mpYD+zmDe/MGRkZ2Y/6C7r958+ff2m/49Hs46oTkiRJkiSpZ0w0SJIkSZKknjHRIEmSJEmSesZEgyRJkiRJ6hkTDZIkSZIkqWdMNEiSJEmSpJ7Zqd8BSJpeu5x0T+jzklAr+3XgPpkbS0Kt7HcAd+ESaDNvblzr25+eXesrexXR3OD1LkmTZ48GSZIkSZLUMyYaJEmSJElSz5hokCRJkiRJPWOiQZIkSZIk9YyJBkmSJEmS1DOuOiHt4DYetQ5g/RWs63coE1rBgn6HMB0umWzFTcunM4w5Zz3rrpj63gtW9C6S7dRyNvW6yUlf6+qp9e2X+hy4dLcXXu8zYJ+Vq0q/Y5A0dfZokCRJkiRJPWOiQZIkSZIk9YyJBkmSJEmS1DMmGiRJkiRJUs84GaS2exGxGjgQuB3YDPwAeG1mXh4RBwOrMnOvjn1OAV4LPDIzf9xWfjywb2a+qKP+VcARmXn+9J2JJEmSJO347NGg2eLIzNwVuD+wFjh9vIoRMR94CXATsHRGopMkSZIkASYaNMtk5kZgFfDYCaodBgwAbwIOjwh77kiSJEnSDDHRoFklIhYBLwWumKDaMuDzwKeBhcBzZiA0SZIkSRImGjR7nBQR64GbgQOAJd0qRcRewCHAmZm5ATiHOvEgSZIkSZoBdinXbHFUZp4WEQ8GvgI8BPjfLvUOB64FLmyenwGcFxF7ZOZaYASY32W/+c22nmu1WjsDO09H25OwqE/HlSRJmrJWq7W4+XHss8yiVqvVr3DmnMHBwYUDAwOMjo4uXLt27eJudYaGhm6e6bg0e5ho0KySmVdGxJHAxyLiK12qLAX2Aq6LCIBCnURYAnwAuAb46/YdImIXYE/g6mkK+1jgbdPUtiRJ0o5ofcfz3/QlijlqeHh47Mc1E1Qr0x+JZisTDZp1MvMrEXE98CrgR2PlEXEAsC/wBOpeDWPeQD184gPUvSFOiYiXA5+k7mnwHuC/gV9OU8jvBk6apra3ZBH+xyxJkmaf3Zp/xz7L3A+4pX/hzC2Dg4OPHhgYWDM6OnrQ8PDwZf2OR7OPiQbNVidQJw7+vq1sGXB+Zl7SXjEiTgaOjIj9M/OSiDik2f8E4PfUmdoXZGY1HYEODQ1tBjZPR9tbYhdDSZI0G411y2/7LHOLXfVnzsjIyAaAefPmbfB111SUqpqWeytJ24FWq7V441HrOrsebpdWsKDfIfTVpuX9jkB/sGBFvyOYdsvZ1O8QNA3mwKWrOWSflasK/GGuhvXAbt7wzpyRkZH9gEuA/efPn39pv+PR7OOqE5IkSZIkqWdMNEiSJEmSpJ4x0SBJkiRJknrGRIMkSZIkSeoZEw2SJEmSJKlnTDRIkiRJkqSe2anfAUiaXrucdE+YBUtCrex3AD3kklD90bsl0Fb2KKIdn9d6f4x7ra/sV0Rzg9e7JE2ePRokSZIkSVLPmGiQJEmSJEk9Y6JBkiRJkiT1jIkGSZIkSZLUMyYaJEmSJElSz7jqhLSD23jUOoD1V7Cup+2uYEFP29tWm5b3O4KuLpl0zQUrpjGMOWc9V/Q7hJm1nE39DmHy17p6af26bbzWfeuZEq/3abLPylWl3zFI6g17NEiSJEmSpJ4x0SBJkiRJknrGRIMkSZIkSeoZEw2SJEmSJKlnnAxyBxcRq4EDgduBzcAPgNdm5uXN9oOBVZm5V8d+pwCvBR6ZmT9uKz8e2DczX9RR/yrgiMw8v0sMd9onIg4F3g7sA4wC/we8PjN/MF48He09Bvgh8P7MPLpLHIuBB2fmcFN2CHBaZu7dPF8JvKR5PUaB64GvAu/KzN+Od1xJkiRJ0pbZo2FuODIzdwXuD6wFTp+ockTMp74RvwlY2stAIuJPgE8BxwH3AB4AvJv6pn+yljWxHR4R3ZJlFfCmLbRxUmYuysxB4C+BewGXRMS4CQ5JkiRJ0paZaJhDMnMjsAp47BaqHgYMUN+sj3czP1WPBX6dmedn5h2ZeWtmfikz/2cyO0fE3YCXAq8HFgLP7lLtvcA/TTZpkJk/B14GrAPeMJl9JEmSJEndmWiYQyJiEfVN+pZW3V4GfB74NPXN/HN6GMalwJ9ExAcj4pkRsdtW7n8YMB/4DHB2E2un/wES+OfJNpqZtwPnAgdtZTySJEmSpDYmGuaGkyJiPXAzcACwZLyKTS+AQ4AzM3MDcA7db+anJDOvBA4G7g18EvhdRJwdEXtMsollwBcycxNwBnDoOPu+FVgaEQ/eivBawD23or4kSZIkqYOTQc4NR2Xmac1N91eAhwD/O07dw4FrgQub52cA50XEHpm5Fhih7lHQaX6zbYsy83vA2MSQj6BOOJxCPS/EuCLiPtRJkGc1RRcAN1D30ji54xi/jIhPAO8AzpxMXMAQ9fCJnmq1WjsDO/e63Ula1KfjSpIkbZVWq7W4S/HYZ5lFrVZrJsOZ0wYHBxcODAwwOjq6cO3atd1+LwwNDd0803Fp9jDRMIdk5pURcSTwsYj4Smbe1qXaUmAv4LqIACjUSYQlwAeAa4C/bt8hInYB9gSunkJMP46I04FXTaL64dRzR3w6IqqmbJC6l8PJXer/C3A59VCKCUXEAPWkkF+dRBxb61jgbdPQriRJ0o5k/QTbfjNjUYjh4eGxH9dMUK1MfySarUw0zDGZ+ZWIuJ76xv7k9m0RcQCwL/AE6l4NY95AfTP/AeoeEadExMupeyLsDLwH+G/gl1s6fkQ8GXgEcG5mXhcRD6TukfDdjnoLOnb9PXUS5D3UvR/G3B/4fkTsl5mXdpzrdRHxIepJLW+dIKaHUM/ncC/gpC2dwxS8e5ranYxF+B+zJEmaHbrN3TX2WeZ+wC0zG87cNTg4+OiBgYE1o6OjBw0PD1/W73g0+5homJtOAD4QER/pKF8GnJ+Zl7QXRsTJwJERsX9mXhIRhzRtnECdAFgDvCAzK7ZsmHpyyeObySnXAecBx7TV2RPo7G1xLPWQj1Mz8/q28usj4qtN7JdyVycAR3QpPyoi/pF6KczrqHsy7J+Z103iHLbK0NDQZrZu+c6esYuhJEmaLbp1xW/7LHOLXfVnzsjIyAaAefPmbfB111SUqprMvaGk2ajVai3eeNS6ibohTtkKOjud9Nem5f2OYBstWNHvCDSLLWdTv0PQLOVbj7Yn+6xcdZeu+M28DeuB3bzhnTkjIyP7AZcA+8+fP7/bl3nShFx1QpIkSZIk9YyJBkmSJEmS1DMmGiRJkiRJUs+YaJAkSZIkST1jokGSJEmSJPWMiQZJkiRJktQzO/U7AEnTa5eT7gnTsCTUyl42toOZ2pJQK6cxornBJdBmnsuf9UdPr/WVvYhobvB6l6TJs0eDJEmSJEnqGRMNkiRJkiSpZ0w0SJIkSZKknjHRIEmSJEmSesZEgyRJkiRJ6hlXnZB2cBuPWgew/grW9TWOFSzo6/H75JJ+BzBZm5b38eALVvS6xfVc0esmtQXjXuvL2TSTccyo3l+6W229l3pfzJr39tlgn5WrSr9jkNR79miQJEmSJEk9Y6JBkiRJkiT1jIkGSZIkSZLUMyYaJEmSJElSzzgZpLYrEbEaWJWZpzXPnw+cDbwmMz/cUbcCbgb2yszb2sp/BDwaeFhm/iwilgIfA8bqDAP/kZnHd7T1sMz82XSclyRJkiTNFfZo0PZuKXATsGyc7dcDzx97EhGPga7LG/wgM3fNzF2BpwKviIgX9DZUSZIkSZKJBm23ImJP4DnAK4H9IuKRXap9gjoZMWZZUzauzPwl8B3gz3oTqSRJkiRpjIkGbc+WAFdm5ueBC+neq+E84NERcb+ImA/8LfDJiRqNiIcCfw58r8fxSpIkSdKcZ6JB27OlwFnNz2cAS5pkQrsR4DPUSYlDgcsy89oubT0uIoYj4hbg59Q9Gr45LVFLkiRJ0hzmZJDaLkXE44FHAM9rij4HnAo8Fzino/pK6oTE5c3P3fx3Zh7YtL0n8Cng/cDrexd1d61Wa2dg5+k+zjgW9em4kiRJW9RqtRZvocrYZ5lFrVZrusNRY3BwcOHAwACjo6ML165d2/V3NDQ0dPNMx6XZw0SDtlfLgAr4TkSMle3UlJ/TXjEzL42I3wNPoR46MaHM/G1EnA28upcBT+BY4G0zdCxJkqTZZP0k6/1mWqPQnQwPD4/9uGaCamX6I9FsZaJB26sXAa+hXtpyzBOBz0bEnpn52476fwMszMxNW2o4InanXqnix70KdgveDZw0Q8fqtAj/Y5YkSduv3bawfeyzzP2AW6Y/HAEMDg4+emBgYM3o6OhBw8PDl/U7Hs0+Jhq0PdoTuAM4vSNx8MWIuJx6PoYT23fIzJ9voc3HR8Stzc8bqedneF2P4p3Q0NDQZmDzTByrk10MJUnS9mxL3e/bPsvcYlf9mTMyMrIBYN68eRt83TUVJhq0vVkM/CQz79VtY2Y+vO3ncbtrtW/LzJWMP3fDFtuSJEmSJE2eq05ouxERDwf+DLi037FIkiRJkqbGRIO2CxHxXuDrwFsy88p+xyNJkiRJmhqHTmi7kJnHAMf0Ow5JkiRJ0raxR4MkSZIkSeoZEw2SJEmSJKlnTDRIkiRJkqSecY4GaQe3y0n3BNit32sgr+znwWfYyMjIfsAlwP7z5893FZUtWtmTVlqt1mJgPdvB9T5XzPlrfWV/Duu13h9z/nqXpK1gjwZJkiRJktQzJhokSZIkSVLPmGiQJEmSJEk9Y6JBkiRJkiT1jIkGSZIkSZLUM646Ie3gNh61DmD9FazrdyjbbAUL+h3C1rqk3wHMlE3L+x3Bnaxn3RX9O/qCFdN+iOVsmvZjbKU5c61PxTReEuv7eKXPZXP+et9n5arS7xgkbd/s0SBJkiRJknrGRIMkSZIkSeoZEw2SJEmSJKlnTDRIkiRJkqSemXOTQUbEC4E3AI8ANgL/B5yYmedFxMHABU15u5dl5hci4njgbcDSzPxEW5vXAy8CngS8pSkeAHZubyszd42I1cCBwO3AZuAHwGsz8/KOOM8FDgHuk5nr2sqXAkdk5oGTONfVwKrMPK15vh9wPrAiMz/YlM0HWsBVmfn4jv1XAtdn5pu7tH1VE8f5zev2X8A3MvOZbXX2AK4F1mXmXh37nwK8FnhkZv64rXysrZWZuaytfBXwM+CbwFfamlpI/RpXzfNnZ+aFEfF64CTg0Mz8Uls7ewO/AlZn5tPayt8D7JWZSzvPVZIkSZI0eXMq0RARrwP+Gfh/1DerG4GDgZcA5zXVbui8Ke6wDnh7RHw6M3/fviEz3wW8qznWIcBpmbl3lzaOzMzTImIX4CPA6cCT2+K8N/Bs4NYmtg9t3ZneVUT8OfU5vjEzT2/bdCgwH9gvIh7RftO/ldYBj4qI+2Xmb5qyJcCVwGBHLPOpz+smYCnwxo62NgIvjIgTMvOn7Rsy80Jg16adBcBtwMMz86qONpY27S8DvsRdPSoinpWZX5v8KUqSJEmStmTODJ2IiMXAO4F/zMzPZuYtmTmamd/MzH/Yiqa+AawFjtjWmDJzI7AKeGzHpiXAL4APUN8ob5OIeCb1zfarO5IMNO2fBazexmONAJ8B/q6t7GXAJ7rUPYy6x8ebgMMjojPhdQt1AuadUwmk6bnxcOrf0WERsXuXau8B3hURLs8kSZIkST00ZxIN1MMaFgBnb2M7FfXwiOMiYtdtaSgiFgEvBTqXwR67+T+TuqfBo7bhMM8GPgccnpmf6Tj+ns32sWMtaXobTNVK6uQCEfEY6tf7u13qLQM+D3yaeujDc7rUeRfw9Ih4whTiWEY9BOZz1MNCXtqlzkeA3YEXTKF9SZIkSdI45lKiYXfgd5k5soV6946I4Y7HQ9orZObXgR8Dr59iLCdFxHrgZuAA6h4MAETE46i/jT8rM38FfIdt62nwNOAq6h4LnQ4HrsnMi6hv/BfR/aZ/UjLzUmBTRBxIHfNdejNExF7Uc0+cmZkbgHPocn6ZeSNwIvDurYkhIu5GPSzjzMysqJMo3V6/31PPt/EvETGwNceQJEmSJI1vLs3RcCNwr4iYv4Vkw5bmaBjzFuCrEfGvU4jlqGaOhgdTzxXxEOB/m23LgG9n5tXN8zOAFRHxpkkkSbp5G/U8DF+JiEMy89a2bUupb8TJzFuaCSiXAedO4ThjPgG8AngusD/1ubU7nHqCyAub52cA50XEHpm5tqPuScBrIuIZW3H8v+TOPVfOoO598pjM/FFH3TOBo+nB8JSJtFqtnaknBu2HRX06riRJ2kG1Wq3FM3i4sc8yi1qt1gwedm4bHBxcODAwwOjo6MK1a9d2/X0PDQ3dPNNxafaYS4mGi4BNwPOBz25rY5n5/Yj4L+DYbWjjyog4EvhYRHwFuAN4MbBzs5IF1L+j3amTBV+cwmFuo54T4UvAlyPi2Zm5oRmS8HDgvhHxyqbuLsDdI+LemXnDFE/rTODX1Ks6XNvZG4Q6ubEXcF1EABTqySiXUM9J8QeZeWtEvJO6V8MvJ3n8ZcDdgCua9qEe7rIMeF1H+3dExHLqyTa/MMn2p+JY6oSPJEnSjmB9H475my1XUa8MDw+P/bhmgmrOdaZxzZlEQ2beHBHHAR+KiDuol3m8jXq1hyWZ+YopNHsccDHb8EeWmV9pkgqvAq6j/p08ooltzMnUN8pjiYbSrLjQbnMzVKDbMTZGxKHAl4EvRcRzmvbWAH/bVrVQz6mwhLo3AcBAx7GqzNw8wfncEBFPBX7buS0iDgD2BZ5A3athzBuaeD7QuQ/wb9RDVB5EvbzluCJiCHgWdTLpB22b/gZ4a0Qc3SXecyPizdTn/J8Ttb8N3s0fX8+Ztgj/Y5YkSb212wwea+yzzP2oJwzXDBgcHHz0wMDAmtHR0YOGh4cv63c8mn3mTKIBIDNPiYjrqJdT/ASwAfgJ8P62aveOiFs7dn1TZt5liERm/l9EfJ5mAsRtcAL1Tfb/AGc0czP8QUR8APh2M3kj1Dfqt925CR5EPRdDV00vhudSD9X4T+qVLl6Zmde314uIf6O+6R+7MX4jd15+8mpg74lOJjO/N86mZcD5mXlJxzFPBo6MiP27tPX7iDge+PhEx2z8HfDzzDyvvTAiPkrdo+Aw4JIu+x0L/Nck2p+SoaGhzcC4yZnpZBdDSZLUazPZZb7ts8wtdtWfOSMjIxsA5s2bt8HXXVNRqqrrl+CSdgCtVmvxxqPW9aN747RYQWdHHm0vNi3vdwTbkQUrpv0Qy9k07cdQ78zAJSHNqH1WrpqxLvPNfBDrgd284Z05IyMj+1F/Qbf//PnzL+13PJp95tKqE5IkSZIkaZqZaJAkSZIkST1jokGSJEmSJPWMiQZJkiRJktQzJhokSZIkSVLPmGiQJEmSJEk9s1O/A5A0vXY56Z6wgywJtbLfAUySS0L1x/azBNrK/h16hnmtT9LK3ja3/Vzrc4vXuyRNnj0aJEmSJElSz5hokCRJkiRJPWOiQZIkSZIk9YyJBkmSJEmS1DMmGiRJkiRJUs+46oS0g9t41DqA9VewriftrWDBnZ5vWt6TZndUl9ylZMGKPoQx56znit42uJxNvW1wx3PXa13AtP/Jr+/xpa7JmXPX+z4rV5V+xyBpdrFHgyRJkiRJ6hkTDZIkSZIkqWdMNEiSJEmSpJ4x0SBJkiRJknrGySA1a0TEauBA4HagAn4OvCEzv9VW5/nA2cBrMvPDHftXwMMy82cd5QcDqzJzr2k9AUmSJEmaA+zRoNnmyMzcFdgN+AhwTkTMb9u+FLgJWNaH2CRJkiRpzjPRoFkpM+8AzgIGgfsARMSewHOAVwL7RcQj+xagJEmSJM1RJho0K0XEAPAy4Bqg1RQvAa7MzM8DF2KvBkmSJEmacSYaNNucFBHDwEbgJODozLy92baUupcDwBnAko5hFZIkSZKkaeZkkJptjsrM0yJiHvAk4EsR8UvqpNkjgOc19T4HnAo8FzinD3H+QavV2hnYuU+HX9Sn40qSpB1Eq9Va3MfDj32WWdRqtSasqN4ZHBxcODAwwOjo6MK1a9d2/f0PDQ3dPNNxafYw0aBZqZmj4dsRcTnwNODB1CtRfCcixqrtRD184px+xNjmWOBtfY5BkiRpqtb3OwDgN/0OYC4ZHh4e+3HNBNXK9Eei2cpEg2atiDgQ+DPgx8BbgNdQL2055onAZyNiz8z8bVN2t4hY0Fbndqbfu6mHefTDIvyPWZIkbZvd+njssc8y9wNu6WMcc8rg4OCjBwYG1oyOjh40PDx8Wb/j0exjokGzzckR8f7m5+uB5dQrT9wBnJ6Zm9rqfrHp8bAEOLEp63yjfDuwetqiBYaGhjYDm6fzGOOxi6EkSdpW/ewi3/ZZ5ha76s+ckZGRDQDz5s3b4OuuqTDRoFkjMw+eYPOqcfZ5eNvPE3Xv2muKYUmSJEmS2rjqhCRJkiRJ6hkTDZIkSZIkqWdMNEiSJEmSpJ4x0SBJkiRJknrGRIMkSZIkSeoZEw2SJEmSpO1eKeX4UkrV5fGzHrX/mOYYu/SivbnM5S2lHdwuJ90TYLderYG8sheN7OBGRkb2Ay4B9p8/f/6ld966sg8RzQ2tVmsxsJ4eXu+a2MTXuoBp+ZP3Wu8Pr3dpu3Eb8BddynrhMcDbgA8BG3vU5pxkokGSJEmSNFvcUVXV9/odxGSUUu5eVVWvkiCzikMnJEmSJEmzVillYSnlQ6WUn5dSNpZSriqlnFZK2a1L3b8rpfywlLKplPK7UsqXSykPLKUsBT7eVFvbDMm4qm2/R5RSzi+l3FpKubmUcm4pZZ+OtqtSyptLKe8tpVwPrJ3G096u2aNBkiRJkjRrlFI672N3AQaA46hv7u/f/PxF2oZZlFKOBk4APtZsn99s3wP4ErACWA4cQj1EbXOz3/2BC4GrgJc1x3o7cGEp5VFVVbUnFF4HXAT8PXC3Hp3yrGOiQZIkSZI0WywERjrKDq+q6tVjT5pExK+Ab5dSHlpV1eVN74bjgX+vqupVbfue27bfL5sfL6mq6ndtdV5PnTR41lhSoZTyfeAXwD827Y65EXhBVVXV1E9x9jPRIEmSJEmaLW4DDuoou7KUcjhwFPAQ6mTEmIcClwNPpO758LEpHPMpwAXtPReqqrq6lHJRs63dV+Z6kgFMNEg7vI1HrQNYfwXr+h3KH6xgQb9DmCmXzMRBNi2fiaPMKutZdwUsWNHvOKbNcjb1O4ROM3Ktb40d+Nffbv0V/Y5gbtrurvfptM/KVaXfMUgd7qiq6r/bC0opzwc+Cfw79ZCIG4H7UA+dGPvguXvzb2sKx7wH8KMu5dcDf9pRdsMU2t/hmGiQJEmSJM1mLwR+1D4kopTy1I46Nzb/DgG/2cr21wF7dinfq9nWbs73ZgBXnZAkSZIkzW53B37fUfbSjuffBTYCyyZoZ6yNzu633waeXkoZ6xUxNkHkk6gniVQHEw2SJEmSpNns68ATSilvLaU8o5RyIvD09gpVVa2nXiniiFLKv5dSnlNKObSUcmIp5XFNtZ82//5jKeWAUsojm+cfoE5CfK2U8lellBcCX6XuzfDh6T652chEgyRJkiRpNvsIcCLwGuBs4AHASzorVVV1AvWykwdSz9+wknqyyBua7T+kXkFiCfUSlec15b+mnoDyd8AZwOnAFcBTOpa2VMM5GmZARDwJeC8wlhG7AnhrZn652b4YeCfw18AgcA1wGnBKZlZNnauAIzLz/LZ2DwZWZeZeEXFr2yHvTr3ky+3N83dR/6Gsysy9OmJbBfwsM48fJ/Y3Aa+iHpN0K/UESC/KzFsiYnXT5mlt9femXkrm7pm5KSJWAtdn5psneH1OAV4LPDIzf9yUfQS4W2Yua6v3a+DHmfnstrL/Bs7IzFOaeA5sO2+An2fm/k3dpcDR1G88m4HLgH/IzKuabUdk5oHjxSlJkiSpf6qqOp47LyU5Vj4KvLF5tLvLZKZVVX0c+PgEx3g7dc+HzvL/Bf6/LcTn5KkNEw3TrEkifAk4EjgLmA8cAIw22+9G3dXnFuCp1DfpT6SeNfWB1Gu2blFm7tp2zO8Bp2Xmyrayg6cQ+98BrwCek5k/j4h7A4dubTtbOMZ86mzjTcBS/vjmsJo6+TJW78HUyZPHRcRAZo5GxCLgMcDL25o8sj3x0bb/QcD7gOcCP6BO6DwLJ2uRJEmSpJ4y0TD9HgrMz8xPNM9vp76JHrME+BPgwZl5c1N2YUQsAdZExIcy85czFu2dPQH4Wmb+HCAzb6DuJtRLhwEDwJuAd0bEmzNz7DV6UETcPzN/TZ2E+QbwMGA/6mTBk4Gbgf+Z5LlcnJkXN89vAj7TyxORJEmSJDlHw0y4HNgcEWdFxKERsUfH9mcCX25LMgCQmd8BrgWeMUNxdvM9YElEHBMRBza9L3ptGfB54NPAQuA5AJl5HfAL6gQD1GOi1jSP9rILM/OOSRzne8AzImJFRBwUEbv07hQkSZIkSWNMNEyzJoHwZOo5AT4MXB8RF0TEnzRV7gW0xtn9umZ7r9w7IobbH8BfjVc5M88EXk09Y+vXgN9FxAkRMdCLYCJiL+AQ4MzM3ACcw52Xm1nNH5MKT+WuiYancufeIQAndZzjx5pz+TbwPOp5Mr4I3BgRH4uIhb04F0mSJElSzaETMyAzf0o9u+nYZIkfoZ6t9EnUM5cOjbPrfZrtUM9PML9j+/ymfLJuGGcyyIli/xTwqSa58AxgFfVklv8+QUwVzRwUW3A4da+NsbVnzwDOi4g9MnMt8C3gbRFxP6Bk5jURsQ44KyJ2BR5HPbNsu6O6zdHQnMtXgK9ERKGeNPLTwHHAWyYR65S1Wq2dgZ2n8xgTWNSn40qSpB1Aq9Va3OcQxj7LLGq1xvtuTr02ODi4cGBggNHR0YVr167teg0MDQ3d3K18Olyx9EXTMq/aPitXOXnjNDHRMMOaFQ5Opb7JhXregfdExKLMvGWsXkQ8Ebgv8M2m6BrgQR3NPRi4eppDBiAzR4GvRsQ3+ePqGePF1MrMySRAlgJ7AddFBNSzws6nnrfiA9S9Fc4EXkSTjMjMWyPiV8ARwEbgR1M4lwr4bkR8vu1cptOxwNtm4DiSJEm9tr7fATR+0+8A5pLh4eGxH9dMUM2bdI3LRMM0i4h9qSc8/Azwa2AP6lUSvttUOYN6eMIXIuLV1ImDA4FPAB/OzCuaemcBx0XEBcBPgH2Bo4BTpjH2ZdQ9KtZQT7p4IHAw9VKUYzF9LiK+0JzPfYG3Ap/qaGogIha0Pa+oV4vYl3qSxmvbtr2BevjEBzLz2oj4JfVKFMvb6qxpyiY7PwMR8ZfUc0B8NTNvjIg/A/6SCZa26aF3AyfNwHG6WYT/MUuSpKnbrc/HH/sscz/qVdo0AwYHBx89MDCwZnR09KDh4eHL+h2PZh8TDdPvFuou/q+jXlLxZuAC6uQCmfn7iHgG9VKO327qXAP8K3e+Of14s+0L1EMtrgM+BnQdJtAjw8Ax1EmPnajnknhXM5yCzLwgIl4H/BuwN7COOqFyfEc7nWvaXg2cD5yfmZe0V4yIk4EjI2L/Zttq4B+4czZ1DXWSZXWXmE+OiPe3n0Nm3o96lYl/Aj7YJD1uoB4GcsLEL8G2Gxoa2kw9R8eMs4uhJEnaFjPZPb6bts8yt/Q7lrlkZGRkA8C8efM2+LprKkpVTctwF0nbgVartXjjUeu2ly6Pf7CCBVuupEnbtHzLdeakBSv6HcG0Wc6mfoew3duBf/3SjOr3GPZmjoj1wG7e8M6ckZGR/YBLgP3nz59/ab/jcY6G2cdVJyRJkiRJapRSVpdSNpVSbm17PG8b2zuihyFu6Xj/Xkr5eSnljpk8bjsTDZIkSZIk3dmRVVXt2vY4p1+BlFI6V/rbksuA/wdcPA3hTIqJBkmSJEmStqCUclIp5ZpSyi2llEtLKU9t2zavlPKGUsrlzfaflFL2K6W8E3gKcHLTM+KMpv5DSynfKKXc1PQ+WNrW1vGllLNLKStLKcPAG0op+zQ9I9aXUm4spZwzXpxVVX24qqpvQv/GWppokCRJkiRpyy4B9gPuQbMCXylll2bba4FXAH8FLAaeD9xYVdVxwIX8sYfE4U0Phf8ELgL2BF5GnYh4atuxDqOeQP+e1CsN/gvw9ebY9wVOnM4T3VYmGiRJkiRJurOTSinDzeNqgKqqzqqq6ndVVd1eVdWJwHzgYU39I4DlVVX9uKpdXlXV1eO0fQB1AuHtVVX9vqqq7wErgcPb6lxSVdWqqqruqKrqNmAEeCAwVFXVpqqqLuz9KfeOiQZJkiRJku7sqKqqBpvHAwGaoRE/bYYvDAO7Afdq6j8AuGKSbd8X+HVVVaNtZVc15WOu6djnTc2/3y+l/F8p5VVbcS4zbqd+ByBpeu1y0j1hO1sSamW/A5hm29uSUHPFXZdAW9nniHZ82/W1vrLfAUwfl/vrj+36epc07UopTwHeAjwN+HFVVXeUUm4CxpbIvAbYB/hRl907l+e8FrhfKWWgLdmwd1M+5o47NVBV1wOvbGJ5InBBKeU7VVX9eMonNY3s0SBJkiRJ0sQWAbcDvwN2KqUcRz0Xw5h/B95RSvmzUntIKeWBzbbfAn/SVvf7wDBwbCnlbqWUJ1DP03DWeAcvpbywlHK/5unN1MmL0XHq3q2UsoD6fn+nUsqCUsrAVp7vNjHRIEmSJEnSxL5KPYHjz4CrqedM+HXb9lOATwLnUScCzqaeh2FsWzQrTHyiqqoR6ske/wK4ATgTeGNVVf81wfEfRz1s4tYmjqOrqvrpOHW/BtxGvdrFqc3Ph49Td1o4dEKSJEmSpEZVVQd3KRsF/qF5jDmhY/t7mkfnvt8F/rSj7GfUiYZuxz++S9kxwDFTjX+m2aNBkiRJkiT1jIkGSZIkSZLUMyYaJEmSJElSzzhHg7SD23jUOoD1V7Bui3VXsGDa45ljLpnuA2xaPt1H6IEFK2b6iOsnvYq1emXar/V2y9k0k4fbnq1fd0U//sTmvBm93vtln5WrypZrSVJ39miQJEmSJEk9Y6JBkiRJkiT1jIkGSZIkSZLUM87RsAOLiGOBZ2Xm09rKvg3snpkPayv7PPDrzHx9RKwEXgL8vq2pTZl5r6buocDbgX2AUeD/gNcDzwTe0tQfAHYGNo41kJm7donvKmDPpp2NwH8Br83M3zbbHwP8EHh/Zh492X0jYjWwKjNPa6u/N/Ar4O6Zuamt/BTgtcAjM/PHXV9ISZIkSX3jnCGzjz0admyrgQMjYmeAiFgAPAxYGBF7ttV7CvCttucnZeaubY+xJMOfAJ8CjgPuATwAeDewOTPfNVYfeD5wTXsbE8T4/Gb7nwH3Bj7Qtm0ZcBNweER0S4pNtO8WRcR86qTKTcDSrdlXkiRJktSdiYYd2w+ov/F/QvP8idQzJX8LOAggIh4G7AGsmUR7j6Xu+XB+Zt6Rmbdm5pcy83+2NdDM/B3weeCRTVx3A15K3VtiIfDsye67FQ6j7n3xJsZPZkiSJEmStoI3VjuwzLw9Ii4CngpcSJ1cWAP8tin7XFP2v5m55bUP4VLgTyLig8B5wMWZub4XsUbEvYEXUg+VgDoJMB/4DPAX1L0bzpvkvpO1jDpB8WngZOA5QG5lG5IkSZKm0Y+veFE1He0+Yh+HZEwXezTs+FZTJxVo/l3TPNrLVnfsc2REDLc9vg6QmVcCB1MPU/gk8LuIODsi9tiG+D4fETdR97S4mroHA9RJgC808ymcARza5Tjj7btFEbEXcAhwZmZuAM5pjilJkiRJ2gb2aNjxfQs4LiIWAo8Bvp+ZmyPiXhFxL+r5GV7Xsc/Jmfnmbo1l5veAFwFExCOoEw6nUM91MBUvyMzz2wsi4j7USYBnNUUXADdQD6U4eaJ9GyPUvSHazQcq6qEkAIcD11L39IA6mXFeROyRmWundirdtVqtnaknx+yHRX06riRJmsVardbifsfQGPsss6jVavU1kLlkcHBw4cDAAKOjowvXrl3b9VoYGhq6eabj0uxhomHHd3Hz76uBH2fm5ub5t6knQLwvk5uf4S4y88cRcTrwqm0NssPh1HMnfDoixrpJDVL3ODh5EvtfAzyoo+zBQCszR5rnS4G9gOsiAqBQJyOWsJWTSk7CscDbetymJEnSdOrJ8Nge+k2/A5hLhoeHx36c6D7BYQcal4mGHVxmjkTEd4E3Av/RtmkN9eoRP2kmU9yiiHgy8Ajg3My8LiIeSN3L4Ls9Dnsp8B7qnhJj7g98PyL2y8xLt7D/WcDnIuILTWz3Bd5KvWIGEXEAsC/1JJnXtu33BupkRq8TDe8GTupxm5O1CP9jliRJW2+3fgfQGPsscz/glj7HMmcMDg4+emBgYM3o6OhBw8PDl/U7Hs0+JhrmhtXA07lzRnIN8EHqCSE7HRURr+kouy8wTD1h4vERsQhYRz1B4zG9CjQiDgQeApyamde3bbo+Ir5KnQiYMNGQmRdExOuAfwP2buL8DHB8U2UZcH5mXtJx7JOp56fYv3PbthgaGtoMbN5ixWlgF0NJkjQV20u3+LbPMrdsLzHNBSMjIxsA5s2bt2Euvu6llNXAgcDtbcVLqqo6ZxvaW1VV1WnbHNyWj/VQ4ATqFQd3Bv4HeENVVT+Y7mPfKY6qmpYJPCVtB1qt1uKNR62bdNfHFSyYznA0DTYt73cEk7BgRb8j0A5mOZv6HcJ2xT8xTYd9Vm4fs/E3c0WsB3abize8/TIyMrIf9YTr+8+fP39LvYmn3UyvOtHrxMC2tldKmV9V1ciWa0Ip5QnUc/OdDdwE/D/q3t17V1W1YSrHnwpXnZAkSZIkaQtKKSeVUq4ppdxSSrm0lPLUtm3zSilvKKVc3mz/SSllv1LKO6kn4D+5lHJrKeWMpv5DSynfKKXcVEr5eSllaVtbx5dSzi6lrCylDANvKKXsU0pZXUpZX0q5sZRyTrcYq6q6uKqqf6+q6ndVVY1WVXUqsJB66PiM2eZEQynlYaWUw0spbyml7NWU7VNKcbZ7SZIkSdKO4hJgP+AeNPPClVJ2aba9FngF8FfAYuD5wI1VVR1HvdLdkVVV7VpV1eGllPnAfwIXAXsCL6NORDy17ViHAecD96Seu+5fgK83x74vcOJkAi6lPJ76vv+KqZ70VEw50VBK2aWU8ingf4GPU5/4ULP53cA/b3t4kiRJkiTNuJNKKcPN42qAqqrOanoK3F5V1YnUq9Y9rKl/BLC8qqofV7XLq6q6epy2D6BOILy9qqrfV1X1PWAl9ep7Yy6pqmpVVVV3VFV1GzACPBAYqqpqU1VVF27pBEopuwNnAv9cVdWMriSzLT0a3g/8BXAo9ay07eNbvgwcsg1tS5IkSZLUL0dVVTXYPB4I0AyN+GkzfGGY+j74Xk39BzD5XgP3BX5dVdVoW9lVTfmYazr2eVPz7/dLKf9XSnnVRAcopewGfAX4SlVV75tkXD2zLatOvAA4uqr+f/buPD6uqv7/+Os0xFZKS4SyBfyCUhUERfblK5uKX0D4COJSoEiriPX74yulgGwVClZAlLKJ1g2DpVJl/6AColjKDoIiZbXsMBRaS9LSkhLS+/vj3IHb6SSZJDczSfN+Ph55kDn33HM+d3pp537mLMnNIYS6kmPPEVf7FxERERERERnQQgi7A6cCewNzkyRZEUJ4nXe/cH8BGA38s8zppYtZvgxsEkKoyyQbNkvLi1as1ECSzAeOTmPZFbgthHBXkiRzy8Q6ErgFeChJkomVXmOeejOiYS3glQ6ODe9FuyIiIiIiIiL9yQjidpcLgTVCCKcR12Io+jlwVgjhoyH6UAhh0/TYq8Dmmbr3Ac3AKSGE96Q7RRxJXPehrBDCl0IIm6QvFxOTF+1l6hWTDI8B3+r+ZeajNyMa/gUcAvy5zLHPAX/vRdsikpM1p60DFW4J1dTn0QwO/W1LqNprqkov2gKt+nSv18Yq93pTjQMaJHS/iwx6txAXcHwCWApcALyYOX4R8B7gRmB94ij/rwLPp8eaQghHAZ4kyZEhhAOBnwAnAK8BJyRJ8rdO+t+BuGDk2sAC4uyCx8vUOxjYBfg48OUQ3lnhYL9K1nXIS28SDd8DbkhX2byKmFHZKYRwKPA1YP8c4hMRERERERGpmiRJ9ipT1g58Pf0pOq/k+LnpT+m59wAfKSl7grjmYbn+p5QpOwk4qYLYLwcu76peX+vx1IkkSf4IjAE+CVxPnJvyE+ArwOFJkvw1jwBFREREREREZODozYgGkiS5Grg6hPBh4mqbi9LMjIiIiIiIiIgMQr1KNBQlSfIU8FQebYmIiIiIiIjIwNXjqRMhhO+HEH7WwbGfhRDO6nlYIiIiIiIiIjIQ9WZ7y0OBOzs4dkd6XEREREREREQGkd5MnWhk5e08sl4CNungmIhU0bJJiwBa5rGoz/qYyrA+a3uAe7AnJ7VOzjuMAWTY1DxaaWFeHs1IN3R4r0+mtZpx5CafW7HPtehWr4ke/d0+UIxumhW6riUi0rnejGhYAGzdwbGtoQ+fakRERERERESkX+rNiIbrgSkhhPuTJLm/WBhC2Ak4Hfh9L2MTERERERGRQW7r0RppM9D0JtEwGfhv4J4QwuNAgTidYkvgn8BpvY5ORERERERERAaUHicakiRpCSHsAhwJfApYF3gEuACYkSTJW/mEKNVkZrOBXYC3gQR4Ejje3W83s3HAr4A3S07b290fMLMm4v2wl7vfnrY3LK3/AXd/Li3bHDgL+AywJvAacDtwnrs/kdZJgC0zr8cD5wMGHAXMd/eTS2J/5xwzmwJs4e5jSuo0dXVuN98yERERERHpQ2PmjUv6ot1Zo5s0UqKP9GZEA2ky4Rfpj6w+Jrr7dDMbAnwduN7M1k+PPeDuu3Ry7iLgHGC3cgfN7IPA/cBMYEfigqLvA74AfBZY5UHfzL4NfBfYx90fNLOjenZZIiIiIiIi0td6lWgoCiGsD6suO58kyQt5tC+14e4rzGwm8HNgowpPmwEcYmbm7l7m+JnAve7+7UzZIuCX5Rozs1OBY4ijJB6tPHoRERERERGphR4nGkII6wKXEL+Jri89TBx2X9fz0KTWzKyOOBXiBeIaHJVoJU6L+L6Z/aHM8X2AUyps6yxgZ2APd9cOXiIiIiIiIgNAb0Y0/BLYC/gh8BigNRlWH9PM7FzgvcAK4Eh3f9vMAHYws+aS+hu4+/LM618DJwCHA1eV1B0FvFJ8YWZHEBNWdcA97v7ZTN19gauUZBARERERERk4epNo2Bv4dpIkv8krGOk3JmXWaNgN+KOZPZ0e+3sXazSQJiW+C5xL3AY1ayFxd5Ji3RnADDObAIwpqXsoMN3MLnD34zLlbZSMojGz+syxzvTm3B4pFApDgaF90XYFRtSoXxERERmACoXCyFrHUKL4WWZEoVDpAFvprYaGhuF1dXW0t7cPX7BgQdl7orGxcXG145KBozeJhmbiQ6Osptx9BXCnmT1FTCx158/7KuAk4Jsl5X8FDgEuq6CNp9N+bzezFe5+fFr+ArBtSd0PEkdfvNhFm705t6dOAc7oo7ZFRERE8tRS6wA68FKtAxhMmpubi7/O6aTaartjQwhhNu/uxFc0NkmS63vR3qwkSab3Oriu+1oL+BPwUeA9wDPAGUmS3NDXfWf1JtHwQ+D/Qgh/TpLk7S5ry4BkZrsQb9K5wIaVnufuSbqQ48ySQ2cAD5jZxcR76CVgJLBNB+3MM7O9gdlpsuFEYhLjZDM7ALgZWJu408U17p6dwjMk3V4zq9Jz83QOMK2P2u7KCPQPs4iIiFRu7VoHUKL4WWYTYEmNYxk0Ghoatqmrq5vT3t6+R3Nz88O1jqdGJlYjMVCJEEJ9kiSVjr5eDkwAnkySpD2EsBtwSwhhiyRJXu67KFfWm0TDFsQH0KdDCLcTRzhkJUmSHNuL9qV2LjSzH6W/zwcmu/vNZjYO2NHM3iipP8bdV1n40d1vMbNHiGt5FMvmmdlOxIUeHwTWJK7ZcAfxf4hVuPtTmWRDu7ufbGaHpG1cAbxBzNqdVHLql9KfbFuhwnNz09jYuJz4P3zVaYihiIiIdEd/Gw6f+SyzpL/Ftjpra2tbCjBkyJClet/fFUKYBnwReB/wb+C4JEluT48NAY4jjujeiDiS+gjiaO7dgV1CCD8CrkuS5IgQwoeBnwDbA68B5yRJ0pS2NQX4OLAYOAg4N4RwNXGdxG2JIy3uSJLkoNIY04TEY2k7gThyux7YFKhaoiEkSdKzE0N4tosqSZIkH+xR4yKSi0KhMHLZpEV9PgRy6qq720ovtE6udQQ1NGxqrSOQnE2mtdYh9IhuRRmsRjfN6lfD4dM1I1qAtfXAWz1tbW3bEb8U3L6+vv6hWsczZt64nj20dmHW6Kay93tHUx1CCIcDtxC/ZD+W+GXlZkmSLAshTCR+cfpF4FHgQ8DyJEmeL20vhFCf1pkFTAW2I462/nySJLeniYbTiImK3xPXe7uMOMr8HOKUiB2TJLmjo2sLIdwB7JTW/Quwb5Ik7ZW/O73T4xENSZJ8IM9ARERERERERPqJaSGEc9PfW5Ik2TRJkuy08PNDCJOBLYlJmQnA5CRJ5qbHn+qk7Z2BdYAz04f/e0MITcTEwu1pnQeTJJmV/v5mCKGNOCqhMUmSl4gjwjuUJMnuIYT3APsBm1czyQAwpJqdiYiIiIiIiAwAk5IkaUh/NgUIIRwfQng8hNASQmgmrmkyKq3/X8C8CtveGHix5OH/ubS86IWSc76T/ve+EMJjIYTSRfdXkSTJW+kikJ8LIRxYYWy56NaIhhDCF4DbkiRpTn/vVJIk1/Y4MhEREREREZF+IISwO3AqcVe8uUmSrAghvM67u2+8AIwG/lnm9NKpHy8Dm4QQ6jLJhs1YeQ2FFSs1kCTzgaPTWHYFbgsh3JUZQdGZNdLYqqa7UyeuJm7zcX/6e2cSoK4nQYmIiIiIiIj0IyOIizAuBNYIIZxI3D2v6OfAWSGEx4DHiQ/2byVJ8jzwKrB5pu59xHUeTgkhnAd8AjgS6PDL/BDCl4B70mkTi4nP26tMhwghbEccaXF3WucIYFdgYncvuDe6m2j4AHGHgOLvIiIiIiIiIqu7W4A/AE8AS4ELgBczxy8iLrx4I7A+cSrEV4Hn02NNIYSjAE+S5Mh0KsNPgBOIu06ckCTJ3zrpfwfgwhDC2sAC4MQkSR4vU68e+BHwYWJi5Engi0mS/KMnF91T3Uo0pNmYVX4XERERERERWR0kSbJXmbJ24OvpT9F5JcfPTX9Kz70H+EhJ2RPApzrof0qZspOIu1x0Fft9xC0za6rHu06EEO4Ffgv8Pp0vIiL90JrT1oE+3hKqqa8aHqD625ZQA0tTj8/UFmjVt1rf6021DqBjutdrY7W+30VEctabXSdeJmZrXgwh/CWE8LUQQkM+YYmIiIiIiIjIQNTjREOSJIcQ5558HVgOTAfmhxCuDyF8JYTw3pxiFBEREREREZEBojcjGkiS5I0kSX6TJMnngI2AY4krXF5BXFlTRERERERERAaRXiUaspIk+Q9wF3APcRXM4Xm1LSIiIiIiIiIDQ48XgywKIWwOjAEOBbYkbn95ZfojIiIiIiIiIoNIb3adOI6YXNgeeB24BjgGuD1JkiSf8ERERERERGQwmzW6KdQ6Bume3oxoOAvw9L83J0nydj4hiUielk1aBNAyj0V91sdUhvVZ27XWOrlXpz+YUxgDy7CptY6ghXn5NTaZ1vwaW331i3u99rde1bXkeKtL5frF/Z6n0U2z9BAnIrnqTaJhgyRJluUWiYiIiIiIiIgMeD1ONBSTDCGEPYDdgXWARcAdSZLMySc8ERERERERGczGzJ3XJ1PzZ209WqN5+khv1mgYDlwHfAZ4G/gPsC5QF0L4C3CwRjyIiIiIiIiIDC69mTrxA2Bn4DDgqiRJ2kMIdcAXgZ8B5wLf7n2ItWdmuxGv92Np0TzgdHf/U3p8JPB94BCgAXgBmA5c5O5JWuc5YIK735xpdy9glrtvaGZvZLp8L9BGTOAAnA3cXaxbEtss4Al3n1Im7s2AZ4H3untrWnY6cDTwGXd/Ii07GLgWOMbdLy1pIwG2LNYtF3v6ugk4Ehjr7jMz9Y4DpgE/cPeTM+X1QAF4zt13LGm72NZe7n57WjYMeBP4AHAyMDatvgZQnx4DeN7dt0rP+SewAfB+d3870/4U4AxgnLtfnimfD4xx99ml76WIiIiIiIhUpjeJhkOAk5MkmVUsSJKkHfhdCGFd4LusBomGNInwR2AiMJP4ULsz0J4efw9wK7AE2JP4YL8r8BtgU+C4Svpx97Uyfd4LTHf3pkzZXjlcyw+Jf267u/uzmUPjiDuHjAcuLXNqpZ4iJghmZsqOBJ4sU/cA4nu5nZlt7e5zS44vAs4Bdis90d0nABMAzGwCMTmwV7aOmW0LbEVMQOwL/KFM+2ea2ZXu/lZFVyciIiIiIiJdGtKLcxuAZzo49nR6fHXwYaDe3S9397fd/U13n+3ud6THxwKbA19w93+nde5Iy79tZpvXKvCMIWY2nfhwv1KSwcw2APYnjnLYzsw+1kEblfgDsI2ZbZK2/QlgGHBvmbrjiQmJ2envpWYA7zcz62Es44E/A1d10P5fgAWkCQsRERERERHJR28SDY8Tv60u50jgsV603Z88BSw3s5lmdoCZrVdyfB/gT+6+OFvo7ncBLxPXsKi1JuIojD3c/eWSY2OBZ9z9auAOyj+UV6oN+B1wRPp6PHB5aaU0ubEfMdFwBTA2nUqR1UrcOvX7Ztat+zQdZXJYpv0DzWxUSbUEOBU4zczWQkRERERERHLRm0TDWcBXQgh3hxCOCyEcGkKYGEK4G/hyenzASxMInwSWE6cVzDez2zIjFUYR1xoo55X0eF7WN7Pm7A/whQrO2xe41t0XlDk2jnenOsyg/EN/dzQBR6ZtfIU4haTUEcAL7n43cDUwgjiqotSvgfcAh3czBgOGAtcTR0zML9eGu98KzKXC6S0iIiIiIrL6CyHMDiG0hhDeyPwc1Mv2qj6SOoSwVwghCSGcW+2+e7O95fUhhIOJi+r9CAjEb4n/Sdxx4sZcIuwH3P1x4GvwzgKLPyM+lO8GLAQaOzh1o/Q4xG/7Sx/g69PySr3WwWKQXfkccKOZLXH3CzPn7ghsDRyUFl0FXJLWv74bcb3D3R8ys+XAVOBhd3+5zOyHcaTJDXdfYmY3EEc/3FDS1ttm9l3iwqLdiWc8cJ27LwMws5lp2UVl6p4K3GJmP+lG+91SKBSGEhMftTCiRv2KiIjIAFEoFEbWOoZOFD/LjCgUOvpuT/LW0NAwvK6ujvb29uELFiwoe380NjYuLle+GpmYJMn0WgcBEEKoT5KkO8+NhBCGEp9/7umbqDrXo0RDCOE9wIHAP5Mk2T7d6rIBaE6SZGmO8fU77v6cmV0CXJkW/QU418xGuPuSYj0z2xXYGPhrWvQCcceErA8Cz/dxyAAPAP8D/NnMVrj7xWn5eGJy6K5MMmCNtPz6XvR3OTH5tMooAjPbibhI48ZmdnRavCbwXjNb391fKznlKuAk4JuVdGxmGxGvdVm6iwTEh/wGM9vW3f+Rre/u95nZ34BTKru0HjmFmJATERER6Y9aah1ABV6qdQCDSXNzc/HXOZ1UC30fSf8SQphG3GXxfcC/geOSJLk9PTaEOFL6m8QvnF8gjuQ+BNgd2CWE8CPguiRJjgghfBj4CbA98BpwTpIkTWlbU4CPA4uJXwqfG0K4GvglsC1xd8I7kiQ5qJNwTwFuBDbJ5+q7p0eJhiRJ3gohzCQOyX86TS6slgkGM9uCmFT5HfAisB5wFO9mhmYA3wKuMbNvERMHuxAfti9193lpvZnE9QBuAx4FtgAmUf5b9tylD9T7AjebWTvwK2AMcAxxa8uiXYHfm9kG7v5qWvaedHvJorfp3C+BfxHXfCg1nvgX1lcyZYH4fo4lboWZjTsxs1NZeSeLznyV+D916W4V16R9/2OVM+A04H767i/Lcyi5rioagf5hFhERkc6tXesAOlH8LLMJcZc3qYKGhoZt6urq5rS3t+/R3Nz8cK3j6UceBM4GmoFjgatCCJslSbKMuOPiN4hT2x8FPgQsT5LktBDCfwOziiMkQgj1xIX0ZxGnkG8H3BxCeLaYuCA+gx5BHFk/FLiMuNvhp4jTy3fsKMg0iTGGmJT4aW5X3w292d7yCeD9eQXSjy0BdiDeSA3ErNJtxOQC7v6WmX0G+D5wZ1rnBWJ2Kvtw+ev02DXEqRavEB/2qzYcx93vMbP9gZuI/6CsAC5z99ZMtevM7CniQ//5aVnpXy5nEtc+6KifxcSRHitJkxVjgKPdfX7JsZ8SEwGrPJC7+y1m9giwV2fXlxoH/LRM+xcDl5rZCWXaf8zMrqbjxU17pbGxcTlxjY+q0xBDERER6Up/HgKf+SyzpD/Hubppa2tbCjBkyJClg/h9n5ZZ26AlSZJNkyTJfvl5fghhMrAlMQExAZicJMnc9PhTnbS9M7AOcGaSJO3AvSGEJmJioZhoeDBJkuI0+TdDCG3ApkBjkiQvUf5L3aLpwIlJkrwZQm0GnoQkSXp2Ygj7ARcChyVJ8mCeQYlIPgqFwshlkxb1+XDIqQzrutIA1Tq51hEMQMOm1jqCXE2mtetK0i+sZreeSNWMbprVb4fAp+tHtABrD+IH3qpra2vbjvjwvH19ff1DtY5nzNx5PXto7cKsrUeXvfdDCLPJjEDIlB9PHN3eSJyCPhLYL0mSW0IIy4DdkiT5Z1fthRC+ApycJMm2mToTgf9JkmS/dOrER5Mk+XLm+IbEDRc+R/x/4qIkSX5Wpq+vAockSfL59HUTMD9JkpMreEty05sRDecRd1S4P4SwkDivJHsDJEmSbNOb4ERERERERERqLYSwO3Eh+b2BuUmSrAghvM67069fAEYTN0coVZooeRnYJIRQl45oANgsLS9asVIDSTIfODqNZVfgthDCXZkRFEWfAj6VPqMDrAWsCCHsnCTJ3hVdbA56k2j4e25RiIiIiIiIiPRfI4hr1S0E1gghnEgc0VD0c+CsEMJjwOPEpMNbSZI8D7wKbJ6pex9xnYdTQgjnAZ8gTuP+QkedhxC+BNyTTptYTExetJepehyQHZM7DVhAnP5eNd1ONIQQtiKupDkKKABXJ0lya96BiYiIiIiIiPQTtxAXcHyCuBHCBcTNAoouIi7SeCOwPvAccaH659NjTSGEowBPkuTIEMKBxHX9TiDODjghSZK/ddL/DsCFIYS1iYmDE5Mkeby0UpIkrwOvF1+nUzqWJElSurtfn+pWoiGE8Enido1rEDM56wBHhRD+X3/ZY1RERERERESkp5Ik2atMWTvw9fSn6LyS4+emP6Xn3gN8pKTsCeI0h3L9TylTdhJwUiXxl5w3rrvn5GFIN+tPAR4DNkuSZANgXeB6QMsviYiIiIiIiEi3Ew0fB76XJMmLAEmSLAaOB9YJIQyGrS5FREREREREpBPdXaNhFPBSSdmLmWMvIiL9yprT1oE+3hKqqa8aHqD625ZQ1ddUk161BVr19bt7vanWAVSH7vXa6Hf3u4hIP9bdEQ2w6tYcIiIiIiIiIiJAz7a3/FsIYUWZ8jtKypMkSdbuYVwiIiIiIiIiMgB1N9FQ1b03RURERERERGRg6VaiIUkSJRpERERERESkamZtPTrUOgbpnp6s0SAiIiIiIiIiUpYSDSIiIiIiIiKSm54sBikiA8iySYsAWuaxqNahdGoqw2odQre1Tu6yyoNVCKM2hk2tdQSdaWEeTKa11nEMJgP2Xu/ft3KXWubVOoLBacDe70Wjm2ZpGLoMKOPGzOuTnQ+bZmlKRl/RiAYRERERERERyY0SDSIiIiIiIiKSGyUaRERERERERCQ3WqNBcmVms4FdgLeBBHgSON7db8/UORi4FjjG3S8tOT8B/g181N3fTssmAGPcfS8zeyNT/b1AW9oXwNnA3cBtwLKS0I5092vMbApwBjDO3S/P9Ds/7WN2z69eRERERERElGiQvjDR3aeb2RDg68D1Zra+u7elx8cBrwPjgUvLnL8u8DXg56UH3H2t4u9mdi8w3d2bMmV7Aa+5+4adxLcIONPMrnT3t7pzYSIiIiIiItI5TZ2QPuPuK4CZQAOwEYCZbQDsDxwNbGdmHytz6rnA6Wb23j4K7S/AAmBCH7UvIiIiIiIDVAhhdgihNYTwRubnoF62V7VnjxDCcyGENzOxP1qtvouUaJA+Y2Z1wJHAC0AhLR4LPOPuVwN3EEc1lLoReB44po9CS4BTgdPMbK2uKouIiIiIyKAzMUmStTI/19cqkBBCfQ9OOzgT+1a5B9UFJRqkL0wzs2biOgnTgBOL6y0Qp03MTH+fAYw1s3L/45wCnGxma/eg//XNrLnk50PZCu5+KzAXOK4H7YuIiIiIyCATQpgWQnghhLAkhPBQCGHPzLEhIYTjQwhPpccfDSFsF0L4PrA7cGE6umBGWv/DIYS/hBBeDyE8GUIYl2lrSgjh2hBCUwihGTg+hDA6HRnREkL4Twjh+upeffdojQbpC5MyazTsBvzRzJ4mJra2Bg5K610FXAJ8Drg+24C7zzGz+4ATgZe62X9XazQUnQrcYmY/6Wb73VIoFIYCQ/uyj06MqFG/IiIi0k8VCoWRtY6hG4qfZUYUCoVOK0p+GhoahtfV1dHe3j58wYIFZe+XxsbGxdWOqx94kLgAfTNwLHBVCGGzJEmWAd8GvgF8AXgU+BCwPEmS00II/w3MSpJkOrwzQuEPwCzitPLtgJtDCM8mSVJcRP9A4Aji2nVDgcuAW4FPAe8Bduwi1stDCEPSWE5LkuSuHK6/Yko0SJ9J12i408yeAvYGPkictnCXmRWrrUGcPnF9mSZOBeYA5/dRfPeZ2d+Ioyf60inEnS5ERERE+oOWWgfQA9394kl6obm5ufjrnE6qhb6PpKamhRDOTX9vSZJk0yRJZmaOnx9CmAxsSUxATAAmJ0kyNz3+VCdt7wysA5yZJEk7cG8IoYmYWCgmGh5MkmRW+vubIYQ2YFOgMUmSl4jT0DsyNo0J4ojym0IIH0uS5PnOLzk/SjRInzKzXYCPEqcpnEpcd+HaTJVdgd+b2Qbu/mr2XHf/p5n9Efi/9Py+cBpwP337F+U5xCkktTAC/cMsIiIiK+vJ1NRaKX6W2QRYUuNYBo2GhoZt6urq5rS3t+/R3Nz8cK3jqZFJxREIRSGE44GjgEbiF6gjgVHp4f8C5lXY9sbAi2mSoeg54H8yr18oOec7wFnAfSGEFuCiJEl+Vq7xJEnuzLz8aQhhDLAfML1c/b6gRIP0hQvN7Efp7/OBycSdJ1YAl7l7a6budemIh7GUH7nwXeCL3ex/fTN7o6TsO+6+yhQJd3/MzK4mLlrZJxobG5cDy/uq/c5oiKGIiIiUGkhD3jOfZZYMpLgHura2tqUAQ4YMWar3PQoh7E784nRvYG6SJCtCCK/z7heWLwCjgX+WOT0pef0ysEkIoS6TbNgsLS9asVIDSTKfuHMfIYRdgdtCCHdlRlB0ZgVVHoGiRIPkyt336uTwrHKF7r5V5vdQcmweUHaVVXffpUzZbDpZ5NTdp5QpG0ccUiQiIiIiIlLOCOBtYCGwRgjhROKIhqKfA2eFEB4DHicmHd5Kpyu8CmyeqXsfcZ2HU0II5wGfIH7x+YWOOg8hfAm4J502sZiYvGgvU++/iFMs7kuLjiSu53BU9y63d7TrhIiIiIiIiEjnbiEu4PgE8DzQBryYOX4R8BvgRmIi4FriOgzFY5buMHF5kiRtxMUePwW8BlwBnJAkyd866X8H4rSJN9I4TkyS5PEy9dYiLri/iDi6/EjggCRJnu7+JfecRjSIiIiIiIiIpJIk2atMWTvw9fSn6LyS4+emP6Xn3gN8pKTsCWKioVz/U8qUnQScVEHsjxFHSNSURjSIiIiIiIiISG6UaBARERERERGR3CjRICIiIiIiIiK5UaJBRERERERERHKjxSBFVnNrTlsHYO3+vgdyU60DyFFbW9t2wIPA9vX19Q/VOp6+0VTrAFZRKBRGAi0MgPt9dbFa3OtNtQ6g+3Sv18Zqcb+LiFSJRjSIiIiIiIiISG40okFERERERET6raZZo0OtY5Du0YgGEREREREREcmNEg0iIiIiIiIikhtNnRAREREREZF+a96YuUlftDt61taaktFHNKJBRERERERERHKjEQ0iq7lTJy0DaIF5tQ5lQGqd3KvTH8wpjP5t2NRaR1Cqpa9v98m09m0HA0+P7/X+d/sMKC36m70mBtzf7aObZulbWxGpKo1oEBEREREREZHcKNEgIiIiIiIiIrlRokFEREREREQkFUKYHUJoDSG8kfk5qJftTcgxxK76GxJCOCOE8GIa+6MhhM2r1T9ojYZBxcy+CEwCPg4sB54HZgEXu3urmX0EOAf4FPHe+BdwlrvfnGnjOWADoB1YBtwOHOPur2bqVNrOSOCD7t6clu0LTHf3zczsUWDTtPpQIAHeSl9f4e4TzGw94GXgBnf/Usm1zgZmufv0Mu9Dl/GJiIiIiMigNjFJklWeJWohhFCfJElbN045Hdgb2AN4DvgQsKgPQuuQRjQMEmY2EfgpcDHQ6O7rAmOJD/PvN7MPAHcDzxJvxA2AnwNXm9nBJc0d7O5rAVsA7wPOz/TTnXYS4Dvl4nX3rdx9rbSfa4Czi6/dvZgNHAu8Ebu1dSt8H7oTn4iIiIiICAAhhGkhhBdCCEtCCA+FEPbMHBsSQjg+hPBUevzREMJ2IYTvA7sDF6ajC2ak9T8cQvhLCOH1EMKTIYRxmbamhBCuDSE0hRCageNDCKPTkREtIYT/hBCu7yDGBuAE4KgkSZ5NoqeSJHm9z96YMjSiYRAws7WBqcB4d7+qWO7ujwH/L63zG+BBdz8+c2qTmW0MXGBm17v7SvvXuvsiM7sO+N9M8ZndaOcHwHfN7GJ3n9+DSxsPnAscDRwGXFLBOd2JT0REREREpOhB4GygGTgWuCqEsFmSJMuAbwPfAL4APEr8UnN5kiSnhRD+G5hVHCERQqgH/kAcXb4/sB1wcwjh2SRJbk/7OhA4AvgacYT3ZcCtxFHZ7wF27CDGjwFvA4eEECYCS4EmYGqSJFV7ztGIhsFhV2AYcH0ndfYh3uilriSOevhw6YF06sIhrLxvYnfa+RfgwHc7iassM9se2Ar4LTCTmHSoRLevU0REREREBp1pIYTm9Od5gCRJZiZJsjBJkreTJDkfqAe2TOtPACYnSTI3M4rg+Q7a3hlYBzgzSZK3kiS5l5gMOCJT58EkSWYlSbIiSZI3gTbi80pjkiStSZLc0UHb7wfWTuPaHNgP+DowrmdvQ88o0TA4jAIWuvs783rM7CYzazazZWZ2RFqnUObcVzJtFF1tZouB14g38TElfVXaDsT5Q+PM7IMVX000Hrjd3V8CZgDbmtk2FZzX3fhERERERGTwmZQkSUP6sylAOjXi8XT6QjPxWaj4/PBfrPwFbGc2Bl5MkqQ9U/ZcWl70Qsk5xSnn94UQHgshfLODtpel/z0rSZKlSZI8BfyCOHKiajR1YnBYCIwys/pissHd9wMws3uBurROY5lzN8q0UfRFd7/ZzLYljkjYGHgxU6/SdnD3p83scuAs4IpKLsbMhgKHAiembcxLr2M8MLGL07sVXx4KhcJQ4nCnWhhRo35FRESknygUCiNrHUMvFD/LjCgUyn1XJH2hoaFheF1dHe3t7cMXLFhQ9v5pbGxcXO24aimEsDtwKnGRxblJkqwIIbwOhLTKC8Bo4J9lTi+dsvAysEkIoS6TbNgsLS9asVIDSTKfOGWcEMKuwG0hhLuSJJlb0va/OuizqpRoGBzuIe4ycRBwVQd1/gJ8mTj3J+srxP9pnio9wd3/YWZnAz8xs+3TtQ263Q7wvbT8X2WOlfN54lCj89L+If4jNNrMTsyO3CijJ/H11inAGX3QroiIiEglWmodQA5eqnUAg0lzc3Px1zmdVAudHFsdjSCufbAQWCOEcCJxF72inwNnhRAeAx4nJh3eSqdPvEqcxlB0H3Gdh1NCCOcBnwCOJK7vUFYI4UvAPUmSvAQsJiYS2kvrJUnyTAjhb8DkEML/Er9kPYo4krxqlGgYBNy9xcxOBy41syHATcAS4noE66XVpgB/N7PzgPOIQ24OIWbtxneyQOJlxJv288Q1ILrdjru/YmY/Jg4HeqOCSxpPXJfhhEzZmsRExYHAtWnZGmY2LFNnRS+uszfOAab1QbuVGIH+YRYRERns1q51AL1Q/CyzCfHzq1RBQ0PDNnV1dXPa29v3aG5ufrjW8fQTtxAXcHyCuMDiBbw7qhvgIuIijTcC6xOnQnwVeD491hRCOArwJEmODCEcCPyE+EzzGnBCkiR/66T/HYg7V6wNLABOTJLk8Q7qHk6cLrGQuK3lT5IkmdHtK+4FJRoGCXc/38xeBo4jJgfeJN70PwGucvelZrYb8aH4aeK98QjwFXf/UyftLjezi4AzzOyGdCpEt9shPvRP6OQ4AGbWSFzQcdfSnSrMbAYxCVFMNFzCyjtR3O7ue/Uwvh5rbGxcThxRUnUaYigiIiIDeYh75rPMkoF8HQNNW1vbUoAhQ4YsHYzve5Ike5Upaycuqvj1TPF5JcfPTX9Kz70H+EhJ2RPEHSTK9T+lTNlJwEkVxv8KcEAldftKqOIOFyJSZYVCYeSpk5atDsMla6Z1cq0jGACGTa11BFU3mdZah7DaGIS3j0jVjW6aNWCHuKfrS7QAaw/GB95aaWtr2464leP29fX1D9U6nnlj5vbJQ+voWVsP2P83+jvtOiEiIiIiIiIiuVGiQURERERERERyo0SDiIiIiIiIiORGiQYRERERERERyY0SDSIiIiIiIiKSGyUaRERERERERCQ32t5SZDWmLaFqo79tCTVY6H6vPt3rtaF7vTZ0v9eG7vfa0P0uvaURDSIiIiIiIiKSGyUaRERERERERCQ3SjSIiIiIiIiISG6UaBARERERERGR3CjRICIiIiIiIiK5UaJBRERERERERHKzRq0DEJG+tWzSIoCWeSyqSn9TGVaVfgaIByut2Dq5L8Pox4ZN7YtWW5jXF81KJx6cTGutY6iKvrlle6xFt3pNVPx3e38wumlWqHUMIjL4aESDiIiIiIiIiORGiQYRERERERERyY0SDSIiIiIiIiKSG63R0ANm9iXgeGBrYBnwGHC+u99oZnsBt6XlWUe6+zVmNgU4Axjn7pdn2pwPjAF2A05Ni+uAodm23H0tM5sN7AK8DSwHHgC+7e5PlcR5A7AvsJG7L8qUjwMmuPsuFVzrbsAPgI+lRfOA0939Tx21k8Y3y92np+/HLHffsJM+PgH8A/iRu5+Ylu1KfB8b3H15WjYVOA3Y0N1fTcuOAb7u7tum8fwKeLOki73d/QEz2xKYBuxEvPdfIP65NaVtJcCW7v5EV++LiIiIiIiIlKdEQzeZ2bHAd4H/BW4iJgH2Ag4DbkyrvdbZgzWwCDjTzK5097eyB9z9bODstK99genuvlmZNiamD/JrAj8DLgM+mYlzfWA/4I00th9370rBzEYCfwQmAjOBemBnoL27bXVhPPA6cISZneLubxOTJ+1pf3PSensAjwN7Ar/PlN2eaeuBThIofyC+TwcDK4BPAKPyuwwRERERERFRoqEb0gfv7xO/Qf995tBf059K/QX4IDABuLg3Mbn7MjObxbsP3kVjgX8Ds4gP8t1ONAAfBuozIy/eBmb3MNSyzOw9wOHAccQY9wNudPe3zewuYlJhjpkNA7YijmgoTTRMqKCfUcT3/OfuXlwa/f48r0VERERERES0RkN37QYMA67tZTsJcXrEaWa2Vm8aMrMRxAf10h2uxhNHIVwBbGdmH+9B808By81sppkdYGbr9SbWDhxIHCnxO+L7Oj5z7HZiUgHiyIZ/EBM6ewKY2UeA9YE7KujnP8TEy2/M7BAz2ziX6EVERERERGQlSjR0z7rAQndv66Le+mbWXPLzoWwFd78VmEv8Jr8npplZC7CY+BA+tnjAzHYgfvs/092fBe5i5Qf4irj7YuJ0jOXApcB8M7vNzDbvYczljAeuSUcZzACyCY3ZwK5mVk86ssHd/w28Lx2hsCfwiLv/J9PeDmXe+6HungCfIiZkzgFeNLO/m9n2OV6LiIiIiIjIoKepE93zH2CUmdV3kWzoao2GolOBW8zsJz2IZVK6RsMHiWtFfAh4JD02HrjT3Z9PX88ApprZdypIkqzE3R8HvgZgZpsR14OYQRzd0UYcjVCqPj3WKTPbiLhY5WfTotuA14gjNC4krtMAsCNxisTU9PWd6evS9RkA/t7RGg3u/hLwf2nfGwA/Am4ws/eniYg+USgUhhIX9ayFETXqV0RERPqBQqEwstYx9FLxs8yIQqFQ00AGk4aGhuF1dXW0t7cPX7BgQdl7qLGxcXG145KBQ4mG7rkbaCUuJli6JkK3uft9ZvY34JRetPGMmU0EfmVmNxEXOTwUGJruZAHxz3ld4ADgul709ZyZXQJcmRa9APyXmdW5ezuAmQVgM+D58q2s5AjizhpXpjs+ADQQEyUXunubmd0NfAbYDrgvrTOHOJphD+JClT25llfN7AfEkSDrEJNIfeUU4k4jIiIiItXWUusAcvJSrQMYTJqbm4u/zumkWuj7SGSgUqKhG9x9sZmdBvzYzFYANxO3UvwkMNbdv9GDZk8jLkrY4/9R3f2mNKnwTeAV4p/r1qy8zeOFxAf4YqIhpAssZi3PfrNvZlsQ11D4HfAisB5wFHBPWuV+oBk4PX1oXwFMIo5muCvbcJm+3gLGAecCF2XK3w/cZ2bbuftDxBELxwCPuXvxeuYQd/5Yn87/8sv2/740thnA08Baabv/Lpl60RfOIW6rWQsj0D/MIiIig9natQ6gl4qfZTYBltQ4lkGjoaFhm7q6ujnt7e17NDc3P1zreGTgUaKhm9z9IjN7BTgBuBxYCjxKHIZftL6ZvVFy6nfcfZUpEu7+mJldDRzZy9DOAy4A/gXMSNdmeIeZXQDcmU4ZANiJlRMRAB8Ansu8XgLsABxLHGmwmDi94Vtp7MvN7HPEh+jiCIa/A/tnkgIAG5Tp6xTidI9L3H1+pny+md1CTIo8RFyn4XvEbSmL5hKnZzzq7gtL2t2xzHs/BvgbMYlxCzFhsoyYMDmQPtbY2LicuM5F1WmIoYiIyOA20Ie3Zz7LLBno1zKQtLW1LQUYMmTIUr3v0hMhSfpsarqI1FihUBi5bNKiqg6ZnErp4BWpROvkWkdQI8Omdl1HBoTJtHZdaTWgW1YGmtFNswb08PZ0jYkWYG098FZPW1vbdsCDwPb19fUP1ToeGXi064SIiIiIiIiI5EaJBhERERERERHJjRINIiIiIiIiIpIbJRpEREREREREJDdKNIiIiIiIiIhIbpRoEBEREREREZHcrFHrAESkb605bR2o4pZQTdXopJ/TllDd0ZRbS9oCrfoG5b3eVOsAdK/XyqC830VEekgjGkREREREREQkN0o0iIiIiIiIiEhulGgQERERERERkdwo0SAiIiIiIiIiuVGiQURERERERERyo0SDiIiIiIiIiORG21uKrOaWTVoE0DKPRVXtdyrDqtpff9M6GYjboA1Ow6bWsvcW5tWy+9qaTGstuu1X93ptb7+qahnEt3ot9av7vSOjm2aFWscgIoOXRjSIiIiIiIiISG6UaBARERERERGR3CjRICIiIiIiIiK5We3WaDCzU4DPuvvembI7gXXdfctM2dXAi+5+nJk1AYcBb2WaanX3UWndA4AzgdFAO/AYcBywD3BqWr8OGAosKzbg7muVie85YCTwQXdvTsv2Baa7+2aZOhPc/ebMeXsBs9x9w/T1bsAPgI+lVeYBp7v7n0r6+yewAfB+d3+7g/fsUWDT9OVQIMm8F1cA5wLPAktLTj3d3aeZ2Tjg18AUdz8z0+696XU1pa/XAk4HDgE2BF4HHgYudPdbM+d9EZgEfBxYDjwPzAIudvfWTL2DgWuBY9z90pJrSoh/FgmwBPgjcKy7L83UqQcKwHPuvmO590ZERERERES6Z7VLNACzgdPNbKi7LzezYcCWwFIz28DdX03r7Q58M3PeNHc/ubQxM9sc+C3wZeDPwJrAnsBydz8bODutt1KyoAsJ8B3eTVJ0i5mNJD44TwRmAvXAzsQkSLbetsBWwJvAvsAfyrXn7ltlzpkFPOHuUzJlm6W/jso+6JdYBEwys0vdfWGZmN8D/JWYrPgC8Cjx/vsUcCBwa1pvInAa8H/An9x9sZl9FPh/wPuBf2eaHUdMVowHVko0pLZ39yfMbGPgJuAUYHLm+AHE9247M9va3ed2cG0iIiIiIiJSodUx0fAA8YF7J+AOYFfi6sCvAnsAV5nZlsB6wJwK2tuWOPKhOLrgDeJDfm/8APiumV3s7vN7cP6HgXp3vzx9/TYxwVJqPDE5Mj/9vWyiISf/Bl4mJk8mlTl+BHHUxGh3fyMtexv4U/qDma0NTAXGu/tVxRPd/TFiouEdZrYBsD9wKPB7M/uYuz9SLjB3f9nMbiH+WWaNJyZqtkh/P77iqxUREREREZGyVrs1GtLpAXcTRx1ATC7MSX+yZY+4eyX7/T0EbG5mF5vZPunDcG/9C3Dguz08/ylguZnNNLMDzGy90grpCILDiA/SVwAHmtmongZcodOAo83s/WWO7QPckkkylLMrMAy4voK+xgLPuPvVxITS+I4qmtl/EZMS8zJlGwD78e77MzadSiEiIiIiIiK9sNolGlKzeTepsCerJhr2ZNURABPNrDnzcyuAuz8D7AWsD/wGWGhm15Z7uO+m04FxZvbB7p7o7ouBTxLXL7gUmG9mt6XTPIqMuN7C9cRrnQ8c3suY55e8R58uiesJ4PfAlDLnjgJeeSc4sw+kbbSYWWumzkJ3b8vUuymtt8zMjsi0N46YJACYQflEwf1m9gZxjYeXgTMyx44AXnD3u4GrgRHEZISIiIiIiIj0wuo4dQLgduA0MxsOfAK4L12vYVT6rf7uwLEl51xYbo0GAHe/FxgDYGZbExMOFxFHDPSIuz9tZpcDZxG/Uc9qI64dkFWflhfPfxz4WhrTZsDPiA/cu6VVxgPXufuytM7MtOyinsYMbNjJGg1FZwCPm9kPS8oXAo2Z+J8FGsxsC+DxTJ1RZlZfTDa4+35p/PcSF9zEzHYEtgYOSs+7CrgE+Bwrj4bYCXgS+AzQBKwDNKfHxpEmKtx9iZndQHx/buji+rqtUCgMJSZ9amFEjfoVERGRGioUCiNrHUNOip9lRhQKhZoGMpg0NDQMr6uro729ffiCBQvK3kuNjY2Lqx2XDByra6Lh/vS/3wLmuvvy9PWdxAfMjalsfYZVuPtcM7uMlReS7KnvEadB/Kuk/AXgAyVlHyR+M18upufM7BLgSgAz2wj4H2CZmRXXgBhKfLDf1t3/kUPsZbn7i2b2C+JaC1l/Bb5nZiPcfUkHp99DHKVxEDF50JHxxAU17zKzYtkaafn1JfEkwK1mdgVwPnCwme1EXCRzYzM7Oq26JvBeM1vf3V/r8kK75xRWHk0hIiIi0tdaah1Azl6qdQCDSXNzc/HXzp6ZQt9HIgPVaplocPc2M7sHOAH4ZebQHOI6Ao+W2xmhHDP7JPHb8xvc/RUz25Q4BeGeHOJ8xcx+TNyBIrt2wUziiIzbiLszbEFcYPGiNKYtiDs1/A54kbiw5VGZmL5KTFbsxsquIT6M91miIfV94GniYo9FvyEmZ643s0nE6xoC7FKs4O4tZnY6cKmZDSHuFLGEuPjlegDpLiJjgGOIW1sW7UpcFDK7s0jWNODZdCeO8cR74SuZ44H4/o1N6+bpnD5os1Ij0D/MIiIig1Ee64r1B8XPMpsQPxdKFTQ0NGxTV1c3p729fY/m5uaHax2PDDyrZaIhNRv4NCtn4eYAF1P+2/JJZnZMSdnGxKH2+wNTzGwEcRvHG4GTcorzPGBCSdmvgQZiYqCRuLbBr4Dp6fElwA7E6R8NwGLgNuIIDoijNn5auqOFmV1MfIg/wd3f6kGsCzMjCAAudfdV3gd3X2hmF5D5Fj+durJ3WnY9sAHwH+Jojs9m6p1vZi8DxwGXEbfmfB74CfHP7SBgBXBZyTSO68zsKWKi4PwyMb1qZr8hPvTvDBxd5v35KTEJkWtSoLGxcTlxpEbVaYihiIjI4LS6DGvPfJZZsrpc00DQ1ta2FGDIkCFL9b5LT4QkSWodg4j0kUKhMHLZpEU1GTo5lWG16LbfaJ1c6whqbFjp7Cmplsl0tZTO6k+3nwiMbpq1WgxrT9eaaAHW1gNv9bS1tW0HPAhsX19f/1Ct45GBZ3XddUJEREREREREakCJBhERERERERHJjRINIiIiIiIiIpIbJRpEREREREREJDdKNIiIiIiIiIhIbpRoEBEREREREZHcrFHrAESkb605bR2owZZQTdXsrJ/RllBQiztAW6BVX7+915tqHUDf0r1eG/32fhcR6Yc0okFEREREREREcqNEg4iIiIiIiIjkRokGEREREREREcmNEg0iIiIiIiIikhslGkREREREREQkN0o0iIiIiIiIiEhutL2lyGpu2aRFAC3zWNTjNqYyLLd4eqJ1ck27740HK645bGofhjHotDCv1iFU12Raax1C5fd6F/S/Qre0DLJbvb/I7X4vZ3TTrNCX7YuIVINGNIiIiIiIiIhIbpRoEBEREREREZHcKNEgIiIiIiIiIrnRGg1VZmanAJ91970zZXcC67r7lpmyq4EX3f04M2sCDgPeyjTV6u6j0roHAGcCo4F24DHgOGAf4NS0fh0wFFhWbMDd1yoTX9m23P0BM5sCbOHuY0rOeQ6Y4O43m9k44NfAL939G5k6nwD+Adzn7ruUnH8DsC+wkbsvMrPpwNj08BpAPfBm+vp5d98q7XODNMaiW939YDPbDHgWWJqWvw5cCZzs7isy/a4HvAzc4O5fKn0vREREREREpPuUaKi+2cDpZjbU3Zeb2TBgS2CpmW3g7q+m9XYHvpk5b5q7n1zamJltDvwW+DLwZ2BNYE9gubufDZyd1tsXmO7um3UUWGdtdfManwEONrNvu3sxQTAeeLJMn+sD+wFvEJMpP3b3CcCE9PgEYIy771Wmn4Pd/eZO4hjl7q1m9hHgb8BTwC8zx8em/ZqZrevu/+nORYqIiIiIiMiqlGiovgeI38LvBNwB7EpcvfhVYA/gKjPbElgPmFNBe9sSRz4UH7jfAP7Yw9jyamsB8ChwMPBbM6sHvgJcAhxYUncs8G9gFjEZ8eMe9Ncpd3/SzO4iXl/WeOBc4GhikuOSvPsWEREREREZbLRGQ5W5+9vA3cSRAhCTC3PSn2zZI+5eyX6EDwGbm9nFZraPma3di/DybKsJODL9/QDgYeI0hVLjgZnAFcB2ZvbxXvRZlpl9lDhCZF6mbHtgK+IIjplpHCIiIiIiItJLSjTUxmzeTSrsyaqJhj3TOlkTzaw583MrgLs/A+wFrA/8BlhoZtem6w90S55tATcCnzCzjYFxxMTDSsxsB+LD/kx3fxa4i+498F9d8p6cUXJ8vpktI46u+AtwaebYeOB2d38JmAFsa2bbdKNvERERERERKUNTJ2rjduA0MxsOfIK4QOJyMxtlZqOI374fW3LOheXWaABw93uBMQBmtjUxSXARcTpAt3TRVhtxYcZS9emxbDttZvY7YBKwG3HqxJiS88YDd7r78+nrGcBUM/uOu7fRtS92sUbDhsQFNA8jLnA5HHjLzIYChwInprHOM7N703gmVtBvtxQKhaHEhThrYUSN+hUREZEeKBQKI2sdQz9T/CwzolAo1DSQwaShoWF4XV0d7e3twxcsWFD2nmxsbFxc7bhk4FCioTbuT//7LWCuuxcXW7yT+O3/xlS2PsMq3H2umV3GygtJ9kiZtl4ADsnWMbM1ibs/PM+qmoC/A79IF2XMnld82B9qZvPT4jWAdYlTLa7rbfzpNawArjCzA4HTibtxfB5YBzjPzM5Oq44ARpvZiRUmObrjFKB0tIWIiIhIOS21DqCfeqnWAQwmzc3NxV87eyYJfR+JDFRKNNRA+m3/PcAJrLwLwhzgNOBRd19YSVtm9klga+IWja+Y2abA4cA93Y2rgrZuAi4ys6OIIx2GEhdT/DvwdJnrfMjMPg08Xqa7g4j339a8u3UlwIXEkQW5JBoyzgbuMbPzeHddiBMyx9cE/kVcrPLanPs+B5iWc5uVGoH+YRYRERlIerNG1uqo+FlmE2BJjWMZNBoaGrapq6ub097evkdzc/PDtY5HBh4lGmpnNvBpVs4SzgEuBq4qU3+SmR1TUrYx0AzsD0wxsxHAIuL6CCf1IKZO23L3hek2meelP2+lMX/R3ZNyDbr73zroazwwI12b4R1mdgFwZ8lWnx25zszaM6//5e67dRDHw2Y2hziFYh9gV3efn61jZjPSuHJNNDQ2Ni6n+1uE5kJDDEVERAYWDUdfWeazzBK9N9XT1ta2FGDIkCFL9b5LT4QkKft8KCKrgUKhMHLZpEW9HoI5lWF5hNNjrZNr2n11DJta6whkAJtMa61DyI3+V5DBbnTTLA1Hz0jXrGgB1tYDb/W0tbVtBzwIbF9fX/9QreORgUe7ToiIiIiIiIhIbpRoEBEREREREZHcKNEgIiIiIiIiIrlRokFEREREREREcqNEg4iIiIiIiIjkRokGEREREREREcnNGrUOQET61prT1oFebgnVlFs0g0PPtoRq6sOIBgdtgVZ9fbL9WVMurazWdK/Xhrb7ExGpnEY0iIiIiIiIiEhulGgQERERERERkdwo0SAiIiIiIiIiuVGiQURERERERERyo0SDiIiIiIiIiORGiQYRERERERERyY22txRZzS2btAigZR6L+ryvqQzr8z4GgtbJ7/z6YE0CGDa1Jt1WYjKt1eimZdG8anQj8M7tVpt7XVp0q9dEn9zvo5tmhb5oV0SkFjSiQURERERERERyo0SDiIiIiIiIiORGiQYRERERERERyU3N12gws9nALsDbQAI8CRzv7reX1DsYuBY4xt0vLTmWAP8GPurub6dlE4Ax7r5Xpt4XgUnAx4HlwPPALOBid281s3HABHffJa3/XuAaYE3gAHd/Iy2/CPg28DF3n9vJtY0DfgW8mRY1A7909yklsS9Lr73ol+4+0cz2Ama5+4Zl2p4CbAF8B3gsc2jN9Nra09ffBPYB5rv7yWXety3d/Ym0vTOAce5+eabOfOL7ODt9vT5wFvA5YB1gIXAf8CN3v7+D9yHbz9rAj9LzRwILgOvd/bi07uz0mqeXayutcwOwL7CRuy/KlI8Dfg1McfczM+X3AtPdvcnMNgOeBZYCK4BW4J/Az9z9mo76FBERERERkcr0lxENE919LWBt4GfA9WZWX1JnHPA6ML6DNtYFvtZRB2Y2EfgpcDHQ6O7rAmOBTYH3l6m/FvCn9OV+mSRDPXBYGsu4ri+NB9x9rfT69gS+kSY8srYv1kl/JlbQLgDu/kL2XOC1NN5i2cxK2wIWAWea2XvKHTSzdYB7gPcBnwJGAFsBVxMTB5W4gPhn9XFiouGzxAf9iqSJjv2IiYLDOriGSWY2qoumRrn7SOADwC+B6WY2uYtzREREREREpAs1H9GQ5e4rzGwm8HNgI+AFADPbANgfOBT4vZl9zN0fKTn9XOB0M5vh7m9mD6Tfok8Fxrv7VZn+HgP+X2kcZvY+4CbgJeAwd38rc/hAoI44kuD7ZnZycRRFBdf3tJndBXy0kvo18Bfgg8AEYkKm1HHE0ReHuvuKtOwN4Pfd6GMn4Ex3X5i+/nf6U6mxaf1ZxKTTj0uO/xt4GTiVOHqlU+6+lHhPBeByM/tJdpSEiIiIiIiIdE9/GdEAgJnVAUcSEwyFzKGxwDPufjVwB+VHNdxInApxTJljuwLDgOsrCON9wGziFI6vlCQZSPu+GrgSGE5MgFTEzD4M/Ddwb6XnVFlCfEA/LR3RUWof4NpMkqEn7gW+Z2ZfN7OeJFzGAzOBK4DtzOzjZeqcBhxtZquMVOnEdUA9sHMPYhIREREREZFUf0k0TDOzZuK35dOAE0tGCYwjPlwCzADGlplaAXAKcHI6giFrFLDQ3duKBWZ2k5k1m9kyMzsiU7eROB3gMndvzzZiZhsS1wa4Iv0m/Ho6nspRtEPazxJi8uIu4K8lde5P6xR/umqzz7j7rcBc4uiFUqOAV4ovzGzPNN7FZvZkhV38H3A5ce2If5rZS2Z2eCUnmtkOxD+bme7+LPG9XOW9cvcniKMsplQYE2lCaSFx3QkRERERERHpof4ydWKSu083syHAbsAfzexpd3/QzHYEtgYOSuteBVxCXBPg+mwj7j7HzO4DTiROeyhaCIwys/pissHd94N3Fgqsy9R9lLig4I1mtr+735k5dgRxWP4d6esZab313H1BB9f298zikhsAvyUuhph9kN8pfTjuK23Eb+vfkUnUtK1anVOBW8zsJyXlC4mJGADSBTsbzGxfoMPFG7PSaS3nAOeY2XDgKOKUhYfc/fEuTh8P3Onuz6evZwBTzew72SRS6gzgcTP7YSVxpetSjCKu8ZCrQqEwFBiad7sVGlGjfkVERKQbCoXCyFrH0E8VP8uMKBQKnVaU/DQ0NAyvq6ujvb19+IIFC8rem42NjYurHZcMHP0l0QDENRqAO83sKWBv4EHiw2UC3GVmxaprpOXXl2nmVGAOcH6m7B7iTgwHERMVXcXxs3Qax5/MbF93vzs9NA7YEHgljSUQH+DHEhc57KrdV83sWuBbXdXN2QvAtiVlHyTuuvBiaWV3v8/M/kYcIZL1V+AgM5vSy+kTxX6WAheZ2XeJ61Z0mGgws6HENTqGpjthQLwP1gUOIE59yLb9opn9grg2RyUOIiZd7uvONVToFGLiQ0RERKQjLbUOoJ97qesqkpfm5ubir3M6qRb6PhIZqPpVogHAzHYhPnTONbNhwBjiugvXZqrtSlzAbwN3fzV7vrv/08z+SByiPzctazGz04FL01ETNwFLgA8D65WLw91/kiYbbkq/sV9B3E5yJ+KohqLjiUmPLhMNZrYucHAxrkql70NW6boRXbmKOKXkAOBm4u4e5wDXlFmDoug04H5W/gtkGnA4cGW6Q8PTxLUvdqg0kPTP4RbiThMriKNE1gIeylRbo+SaVxATAWsQR7dkF/u8kPj+r5RoSH0/jbHDxTrNbE3iOhuXAOf00UKQ5xDfu1oYgf5hFhERGQhKp/5KVPwsswnx87tUQUNDwzZ1dXVz2tvb92hubn641vHIwNNfEg0XmtmP0t/nA5Pd/WYzG0N8yLzM3Vsz9a9LRz2MZeWRC0XfBVbaQtLdzzezl4lTFi4jPqw+D/yEDkY5uPslmcTEP4Cb3f3BbB0zuxCYaGbblx5L7Whmb6S/LyOOCji2pM6DZpZkXt/o7oemv2/Ayg/WEEd7VMzdnzCzQ4CziIsovkHcuvOkTs55zMyuJi7OWSz7T5oIOou4YGYDsICYkPhSheGsIG4nuSnQDjwBHJyuuVB0SfpTdDvQCswoqYeZXUAcBbNBmWtYmB4vN5pgoZmtII50eRj4P3fvzu4ZFWtsbFye9lN1GmIoIiIyMGgYenmZzzJL9B5VT1tb21KAIUOGLNX7Lj0RkiTpupaIDEiFQmHkskmLqjYUcyqlg28Gp9bJNQ5gWKUzhqpvMq1dV5IBpR/fbiIDyuimWRqGXka6dkULsLYeeKunra1tO+I09u3r6+sf6qq+SKn+suuEiIiIiIiIiKwGlGgQERERERERkdwo0SAiIiIiIiIiuVGiQURERERERERyo0SDiIiIiIiIiORGiQYRERERERERyc0atQ5ARPrWmtPWgSptCdXU1x0MELXfEqqp+l32A9oCrfra2tq24xfa/qzadK/XRu3/bhcRGTg0okFEREREREREcqNEg4iIiIiIiIjkRokGEREREREREcmNEg0iIiIiIiIikhslGkREREREREQkN0o0iIiIiIiIiEhutL2lyGpu2aRFAC3zWFTTOKYyrKb9d6V1cp80+2DuLQ6bmnuTq6EW5tU6hL4zmdZah1BO/vd6jlbj/21aVuNbvT/L7X4f3TQr5NWWiEh/ohENIiIiIiIiIpIbJRpEREREREREJDdKNIiIiIiIiIhIbpRoEBEREREREZHcaDHIPmBms4H/BrZ093lp2RbA4+4eMvV2Ar4P7AwE4F7gNHe/P1MnAZYBCbAE+CNwLHA+MDattgZQD7yZvn7e3bcys+eACe5+c6a9fYHp7r5ZB7HvBvwA+FhaNA843d3/ZGbj0vZ2KXO9s9x9upntBfwN+Iu775Opsx7wMrDI3TcsOf8i4NvAx9x9rpmdCpyaHq4DhqbvAQDuvlba5y7A25mmnnT37Tt739x9aabfeqAAPOfuO5Z7P0RERERERKR7lGjoO4uBs4DDyh00s52BvwJnAl9Mi48GbjOzT7v7fZnq27v7E2a2MXATcIq7TwAmpG1NAMa4+169CdjMRhIfyCcCM4nJi52B9m42tQj4uJlt4u4vpWVjgWeAhpI+64nv0evAOOAEdz8bODs93lliZKK7T+8kjlXeNyC7t8ABxGvczsy2dve53bpKERERERERWYWmTvSdS4ADzewTHRz/IfBbd/+hu7ekPz8ErgTOK3eCu78M3AJs2xcBAx8G6t39cnd/293fdPfZ7n5HN9tpA34HfDVTdiRweZm6BxJHLXwHOMLMck9+dfK+jScmVGanv4uIiIiIiEgvKdHQd+YDFxOnRqzEzNYkTq2YVea8K4FPmtl7y5z3X8D+0Gc7xD8FLDezmWZ2QDrdoaeaiMkF0mTLMOCeMvXGA1cTr3s48fpyVe59M7MNgP2IiYYrgLHp6AoRERERERHpBU2d6FvnAc+Y2e7Agkz5+4hJnkKZc15Jj61DXNMA4H4zG0J8EL8VOKMbMVxtZtl1DNYAFpar6O6LzeyTwInApcAmZnY78A13f7obfeLuD5lZq5ntAhxKmdEMZrYhsC/waXdfambXExMPXmE308zs3Mzra9z965nXnb1vRwAvuPvdZvYI8Xr3B26osO+KFQqFocR1JmphRI36FRERkS4UCoWRtY5hACh+lhlRKJT76Cx9oaGhYXhdXR3t7e3DFyxYUPY+bWxsXFztuGTgUKKhD7l7i5n9ADgHOCpz6HVgBdAIPFFy2kbpsdczZTsBTwKfIY4UWAdorjCML5ZbDLKTmB8HvpbW3Qz4GTAD2I04JaLct/716bFSlwPfAD4HbA98qOT4EcRkSnFqxgzgRjNbz90X0LVJXazR0Nn7No44mgF3X2JmNxCTHLknGohrQ3QnOSQiIiKDQ0utAxhAXuq6iuSlubm5+OucTqqFTo7JIKdEQ9+7hLhLxAHFAndfZmZ3A18Gbiup/xXgbndfli109wS41cyuIO44cXCfRh37fM7MLiFOawB4AfgvM6tz93YAMwvAZsDzZZq4AngRmO3uL5tZaaJhHLAh8IqZQfzLqp64cOQFOV3DKu9butvHVsDGZnZ0WnVN4L1mtr67v5ZH3xnnANNybrNSI9A/zCIiIv3V2rUOYAAofpbZhLiTmFRBQ0PDNnV1dXPa29v3aG5ufrjW8cjAo0RDH3P3N83sLFZdq+Ek4gPwv4FfEB+yv058yP5MJ01OA541s23d/R95xppuwXkgcSHHF4H1iCMximsr3E8cEXB6OlJjBTCJOJrhrtL23P01M9sTeLVMXzsDWxBHHbycOXQ8cWRBLomGjHfet7T9OcSkTlEgXudYck4KNDY2LgeW59lmpTTEUEREpP/S0POuZT7LLNH7VT1tbW1LAYYMGbJU77v0hBaDrI5fsfJUCNz9buDTxAUJXyZmavcnrldQbtHE4nmvAr+hb4biLwF2AO5Of/8n8Abpoo7uvpx3p0E8T0xG7A7s7+5vdhDvve7+bJlD44Gb3f1Bd59f/AEuBLY0s+0riPdCM3sj89PhN/eZ9+0cYAzw42y/7v4K8FO0+4SIiIiIiEivhCRJah2DiPSRQqEwctmkRf1i/udUhtU6hE61Tq51BBUaNrXWEUiNTaa11iEMOPrfRvqr0U2zNMe9C+mCmS3A2vpmvXra2tq2Ax4Etq+vr3+o1vHIwKMRDSIiIiIiIiKSGyUaRERERERERCQ3SjSIiIiIiIiISG6UaBARERERERGR3CjRICIiIiIiIiK5WaPWAYhI31pz2jrQD1Zqbqpl51XWtys1N+Xb3GpEK5NX34BZlbyp1gHkS/d6bQyY+11EpB/QiAYRERERERERyY0SDSIiIiIiIiKSGyUaRERERERERCQ3SjSIiIiIiIiISG6UaBARERERERGR3CjRICIiIiIiIiK50faWIqu5ZZMWAbTMY1GtQwFgKsP6tP3WyX3afHc9WPUeh02tepf9UAvzVi2cTGv1Ixk8VrrXdRtWTUuZW136Xi5/t49umhXyaEdEpD/SiAYRERERERERyY0SDSIiIiIiIiKSGyUaRERERERERCQ3SjSIiIiIiIiISG60GKS8w8xOAT7r7ntnyu4E1nX3LTNlVwMvuvtxZtYEHAa8lWmq1d1HpXUPAM4ERgPtwGPAccA+wKlp/TpgKLCs2IC7r1UmvueACe5+c6bsOGAacIC7/zEtexz4sbtfWnL+QcAvgUZ3f8vMPgH8A/iRu59Y2bskIiIiIiIinVGiQbJmA6eb2VB3X25mw4AtgaVmtoG7v5rW2x34Zua8ae5+cmljZrY58Fvgy8CfgTWBPYHl7n42cHZab19gurtv1oOYxwGvA+OBP6ZlTcCRwKVl6v7W3YtJkfHpuUeY2Snu/nYP+hcREREREZEMJRok6wHiqIOdgDuAXYlbOL0K7AFcZWZbAusBcypob1viyIfiCIQ3eDcZ0Gtmth2wFXFExQwzW9fd/wP8Bvi+mW3p7o+ndUcB+wM7p6/fAxxOHF3xY2A/4Ma8YhMRERERERmstEaDvCP9Rv9u4qgDiMmFOelPtuwRd19UQZMPAZub2cVmto+ZrZ1zyOOB24CrgAIxcYC7vwLcQhzVUHQ48Ji7/yN9fSBQD/wOuDZtS0RERERERHpJIxqk1Gxgb2AqMbkwhTii4dvp8T3TOlkTzWxC5vUD7r6Puz9jZnsBE4mjDEaZ2Y3AN919QW+CTEckHAYc5+6Jmc0kJgsuTqv8GrjQzE519xXEpMOvM02MB65x91YzmwH8yczW621c5RQKhaHENShqYUSN+hUREZFOFAqFkbWOYYAofpYZUSgUahrIYNLQ0DC8rq6O9vb24QsWLCh7rzY2Ni6udlwycCjRIKVuB04zs+HAJ4D70vUaRqXTD3YHji0558JyazQAuPu9wBgAM9uamHC4iJgk6I3PA8OIoxEAZqRxf8Ld/wk4MB34jJm9AmwNzEzj2AjYF/hseu5twGvEUQ8X9jKuck4BzuiDdkVERGTgaql1AAPMS7UOYDBpbm4u/trZdOnQ95HIQKVEg5S6P/3vt4C57r48fX0ncTHFjalsfYZVuPtcM7uMlReS7KnxwHuAeWZWLEvS8mPTXSV+SxzJMB+40d0XpvWOIO50caWZJWlZQ3ruhTnEVuoc4s4YtTAC/cMsIiLSH+U9pXR1VfwsswmwpMaxDBoNDQ3b1NXVzWlvb9+jubn54VrHIwOPEg2yEndvM7N7gBOIW0EWzQFOAx7NPLB3ysw+SRxJcIO7v2JmmxJHDdzTmxjNrJE4GuFg4gKWRV8m7ppxYrqzxK+Bu4j/KH09U28ccC5xZEXR+4H7zGw7d3+oN/GVamxsXA4s77JiH9AQQxERkf5Jw84rk/kss0TvWfW0tbUtBRgyZMhSve/SE0o0SDmzgU+z8siFOcT1D64qU3+SmR1TUrYx0Ezc6WGKmY0AFhF3djipF7ElwFeBJ919pV0izOwXxCkKBxLXX/iHmT0FbAjcnNbZBfgQcIm7z8+cPt/MbiGOasg10SAiIiIiIjKYhCRJuq4l0g+Y2SLgs+7+91rHMlAUCoWRyyYt6ldzQKcyrE/bb53cp833f8Om1jqCfmsyrbUOYdDQbSjStdFNszS/vQLpopktwNr6Zr162tratiNuc799fX29voSTbtP2ljIgmNk+xO0on6x1LCIiIiIiItIxTZ2Qfs/MZgG7AEe7uxYBEhERERER6ceUaJB+z93H1DoGERERERERqYymToiIiIiIiIhIbpRoEBEREREREZHcaOqEyGpuzWnrQD9aqbmp1gFUQW1Xam6qbnf9iFYmr74O7/WmWkU0OOherw2twi8iUjmNaBARERERERGR3CjRICIiIiIiIiK5UaJBRERERERERHKjRIOIiIiIiIiI5EaJBhERERERERHJjRINIiIiIiIiIpIbbW8psppbNmkRQMs8FuXe9lSG5d7mQNM6udPDD1YpjNXS5GGdv7mdaFk0L89IpAIr3evDptYqjEGnRbd6TXT6d/voplmhWoGIiPRXGtEgIiIiIiIiIrlRokFEREREREREcqNEg4iIiIiIiIjkRokGEREREREREcmNFoPsBTM7Bfisu++dKbsTWNfdt8yUXQ286O7HmVkTcBjwVqapVncfldY9ADgTGA20A48BxwH7AKem9euAocCyYgPuvlaZ+J4DJrj7zenrfYFZwNfd/Zq0bD3gZeAGd/9SyfmzgVnuPr1M2wmwpbs/YWbjgF8Dv3T3b2TqfAL4B3Cfu+9Scv4NwL7ARu6+KFNebGuKu5+ZKb8XmA60AT9LiwOwJrA00/RH3f0FM7sI+DbwMXefm2lnL+BvQJO7j8+UzwKecPcppdcqIiIiIiIilVOioXdmA6eb2VB3X25mw4AtgaVmtoG7v5rW2x34Zua8ae5+cmljZrY58Fvgy8CfiQ/RewLL3f1s4Oy03r7AdHffrNJAzewLwGXAoe5+U+bQWOCNWMXWdff/VNpmiWeAg83s2+7+Zlo2HniyTCzrA/ul/R4G/LikyiJgkpld6u4LswfcfSYwM21nC+Dx0iSLmdWn7b4OjANOKGl/GfAlMzvP3R/v7oWKiIiIiIhIxzR1onceII462Cl9vStxy6PbgT0AzGxLYD1gTgXtbUsc+XCzu69w9zfc/Y/u/q/eBGlmXwV+BXy+JMkAMRlwLvAi8eG8pxYAdwMHp33WA18BZpSpOxb4N3BB2n+pfwN/4d0RHN11IHHUx3eAI8ysNKG2hDgq4vs9bF9EREREREQ6oERDL7j728SH6z3Toj2ICYU5JWWPZKcHdOIhYHMzu9jM9jGztXMI8+vANGBfd789e8DMtge2Io6imEn5h/7uaAKOTH8/AHiYOC2j1Pi0vyuA7czs42XqnAYcbWbv70Ec44GrgSuB4cD+ZeqcDXzazHYqc0xERERERER6SFMnem82sDcwlZhcmAK8SlwfgLRsdsk5E81sQub1A+6+j7s/k64hMBH4DTDKzG4EvunuC3oY3/8QkyEPljk2Hrjd3V8ysxnEaSDbuPvDPezrRuCnZrYxccpCE3EtiXeY2Q7E5MZMd3/ezO5K4zguWy9d++H3xPfz65UGYGYbEtd++LS7LzWz69P2vaT9/5jZ+cA5wKcrv8TuKxQKQyl5H6poRI36FRERGZQKhcLIWsewmil+lhlRKBRqGshg0tDQMLyuro729vbhCxYsKHtPNzY2Lq52XDJwKNHQe7cDp5nZcOATxIUPl5vZKDMbRVyf4diScy4st0YDgLvfC4wBMLOtiQmHi+j5tIb/JU4huNLMDk1HYWBmQ4FDgRPTfuelCy6OJyY6us3d28zsd8AkYDfi1IkxJdXGA3e6+/Pp6xnAVDP7jru3ldQ9A3jczH7YjTCOII6iuCPT/o1mtl6ZZM004Bgz+0w32u+JU4jXIiIiIqu/lloHsJp6qdYBDCbNzc3FXzub/h36PhIZqJRo6L370/9+C5jr7svT13cSv9XfmMrWZ1iFu881s8tYeSHJ7lpI/Mb+b8BMMzvM3duBzwPrAOeZ2dlp3RHAaDM7scxDf6WagL8Dv3D3VjN750AmuTHUzOanxWsA6xKnWlyXbcjdXzSzXxBHi1RqHLAh8EradwDqietCXFDS/htm9n3iqIanu9FHd51DTGrUwgj0D7OIiEg15TH1Vd5V/CyzCXGdLamChoaGberq6ua0t7fv0dzc3NPRzjKIKdHQS+m3+PcQdzb4ZebQHOI6A4+W7pzQETP7JLA1cavJV8xsU+Bw4J5exrjAzD5FTDZcYWZjeXedhOyODGsC/yIupnhtWrZGuptG0Qp3z27NWdrXQ2b2aaDcbg4HEe+5rYE3M+UXpvFct+opfJ+YBHi7oz6LzGxnYAvi4pzZtSGOT9u/oMxpPyVO2/gA8ERXffREY2PjcmB5lxX7gIYYioiIVJeGk+cr81lmid7b6mlra1sKMGTIkKV636UnlGjIx2ziqIHsyIU5wMXAVWXqTzKzY0rKNgaaiQsXTjGzEcRtHm8ETuptgO7+WppsmE3c0WEvYCd3n5+tl67VMJ53Ew2XpD9Ft6fndtbX3zo4NB6Y4e7PlvR5AXCnmW1Qpq2F6fFKph6MB25295XWozCzC4nrYmxfpv23zGwK8OsK2hcREREREZEuhCRJah2DiPSRQqEwctmkRX02V3Qqw7qutJprnVzrCFZfk4fpzR2ohnVnwpvIamZ00yzNW89RurhmC7C2vlmvnra2tu2Ii8lvX19f/1Ct45GBR9tbioiIiIiIiEhulGgQERERERERkdwo0SAiIiIiIiIiuVGiQURERERERERyo0SDiIiIiIiIiORG21uKrObWnLYO9NFKzU15N7ia0ErNeZnVrdpambz6OrzXm2oV0eCge7029He7iEjlNKJBRERERERERHKjRIOIiIiIiIiI5EaJBhERERERERHJjRINIiIiIiIiIpIbJRpEREREREREJDdKNIiIiIiIiIhIbrS9pchqbtmkRQAt81hUtT6nMqxqffVzD1ZasXVyX4bRTwybWq2eWpiXX2OTac2vsdVIyR9nxfe65Kolx1tdUqObZoVaxyAiMtBpRIOIiIiIiIiI5EaJBhERERERERHJjRINIiIiIiIiIpIbJRpEREREREREJDdaDLLGzOwU4LPuvnem7E5gXXffMlN2NfCiux9nZk3AYcBbmaZa3X1UWvcA4ExgNNAOPAYcB+wDnJrWrwOGAsuKDbj7WmXiK9uWuz9gZlOALdx9TMk5zwET3P1mMxuX/r5LJ+/BwcC1wDHufmladihwtrt/IFPvCsCAddz97bTsR8Dm7n5wGs9pwPKSLj7o7q+Z2W7AD4CPpeXzgNPd/U9mthnwLPBed9fKbyIiIiIiIj2kREPtzQZON7Oh7r7czIYBWwJLzWwDd381rbc78M3MedPc/eTSxsxsc+C3wJeBPwNrAnsCy939bODstN6+wHR336yjwDprq+eXW9Y44HVgPHBpWjYb2MzM/svdX0jLdgdeBrYD7k/L9khjLLqmNPEBYGYjgT8CE4GZQD2wMzF5IiIiIiIiIjlRoqH2HiA+7O4E3AHsStwm7FXiQ/RVZrYlsB4wp4L2tiWOfLg5ff0G8QG7J/Jsqywz2wDYHzgU+L2ZfczdH3H3V8zsKWJiY4aZfYCY4Lg6LbvfzNZKYzy6gq4+DNS7++Xp67eJyQwRERERERHJkdZoqLF0CsDdxIdniMmFOelPtuwRd19UQZMPAZub2cVmto+Zrd2L8PJsqyNjgWfc/WpiomV85tjtdP6+/DewBPhXBf08BSw3s5lmdoCZrZdH8CIiIiIiIrIyjWjoH2YDewNTiQ/RU4gjGr6dHt+TVb99n2hmEzKvH3D3fdz9GTPbizhF4DfAKDO7Efimuy/oTlB5ttWJccSpDAAzgLPN7CR3byNe85npseJ7cDdwpZkNScvucPcVmfa+YGbNmdevuvtH3H2xmX0SOJE4PWMTM7sd+Ia7P53TtZRVKBSGEtfDqIURNepXRERkQCoUCiPLlTc0NAyvq6ujvb19+IIFC8rWkT5R/CwzolAo1DSQwaSS+72xsXFxteOSgUOJhv7hduA0MxsOfAK4L12vYZSZjSKuTXBsyTkXllujAcDd7wXGAJjZ1sQkwUXEBSS7pYu22ohrHZSqT491ysx2BLYGDkqLrgIuAT4HXE98X0abWSNxRMNZ7r7UzJ4mvk97EBeRzLq23BoN6bU8Dnwt7Xsz4GfE5MZuXcXaS6cAZ/RxHyIiIpKPlnKFzc3NxV8rmcoq+Xup1gEMJhXe76HvI5GBSomG/qG4sOG3gLnuXlxs8U7iN/4b08N/1Nx9rpldxsoLSfZImbZeAA7J1jGzNYENgOcraHI8kAB3mVmxbI20/Hp3f9nM5hGTGu9x9+fSOnOAfYEdeXfUR3ev5TkzuwS4sifnd9M5wLQq9FPOCPQPs4iISHeUnSra0NCwTV1d3Zz29vY9mpubH652UINY8bPMJsQps1IFut+lt5Ro6Afcvc3M7gFOAH6ZOTSHuF3jo+6+sJK20ukBWwM3pAsqbgocDtzT3bgqaOsm4CIzO4o40mEocC7wdyA7HSGku2lkBeJIiWNYeVTCrsRFIYs7btxOfF/+kqkzB/gF8CbwzwqvZQvgQOB3wIvExTWPogfvS3c1NjYuJ/+dOiqiIYYiIiLd09Fw8La2tqUAQ4YMWaoh49WT+SyzRO979eh+l95SoqH/mA18mpVHLswBLiZOKSg1ycyOKSnbGGgm7uIwxcxGAIuAG4GTehBTp225+8J0m8zz0p+30pi/6O5Jpp2diEmBrFOAFcBl7t6aKb8u3W1iLHA+8X35Oiu/L3cSEwV/KlmfAeAQM3ujpGzXNPYdiFNQGoDFwG3EUSQiIiIiIiKSk5AkSde1RGRAKhQKI5dNWlR2rmlfmkrpABbpSuvkWkdQBcOm1jqCHplMa9eVBqEB+scp0qXRTbPKzjtva2vbjrgF+fb19fUPVTeqwStdnLMFWFvfrFeP7nfpLW1vKSIiIiIiIiK5UaJBRERERERERHKjRIOIiIiIiIiI5EaJBhERERERERHJjRINIiIiIiIiIpIbbW8psppbc9o6UOWVmpuq1VE/pZWaO9LUp61rZfIqa9K9Xiu610VEpL/TiAYRERERERERyY0SDSIiIiIiIiKSGyUaRERERERERCQ3SjSIiIiIiIiISG6UaBARERERERGR3CjRICIiIiIiIiK50faWIqu5ZZMWAbTMY1GftD+VYX3SbqnWyVXpJm8P5t7isKm5N7kaamFe/GUyrbWNpJ/qg9so/3tdKtEyr9YRDDCjm2aFWscgIjIYaESDiIiIiIiIiORGiQYRERERERERyY0SDSIiIiIiIiKSGyUaRERERERERCQ3WgyyD5jZbsAPgI+lRfOA0939T+nxkcD3gUOABuAFYDpwkbsnaZ3ngAnufnOm3b2AWe6+oZm9kenyvUAb8Hb6+mzg7mLdkthmAU+4+5QOYv8O8E1gA+AN4gJfY9x9iZnNTtucnqm/GfAs8F53bzWzJuBIYKy7z8zUOw6YBvzA3U/OlNcDBeA5d98xLXsU2DStMhRIgLfS11cA56Z9Li0J/3R3n2Zm44BfAW8CK4CXgXPc/Tcl13owcC1wjLtfWu79EBERERERke5RoiFnaRLhj8BEYCZQD+wMtKfH3wPcCiwB9iQ+MO8K/Ib4cH1cJf24+1qZPu8Fprt7U6Zsrx7E/lXgG8D+7v6kma0PHNDddoCniMmGmZmyI4Eny9Q9gPgebWdmW7v7XHffKhPTKomRNLkBMMrdO1pS/gF338XMQtrHtWZ2n7tnYxgHvA6MB5RoEBERERERyYESDfn7MFDv7penr98GZmeOjwU2Bz7o7ovTsjvMbCwwx8x+7O5PVy3ale0E/Ln4MO7urwGX9aCdPwBjzWwTd3/JzD4BDAPuLVN3PDEhsUX6+/E9Cbwj6QiRG82sGfg4abLDzDYA9gcOBX5vZh9z90fy7FtERERERGQw0hoN+XsKWG5mM83sADNbr+T4PsCfMkkGANz9LuIQ/89UKc5y7iUmCE4ys13S0Rc90Qb8DjgifT0euLy0Uvqwvx8x0XBF2nd9D/ssy8yGmNkXgHWJU1iKxgLPuPvVwB1pjCIiIiIiItJLGtGQM3dfbGafBE4kDsffxMxuB76RjlQYRVz3oJxX0uN5WT/9Jj9rTeIaDqtw9yvMbAVxSsFpAGY2HTjF3du72XcT8Fsz+xHwFWB74roUWUcAL7j73Wb2CPH92h+4ocI+5ptZ9vUh7v7X9Pcd0mtfk5hQm+ju/8jUHce7UztmAGeb2Unu3lZh3xUrFApDiWtN1MKIGvUrIiLS7xQKhZE9PbehoWF4XV0d7e3twxcsWNDjdqTbip9lRhQKhZoGMphUcr83NjYuLlcuAko09Al3fxz4GryznsDPiA+zuwELgcYOTt0oPQ5xVEDpt/v1aXmlXutgMcjOYv8tMUFQRxxdMYs4EuDnncSUkK5BkWnnITNbDkwFHnb3l0uSApB52E8Xm7yBOLKg0kTDhp2s0fD3dI2GYcCPgL2BiwHMbEdga+CgtO5VwCXA54DrK+y7O04BzuiDdkVERKR7Wnp6YnNzc/HXOblEIt31Uq0DGEwqvN9D30ciA5USDX3M3Z8zs0uAK9OivwDnmtkId19SrGdmuwIbA8Vv5F8APlDS3AeB5/s4ZADSEQy3mNlfeXf3jI5iKnQwEuBy4kP+4aUHzGwnYCtgYzM7Oi1eE3ivma2frg/Ra+lOGMcDT5nZ5929mMxIgLsyyY810vLr8+i3xDnEHTdqYQT6h1lERKRo7Z6e2NDQsE1dXd2c9vb2PZqbmx/OMyjpVPGzzCbExdSlCnS/S28p0ZAzM9sCOJC4RsGLwHrAUcA9aZUZwLeAa8zsW8TEwS7Eh/JL3b24jsBM4DQzuw14lLhY4iTgoj6MfTxxRMUcYHEa117AtzMxXWVm16TXszFwOvDbDpr8JfAv4hoIpcan/XwlUxbSdseS44O5uy83s2nAFDP7MzAGOIa4tWXRrsRFITdw91fz6hugsbFxObA8zzYrpSGGIiIi7+rNUO+2tralAEOGDFmqIePVk/kss0Tve/XofpfeUqIhf0uAHYBjgQbiA/ttxOQC7v6WmX2GuF7BnWmdF4CfsPLD9a/TY9cQp1q8AvwKmN6HsTcDJxGTHmsABeDsdDoF7n6bmR0L/BTYDFhETKhMKddYuuDlX0rL0+kMY4Cj3X1+ybGfEpMQlSQaFpZMx7jU3U/qoO4vge8CnwdWAJeVTLu4zsyeIiY5zq+gbxERERERESkjJElS6xhEpI8UCoWRyyYt6vF81EpMZVhfNv+O1slV6ab/Gza11hEMKJPpaBmXwU23kQxWo5tm9XhOeVtb23bEBb23r6+vfyi/qKQz6QKeLcDa+ma9enS/S29pe0sRERERERERyY0SDSIiIiIiIiKSGyUaRERERERERCQ3SjSIiIiIiIiISG6UaBARERERERGR3Gh7S5HV3JrT1oE+XKm5qS8aHeD6dqXmpnybW41oZfJuaMqnGa1KXhu610VEpL/TiAYRERERERERyY0SDSIiIiIiIiKSGyUaRERERERERCQ3SjSIiIiIiIiISG6UaBARERERERGR3CjRICIiIiIiIiK50faWIqu5ZZMWAbTMY1FV+53KsB6f2zo5x0Bq68FOjw6bWqUwBpbJtPa2iZZF8/KIZGDoJ7dR5/e69JWWQXSr98roplmh1jGIiAwmGtEgIiIiIiIiIrlRokFEREREREREcqNEg4iIiIiIiIjkRokGEREREREREcmNFoMc4MzsS8DxwNbAMuAx4Hx3v9HM9gJuS8uzjnT3a8xsCnAGMM7dL8+0OR8YA+wGnJoW1wFDs225+1pmNhvYBXgbWA48AHzb3Z8qifMGYF9gI3dflCkfB0xw910quNbZwCx3n54pOxi4FjjG3S9Ny24GHnH3E0vO3wb4O7CJu79qZusBLwM3uPuXuupfREREREREuqYRDQOYmR0L/BSYBmyU/nwPOChT7TV3X6vk55rM8UXAmWb2ntL23f3s4jnAwcAL2XYyVSemr98PLAAuK4lzfWA/YClwWC8vu9Q44HVgfKbs18DhZlZXUnc8cJO7v5q+Hgu8EUO0dXOOS0REREREZFBSomGAMrORwPeB/+fuv3f3Je7e7u5/dfevd6OpvxCTAxN6G5O7LwNmAduWHBoL/Bu4gJUTAr1iZhsA+wNHA9uZ2cfSQ9cDw4DPZuquQUxy/DrTxHjgXOBF8k+AiIiIiIiIDEpKNAxcuxEfpq/tZTsJcXrEaWa2VleVO2NmI4DDgdJtvccDM4EriAmBj/emn4yxwDPufjVwR9oP7r4cuBI4MlP3c0AA/pDGuj2wFfDbNLbcEiAiIiIiIiKDmdZoGLjWBRa6e1sX9dY3s+aSsh3d/d/FF+5+q5nNBY4jTr3ormlm9gNgJPAMmakbZrYD8YF+prs/b2Z3ER/qj+tBP6XGEZMEADOAs83spPQ9+TVwh5mt7e4txKTDFZn3azxwu7u/ZGYzgNPNbBt3fziHuFZSKBSGEte3qIURNepXRESk3ygUCiN720ZDQ8Pwuro62tvbhy9YsKDX7UnFip9lRhQKhZoGMphUcr83NjYurnZcMnAo0TBw/QcYZWb1XSQbXnP3DSto71TgFjP7SQ9imeTu083sg8BNwIeAR9Jj44E73f359PUMYKqZfaeCJEmHzGxH4gKYB6VFVwGXEEcuXO/ufzezecBXzOyatHzH9NyhwKHAiQDuPs/M7k1jndjTmDpxCnHRTREREamNlt420NzcXPx1Tm/bkh55qdYBDCYV3u+h7yORgUqJhoHrbqCVuEjj73vbmLvfZ2Z/Iz4U97SNZ8xsIvArM7sJWEF8oB+a7mQB8Z5bFzgAuK4XIY8nTvu4y8yKZWuk5denr39NHMkwFJjr7v9Kyz8PrAOcZ2Znp2UjgNFmdmJvEiAdOIe4YGctjED/MIuIiKzd2wYaGhq2qaurm9Pe3r5Hc3Nz7iMgpUPFzzKbAEtqHMugoftdekuJhgHK3Reb2WnAj81sBXAz8CbwSWCsu3+jB82eBtxPL7KT7n5TmlT4JvAK8R7bOo2t6EJiQqCYaAhmNqykqeXunpTrI607BjiGldeo2BX4vZltkO4scQVxsceNgR9l6hXXjDghU7Ym8C/gQHq/7sVKGhsblxO3/qw6DTEUERHJZ4h3W1vbUoAhQ4Ys1ZDx6sl8llmi9716dL9LbynRMIC5+0Vm9grxgfly4vaRj7LyQ/X6ZvZGyanfcfdVpki4+2NmdjUrL6LYE+cRd5j4FzDD3Z/NHjSzC4A7010jAHZi5UQEwAeA58q0nRCnS6wALnP31syx68zsKeIikee7+2tm9ifi1pq/TftuBPYBdnX3+dmG07UaxpNzokFERERERGQwCUlS9ktjkX7HzB4Czk53mZAKFAqFkcsmLer1vNSemErpIJXKtU7OMZD+bNjUWkfQL02mtetK8g7dRiJdG900q9dzydva2rYDHgS2r6+vf6j3UUkl0oU8W4C19c169eh+l97S9pYyIJjZVsBHAf1FJyIiIiIi0o8p0SD9Xrp15q3Aqe7+TK3jERERERERkY5pjQbp99z9JOCkWschIiIiIiIiXdOIBhERERERERHJjRINIiIiIiIiIpIbTZ0QWc2tOW0dqMFKzU3V7KyfqXyl5qYqRTQ4DNqVyZtq17VWJa+NQXuvi4jIgKERDSIiIiIiIiKSGyUaRERERERERCQ3SjSIiIiIiIiISG6UaBARERERERGR3CjRICIiIiIiIiK5UaJBRERERERERHKj7S1FVnPLJi0CaJnHIgCmMqym8eShdXKtI+jCsKnF3x6sZRiDWAvzqtvhZFqr22EH3r31qk73em20VPlWHzBGN80KtY5BRGQw04gGEREREREREcmNEg0iIiIiIiIikhslGkREREREREQkN0o0iIiIiIiIiEhuBsVikGY2G9gFeDtT/KS7b5+pUw8UgOfcfceS87cEpgE7Ed+zF4DzgaeBmzJVhwPLgCR9vZ+731HSVhNwJLCXu9+elg0D3gQ+4O7PpXXmu/vJJecmwJbu/oSZbZzGtDfw3jT2y9z9ByXnXAR8G/iYu8/t4P2ZDoxNX64B1KfxADzv7luZ2XPABkB75tRb3f1gM9sMeBaY7e57Z9o9F9jQ3cdlyiYA3wQ+AryRvoeXAz9z9yStsy0wBdg9jWc+8CfgR+7+Uqat9YCXgRvc/Usl1zSbd//MlwMPAN9296dK6t0A7Ats5O6Lyr0/IiIiIiIiUrlBkWhITXT36Z0cP4D4gL2dmW1d8lD+B+Ay4GBgBfAJYFSaRFgLVkoWbOXuz3URyyLgHGC3HlxH0QzgcWBzYnLjo8AW2Qpp8uQw4HVgHHBCuYbcfQIwIT1nAjDG3fcqU/Vgd7+5k5g+bmafdfc/lztoZhcCBvwvMAdoBbYDjgd+DSw3s12AW4HzgAnu/oqZbZRexyeBWZkmxxKTFWZm67r7f0q6nOju081sTeBnxD/DT2biWR/YL23jMODHnVybiIiIiIiIVGAwJRq6Mh6YSXxYH098+MXMRgEfBH7u7sX9y+7vZV8zgEPMzNzde9jGTsBJ7r4kff1I+pN1IFAHfAf4vpmd7O5v03fOBc42s1uLoxOKzOxDwP8Bu7p79v37O3Bo5vUPgd+4+/eKBe7+CnEESanxaZ9HExMFl5QLyt2Xmdks4Pclh8YC/yYmL8ajRIOIiIiIiEivaY0GwMw2IH6zPRO4AhibjgYA+A/xYfQ3ZnZIOmWht1qBs4gP/z39M7gXuMTMDjezD3ZQZzxwNXAlcVrH/j3sq1I/A9YFvljm2KeBl0qSDCsxs+HEUR5Xd9WRmW0PbAX8lvjnNr6TuiOAw4HS7caLyaUriCNZPt5VvyIiIiIiItK5wTSiYVq6ZkDRNe7+9fT3I4AX3P1uM3sEuJT4UH6Duydm9ingJOJ0h9Fm9hDwTXd/sBfx/Jo4leFw4KoenP8l4kiFk4CPmtnTwP8Vpy2Y2YbEtQc+7e5Lzex64oN1T0dQAFxtZtkRERe4+5mZ128BZwDfM7NrS84dBbySLTCzR4GNgaHA/wDPEJNfr2TqnAacSLxXr3T3b6SHxgO3u/tLZjYDON3MtnH3hzNdTDOzHwAj07YPyrS7AzFRMdPdnzezu9I2j6v43ahQoVAYml5jLYyoUb8iIiI1UygURubdZkNDw/C6ujra29uHL1iwIPf2pUPFzzIjCoVCTQMZTCq53xsbGxdXOy4ZOAZTomFSJ2s0jCN+s427L0kXCBwP3JCWvUQc9l8c/fAj4AYze3/pFIFKufvbZvZd4tD/60sOtxHXi3hHZoRFW3r+68ApwClm1pD+fq2Z/Ve6qOERxIUSi4tRzgBuNLP13H1BT2IGvtjFGg0QRwecyKojDBYCjdkCd98KwMzmExMMrxPXwGgEnkjrfJ848uNcYMO0/lDidIsT0zr/v717D7OrrA89/n0zhEQgMHLRw4D1lEatlcrNg2jPY62tVjzw4yhFRKEmnnptVYhyNQWtUZRyO14ApUokoEGKHl68QFHAeAMVKEgVBEQRhkAgTLiEhCGs88daI5vtTGb2zJq9ZjLfz/PMM3u9+13r/a2dNzOzf/u93BYRV1dtHt7SxKJqjYZdKBftfB5PTS9ZCPwg5/zb6ngZsCQijso5D45yj506ljIBI0mSumNN3RccGBgYerii7mtrTO4avYrqMsb+niY/Ek1XMynRMKyI2Jvyk+2dIuIdVfEWwDMi4lk55/ta6+ec760+JT8U2JZyasV4XUg5IuGdbeV3Anu0le1C+Sb8d+0XyTkPRMRHKUc4/DHlYpMLKN+Y3xMRUP4gmF3FfdoEYt6onPOTEbGYcr2Di1qeugL4bETsPdL0iWrkxdXAgVX9kRxA+dqfFBEfr8rmUY42ObI9UZBz/nVEHA58ISK+Tfk6HgLMqZIcUP5f2I5yUdCvj/2Ox+REyh1CmjAPfzFLkmaebeq+YG9v7249PT0rNmzY8IqBgYEbRj9DNRn6W2Zn4OFR6qom9ndN1IxPNFB+sr0COLilLAE/plyr4RxgEeUn3rdT7jLxT8Ctw+xy0JFqWsZxVKMpWlwIHBMR+wGXUv6yPJFyusfjABFxEuXogV9S/jseQTki4OaIeCnlopZ7U45qGPKB6n4nLdEAkHO+OCKOoUxqfKMq+1VEnAEsj4jWXSd2p0zsDDkSuLxKAJydc15Z7Q7xp8BAVWdobYXWXTS2AG6kXACzfdoGOedvV9d8J+XUjM2AXXlqG0+A06tr15po6OvrW0+5xWbXOcRQkjQTTcaQ7sHBwUcBZs2a9ahDxrun5W+Zh33du8f+romaSYmG0yPi5JbjAWA+8CbgHTnnla2VI+JMyjednwOeA1wG7EC5leSPKd/QTljO+bJqXYhXtpTdHBEHUi4YeR7l9ovfohz9MOQZlIsm7kj5JvYG4HXVqICFwKXta0hU20seHhF7jXN9ia9HxIaW4xtzziNt0XkscGVb2fsop0R8Eng+8BDl2glHAD8EqNbJ+EvKqQaLIqIH6KdMuJwcEX3Aqyl3r2j/N1tG+W/2B4mGykmUSZYbgWU55zvazj8N+EFEPDvnfO8I15AkSZIkbUQqinEtMSBpGujv79967aLVT5unuoS5TYVTm3WLm45gFHOXNB2Bumwx60av1AV2Pak0f+ny2ueODw4O7glcC+w1e/bs6+q+voZXLey5BtjGT9a7x/6uiXJ7S0mSJEmSVBsTDZIkSZIkqTYmGiRJkiRJUm1MNEiSJEmSpNqYaJAkSZIkSbWZSdtbSjPSFqduCy0rNS9tNJqZYXDwbFdqboArk9P1/+CuSt4M+7okaapzRIMkSZIkSaqNiQZJkiRJklQbEw2SJEmSJKk2JhokSZIkSVJtTDRIkiRJkqTamGiQJEmSJEm1cXtLaRO3dtFqgDW3sXpS21m8eO6kXn/M5i5pOoJW1zYdwAy1htvGVnEx6yY3kjGYWl123OzrzVgzxq6+SZi/dHlqOgZJ0tg4okGSJEmSJNXGRIMkSZIkSaqNiQZJkiRJklQbEw2SJEmSJKk2LgapjYqIq4B9gCdaim/JOe/VUmc20A/8Juf8P9rOfyFwKrA3ZX+7EzgFuB34dkvVLYG1QFEd75tz/n7btZYCK3POx7SU7Q5cD5yccz6yKjsL2C7nfFDb+TsAdwMvyzlfu7G4JUmSJEnjY6JBY3F4zvmsjTy/HzAb2DMids0539Ty3DeALwKvB54Edge2r5IIWwFExFzgMeBFOeffdBjbQuBB4LCIODbn/ARwDvC9iHhmzvnBlrpvAW7OOQ+tjr6xuCVJkiRJ42CiQXVYCJwP/Gn1+AMAEbE9sAvw+Zzz0B5yP6mr0YjYnDJ5cATwGWBf4JKc8zURcTvwJuDMllPeSpmE2GjckiRJkqTxc40GTUhEPJvyDf75wHnAodWUBIAHgFuBcyPiwIjYqebm96cckXAB8DXKZMGQpZSJhaE4Xwy8qIpxtLglSZIkSePkiAaNxakR8YmW44tyzv+nenwYcGfO+UcR8XPgs8DrgItzzkVEvAo4GjgRmB8R1wHvbJm+MBELq1jWRcQy4FsRsUPOeRWwDPh4RLwg53wLsAD4ZvXcRuOuIa6n6e/vnwPMqfu6YzSvoXYlSapVf3//1k2239vbu2VPTw8bNmzYctWqVY3GMsMM/S0zr7+/v9FAZpKx9Pe+vr6Huh2Xpg8TDRqLRRtZo2EB5agAcs4PR8TFlAmAi6uyu4D3wu9HEZwMXBwRz8k5F8NecQwiYkfgtcBrqqIrgPsop1KcnnNeGRGXAm+NiOOr8rePNe6aHQucMAnXlSRpJlnTZOMDAwNDD1c0GMZMdlfTAcwkY+zvafIj0XRlokHjFhF7U05H2Cki3lEVbwE8IyKelXO+r7V+zvneiPgkcCiwLeXUivE6DOgBvhIRQwmLXspkwenV8TnA/wWuqY6/NZ64a3Ai5c4bTZiHv5glSZuGbZpsvLe3d7eenp4VGzZseMXAwMANTcYywwz9LbMz8HDDscwY9ndNlIkGTcRCyiznwS1lCfgx5ZoH5wCLKKcx3E65y8Q/AbfmnCeSZIByRMInKBMJQ54DXBMRe+acrwMuAT5X1VlW7UgxatzUnBTo6+tbD6yv85pj5RBDSdKmoulh2oODg48CzJo169GmY5lJWv6WedjXvXvs75ooEw0ai9Mj4uSW4wFgPuWuDu/IOa9srRwRZ1K+mf8c5Zv/y4AdgLWUb+b3n0AsRUTsAzwP+HRb2ysj4rKq7etyzoMRcT7wfsrFIYe20hwt7qZGH0iSJEnStJeKYtzT5KWuioivAT/KOZ88amUB5cJZaxet7sqc1sWL53ajmdHNXdJ0BJpGFrNu9EqTzC4rjc38pcsbnQ8+ODi4J3AtsNfs2bOvazKWmaRaBHQNsI2frHeP/V0T5faWmhaqrTH/J/CzpmORJEmSJI3MRIOmvIh4D3A9cG7O+aqGw5EkSZIkbYRrNGjKyzmfAZzRdBySJEmSpNE5okGSJEmSJNXGRIMkSZIkSaqNUyekTdwWp24LXVipeflkXrwjS5sOwJWaGzJtVyZf2nQA42dfb8a07euSpBnDEQ2SJEmSJKk2JhokSZIkSVJtTDRIkiRJkqTamGiQJEmSJEm1MdEgSZIkSZJqY6JBkiRJkiTVxu0tpU3c2kWrAdbcxuqOz13C3NrjabduyZJJb6NB1zYdwAy1htsmt4ElS9ZNbgPTj329GWsmuavXav7S5anpGCRJ3eGIBkmSJEmSVBsTDZIkSZIkqTYmGiRJkiRJUm1MNEiSJEmSpNq4GKTGJCKuApbnnM8a4fmLgdcCO+acV7eULwDOAf4t5/z2lvLdgeuBa3LO+7S0sQ/wBLAeuAZ4f8751ohYCqzMOR/T1m4BvDDnfHNEfBg4AViQc/5SS52VwJtyzldVx88C/gX4X8C2wP1VWyfnnH/S+asjSZIkSRriiAZNWPXGfV/gUeDNw1T5NfD6iHhGS9lC4JZh6h6ec94KeC6wBvjSMHU2ZjXwkYjYfIRYtwV+DDwTeBUwD3gR8O+UiQdJkiRJ0gQ4okF1OBS4FVhOmUD4TNvzq4D/Al4PfDkiZgMHA58G9h/ugjnnRyLivOqanfgOsAvwLuBTwzx/BLAWOCTn/GRV9gjw1Q7bkSRJkiQNwxENqsNC4HzgPGDPiHjxMHWWAm+tHu8H3ADcPdIFI2Jr4DDK6RWdKIDjgA9FxFbDPP9q4GstSQZJkiRJUo0c0aAJiYiXUE49OD/n/NuI+CFl4uGItqqXAGdGxE7AAsrEw5xhLnlqRJwIrAOu5qnkxJjlnC+PiJuqGD7a9vT2wD0t8f8lcDFl0u2enPMLOm1vNP39/XMY/l67YV5D7UqS9DT9/f1bNx3DRPT29m7Z09PDhg0btly1atW0vpdpZuhvmXn9/f2NBjKTjKW/9/X1PdTtuDR9mGjQRC0EfpBz/m11vAxYEhFH5ZwHhyrlnAcj4gJgEfByyqkTbxrmeotGWHByEJjdWlBNwRh6rt1xwGURcUZb+f1AX0tc3wN6I+K1wLALXdbgWMpFKiVJmsnWNB3ARAwMDAw9XNFgGDPZXU0HMJOMsb+nyY9E05WJBo1bRMwBDgHmVDs7QNmntqOcHvH1tlOWAj8Dzs45r4uITpq7E9ijrWwX4Engd+2Vc87XRMSVlG/yW30X+N8R8eEuTp84ETi1S221m4e/mCVJU8M2TQcwEb29vbv19PSs2LBhwysGBgZuaDqeGWTob5mdgYcbjmXGsL9rokw0qBObRcTcluMDKPvQrsBjLeWnU450eFqiIed8XUT8NfDLcbR9IXBMROwHXEr5x8qJwEU558dHOOdDwE94erb1VOAtwFciYjFwOzAXeMk4YhqTvr6+9ZTbdXadQwwlSVPFdB9mPTg4+CjArFmzHp3u9zKdtPwt87Cve/fY3zVRLgapTnyaMqEw9PUlYFnO+Y6c88qhL+A0YN+IeHb7BXLOV1Z1OpJzvhk4EDiecvrDDdX3d27knF9Qblu5RUvZA8A+lMM3r6LMjP8CeDFwUKdxSZIkSZKeLhVF0XQMkiZJf3//1msXrR73nNglzB290gStW7Jk0tuQ6rZkybqmQ5CmnflLl0/r+dyDg4N7AtcCe82ePfu6puOZKapFRNcA2/jJevfY3zVRjmiQJEmSJEm1MdEgSZIkSZJqY6JBkiRJkiTVxkSDJEmSJEmqjYkGSZIkSZJUm82aDkDS5Nri1G1hnCs1L609muZa6SZXam5GV1cmXzqpV5827OvNcBV+SdJU54gGSZIkSZJUGxMNkiRJkiSpNiYaJEmSJElSbUw0SJIkSZKk2phokCRJkiRJtTHRIEmSJEmSauP2ltImbu2i1QBrbmN1V9tdwtyutgewbnHXmxzNtY21PHdJY00PZzHrutncmtW3dbO5idl1/vLUdAySJEl1ckSDJEmSJEmqjYkGSZIkSZJUGxMNkiRJkiSpNiYaJEmSJElSbVwMUo2JiKuAfYAngPXANcD7c863RsQOwN3AxTnngzo4bymwMud8TNs5BfDCnPPNLWVHAKcC++WcvzkpNylJkiRJM4wjGtS0w3POWwHPBdYAX6rKDwUeASIituvgvE4sAB4EFo7jXEmSJEnSMEw0aErIOT8CnAf8eVW0EPgE8DvgzR2cNyYRsSfwIuBdwP4jJDMkSZIkSR0y0aApISK2Bg4Dro+IvSiTAF8GzmcjIw5az+uwyYXAFcCFQD/wlnGELUmSJElq4xoNatqpEXEisA64Gngr8AHgeznnuyJiGXB8ROyWc75hlPPGJCI2pxwlcUTOuYiIoWTGp+q5pafr7++fA8yZjGuPwbyG2pU0Rv39/Vs3HcN49fb2btnT08OGDRu2XLVq1bS9j2lo6Gf7vP7+/kYDmUns742xvzdgLP29r6/voW7HpenDRIOatijnfNbQQUTMAQ4BjgTIOd8WEVdTJgIOH+m8FoPA7NaCiJjd8hzAAcBc4GvV8TLgQxGxe875Pyd0N8M7FjhhEq4radOwpukAxmtgYGDo4YoGw5jJ7mo6gJnE/t44+3sXjbG/p8mPRNOViQZNNQcA2wInRcTHq7J5wPyIODLnPDjyqQDcCezRVrYL8CTleg9QJi02B26LiKE6RVX+/omFP6wTKXe3aMI8/MUsTXXbNB3AePX29u7W09OzYsOGDa8YGBi4YfQzVJOhn+07Aw83HMuMYX9vjP29AfZ3TZSJBk01CynXZfhgS9kWwI3A/jw1CmEkFwLHRMR+wKWUf8CfCFyUc348IvqA1wCvB37act4bKadoHJlzfryWO6n09fWtp9yGs+scYihNfdN56Ong4OCjALNmzXp0Ot/HdNPys/1hX/fusb83w/7eDPu7JspEg6aMKgnwauBlOeeVbc8to0xCbDTRkHO+OSIOBP6FcjeKR4BvAUdXVf4euCXnfEnb9c+mnN6wP3DRxO9GkiRJkmamVBRF0zFImiT9/f1br120upH530uY2/U21y3uepNT19wlTUfwNItZ13QIU9au85dP2zmug4ODewLXAnvNnj37uqbjmSmqBUTXANv4SWP32N+bYX9vhv1dE+X2lpIkSZIkqTYmGiRJkiRJUm1MNEiSJEmSpNqYaJAkSZIkSbUx0SBJkiRJkmrj9pbSJm6LU7eFBlZqXtrNxqaYqbFS89Jmmm2QK5NLkiRNDY5okCRJkiRJtTHRIEmSJEmSamOiQZIkSZIk1cZEgyRJkiRJqo2JBkmSJEmSVJtUFEXTMUiSJEmSpE2EIxokSZIkSVJtTDRIkiRJkqTamGiQJEmSJEm1MdEgSZIkSZJqY6JBkiRJkiTVxkSDJEmSJEmqjYkGSZIkSZJUGxMNkiRJkiSpNiYaJEmSJElSbUw0SJIkSZKk2phokCRJkiRJtTHRIEmSJEmSamOiQZIkSZIk1cZEgyRJkiRJqo2JBkmSJEmSVBsTDZIkSZIkqTYmGiRJkiRJUm1MNEiSJEmSpNqYaJAkSZIkSbUx0SBJkiRJkmqzWdMBSJocEdELfB7YF3gI+FjO+YxGg5ImaKz9OiL2AT4CvKQquho4POd8a5dClSZkPD/DI2IBcA7w7pzzWZMdo1SXTvp7RMwFPgkcAswFbgVemXN+uDvRShoLRzRIm67PUCYT+4D9gI9GxF81G5I0YWPt188EvgjsAuwI3ATkbgUp1aCjn+ERsR1wDGVfl6abTvr7WVW9Pwd6gbcBj3chRkkdcESDtAmKiC2Bg4A9qgz/9RGxlPKX8ZVNxiaNVyf9Ouf87bZzTwGOiojtcs4PdClkaVzG+TP8FOBk4NCuBCnVpJP+HhHPB94A/FHOeaAqvqF70UoaF1y2rwAACVxJREFUK0c0SJum5wMp5/yLlrL/BHZtJhypFhPp138JrDTJoGmio74eEa+szvnCpEcm1a+T/v5S4LfACRFxf0T8MiLe0YUYJXXIRIO0adqKco5jqwFgXvdDkWozrn4dEbtQDst9/+SEJdVuzH09IuYAnwX+MedcTH5oUu06+dn+HMoExFpgJ+DvgZOcGipNPSYapE3TI8DWbWXbAC6UpOms434dETsDlwOfyDl/dRJjk+rUSV8/GvhOzvn6SY9Kmhyd9Pe1wAbgIznn9TnnnwIXAq+b3BAldcpEg7Rp+hVQRMQLW8p2x0XCNL111K8jYifK+b1n55xPm/zwpNp00tdfBby1GkZ+P/AXwMkRce7khynVopP+fmNXIpI0YakoHGUnbYoi4nxgDrCQcuX97wJvzDlf0Whg0gSMtV9HRB/wPeC8nPNHuh6oNEEd9PUdqnpDLgQupkywuSaJpoUO+vtmwC+ArwAfpdx54grggJzziq4GLWmj3HVC2nT9I3A2cA/l3MfjTTJoEzBiv46IR4B9c87fB94OzAeOjIgjW87/s5zznV2OWRqPMfX1nPOq1pMiYj0wYJJB08xY+/sTERFV3Q8C/cAikwzS1OOIBkmSJEmSVBvXaJAkSZIkSbUx0SBJkiRJkmpjokGSJEmSJNXGRIMkSZIkSaqNiQZJkiRJklQbEw2SJEmSJKk2JhokSZIkSVJtTDRIkiRJkqTamGiQJGmaSCm9LqV0aUrpgZTS4yml36aUzkgp/UnTsU2GlNKClFKRUtq+Ou5NKX04pfRnNbaxNKV0U03X2r6Kd0Ed15Mkaboy0SBJ0jSQUloCfBNYC7wT+Bvgn4EXAN9pMLTJ9E3gZcBAddwLnADUlmiQJEn126zpACRJ0sallF4LfAg4sSiK41qeWgGcm1Lav5nIJldRFKuAVU3HIUmSOuOIBkmSpr4PAvdSfpr/B4qiuGTocUppVkrpuJTSHSml9SmlW1NKh7fWr6YfPJJS2iuldE1K6bGU0vXV8dyU0pkppdUppbuGOXdpSummlNK+1fd1KaVrU0r7tNUbSxw7p5S+mlK6t7rOHSml01qe//3UiZTSfwfuqJ66sCovqnJSSnNSSh+vppOsTyn9MqX05o5e5fI6r6yu+5qU0pdTSg9X1zxqmLpvTyn9JqW0NqX0XWD+CNdckFK6sbrHu1NKH0spbVY9t3V1/QvbzvlsSunBlNLOnd6DJElNM9EgSdIUVr0h/QvgO0VRDI7hlH8FPgqcB+wP/D/gtJTSP7fVmw18ETgTOJBylOPXgC8AjwEHt5z78rZzdwTOqNp6I7AeuCyl9KwO4zgXeDHwPuC1lImUnhHu6x7gDdXj4yinVLysKgf4KuWUklOA/YBLgfNSSvuOcL3RnAn8Cng95RSOT1YjSwBIKe0HfB64sqpzBbC8/SIppUXAvwGXUb4On6S83yUARVE8BCwADkwpHVad87fAe4D3FEVx1zjjlySpMU6dkCRpatsOmAv8brSK1aKJ7wVOKYpi6A39f6SUtgaOTimdVhTFI1X55sDRRVFcWp07C7gE6CmKYlFVdgVwUPX1o5amtgUOKoriiqreiiq+w4HjOohjb+DYoiguaLn2ucPdW1EU61NK11eHtxZFcXXLff8VEMDfFkXxH1Xx5SmlnYCPAN8e7bUbxkVFUXy45XXYD/g7ygQGwGLg+0VRLKyOL0spbQkc2xLXvKr9k1qmvFyeUnoCODml9K9FUTxQFMWVKaXTgU+nlH5OmQC6oCiKr4wjbkmSGueIBkmSprZUfS/GUPellCMVLmgr/wqwJbBHS9mTlJ/CD/lV9f33C0sWRbEBuB14Ttv11gwlGap6A9W1hqZPjDWO64APppTenVIadtrBGL0GWA1ckVLabOgL+C6wR0pppFESGzOUsKAoiieBm4GdAarr7QV8ve2cf287fjmwFeVUj9a4rgCeAezaUvc44G5gKIHy7nHELEnSlGCiQZKkqe1+YB3wR2Oo+8zq+8q28qHjbVvKHiuK4vGW46HHA23nPk45oqLVcAs03kc5paKTOA6mTAZ8DLg1pXRzSukNdG776pqDbV9nUY7e3HHkU0c00Hbc+jrsUF33vrY69w4TF5QJlda4flmV/z6BUxTFOsqpK3OA84uieHAcMUuSNCU4dUKSpCmsKIonUko/AP4mpTR7lHUaVlffn0356fiQ/9b2/ETtMEzZs3hqvYQxxVEUxT3A21JK/0A5QmAxcEFK6QVFUfy6g3hWUyY/XjfC8+0JgYlaBTxBec+tnj1MXFCuLTHc1JehxS1JKe0KHAlcD7w3pbS0KIpf1BOuJEnd5YgGSZKmvlMo38QeP9yT1cKEAD+h/MT8jW1VDgYepfxkvQ7bpJRe1dL+NsCrgGvGE0dRFE8WRfFTykTDZoywewNPjbpoH2HxHcrkx+NFUfxsmK/HqVE1peQ6ykUgW/1d2/GPgLXAziPE9QBASmlzYBnwM8rpJz8HlqWUZtcZtyRJ3eKIBkmSpriiKC5NKX0MWJxSeiHlWgf3Ac8FDgOeD3yjKIr7U0qfolz3YD3wQ+CvKXdjOKEoikdrCmk18IWU0gmUUwyOqcpPr+IdNY4qOXEZ5RvsWyjXdHhfdb2REiIrq+cPSSndQbnbxY1FUVyeUroEuDSldBJwI+VaEC8C5hdF8Q813XerjwEXp5TOodxt4iXA07bTLIpiTUrpeOCkapvKKynXxtgFOAA4sCiKtZQLRj4P2K0oiser3Seup0wste8WIknSlGeiQZKkaaAoisUppR9Tvhk/G5gH9AOXA0e0VD0KeBB4O+UOCHcCHyiK4rQaw7kHOJpyC8s/Af6LcseH1jUKRotjHeUn9++lXH/iMcpP9F9TFMX9wzVaFMWTKaW3Ub7J/y7legZ/DPyGcjTBMZTbQj4XWAPcBJxTyx3/YSw5pfQu4EPAmyhHcxzC03fnoCiKU1JKdwOLKO91kHKBzW8Aj1dbhx5FuZXl7dU5t6SUjgJOTyl9oyiKa5AkaRpJRTGWRawlSZIgpbQUeElRFLuOVleSJM1MrtEgSZIkSZJqY6JBkiRJkiTVxqkTkiRJkiSpNo5okCRJkiRJtTHRIEmSJEmSamOiQZIkSZIk1cZEgyRJkiRJqo2JBkmSJEmSVBsTDZIkSZIkqTYmGiRJkiRJUm1MNEiSJEmSpNqYaJAkSZIkSbX5/3HvV4pWl9ETAAAAAElFTkSuQmCC\n",
"text/plain": [
"<Figure size 900x1200 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"<ggplot: (103616345579)>"
]
},
"execution_count": 74,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Data viz\n",
"plotnine.options.figure_size = (9, 12)\n",
"contribution_factors_composite_index = (\n",
" ggplot(data = df_contribution)+\n",
" geom_bar(aes(x = 'Province',\n",
" y = 'Factor Value',\n",
" fill = 'Factor'),\n",
" width = 0.75,\n",
" position = 'stack',\n",
" stat = 'identity')+\n",
" scale_x_discrete(limits = df_index_reverse['Province'].tolist())+\n",
" labs(title = 'Education Index by Province in Indonesia 2020')+\n",
" xlab('Province')+\n",
" ylab('Composite Index')+\n",
" coord_flip()+\n",
" theme_minimal()\n",
")\n",
"# Display the viz\n",
"contribution_factors_composite_index"
]
},
{
"cell_type": "code",
"execution_count": 75,
"id": "caring-territory",
"metadata": {},
"outputs": [],
"source": [
"# Save the graph\n",
"contribution_factors_composite_index.save(filename = 'img/contribution_factors_composite_index.png', \n",
" dpi = 1000, \n",
" verbose = False)"
]
},
{
"cell_type": "markdown",
"id": "technological-terrorism",
"metadata": {},
"source": [
"#### 4 Composite index by region"
]
},
{
"cell_type": "code",
"execution_count": 76,
"id": "different-prayer",
"metadata": {
"scrolled": false
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Province</th>\n",
" <th>Region</th>\n",
" <th>Factors 1</th>\n",
" <th>Factors 2</th>\n",
" <th>Factors 3</th>\n",
" <th>Factors 4</th>\n",
" <th>Factors 5</th>\n",
" <th>Factors 6</th>\n",
" <th>Composite Index</th>\n",
" <th>Rank</th>\n",
" <th>Status</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>DKI JAKARTA</td>\n",
" <td>West</td>\n",
" <td>0.200389</td>\n",
" <td>0.201341</td>\n",
" <td>0.115874</td>\n",
" <td>0.043900</td>\n",
" <td>0.089914</td>\n",
" <td>0.023593</td>\n",
" <td>0.675010</td>\n",
" <td>1.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>ACEH</td>\n",
" <td>West</td>\n",
" <td>0.201991</td>\n",
" <td>0.088058</td>\n",
" <td>0.111502</td>\n",
" <td>0.095218</td>\n",
" <td>0.094912</td>\n",
" <td>0.047016</td>\n",
" <td>0.638697</td>\n",
" <td>2.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>DI YOGYAKARTA</td>\n",
" <td>West</td>\n",
" <td>0.202914</td>\n",
" <td>0.102804</td>\n",
" <td>0.088724</td>\n",
" <td>0.176202</td>\n",
" <td>0.021254</td>\n",
" <td>0.035115</td>\n",
" <td>0.627013</td>\n",
" <td>4.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>RIAU</td>\n",
" <td>West</td>\n",
" <td>0.191519</td>\n",
" <td>0.125554</td>\n",
" <td>0.060936</td>\n",
" <td>0.104750</td>\n",
" <td>0.068498</td>\n",
" <td>0.044904</td>\n",
" <td>0.596161</td>\n",
" <td>10.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>RIAU ISLAND</td>\n",
" <td>West</td>\n",
" <td>0.175006</td>\n",
" <td>0.151281</td>\n",
" <td>0.154005</td>\n",
" <td>0.050418</td>\n",
" <td>0.038577</td>\n",
" <td>0.023975</td>\n",
" <td>0.593262</td>\n",
" <td>11.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>JAMBI</td>\n",
" <td>West</td>\n",
" <td>0.223554</td>\n",
" <td>0.058681</td>\n",
" <td>0.128134</td>\n",
" <td>0.032835</td>\n",
" <td>0.110511</td>\n",
" <td>0.036768</td>\n",
" <td>0.590483</td>\n",
" <td>12.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>CENTRAL KALIMANTAN</td>\n",
" <td>West</td>\n",
" <td>0.192577</td>\n",
" <td>0.114370</td>\n",
" <td>0.026923</td>\n",
" <td>0.071344</td>\n",
" <td>0.109895</td>\n",
" <td>0.054440</td>\n",
" <td>0.569548</td>\n",
" <td>13.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>BENGKULU</td>\n",
" <td>West</td>\n",
" <td>0.203448</td>\n",
" <td>0.049227</td>\n",
" <td>0.124613</td>\n",
" <td>0.067338</td>\n",
" <td>0.089375</td>\n",
" <td>0.026782</td>\n",
" <td>0.560782</td>\n",
" <td>17.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>BANTEN</td>\n",
" <td>West</td>\n",
" <td>0.201559</td>\n",
" <td>0.147797</td>\n",
" <td>0.043665</td>\n",
" <td>0.067148</td>\n",
" <td>0.047066</td>\n",
" <td>0.045426</td>\n",
" <td>0.552661</td>\n",
" <td>19.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>WEST SUMATERA</td>\n",
" <td>West</td>\n",
" <td>0.206013</td>\n",
" <td>0.053522</td>\n",
" <td>0.153202</td>\n",
" <td>0.061361</td>\n",
" <td>0.033656</td>\n",
" <td>0.018639</td>\n",
" <td>0.526394</td>\n",
" <td>23.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>BANGKA BELITUNG ISLAND</td>\n",
" <td>West</td>\n",
" <td>0.225341</td>\n",
" <td>0.124547</td>\n",
" <td>0.041532</td>\n",
" <td>0.034218</td>\n",
" <td>0.069506</td>\n",
" <td>0.029348</td>\n",
" <td>0.524492</td>\n",
" <td>24.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>NORTH SUMATERA</td>\n",
" <td>West</td>\n",
" <td>0.177287</td>\n",
" <td>0.082816</td>\n",
" <td>0.137112</td>\n",
" <td>0.044351</td>\n",
" <td>0.042981</td>\n",
" <td>0.036276</td>\n",
" <td>0.520824</td>\n",
" <td>25.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>WEST JAVA</td>\n",
" <td>West</td>\n",
" <td>0.214715</td>\n",
" <td>0.097048</td>\n",
" <td>0.075698</td>\n",
" <td>0.068674</td>\n",
" <td>0.025410</td>\n",
" <td>0.038431</td>\n",
" <td>0.519976</td>\n",
" <td>26.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>WEST KALIMANTAN</td>\n",
" <td>West</td>\n",
" <td>0.203563</td>\n",
" <td>0.118691</td>\n",
" <td>0.000000</td>\n",
" <td>0.092369</td>\n",
" <td>0.068924</td>\n",
" <td>0.025336</td>\n",
" <td>0.508884</td>\n",
" <td>27.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>SOUTH SUMATERA</td>\n",
" <td>West</td>\n",
" <td>0.202577</td>\n",
" <td>0.075395</td>\n",
" <td>0.080198</td>\n",
" <td>0.070232</td>\n",
" <td>0.028486</td>\n",
" <td>0.025473</td>\n",
" <td>0.482360</td>\n",
" <td>29.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>CENTRAL JAVA</td>\n",
" <td>West</td>\n",
" <td>0.214510</td>\n",
" <td>0.080888</td>\n",
" <td>0.074647</td>\n",
" <td>0.061868</td>\n",
" <td>0.016217</td>\n",
" <td>0.031978</td>\n",
" <td>0.480108</td>\n",
" <td>30.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>31</th>\n",
" <td>EAST JAVA</td>\n",
" <td>West</td>\n",
" <td>0.215459</td>\n",
" <td>0.035866</td>\n",
" <td>0.148661</td>\n",
" <td>0.035949</td>\n",
" <td>0.000000</td>\n",
" <td>0.028245</td>\n",
" <td>0.464181</td>\n",
" <td>32.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>32</th>\n",
" <td>LAMPUNG</td>\n",
" <td>West</td>\n",
" <td>0.219731</td>\n",
" <td>0.000000</td>\n",
" <td>0.185293</td>\n",
" <td>0.000000</td>\n",
" <td>0.025891</td>\n",
" <td>0.016747</td>\n",
" <td>0.447661</td>\n",
" <td>33.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Province Region Factors 1 Factors 2 Factors 3 Factors 4 \\\n",
"0 DKI JAKARTA West 0.200389 0.201341 0.115874 0.043900 \n",
"1 ACEH West 0.201991 0.088058 0.111502 0.095218 \n",
"3 DI YOGYAKARTA West 0.202914 0.102804 0.088724 0.176202 \n",
"9 RIAU West 0.191519 0.125554 0.060936 0.104750 \n",
"10 RIAU ISLAND West 0.175006 0.151281 0.154005 0.050418 \n",
"11 JAMBI West 0.223554 0.058681 0.128134 0.032835 \n",
"12 CENTRAL KALIMANTAN West 0.192577 0.114370 0.026923 0.071344 \n",
"16 BENGKULU West 0.203448 0.049227 0.124613 0.067338 \n",
"18 BANTEN West 0.201559 0.147797 0.043665 0.067148 \n",
"22 WEST SUMATERA West 0.206013 0.053522 0.153202 0.061361 \n",
"23 BANGKA BELITUNG ISLAND West 0.225341 0.124547 0.041532 0.034218 \n",
"24 NORTH SUMATERA West 0.177287 0.082816 0.137112 0.044351 \n",
"25 WEST JAVA West 0.214715 0.097048 0.075698 0.068674 \n",
"26 WEST KALIMANTAN West 0.203563 0.118691 0.000000 0.092369 \n",
"28 SOUTH SUMATERA West 0.202577 0.075395 0.080198 0.070232 \n",
"29 CENTRAL JAVA West 0.214510 0.080888 0.074647 0.061868 \n",
"31 EAST JAVA West 0.215459 0.035866 0.148661 0.035949 \n",
"32 LAMPUNG West 0.219731 0.000000 0.185293 0.000000 \n",
"\n",
" Factors 5 Factors 6 Composite Index Rank Status \n",
"0 0.089914 0.023593 0.675010 1.0 Above \n",
"1 0.094912 0.047016 0.638697 2.0 Above \n",
"3 0.021254 0.035115 0.627013 4.0 Above \n",
"9 0.068498 0.044904 0.596161 10.0 Above \n",
"10 0.038577 0.023975 0.593262 11.0 Above \n",
"11 0.110511 0.036768 0.590483 12.0 Above \n",
"12 0.109895 0.054440 0.569548 13.0 Above \n",
"16 0.089375 0.026782 0.560782 17.0 Above \n",
"18 0.047066 0.045426 0.552661 19.0 Above \n",
"22 0.033656 0.018639 0.526394 23.0 Below \n",
"23 0.069506 0.029348 0.524492 24.0 Below \n",
"24 0.042981 0.036276 0.520824 25.0 Below \n",
"25 0.025410 0.038431 0.519976 26.0 Below \n",
"26 0.068924 0.025336 0.508884 27.0 Below \n",
"28 0.028486 0.025473 0.482360 29.0 Below \n",
"29 0.016217 0.031978 0.480108 30.0 Below \n",
"31 0.000000 0.028245 0.464181 32.0 Below \n",
"32 0.025891 0.016747 0.447661 33.0 Below "
]
},
"execution_count": 76,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# West region\n",
"df_index[df_index['Region'] == 'West']"
]
},
{
"cell_type": "code",
"execution_count": 77,
"id": "coastal-track",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Province</th>\n",
" <th>Region</th>\n",
" <th>Factors 1</th>\n",
" <th>Factors 2</th>\n",
" <th>Factors 3</th>\n",
" <th>Factors 4</th>\n",
" <th>Factors 5</th>\n",
" <th>Factors 6</th>\n",
" <th>Composite Index</th>\n",
" <th>Rank</th>\n",
" <th>Status</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>NORTH SULAWESI</td>\n",
" <td>Central</td>\n",
" <td>0.193532</td>\n",
" <td>0.115490</td>\n",
" <td>0.075847</td>\n",
" <td>0.080267</td>\n",
" <td>0.119573</td>\n",
" <td>0.042260</td>\n",
" <td>0.626969</td>\n",
" <td>5.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>EAST KALIMANTAN</td>\n",
" <td>Central</td>\n",
" <td>0.193620</td>\n",
" <td>0.138853</td>\n",
" <td>0.085336</td>\n",
" <td>0.116272</td>\n",
" <td>0.046547</td>\n",
" <td>0.032987</td>\n",
" <td>0.613614</td>\n",
" <td>7.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>SOUTHEAST SULAWESI</td>\n",
" <td>Central</td>\n",
" <td>0.199485</td>\n",
" <td>0.096840</td>\n",
" <td>0.070293</td>\n",
" <td>0.087865</td>\n",
" <td>0.117310</td>\n",
" <td>0.037360</td>\n",
" <td>0.609152</td>\n",
" <td>8.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>NORTH KALIMANTAN</td>\n",
" <td>Central</td>\n",
" <td>0.179277</td>\n",
" <td>0.124658</td>\n",
" <td>0.133095</td>\n",
" <td>0.040594</td>\n",
" <td>0.083217</td>\n",
" <td>0.035963</td>\n",
" <td>0.596804</td>\n",
" <td>9.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>BALI</td>\n",
" <td>Central</td>\n",
" <td>0.189363</td>\n",
" <td>0.152312</td>\n",
" <td>0.117265</td>\n",
" <td>0.080574</td>\n",
" <td>0.004896</td>\n",
" <td>0.021164</td>\n",
" <td>0.565573</td>\n",
" <td>14.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>SOUTH SULAWESI</td>\n",
" <td>Central</td>\n",
" <td>0.224459</td>\n",
" <td>0.078474</td>\n",
" <td>0.058022</td>\n",
" <td>0.074847</td>\n",
" <td>0.088991</td>\n",
" <td>0.039850</td>\n",
" <td>0.564644</td>\n",
" <td>15.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>SOUTH KALIMANTAN</td>\n",
" <td>Central</td>\n",
" <td>0.220826</td>\n",
" <td>0.113231</td>\n",
" <td>0.056180</td>\n",
" <td>0.081443</td>\n",
" <td>0.058641</td>\n",
" <td>0.026962</td>\n",
" <td>0.557284</td>\n",
" <td>18.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>GORONTALO</td>\n",
" <td>Central</td>\n",
" <td>0.231925</td>\n",
" <td>0.088728</td>\n",
" <td>0.064246</td>\n",
" <td>0.077924</td>\n",
" <td>0.085552</td>\n",
" <td>0.000000</td>\n",
" <td>0.548374</td>\n",
" <td>20.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>CENTRAL SULAWESI</td>\n",
" <td>Central</td>\n",
" <td>0.184056</td>\n",
" <td>0.062294</td>\n",
" <td>0.121894</td>\n",
" <td>0.066592</td>\n",
" <td>0.082584</td>\n",
" <td>0.030146</td>\n",
" <td>0.547567</td>\n",
" <td>21.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>WEST NUSA TENGGARA</td>\n",
" <td>Central</td>\n",
" <td>0.206955</td>\n",
" <td>0.069010</td>\n",
" <td>0.100905</td>\n",
" <td>0.068254</td>\n",
" <td>0.067645</td>\n",
" <td>0.032576</td>\n",
" <td>0.545346</td>\n",
" <td>22.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>WEST SULAWESI</td>\n",
" <td>Central</td>\n",
" <td>0.194232</td>\n",
" <td>0.074546</td>\n",
" <td>0.049240</td>\n",
" <td>0.061333</td>\n",
" <td>0.081510</td>\n",
" <td>0.031177</td>\n",
" <td>0.492037</td>\n",
" <td>28.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>30</th>\n",
" <td>EAST NUSA TENGGARA</td>\n",
" <td>Central</td>\n",
" <td>0.206942</td>\n",
" <td>0.036885</td>\n",
" <td>0.132883</td>\n",
" <td>0.043058</td>\n",
" <td>0.052059</td>\n",
" <td>0.004209</td>\n",
" <td>0.476036</td>\n",
" <td>31.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Province Region Factors 1 Factors 2 Factors 3 Factors 4 \\\n",
"4 NORTH SULAWESI Central 0.193532 0.115490 0.075847 0.080267 \n",
"6 EAST KALIMANTAN Central 0.193620 0.138853 0.085336 0.116272 \n",
"7 SOUTHEAST SULAWESI Central 0.199485 0.096840 0.070293 0.087865 \n",
"8 NORTH KALIMANTAN Central 0.179277 0.124658 0.133095 0.040594 \n",
"13 BALI Central 0.189363 0.152312 0.117265 0.080574 \n",
"14 SOUTH SULAWESI Central 0.224459 0.078474 0.058022 0.074847 \n",
"17 SOUTH KALIMANTAN Central 0.220826 0.113231 0.056180 0.081443 \n",
"19 GORONTALO Central 0.231925 0.088728 0.064246 0.077924 \n",
"20 CENTRAL SULAWESI Central 0.184056 0.062294 0.121894 0.066592 \n",
"21 WEST NUSA TENGGARA Central 0.206955 0.069010 0.100905 0.068254 \n",
"27 WEST SULAWESI Central 0.194232 0.074546 0.049240 0.061333 \n",
"30 EAST NUSA TENGGARA Central 0.206942 0.036885 0.132883 0.043058 \n",
"\n",
" Factors 5 Factors 6 Composite Index Rank Status \n",
"4 0.119573 0.042260 0.626969 5.0 Above \n",
"6 0.046547 0.032987 0.613614 7.0 Above \n",
"7 0.117310 0.037360 0.609152 8.0 Above \n",
"8 0.083217 0.035963 0.596804 9.0 Above \n",
"13 0.004896 0.021164 0.565573 14.0 Above \n",
"14 0.088991 0.039850 0.564644 15.0 Above \n",
"17 0.058641 0.026962 0.557284 18.0 Above \n",
"19 0.085552 0.000000 0.548374 20.0 Below \n",
"20 0.082584 0.030146 0.547567 21.0 Below \n",
"21 0.067645 0.032576 0.545346 22.0 Below \n",
"27 0.081510 0.031177 0.492037 28.0 Below \n",
"30 0.052059 0.004209 0.476036 31.0 Below "
]
},
"execution_count": 77,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Central region\n",
"df_index[df_index['Region'] == 'Central']"
]
},
{
"cell_type": "code",
"execution_count": 78,
"id": "lucky-approval",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Province</th>\n",
" <th>Region</th>\n",
" <th>Factors 1</th>\n",
" <th>Factors 2</th>\n",
" <th>Factors 3</th>\n",
" <th>Factors 4</th>\n",
" <th>Factors 5</th>\n",
" <th>Factors 6</th>\n",
" <th>Composite Index</th>\n",
" <th>Rank</th>\n",
" <th>Status</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>NORTH MALUKU</td>\n",
" <td>East</td>\n",
" <td>0.174165</td>\n",
" <td>0.106911</td>\n",
" <td>0.100701</td>\n",
" <td>0.083896</td>\n",
" <td>0.150799</td>\n",
" <td>0.019639</td>\n",
" <td>0.636111</td>\n",
" <td>3.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>MALUKU</td>\n",
" <td>East</td>\n",
" <td>0.166540</td>\n",
" <td>0.082791</td>\n",
" <td>0.126111</td>\n",
" <td>0.109298</td>\n",
" <td>0.102882</td>\n",
" <td>0.028169</td>\n",
" <td>0.615790</td>\n",
" <td>6.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>WEST PAPUA</td>\n",
" <td>East</td>\n",
" <td>0.159122</td>\n",
" <td>0.072640</td>\n",
" <td>0.159038</td>\n",
" <td>0.043183</td>\n",
" <td>0.116128</td>\n",
" <td>0.012252</td>\n",
" <td>0.562362</td>\n",
" <td>16.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>33</th>\n",
" <td>PAPUA</td>\n",
" <td>East</td>\n",
" <td>0.000000</td>\n",
" <td>0.075569</td>\n",
" <td>0.038739</td>\n",
" <td>0.071085</td>\n",
" <td>0.030425</td>\n",
" <td>0.032620</td>\n",
" <td>0.248439</td>\n",
" <td>34.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Province Region Factors 1 Factors 2 Factors 3 Factors 4 \\\n",
"2 NORTH MALUKU East 0.174165 0.106911 0.100701 0.083896 \n",
"5 MALUKU East 0.166540 0.082791 0.126111 0.109298 \n",
"15 WEST PAPUA East 0.159122 0.072640 0.159038 0.043183 \n",
"33 PAPUA East 0.000000 0.075569 0.038739 0.071085 \n",
"\n",
" Factors 5 Factors 6 Composite Index Rank Status \n",
"2 0.150799 0.019639 0.636111 3.0 Above \n",
"5 0.102882 0.028169 0.615790 6.0 Above \n",
"15 0.116128 0.012252 0.562362 16.0 Above \n",
"33 0.030425 0.032620 0.248439 34.0 Below "
]
},
"execution_count": 78,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# East region\n",
"df_index[df_index['Region'] == 'East']"
]
},
{
"cell_type": "code",
"execution_count": 79,
"id": "amino-movement",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead tr th {\n",
" text-align: left;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th></th>\n",
" <th>Region</th>\n",
" <th colspan=\"2\" halign=\"left\">Composite Index</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th></th>\n",
" <th>mean</th>\n",
" <th>median</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Central</td>\n",
" <td>0.561950</td>\n",
" <td>0.560964</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>East</td>\n",
" <td>0.515675</td>\n",
" <td>0.589076</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>West</td>\n",
" <td>0.548805</td>\n",
" <td>0.539528</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Region Composite Index \n",
" mean median\n",
"0 Central 0.561950 0.560964\n",
"1 East 0.515675 0.589076\n",
"2 West 0.548805 0.539528"
]
},
"execution_count": 79,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Basic statistics\n",
"df_index.groupby('Region').agg(\n",
" {\n",
" 'Composite Index': ['mean', 'median']\n",
" }\n",
").reset_index()"
]
},
{
"cell_type": "code",
"execution_count": 80,
"id": "distributed-columbus",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 800x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"<ggplot: (103616191163)>"
]
},
"execution_count": 80,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Data viz\n",
"plotnine.options.figure_size = (8, 4.8)\n",
"composite_index_region = (\n",
" ggplot(data = df_index)+\n",
" geom_boxplot(aes(x = 'Region',\n",
" y = 'Composite Index'),\n",
" fill = '#c22d6d',\n",
" show_legend = False)+\n",
" scale_x_discrete(limits = ['West', 'Central', 'East'])+\n",
" labs(title = 'Education Index by Region in Indonesia 2020')+\n",
" xlab('Region')+\n",
" ylab('Composite Index')+\n",
" theme_bw()\n",
")\n",
"# Display the viz\n",
"composite_index_region"
]
},
{
"cell_type": "code",
"execution_count": 81,
"id": "subsequent-compound",
"metadata": {},
"outputs": [],
"source": [
"# Save the graph\n",
"composite_index_region.save(filename = 'img/composite_index_region.png',\n",
" dpi = 1000,\n",
" verbose = False)"
]
},
{
"cell_type": "markdown",
"id": "appropriate-spain",
"metadata": {},
"source": [
"#### 5 Composite index status by region"
]
},
{
"cell_type": "code",
"execution_count": 82,
"id": "encouraging-palmer",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Region</th>\n",
" <th>Status</th>\n",
" <th>Province</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Central</td>\n",
" <td>Above</td>\n",
" <td>7</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Central</td>\n",
" <td>Below</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>East</td>\n",
" <td>Above</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>East</td>\n",
" <td>Below</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>West</td>\n",
" <td>Above</td>\n",
" <td>9</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>West</td>\n",
" <td>Below</td>\n",
" <td>9</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Region Status Province\n",
"0 Central Above 7\n",
"1 Central Below 5\n",
"2 East Above 3\n",
"3 East Below 1\n",
"4 West Above 9\n",
"5 West Below 9"
]
},
"execution_count": 82,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Basic statistics\n",
"df_region_status = df_index.groupby(['Region', 'Status'])['Province'].count().reset_index()\n",
"df_region_status"
]
},
{
"cell_type": "code",
"execution_count": 83,
"id": "exotic-newman",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 800x480 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"<ggplot: (103616187206)>"
]
},
"execution_count": 83,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Data viz\n",
"plotnine.options.figure_size = (8, 4.8)\n",
"composite_index_status_region = (\n",
" ggplot(data = df_region_status)+\n",
" geom_bar(aes(x = 'Region',\n",
" y = 'Province',\n",
" fill = 'Status'),\n",
" stat = 'identity',\n",
" position = 'fill')+\n",
" labs(title = 'Composite status by region in Indonesia 2020')+\n",
" xlab('Region')+\n",
" ylab('Proportion')+\n",
" scale_x_discrete(limits = ['West', 'Central', 'East'])+\n",
" scale_fill_manual(values = ['#c22d6d','#80797c'], labels = ['Above', 'Below'])+\n",
" theme_minimal()\n",
")\n",
"# Display the viz\n",
"composite_index_status_region"
]
},
{
"cell_type": "code",
"execution_count": 84,
"id": "cathedral-neighborhood",
"metadata": {},
"outputs": [],
"source": [
"# Save the graph\n",
"composite_index_status_region.save(filename = 'img/composite_index_status_region.png',\n",
" dpi = 1000,\n",
" verbose = False)"
]
},
{
"cell_type": "markdown",
"id": "meaning-faith",
"metadata": {},
"source": [
"#### 6 Map visualization"
]
},
{
"cell_type": "code",
"execution_count": 85,
"id": "turned-confidentiality",
"metadata": {
"scrolled": false
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Province</th>\n",
" <th>Region</th>\n",
" <th>Factors 1</th>\n",
" <th>Factors 2</th>\n",
" <th>Factors 3</th>\n",
" <th>Factors 4</th>\n",
" <th>Factors 5</th>\n",
" <th>Factors 6</th>\n",
" <th>Composite Index</th>\n",
" <th>Rank</th>\n",
" <th>Status</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>PAPUA</td>\n",
" <td>East</td>\n",
" <td>0.000000</td>\n",
" <td>0.075569</td>\n",
" <td>0.038739</td>\n",
" <td>0.071085</td>\n",
" <td>0.030425</td>\n",
" <td>0.032620</td>\n",
" <td>0.248439</td>\n",
" <td>34.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>LAMPUNG</td>\n",
" <td>West</td>\n",
" <td>0.219731</td>\n",
" <td>0.000000</td>\n",
" <td>0.185293</td>\n",
" <td>0.000000</td>\n",
" <td>0.025891</td>\n",
" <td>0.016747</td>\n",
" <td>0.447661</td>\n",
" <td>33.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>EAST JAVA</td>\n",
" <td>West</td>\n",
" <td>0.215459</td>\n",
" <td>0.035866</td>\n",
" <td>0.148661</td>\n",
" <td>0.035949</td>\n",
" <td>0.000000</td>\n",
" <td>0.028245</td>\n",
" <td>0.464181</td>\n",
" <td>32.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>EAST NUSA TENGGARA</td>\n",
" <td>Central</td>\n",
" <td>0.206942</td>\n",
" <td>0.036885</td>\n",
" <td>0.132883</td>\n",
" <td>0.043058</td>\n",
" <td>0.052059</td>\n",
" <td>0.004209</td>\n",
" <td>0.476036</td>\n",
" <td>31.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>CENTRAL JAVA</td>\n",
" <td>West</td>\n",
" <td>0.214510</td>\n",
" <td>0.080888</td>\n",
" <td>0.074647</td>\n",
" <td>0.061868</td>\n",
" <td>0.016217</td>\n",
" <td>0.031978</td>\n",
" <td>0.480108</td>\n",
" <td>30.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>SOUTH SUMATERA</td>\n",
" <td>West</td>\n",
" <td>0.202577</td>\n",
" <td>0.075395</td>\n",
" <td>0.080198</td>\n",
" <td>0.070232</td>\n",
" <td>0.028486</td>\n",
" <td>0.025473</td>\n",
" <td>0.482360</td>\n",
" <td>29.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>WEST SULAWESI</td>\n",
" <td>Central</td>\n",
" <td>0.194232</td>\n",
" <td>0.074546</td>\n",
" <td>0.049240</td>\n",
" <td>0.061333</td>\n",
" <td>0.081510</td>\n",
" <td>0.031177</td>\n",
" <td>0.492037</td>\n",
" <td>28.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>WEST KALIMANTAN</td>\n",
" <td>West</td>\n",
" <td>0.203563</td>\n",
" <td>0.118691</td>\n",
" <td>0.000000</td>\n",
" <td>0.092369</td>\n",
" <td>0.068924</td>\n",
" <td>0.025336</td>\n",
" <td>0.508884</td>\n",
" <td>27.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>WEST JAVA</td>\n",
" <td>West</td>\n",
" <td>0.214715</td>\n",
" <td>0.097048</td>\n",
" <td>0.075698</td>\n",
" <td>0.068674</td>\n",
" <td>0.025410</td>\n",
" <td>0.038431</td>\n",
" <td>0.519976</td>\n",
" <td>26.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>NORTH SUMATERA</td>\n",
" <td>West</td>\n",
" <td>0.177287</td>\n",
" <td>0.082816</td>\n",
" <td>0.137112</td>\n",
" <td>0.044351</td>\n",
" <td>0.042981</td>\n",
" <td>0.036276</td>\n",
" <td>0.520824</td>\n",
" <td>25.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>BANGKA BELITUNG ISLAND</td>\n",
" <td>West</td>\n",
" <td>0.225341</td>\n",
" <td>0.124547</td>\n",
" <td>0.041532</td>\n",
" <td>0.034218</td>\n",
" <td>0.069506</td>\n",
" <td>0.029348</td>\n",
" <td>0.524492</td>\n",
" <td>24.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>WEST SUMATERA</td>\n",
" <td>West</td>\n",
" <td>0.206013</td>\n",
" <td>0.053522</td>\n",
" <td>0.153202</td>\n",
" <td>0.061361</td>\n",
" <td>0.033656</td>\n",
" <td>0.018639</td>\n",
" <td>0.526394</td>\n",
" <td>23.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>WEST NUSA TENGGARA</td>\n",
" <td>Central</td>\n",
" <td>0.206955</td>\n",
" <td>0.069010</td>\n",
" <td>0.100905</td>\n",
" <td>0.068254</td>\n",
" <td>0.067645</td>\n",
" <td>0.032576</td>\n",
" <td>0.545346</td>\n",
" <td>22.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>CENTRAL SULAWESI</td>\n",
" <td>Central</td>\n",
" <td>0.184056</td>\n",
" <td>0.062294</td>\n",
" <td>0.121894</td>\n",
" <td>0.066592</td>\n",
" <td>0.082584</td>\n",
" <td>0.030146</td>\n",
" <td>0.547567</td>\n",
" <td>21.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>GORONTALO</td>\n",
" <td>Central</td>\n",
" <td>0.231925</td>\n",
" <td>0.088728</td>\n",
" <td>0.064246</td>\n",
" <td>0.077924</td>\n",
" <td>0.085552</td>\n",
" <td>0.000000</td>\n",
" <td>0.548374</td>\n",
" <td>20.0</td>\n",
" <td>Below</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>BANTEN</td>\n",
" <td>West</td>\n",
" <td>0.201559</td>\n",
" <td>0.147797</td>\n",
" <td>0.043665</td>\n",
" <td>0.067148</td>\n",
" <td>0.047066</td>\n",
" <td>0.045426</td>\n",
" <td>0.552661</td>\n",
" <td>19.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>SOUTH KALIMANTAN</td>\n",
" <td>Central</td>\n",
" <td>0.220826</td>\n",
" <td>0.113231</td>\n",
" <td>0.056180</td>\n",
" <td>0.081443</td>\n",
" <td>0.058641</td>\n",
" <td>0.026962</td>\n",
" <td>0.557284</td>\n",
" <td>18.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>BENGKULU</td>\n",
" <td>West</td>\n",
" <td>0.203448</td>\n",
" <td>0.049227</td>\n",
" <td>0.124613</td>\n",
" <td>0.067338</td>\n",
" <td>0.089375</td>\n",
" <td>0.026782</td>\n",
" <td>0.560782</td>\n",
" <td>17.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>WEST PAPUA</td>\n",
" <td>East</td>\n",
" <td>0.159122</td>\n",
" <td>0.072640</td>\n",
" <td>0.159038</td>\n",
" <td>0.043183</td>\n",
" <td>0.116128</td>\n",
" <td>0.012252</td>\n",
" <td>0.562362</td>\n",
" <td>16.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>SOUTH SULAWESI</td>\n",
" <td>Central</td>\n",
" <td>0.224459</td>\n",
" <td>0.078474</td>\n",
" <td>0.058022</td>\n",
" <td>0.074847</td>\n",
" <td>0.088991</td>\n",
" <td>0.039850</td>\n",
" <td>0.564644</td>\n",
" <td>15.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>BALI</td>\n",
" <td>Central</td>\n",
" <td>0.189363</td>\n",
" <td>0.152312</td>\n",
" <td>0.117265</td>\n",
" <td>0.080574</td>\n",
" <td>0.004896</td>\n",
" <td>0.021164</td>\n",
" <td>0.565573</td>\n",
" <td>14.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>CENTRAL KALIMANTAN</td>\n",
" <td>West</td>\n",
" <td>0.192577</td>\n",
" <td>0.114370</td>\n",
" <td>0.026923</td>\n",
" <td>0.071344</td>\n",
" <td>0.109895</td>\n",
" <td>0.054440</td>\n",
" <td>0.569548</td>\n",
" <td>13.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>JAMBI</td>\n",
" <td>West</td>\n",
" <td>0.223554</td>\n",
" <td>0.058681</td>\n",
" <td>0.128134</td>\n",
" <td>0.032835</td>\n",
" <td>0.110511</td>\n",
" <td>0.036768</td>\n",
" <td>0.590483</td>\n",
" <td>12.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>RIAU ISLAND</td>\n",
" <td>West</td>\n",
" <td>0.175006</td>\n",
" <td>0.151281</td>\n",
" <td>0.154005</td>\n",
" <td>0.050418</td>\n",
" <td>0.038577</td>\n",
" <td>0.023975</td>\n",
" <td>0.593262</td>\n",
" <td>11.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>RIAU</td>\n",
" <td>West</td>\n",
" <td>0.191519</td>\n",
" <td>0.125554</td>\n",
" <td>0.060936</td>\n",
" <td>0.104750</td>\n",
" <td>0.068498</td>\n",
" <td>0.044904</td>\n",
" <td>0.596161</td>\n",
" <td>10.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>NORTH KALIMANTAN</td>\n",
" <td>Central</td>\n",
" <td>0.179277</td>\n",
" <td>0.124658</td>\n",
" <td>0.133095</td>\n",
" <td>0.040594</td>\n",
" <td>0.083217</td>\n",
" <td>0.035963</td>\n",
" <td>0.596804</td>\n",
" <td>9.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>SOUTHEAST SULAWESI</td>\n",
" <td>Central</td>\n",
" <td>0.199485</td>\n",
" <td>0.096840</td>\n",
" <td>0.070293</td>\n",
" <td>0.087865</td>\n",
" <td>0.117310</td>\n",
" <td>0.037360</td>\n",
" <td>0.609152</td>\n",
" <td>8.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>EAST KALIMANTAN</td>\n",
" <td>Central</td>\n",
" <td>0.193620</td>\n",
" <td>0.138853</td>\n",
" <td>0.085336</td>\n",
" <td>0.116272</td>\n",
" <td>0.046547</td>\n",
" <td>0.032987</td>\n",
" <td>0.613614</td>\n",
" <td>7.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>MALUKU</td>\n",
" <td>East</td>\n",
" <td>0.166540</td>\n",
" <td>0.082791</td>\n",
" <td>0.126111</td>\n",
" <td>0.109298</td>\n",
" <td>0.102882</td>\n",
" <td>0.028169</td>\n",
" <td>0.615790</td>\n",
" <td>6.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>NORTH SULAWESI</td>\n",
" <td>Central</td>\n",
" <td>0.193532</td>\n",
" <td>0.115490</td>\n",
" <td>0.075847</td>\n",
" <td>0.080267</td>\n",
" <td>0.119573</td>\n",
" <td>0.042260</td>\n",
" <td>0.626969</td>\n",
" <td>5.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>30</th>\n",
" <td>DI YOGYAKARTA</td>\n",
" <td>West</td>\n",
" <td>0.202914</td>\n",
" <td>0.102804</td>\n",
" <td>0.088724</td>\n",
" <td>0.176202</td>\n",
" <td>0.021254</td>\n",
" <td>0.035115</td>\n",
" <td>0.627013</td>\n",
" <td>4.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>31</th>\n",
" <td>NORTH MALUKU</td>\n",
" <td>East</td>\n",
" <td>0.174165</td>\n",
" <td>0.106911</td>\n",
" <td>0.100701</td>\n",
" <td>0.083896</td>\n",
" <td>0.150799</td>\n",
" <td>0.019639</td>\n",
" <td>0.636111</td>\n",
" <td>3.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>32</th>\n",
" <td>ACEH</td>\n",
" <td>West</td>\n",
" <td>0.201991</td>\n",
" <td>0.088058</td>\n",
" <td>0.111502</td>\n",
" <td>0.095218</td>\n",
" <td>0.094912</td>\n",
" <td>0.047016</td>\n",
" <td>0.638697</td>\n",
" <td>2.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" <tr>\n",
" <th>33</th>\n",
" <td>DKI JAKARTA</td>\n",
" <td>West</td>\n",
" <td>0.200389</td>\n",
" <td>0.201341</td>\n",
" <td>0.115874</td>\n",
" <td>0.043900</td>\n",
" <td>0.089914</td>\n",
" <td>0.023593</td>\n",
" <td>0.675010</td>\n",
" <td>1.0</td>\n",
" <td>Above</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Province Region Factors 1 Factors 2 Factors 3 \\\n",
"0 PAPUA East 0.000000 0.075569 0.038739 \n",
"1 LAMPUNG West 0.219731 0.000000 0.185293 \n",
"2 EAST JAVA West 0.215459 0.035866 0.148661 \n",
"3 EAST NUSA TENGGARA Central 0.206942 0.036885 0.132883 \n",
"4 CENTRAL JAVA West 0.214510 0.080888 0.074647 \n",
"5 SOUTH SUMATERA West 0.202577 0.075395 0.080198 \n",
"6 WEST SULAWESI Central 0.194232 0.074546 0.049240 \n",
"7 WEST KALIMANTAN West 0.203563 0.118691 0.000000 \n",
"8 WEST JAVA West 0.214715 0.097048 0.075698 \n",
"9 NORTH SUMATERA West 0.177287 0.082816 0.137112 \n",
"10 BANGKA BELITUNG ISLAND West 0.225341 0.124547 0.041532 \n",
"11 WEST SUMATERA West 0.206013 0.053522 0.153202 \n",
"12 WEST NUSA TENGGARA Central 0.206955 0.069010 0.100905 \n",
"13 CENTRAL SULAWESI Central 0.184056 0.062294 0.121894 \n",
"14 GORONTALO Central 0.231925 0.088728 0.064246 \n",
"15 BANTEN West 0.201559 0.147797 0.043665 \n",
"16 SOUTH KALIMANTAN Central 0.220826 0.113231 0.056180 \n",
"17 BENGKULU West 0.203448 0.049227 0.124613 \n",
"18 WEST PAPUA East 0.159122 0.072640 0.159038 \n",
"19 SOUTH SULAWESI Central 0.224459 0.078474 0.058022 \n",
"20 BALI Central 0.189363 0.152312 0.117265 \n",
"21 CENTRAL KALIMANTAN West 0.192577 0.114370 0.026923 \n",
"22 JAMBI West 0.223554 0.058681 0.128134 \n",
"23 RIAU ISLAND West 0.175006 0.151281 0.154005 \n",
"24 RIAU West 0.191519 0.125554 0.060936 \n",
"25 NORTH KALIMANTAN Central 0.179277 0.124658 0.133095 \n",
"26 SOUTHEAST SULAWESI Central 0.199485 0.096840 0.070293 \n",
"27 EAST KALIMANTAN Central 0.193620 0.138853 0.085336 \n",
"28 MALUKU East 0.166540 0.082791 0.126111 \n",
"29 NORTH SULAWESI Central 0.193532 0.115490 0.075847 \n",
"30 DI YOGYAKARTA West 0.202914 0.102804 0.088724 \n",
"31 NORTH MALUKU East 0.174165 0.106911 0.100701 \n",
"32 ACEH West 0.201991 0.088058 0.111502 \n",
"33 DKI JAKARTA West 0.200389 0.201341 0.115874 \n",
"\n",
" Factors 4 Factors 5 Factors 6 Composite Index Rank Status \n",
"0 0.071085 0.030425 0.032620 0.248439 34.0 Below \n",
"1 0.000000 0.025891 0.016747 0.447661 33.0 Below \n",
"2 0.035949 0.000000 0.028245 0.464181 32.0 Below \n",
"3 0.043058 0.052059 0.004209 0.476036 31.0 Below \n",
"4 0.061868 0.016217 0.031978 0.480108 30.0 Below \n",
"5 0.070232 0.028486 0.025473 0.482360 29.0 Below \n",
"6 0.061333 0.081510 0.031177 0.492037 28.0 Below \n",
"7 0.092369 0.068924 0.025336 0.508884 27.0 Below \n",
"8 0.068674 0.025410 0.038431 0.519976 26.0 Below \n",
"9 0.044351 0.042981 0.036276 0.520824 25.0 Below \n",
"10 0.034218 0.069506 0.029348 0.524492 24.0 Below \n",
"11 0.061361 0.033656 0.018639 0.526394 23.0 Below \n",
"12 0.068254 0.067645 0.032576 0.545346 22.0 Below \n",
"13 0.066592 0.082584 0.030146 0.547567 21.0 Below \n",
"14 0.077924 0.085552 0.000000 0.548374 20.0 Below \n",
"15 0.067148 0.047066 0.045426 0.552661 19.0 Above \n",
"16 0.081443 0.058641 0.026962 0.557284 18.0 Above \n",
"17 0.067338 0.089375 0.026782 0.560782 17.0 Above \n",
"18 0.043183 0.116128 0.012252 0.562362 16.0 Above \n",
"19 0.074847 0.088991 0.039850 0.564644 15.0 Above \n",
"20 0.080574 0.004896 0.021164 0.565573 14.0 Above \n",
"21 0.071344 0.109895 0.054440 0.569548 13.0 Above \n",
"22 0.032835 0.110511 0.036768 0.590483 12.0 Above \n",
"23 0.050418 0.038577 0.023975 0.593262 11.0 Above \n",
"24 0.104750 0.068498 0.044904 0.596161 10.0 Above \n",
"25 0.040594 0.083217 0.035963 0.596804 9.0 Above \n",
"26 0.087865 0.117310 0.037360 0.609152 8.0 Above \n",
"27 0.116272 0.046547 0.032987 0.613614 7.0 Above \n",
"28 0.109298 0.102882 0.028169 0.615790 6.0 Above \n",
"29 0.080267 0.119573 0.042260 0.626969 5.0 Above \n",
"30 0.176202 0.021254 0.035115 0.627013 4.0 Above \n",
"31 0.083896 0.150799 0.019639 0.636111 3.0 Above \n",
"32 0.095218 0.094912 0.047016 0.638697 2.0 Above \n",
"33 0.043900 0.089914 0.023593 0.675010 1.0 Above "
]
},
"execution_count": 85,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_index_reverse"
]
},
{
"cell_type": "code",
"execution_count": 86,
"id": "after-citizenship",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Province</th>\n",
" <th>Region</th>\n",
" <th>Factors 1</th>\n",
" <th>Factors 2</th>\n",
" <th>Factors 3</th>\n",
" <th>Factors 4</th>\n",
" <th>Factors 5</th>\n",
" <th>Factors 6</th>\n",
" <th>Composite Index</th>\n",
" <th>Rank</th>\n",
" <th>Status</th>\n",
" <th>Code</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>PAPUA</td>\n",
" <td>East</td>\n",
" <td>0.000000</td>\n",
" <td>0.075569</td>\n",
" <td>0.038739</td>\n",
" <td>0.071085</td>\n",
" <td>0.030425</td>\n",
" <td>0.032620</td>\n",
" <td>0.248439</td>\n",
" <td>34.0</td>\n",
" <td>Below</td>\n",
" <td>91</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>LAMPUNG</td>\n",
" <td>West</td>\n",
" <td>0.219731</td>\n",
" <td>0.000000</td>\n",
" <td>0.185293</td>\n",
" <td>0.000000</td>\n",
" <td>0.025891</td>\n",
" <td>0.016747</td>\n",
" <td>0.447661</td>\n",
" <td>33.0</td>\n",
" <td>Below</td>\n",
" <td>18</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>EAST JAVA</td>\n",
" <td>West</td>\n",
" <td>0.215459</td>\n",
" <td>0.035866</td>\n",
" <td>0.148661</td>\n",
" <td>0.035949</td>\n",
" <td>0.000000</td>\n",
" <td>0.028245</td>\n",
" <td>0.464181</td>\n",
" <td>32.0</td>\n",
" <td>Below</td>\n",
" <td>35</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>EAST NUSA TENGGARA</td>\n",
" <td>Central</td>\n",
" <td>0.206942</td>\n",
" <td>0.036885</td>\n",
" <td>0.132883</td>\n",
" <td>0.043058</td>\n",
" <td>0.052059</td>\n",
" <td>0.004209</td>\n",
" <td>0.476036</td>\n",
" <td>31.0</td>\n",
" <td>Below</td>\n",
" <td>53</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>CENTRAL JAVA</td>\n",
" <td>West</td>\n",
" <td>0.214510</td>\n",
" <td>0.080888</td>\n",
" <td>0.074647</td>\n",
" <td>0.061868</td>\n",
" <td>0.016217</td>\n",
" <td>0.031978</td>\n",
" <td>0.480108</td>\n",
" <td>30.0</td>\n",
" <td>Below</td>\n",
" <td>33</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>SOUTH SUMATERA</td>\n",
" <td>West</td>\n",
" <td>0.202577</td>\n",
" <td>0.075395</td>\n",
" <td>0.080198</td>\n",
" <td>0.070232</td>\n",
" <td>0.028486</td>\n",
" <td>0.025473</td>\n",
" <td>0.482360</td>\n",
" <td>29.0</td>\n",
" <td>Below</td>\n",
" <td>16</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>WEST SULAWESI</td>\n",
" <td>Central</td>\n",
" <td>0.194232</td>\n",
" <td>0.074546</td>\n",
" <td>0.049240</td>\n",
" <td>0.061333</td>\n",
" <td>0.081510</td>\n",
" <td>0.031177</td>\n",
" <td>0.492037</td>\n",
" <td>28.0</td>\n",
" <td>Below</td>\n",
" <td>76</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>WEST KALIMANTAN</td>\n",
" <td>West</td>\n",
" <td>0.203563</td>\n",
" <td>0.118691</td>\n",
" <td>0.000000</td>\n",
" <td>0.092369</td>\n",
" <td>0.068924</td>\n",
" <td>0.025336</td>\n",
" <td>0.508884</td>\n",
" <td>27.0</td>\n",
" <td>Below</td>\n",
" <td>61</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>WEST JAVA</td>\n",
" <td>West</td>\n",
" <td>0.214715</td>\n",
" <td>0.097048</td>\n",
" <td>0.075698</td>\n",
" <td>0.068674</td>\n",
" <td>0.025410</td>\n",
" <td>0.038431</td>\n",
" <td>0.519976</td>\n",
" <td>26.0</td>\n",
" <td>Below</td>\n",
" <td>32</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>NORTH SUMATERA</td>\n",
" <td>West</td>\n",
" <td>0.177287</td>\n",
" <td>0.082816</td>\n",
" <td>0.137112</td>\n",
" <td>0.044351</td>\n",
" <td>0.042981</td>\n",
" <td>0.036276</td>\n",
" <td>0.520824</td>\n",
" <td>25.0</td>\n",
" <td>Below</td>\n",
" <td>12</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>BANGKA BELITUNG ISLAND</td>\n",
" <td>West</td>\n",
" <td>0.225341</td>\n",
" <td>0.124547</td>\n",
" <td>0.041532</td>\n",
" <td>0.034218</td>\n",
" <td>0.069506</td>\n",
" <td>0.029348</td>\n",
" <td>0.524492</td>\n",
" <td>24.0</td>\n",
" <td>Below</td>\n",
" <td>19</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>WEST SUMATERA</td>\n",
" <td>West</td>\n",
" <td>0.206013</td>\n",
" <td>0.053522</td>\n",
" <td>0.153202</td>\n",
" <td>0.061361</td>\n",
" <td>0.033656</td>\n",
" <td>0.018639</td>\n",
" <td>0.526394</td>\n",
" <td>23.0</td>\n",
" <td>Below</td>\n",
" <td>13</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>WEST NUSA TENGGARA</td>\n",
" <td>Central</td>\n",
" <td>0.206955</td>\n",
" <td>0.069010</td>\n",
" <td>0.100905</td>\n",
" <td>0.068254</td>\n",
" <td>0.067645</td>\n",
" <td>0.032576</td>\n",
" <td>0.545346</td>\n",
" <td>22.0</td>\n",
" <td>Below</td>\n",
" <td>52</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>CENTRAL SULAWESI</td>\n",
" <td>Central</td>\n",
" <td>0.184056</td>\n",
" <td>0.062294</td>\n",
" <td>0.121894</td>\n",
" <td>0.066592</td>\n",
" <td>0.082584</td>\n",
" <td>0.030146</td>\n",
" <td>0.547567</td>\n",
" <td>21.0</td>\n",
" <td>Below</td>\n",
" <td>72</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>GORONTALO</td>\n",
" <td>Central</td>\n",
" <td>0.231925</td>\n",
" <td>0.088728</td>\n",
" <td>0.064246</td>\n",
" <td>0.077924</td>\n",
" <td>0.085552</td>\n",
" <td>0.000000</td>\n",
" <td>0.548374</td>\n",
" <td>20.0</td>\n",
" <td>Below</td>\n",
" <td>75</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>BANTEN</td>\n",
" <td>West</td>\n",
" <td>0.201559</td>\n",
" <td>0.147797</td>\n",
" <td>0.043665</td>\n",
" <td>0.067148</td>\n",
" <td>0.047066</td>\n",
" <td>0.045426</td>\n",
" <td>0.552661</td>\n",
" <td>19.0</td>\n",
" <td>Above</td>\n",
" <td>36</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>SOUTH KALIMANTAN</td>\n",
" <td>Central</td>\n",
" <td>0.220826</td>\n",
" <td>0.113231</td>\n",
" <td>0.056180</td>\n",
" <td>0.081443</td>\n",
" <td>0.058641</td>\n",
" <td>0.026962</td>\n",
" <td>0.557284</td>\n",
" <td>18.0</td>\n",
" <td>Above</td>\n",
" <td>63</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>BENGKULU</td>\n",
" <td>West</td>\n",
" <td>0.203448</td>\n",
" <td>0.049227</td>\n",
" <td>0.124613</td>\n",
" <td>0.067338</td>\n",
" <td>0.089375</td>\n",
" <td>0.026782</td>\n",
" <td>0.560782</td>\n",
" <td>17.0</td>\n",
" <td>Above</td>\n",
" <td>17</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>WEST PAPUA</td>\n",
" <td>East</td>\n",
" <td>0.159122</td>\n",
" <td>0.072640</td>\n",
" <td>0.159038</td>\n",
" <td>0.043183</td>\n",
" <td>0.116128</td>\n",
" <td>0.012252</td>\n",
" <td>0.562362</td>\n",
" <td>16.0</td>\n",
" <td>Above</td>\n",
" <td>92</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>SOUTH SULAWESI</td>\n",
" <td>Central</td>\n",
" <td>0.224459</td>\n",
" <td>0.078474</td>\n",
" <td>0.058022</td>\n",
" <td>0.074847</td>\n",
" <td>0.088991</td>\n",
" <td>0.039850</td>\n",
" <td>0.564644</td>\n",
" <td>15.0</td>\n",
" <td>Above</td>\n",
" <td>73</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>BALI</td>\n",
" <td>Central</td>\n",
" <td>0.189363</td>\n",
" <td>0.152312</td>\n",
" <td>0.117265</td>\n",
" <td>0.080574</td>\n",
" <td>0.004896</td>\n",
" <td>0.021164</td>\n",
" <td>0.565573</td>\n",
" <td>14.0</td>\n",
" <td>Above</td>\n",
" <td>51</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>CENTRAL KALIMANTAN</td>\n",
" <td>West</td>\n",
" <td>0.192577</td>\n",
" <td>0.114370</td>\n",
" <td>0.026923</td>\n",
" <td>0.071344</td>\n",
" <td>0.109895</td>\n",
" <td>0.054440</td>\n",
" <td>0.569548</td>\n",
" <td>13.0</td>\n",
" <td>Above</td>\n",
" <td>62</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>JAMBI</td>\n",
" <td>West</td>\n",
" <td>0.223554</td>\n",
" <td>0.058681</td>\n",
" <td>0.128134</td>\n",
" <td>0.032835</td>\n",
" <td>0.110511</td>\n",
" <td>0.036768</td>\n",
" <td>0.590483</td>\n",
" <td>12.0</td>\n",
" <td>Above</td>\n",
" <td>15</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>RIAU ISLAND</td>\n",
" <td>West</td>\n",
" <td>0.175006</td>\n",
" <td>0.151281</td>\n",
" <td>0.154005</td>\n",
" <td>0.050418</td>\n",
" <td>0.038577</td>\n",
" <td>0.023975</td>\n",
" <td>0.593262</td>\n",
" <td>11.0</td>\n",
" <td>Above</td>\n",
" <td>21</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>RIAU</td>\n",
" <td>West</td>\n",
" <td>0.191519</td>\n",
" <td>0.125554</td>\n",
" <td>0.060936</td>\n",
" <td>0.104750</td>\n",
" <td>0.068498</td>\n",
" <td>0.044904</td>\n",
" <td>0.596161</td>\n",
" <td>10.0</td>\n",
" <td>Above</td>\n",
" <td>14</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>NORTH KALIMANTAN</td>\n",
" <td>Central</td>\n",
" <td>0.179277</td>\n",
" <td>0.124658</td>\n",
" <td>0.133095</td>\n",
" <td>0.040594</td>\n",
" <td>0.083217</td>\n",
" <td>0.035963</td>\n",
" <td>0.596804</td>\n",
" <td>9.0</td>\n",
" <td>Above</td>\n",
" <td>65</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>SOUTHEAST SULAWESI</td>\n",
" <td>Central</td>\n",
" <td>0.199485</td>\n",
" <td>0.096840</td>\n",
" <td>0.070293</td>\n",
" <td>0.087865</td>\n",
" <td>0.117310</td>\n",
" <td>0.037360</td>\n",
" <td>0.609152</td>\n",
" <td>8.0</td>\n",
" <td>Above</td>\n",
" <td>74</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>EAST KALIMANTAN</td>\n",
" <td>Central</td>\n",
" <td>0.193620</td>\n",
" <td>0.138853</td>\n",
" <td>0.085336</td>\n",
" <td>0.116272</td>\n",
" <td>0.046547</td>\n",
" <td>0.032987</td>\n",
" <td>0.613614</td>\n",
" <td>7.0</td>\n",
" <td>Above</td>\n",
" <td>64</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>MALUKU</td>\n",
" <td>East</td>\n",
" <td>0.166540</td>\n",
" <td>0.082791</td>\n",
" <td>0.126111</td>\n",
" <td>0.109298</td>\n",
" <td>0.102882</td>\n",
" <td>0.028169</td>\n",
" <td>0.615790</td>\n",
" <td>6.0</td>\n",
" <td>Above</td>\n",
" <td>81</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>NORTH SULAWESI</td>\n",
" <td>Central</td>\n",
" <td>0.193532</td>\n",
" <td>0.115490</td>\n",
" <td>0.075847</td>\n",
" <td>0.080267</td>\n",
" <td>0.119573</td>\n",
" <td>0.042260</td>\n",
" <td>0.626969</td>\n",
" <td>5.0</td>\n",
" <td>Above</td>\n",
" <td>71</td>\n",
" </tr>\n",
" <tr>\n",
" <th>30</th>\n",
" <td>DI YOGYAKARTA</td>\n",
" <td>West</td>\n",
" <td>0.202914</td>\n",
" <td>0.102804</td>\n",
" <td>0.088724</td>\n",
" <td>0.176202</td>\n",
" <td>0.021254</td>\n",
" <td>0.035115</td>\n",
" <td>0.627013</td>\n",
" <td>4.0</td>\n",
" <td>Above</td>\n",
" <td>34</td>\n",
" </tr>\n",
" <tr>\n",
" <th>31</th>\n",
" <td>NORTH MALUKU</td>\n",
" <td>East</td>\n",
" <td>0.174165</td>\n",
" <td>0.106911</td>\n",
" <td>0.100701</td>\n",
" <td>0.083896</td>\n",
" <td>0.150799</td>\n",
" <td>0.019639</td>\n",
" <td>0.636111</td>\n",
" <td>3.0</td>\n",
" <td>Above</td>\n",
" <td>82</td>\n",
" </tr>\n",
" <tr>\n",
" <th>32</th>\n",
" <td>ACEH</td>\n",
" <td>West</td>\n",
" <td>0.201991</td>\n",
" <td>0.088058</td>\n",
" <td>0.111502</td>\n",
" <td>0.095218</td>\n",
" <td>0.094912</td>\n",
" <td>0.047016</td>\n",
" <td>0.638697</td>\n",
" <td>2.0</td>\n",
" <td>Above</td>\n",
" <td>11</td>\n",
" </tr>\n",
" <tr>\n",
" <th>33</th>\n",
" <td>DKI JAKARTA</td>\n",
" <td>West</td>\n",
" <td>0.200389</td>\n",
" <td>0.201341</td>\n",
" <td>0.115874</td>\n",
" <td>0.043900</td>\n",
" <td>0.089914</td>\n",
" <td>0.023593</td>\n",
" <td>0.675010</td>\n",
" <td>1.0</td>\n",
" <td>Above</td>\n",
" <td>31</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Province Region Factors 1 Factors 2 Factors 3 \\\n",
"0 PAPUA East 0.000000 0.075569 0.038739 \n",
"1 LAMPUNG West 0.219731 0.000000 0.185293 \n",
"2 EAST JAVA West 0.215459 0.035866 0.148661 \n",
"3 EAST NUSA TENGGARA Central 0.206942 0.036885 0.132883 \n",
"4 CENTRAL JAVA West 0.214510 0.080888 0.074647 \n",
"5 SOUTH SUMATERA West 0.202577 0.075395 0.080198 \n",
"6 WEST SULAWESI Central 0.194232 0.074546 0.049240 \n",
"7 WEST KALIMANTAN West 0.203563 0.118691 0.000000 \n",
"8 WEST JAVA West 0.214715 0.097048 0.075698 \n",
"9 NORTH SUMATERA West 0.177287 0.082816 0.137112 \n",
"10 BANGKA BELITUNG ISLAND West 0.225341 0.124547 0.041532 \n",
"11 WEST SUMATERA West 0.206013 0.053522 0.153202 \n",
"12 WEST NUSA TENGGARA Central 0.206955 0.069010 0.100905 \n",
"13 CENTRAL SULAWESI Central 0.184056 0.062294 0.121894 \n",
"14 GORONTALO Central 0.231925 0.088728 0.064246 \n",
"15 BANTEN West 0.201559 0.147797 0.043665 \n",
"16 SOUTH KALIMANTAN Central 0.220826 0.113231 0.056180 \n",
"17 BENGKULU West 0.203448 0.049227 0.124613 \n",
"18 WEST PAPUA East 0.159122 0.072640 0.159038 \n",
"19 SOUTH SULAWESI Central 0.224459 0.078474 0.058022 \n",
"20 BALI Central 0.189363 0.152312 0.117265 \n",
"21 CENTRAL KALIMANTAN West 0.192577 0.114370 0.026923 \n",
"22 JAMBI West 0.223554 0.058681 0.128134 \n",
"23 RIAU ISLAND West 0.175006 0.151281 0.154005 \n",
"24 RIAU West 0.191519 0.125554 0.060936 \n",
"25 NORTH KALIMANTAN Central 0.179277 0.124658 0.133095 \n",
"26 SOUTHEAST SULAWESI Central 0.199485 0.096840 0.070293 \n",
"27 EAST KALIMANTAN Central 0.193620 0.138853 0.085336 \n",
"28 MALUKU East 0.166540 0.082791 0.126111 \n",
"29 NORTH SULAWESI Central 0.193532 0.115490 0.075847 \n",
"30 DI YOGYAKARTA West 0.202914 0.102804 0.088724 \n",
"31 NORTH MALUKU East 0.174165 0.106911 0.100701 \n",
"32 ACEH West 0.201991 0.088058 0.111502 \n",
"33 DKI JAKARTA West 0.200389 0.201341 0.115874 \n",
"\n",
" Factors 4 Factors 5 Factors 6 Composite Index Rank Status Code \n",
"0 0.071085 0.030425 0.032620 0.248439 34.0 Below 91 \n",
"1 0.000000 0.025891 0.016747 0.447661 33.0 Below 18 \n",
"2 0.035949 0.000000 0.028245 0.464181 32.0 Below 35 \n",
"3 0.043058 0.052059 0.004209 0.476036 31.0 Below 53 \n",
"4 0.061868 0.016217 0.031978 0.480108 30.0 Below 33 \n",
"5 0.070232 0.028486 0.025473 0.482360 29.0 Below 16 \n",
"6 0.061333 0.081510 0.031177 0.492037 28.0 Below 76 \n",
"7 0.092369 0.068924 0.025336 0.508884 27.0 Below 61 \n",
"8 0.068674 0.025410 0.038431 0.519976 26.0 Below 32 \n",
"9 0.044351 0.042981 0.036276 0.520824 25.0 Below 12 \n",
"10 0.034218 0.069506 0.029348 0.524492 24.0 Below 19 \n",
"11 0.061361 0.033656 0.018639 0.526394 23.0 Below 13 \n",
"12 0.068254 0.067645 0.032576 0.545346 22.0 Below 52 \n",
"13 0.066592 0.082584 0.030146 0.547567 21.0 Below 72 \n",
"14 0.077924 0.085552 0.000000 0.548374 20.0 Below 75 \n",
"15 0.067148 0.047066 0.045426 0.552661 19.0 Above 36 \n",
"16 0.081443 0.058641 0.026962 0.557284 18.0 Above 63 \n",
"17 0.067338 0.089375 0.026782 0.560782 17.0 Above 17 \n",
"18 0.043183 0.116128 0.012252 0.562362 16.0 Above 92 \n",
"19 0.074847 0.088991 0.039850 0.564644 15.0 Above 73 \n",
"20 0.080574 0.004896 0.021164 0.565573 14.0 Above 51 \n",
"21 0.071344 0.109895 0.054440 0.569548 13.0 Above 62 \n",
"22 0.032835 0.110511 0.036768 0.590483 12.0 Above 15 \n",
"23 0.050418 0.038577 0.023975 0.593262 11.0 Above 21 \n",
"24 0.104750 0.068498 0.044904 0.596161 10.0 Above 14 \n",
"25 0.040594 0.083217 0.035963 0.596804 9.0 Above 65 \n",
"26 0.087865 0.117310 0.037360 0.609152 8.0 Above 74 \n",
"27 0.116272 0.046547 0.032987 0.613614 7.0 Above 64 \n",
"28 0.109298 0.102882 0.028169 0.615790 6.0 Above 81 \n",
"29 0.080267 0.119573 0.042260 0.626969 5.0 Above 71 \n",
"30 0.176202 0.021254 0.035115 0.627013 4.0 Above 34 \n",
"31 0.083896 0.150799 0.019639 0.636111 3.0 Above 82 \n",
"32 0.095218 0.094912 0.047016 0.638697 2.0 Above 11 \n",
"33 0.043900 0.089914 0.023593 0.675010 1.0 Above 31 "
]
},
"execution_count": 86,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Append the province's code\n",
"df_prov_code = df_index_reverse.merge(right = df[['Province', 'Code']], how = 'inner', on = 'Province')\n",
"df_prov_code"
]
},
{
"cell_type": "code",
"execution_count": 87,
"id": "purple-permission",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\ProgramData\\Anaconda3\\lib\\site-packages\\xlsxwriter\\workbook.py:329: UserWarning: Calling close() on already closed file.\n"
]
}
],
"source": [
"# Save the result\n",
"writer = pd.ExcelWriter('datasets/5 Indonesia Education Index - Result.xlsx')\n",
"df_prov_code.to_excel(writer, sheet_name = 'Composite Index', index = False)\n",
"writer.save()\n",
"writer.close()"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment