kiwamizamurai/PCA_part1.ipynb

## PCA_part1.ipynb
{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 今回使うデータ\n",
    "- 乳がんのデータ\n",
    "- ラベルは陰性・陽性の２つ\n",
    "- https://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_breast_cancer.html_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "from sklearn.datasets import load_breast_cancer\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 30次元のデータ"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "dict_keys(['feature_names', 'target', 'data', 'target_names', 'DESCR'])\n",
      "(569, 30)\n"
     ]
    }
   ],
   "source": [
    "cancer = load_breast_cancer()\n",
    "\n",
    "print(cancer.keys())\n",
    "print(cancer.data.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "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>mean radius</th>\n",
       "      <th>mean texture</th>\n",
       "      <th>mean perimeter</th>\n",
       "      <th>mean area</th>\n",
       "      <th>mean smoothness</th>\n",
       "      <th>mean compactness</th>\n",
       "      <th>mean concavity</th>\n",
       "      <th>mean concave points</th>\n",
       "      <th>mean symmetry</th>\n",
       "      <th>mean fractal dimension</th>\n",
       "      <th>...</th>\n",
       "      <th>worst radius</th>\n",
       "      <th>worst texture</th>\n",
       "      <th>worst perimeter</th>\n",
       "      <th>worst area</th>\n",
       "      <th>worst smoothness</th>\n",
       "      <th>worst compactness</th>\n",
       "      <th>worst concavity</th>\n",
       "      <th>worst concave points</th>\n",
       "      <th>worst symmetry</th>\n",
       "      <th>worst fractal dimension</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>17.99</td>\n",
       "      <td>10.38</td>\n",
       "      <td>122.80</td>\n",
       "      <td>1001.0</td>\n",
       "      <td>0.11840</td>\n",
       "      <td>0.27760</td>\n",
       "      <td>0.3001</td>\n",
       "      <td>0.14710</td>\n",
       "      <td>0.2419</td>\n",
       "      <td>0.07871</td>\n",
       "      <td>...</td>\n",
       "      <td>25.38</td>\n",
       "      <td>17.33</td>\n",
       "      <td>184.60</td>\n",
       "      <td>2019.0</td>\n",
       "      <td>0.1622</td>\n",
       "      <td>0.6656</td>\n",
       "      <td>0.7119</td>\n",
       "      <td>0.2654</td>\n",
       "      <td>0.4601</td>\n",
       "      <td>0.11890</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>20.57</td>\n",
       "      <td>17.77</td>\n",
       "      <td>132.90</td>\n",
       "      <td>1326.0</td>\n",
       "      <td>0.08474</td>\n",
       "      <td>0.07864</td>\n",
       "      <td>0.0869</td>\n",
       "      <td>0.07017</td>\n",
       "      <td>0.1812</td>\n",
       "      <td>0.05667</td>\n",
       "      <td>...</td>\n",
       "      <td>24.99</td>\n",
       "      <td>23.41</td>\n",
       "      <td>158.80</td>\n",
       "      <td>1956.0</td>\n",
       "      <td>0.1238</td>\n",
       "      <td>0.1866</td>\n",
       "      <td>0.2416</td>\n",
       "      <td>0.1860</td>\n",
       "      <td>0.2750</td>\n",
       "      <td>0.08902</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>19.69</td>\n",
       "      <td>21.25</td>\n",
       "      <td>130.00</td>\n",
       "      <td>1203.0</td>\n",
       "      <td>0.10960</td>\n",
       "      <td>0.15990</td>\n",
       "      <td>0.1974</td>\n",
       "      <td>0.12790</td>\n",
       "      <td>0.2069</td>\n",
       "      <td>0.05999</td>\n",
       "      <td>...</td>\n",
       "      <td>23.57</td>\n",
       "      <td>25.53</td>\n",
       "      <td>152.50</td>\n",
       "      <td>1709.0</td>\n",
       "      <td>0.1444</td>\n",
       "      <td>0.4245</td>\n",
       "      <td>0.4504</td>\n",
       "      <td>0.2430</td>\n",
       "      <td>0.3613</td>\n",
       "      <td>0.08758</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>11.42</td>\n",
       "      <td>20.38</td>\n",
       "      <td>77.58</td>\n",
       "      <td>386.1</td>\n",
       "      <td>0.14250</td>\n",
       "      <td>0.28390</td>\n",
       "      <td>0.2414</td>\n",
       "      <td>0.10520</td>\n",
       "      <td>0.2597</td>\n",
       "      <td>0.09744</td>\n",
       "      <td>...</td>\n",
       "      <td>14.91</td>\n",
       "      <td>26.50</td>\n",
       "      <td>98.87</td>\n",
       "      <td>567.7</td>\n",
       "      <td>0.2098</td>\n",
       "      <td>0.8663</td>\n",
       "      <td>0.6869</td>\n",
       "      <td>0.2575</td>\n",
       "      <td>0.6638</td>\n",
       "      <td>0.17300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>20.29</td>\n",
       "      <td>14.34</td>\n",
       "      <td>135.10</td>\n",
       "      <td>1297.0</td>\n",
       "      <td>0.10030</td>\n",
       "      <td>0.13280</td>\n",
       "      <td>0.1980</td>\n",
       "      <td>0.10430</td>\n",
       "      <td>0.1809</td>\n",
       "      <td>0.05883</td>\n",
       "      <td>...</td>\n",
       "      <td>22.54</td>\n",
       "      <td>16.67</td>\n",
       "      <td>152.20</td>\n",
       "      <td>1575.0</td>\n",
       "      <td>0.1374</td>\n",
       "      <td>0.2050</td>\n",
       "      <td>0.4000</td>\n",
       "      <td>0.1625</td>\n",
       "      <td>0.2364</td>\n",
       "      <td>0.07678</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 30 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   mean radius  mean texture  mean perimeter  mean area  mean smoothness  \\\n",
       "0        17.99         10.38          122.80     1001.0          0.11840   \n",
       "1        20.57         17.77          132.90     1326.0          0.08474   \n",
       "2        19.69         21.25          130.00     1203.0          0.10960   \n",
       "3        11.42         20.38           77.58      386.1          0.14250   \n",
       "4        20.29         14.34          135.10     1297.0          0.10030   \n",
       "\n",
       "   mean compactness  mean concavity  mean concave points  mean symmetry  \\\n",
       "0           0.27760          0.3001              0.14710         0.2419   \n",
       "1           0.07864          0.0869              0.07017         0.1812   \n",
       "2           0.15990          0.1974              0.12790         0.2069   \n",
       "3           0.28390          0.2414              0.10520         0.2597   \n",
       "4           0.13280          0.1980              0.10430         0.1809   \n",
       "\n",
       "   mean fractal dimension           ...             worst radius  \\\n",
       "0                 0.07871           ...                    25.38   \n",
       "1                 0.05667           ...                    24.99   \n",
       "2                 0.05999           ...                    23.57   \n",
       "3                 0.09744           ...                    14.91   \n",
       "4                 0.05883           ...                    22.54   \n",
       "\n",
       "   worst texture  worst perimeter  worst area  worst smoothness  \\\n",
       "0          17.33           184.60      2019.0            0.1622   \n",
       "1          23.41           158.80      1956.0            0.1238   \n",
       "2          25.53           152.50      1709.0            0.1444   \n",
       "3          26.50            98.87       567.7            0.2098   \n",
       "4          16.67           152.20      1575.0            0.1374   \n",
       "\n",
       "   worst compactness  worst concavity  worst concave points  worst symmetry  \\\n",
       "0             0.6656           0.7119                0.2654          0.4601   \n",
       "1             0.1866           0.2416                0.1860          0.2750   \n",
       "2             0.4245           0.4504                0.2430          0.3613   \n",
       "3             0.8663           0.6869                0.2575          0.6638   \n",
       "4             0.2050           0.4000                0.1625          0.2364   \n",
       "\n",
       "   worst fractal dimension  \n",
       "0                  0.11890  \n",
       "1                  0.08902  \n",
       "2                  0.08758  \n",
       "3                  0.17300  \n",
       "4                  0.07678  \n",
       "\n",
       "[5 rows x 30 columns]"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.DataFrame(cancer.data, columns=cancer.feature_names); df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "mean radius                False\n",
       "mean texture               False\n",
       "mean perimeter             False\n",
       "mean area                  False\n",
       "mean smoothness            False\n",
       "mean compactness           False\n",
       "mean concavity             False\n",
       "mean concave points        False\n",
       "mean symmetry              False\n",
       "mean fractal dimension     False\n",
       "radius error               False\n",
       "texture error              False\n",
       "perimeter error            False\n",
       "area error                 False\n",
       "smoothness error           False\n",
       "compactness error          False\n",
       "concavity error            False\n",
       "concave points error       False\n",
       "symmetry error             False\n",
       "fractal dimension error    False\n",
       "worst radius               False\n",
       "worst texture              False\n",
       "worst perimeter            False\n",
       "worst area                 False\n",
       "worst smoothness           False\n",
       "worst compactness          False\n",
       "worst concavity            False\n",
       "worst concave points       False\n",
       "worst symmetry             False\n",
       "worst fractal dimension    False\n",
       "dtype: bool"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().any()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "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>mean radius</th>\n",
       "      <th>mean texture</th>\n",
       "      <th>mean perimeter</th>\n",
       "      <th>mean area</th>\n",
       "      <th>mean smoothness</th>\n",
       "      <th>mean compactness</th>\n",
       "      <th>mean concavity</th>\n",
       "      <th>mean concave points</th>\n",
       "      <th>mean symmetry</th>\n",
       "      <th>mean fractal dimension</th>\n",
       "      <th>...</th>\n",
       "      <th>worst radius</th>\n",
       "      <th>worst texture</th>\n",
       "      <th>worst perimeter</th>\n",
       "      <th>worst area</th>\n",
       "      <th>worst smoothness</th>\n",
       "      <th>worst compactness</th>\n",
       "      <th>worst concavity</th>\n",
       "      <th>worst concave points</th>\n",
       "      <th>worst symmetry</th>\n",
       "      <th>worst fractal dimension</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>14.127292</td>\n",
       "      <td>19.289649</td>\n",
       "      <td>91.969033</td>\n",
       "      <td>654.889104</td>\n",
       "      <td>0.096360</td>\n",
       "      <td>0.104341</td>\n",
       "      <td>0.088799</td>\n",
       "      <td>0.048919</td>\n",
       "      <td>0.181162</td>\n",
       "      <td>0.062798</td>\n",
       "      <td>...</td>\n",
       "      <td>16.269190</td>\n",
       "      <td>25.677223</td>\n",
       "      <td>107.261213</td>\n",
       "      <td>880.583128</td>\n",
       "      <td>0.132369</td>\n",
       "      <td>0.254265</td>\n",
       "      <td>0.272188</td>\n",
       "      <td>0.114606</td>\n",
       "      <td>0.290076</td>\n",
       "      <td>0.083946</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>3.524049</td>\n",
       "      <td>4.301036</td>\n",
       "      <td>24.298981</td>\n",
       "      <td>351.914129</td>\n",
       "      <td>0.014064</td>\n",
       "      <td>0.052813</td>\n",
       "      <td>0.079720</td>\n",
       "      <td>0.038803</td>\n",
       "      <td>0.027414</td>\n",
       "      <td>0.007060</td>\n",
       "      <td>...</td>\n",
       "      <td>4.833242</td>\n",
       "      <td>6.146258</td>\n",
       "      <td>33.602542</td>\n",
       "      <td>569.356993</td>\n",
       "      <td>0.022832</td>\n",
       "      <td>0.157336</td>\n",
       "      <td>0.208624</td>\n",
       "      <td>0.065732</td>\n",
       "      <td>0.061867</td>\n",
       "      <td>0.018061</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>6.981000</td>\n",
       "      <td>9.710000</td>\n",
       "      <td>43.790000</td>\n",
       "      <td>143.500000</td>\n",
       "      <td>0.052630</td>\n",
       "      <td>0.019380</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.106000</td>\n",
       "      <td>0.049960</td>\n",
       "      <td>...</td>\n",
       "      <td>7.930000</td>\n",
       "      <td>12.020000</td>\n",
       "      <td>50.410000</td>\n",
       "      <td>185.200000</td>\n",
       "      <td>0.071170</td>\n",
       "      <td>0.027290</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.156500</td>\n",
       "      <td>0.055040</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>11.700000</td>\n",
       "      <td>16.170000</td>\n",
       "      <td>75.170000</td>\n",
       "      <td>420.300000</td>\n",
       "      <td>0.086370</td>\n",
       "      <td>0.064920</td>\n",
       "      <td>0.029560</td>\n",
       "      <td>0.020310</td>\n",
       "      <td>0.161900</td>\n",
       "      <td>0.057700</td>\n",
       "      <td>...</td>\n",
       "      <td>13.010000</td>\n",
       "      <td>21.080000</td>\n",
       "      <td>84.110000</td>\n",
       "      <td>515.300000</td>\n",
       "      <td>0.116600</td>\n",
       "      <td>0.147200</td>\n",
       "      <td>0.114500</td>\n",
       "      <td>0.064930</td>\n",
       "      <td>0.250400</td>\n",
       "      <td>0.071460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>13.370000</td>\n",
       "      <td>18.840000</td>\n",
       "      <td>86.240000</td>\n",
       "      <td>551.100000</td>\n",
       "      <td>0.095870</td>\n",
       "      <td>0.092630</td>\n",
       "      <td>0.061540</td>\n",
       "      <td>0.033500</td>\n",
       "      <td>0.179200</td>\n",
       "      <td>0.061540</td>\n",
       "      <td>...</td>\n",
       "      <td>14.970000</td>\n",
       "      <td>25.410000</td>\n",
       "      <td>97.660000</td>\n",
       "      <td>686.500000</td>\n",
       "      <td>0.131300</td>\n",
       "      <td>0.211900</td>\n",
       "      <td>0.226700</td>\n",
       "      <td>0.099930</td>\n",
       "      <td>0.282200</td>\n",
       "      <td>0.080040</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>15.780000</td>\n",
       "      <td>21.800000</td>\n",
       "      <td>104.100000</td>\n",
       "      <td>782.700000</td>\n",
       "      <td>0.105300</td>\n",
       "      <td>0.130400</td>\n",
       "      <td>0.130700</td>\n",
       "      <td>0.074000</td>\n",
       "      <td>0.195700</td>\n",
       "      <td>0.066120</td>\n",
       "      <td>...</td>\n",
       "      <td>18.790000</td>\n",
       "      <td>29.720000</td>\n",
       "      <td>125.400000</td>\n",
       "      <td>1084.000000</td>\n",
       "      <td>0.146000</td>\n",
       "      <td>0.339100</td>\n",
       "      <td>0.382900</td>\n",
       "      <td>0.161400</td>\n",
       "      <td>0.317900</td>\n",
       "      <td>0.092080</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>28.110000</td>\n",
       "      <td>39.280000</td>\n",
       "      <td>188.500000</td>\n",
       "      <td>2501.000000</td>\n",
       "      <td>0.163400</td>\n",
       "      <td>0.345400</td>\n",
       "      <td>0.426800</td>\n",
       "      <td>0.201200</td>\n",
       "      <td>0.304000</td>\n",
       "      <td>0.097440</td>\n",
       "      <td>...</td>\n",
       "      <td>36.040000</td>\n",
       "      <td>49.540000</td>\n",
       "      <td>251.200000</td>\n",
       "      <td>4254.000000</td>\n",
       "      <td>0.222600</td>\n",
       "      <td>1.058000</td>\n",
       "      <td>1.252000</td>\n",
       "      <td>0.291000</td>\n",
       "      <td>0.663800</td>\n",
       "      <td>0.207500</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 30 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       mean radius  mean texture  mean perimeter    mean area  \\\n",
       "count   569.000000    569.000000      569.000000   569.000000   \n",
       "mean     14.127292     19.289649       91.969033   654.889104   \n",
       "std       3.524049      4.301036       24.298981   351.914129   \n",
       "min       6.981000      9.710000       43.790000   143.500000   \n",
       "25%      11.700000     16.170000       75.170000   420.300000   \n",
       "50%      13.370000     18.840000       86.240000   551.100000   \n",
       "75%      15.780000     21.800000      104.100000   782.700000   \n",
       "max      28.110000     39.280000      188.500000  2501.000000   \n",
       "\n",
       "       mean smoothness  mean compactness  mean concavity  mean concave points  \\\n",
       "count       569.000000        569.000000      569.000000           569.000000   \n",
       "mean          0.096360          0.104341        0.088799             0.048919   \n",
       "std           0.014064          0.052813        0.079720             0.038803   \n",
       "min           0.052630          0.019380        0.000000             0.000000   \n",
       "25%           0.086370          0.064920        0.029560             0.020310   \n",
       "50%           0.095870          0.092630        0.061540             0.033500   \n",
       "75%           0.105300          0.130400        0.130700             0.074000   \n",
       "max           0.163400          0.345400        0.426800             0.201200   \n",
       "\n",
       "       mean symmetry  mean fractal dimension           ...             \\\n",
       "count     569.000000              569.000000           ...              \n",
       "mean        0.181162                0.062798           ...              \n",
       "std         0.027414                0.007060           ...              \n",
       "min         0.106000                0.049960           ...              \n",
       "25%         0.161900                0.057700           ...              \n",
       "50%         0.179200                0.061540           ...              \n",
       "75%         0.195700                0.066120           ...              \n",
       "max         0.304000                0.097440           ...              \n",
       "\n",
       "       worst radius  worst texture  worst perimeter   worst area  \\\n",
       "count    569.000000     569.000000       569.000000   569.000000   \n",
       "mean      16.269190      25.677223       107.261213   880.583128   \n",
       "std        4.833242       6.146258        33.602542   569.356993   \n",
       "min        7.930000      12.020000        50.410000   185.200000   \n",
       "25%       13.010000      21.080000        84.110000   515.300000   \n",
       "50%       14.970000      25.410000        97.660000   686.500000   \n",
       "75%       18.790000      29.720000       125.400000  1084.000000   \n",
       "max       36.040000      49.540000       251.200000  4254.000000   \n",
       "\n",
       "       worst smoothness  worst compactness  worst concavity  \\\n",
       "count        569.000000         569.000000       569.000000   \n",
       "mean           0.132369           0.254265         0.272188   \n",
       "std            0.022832           0.157336         0.208624   \n",
       "min            0.071170           0.027290         0.000000   \n",
       "25%            0.116600           0.147200         0.114500   \n",
       "50%            0.131300           0.211900         0.226700   \n",
       "75%            0.146000           0.339100         0.382900   \n",
       "max            0.222600           1.058000         1.252000   \n",
       "\n",
       "       worst concave points  worst symmetry  worst fractal dimension  \n",
       "count            569.000000      569.000000               569.000000  \n",
       "mean               0.114606        0.290076                 0.083946  \n",
       "std                0.065732        0.061867                 0.018061  \n",
       "min                0.000000        0.156500                 0.055040  \n",
       "25%                0.064930        0.250400                 0.071460  \n",
       "50%                0.099930        0.282200                 0.080040  \n",
       "75%                0.161400        0.317900                 0.092080  \n",
       "max                0.291000        0.663800                 0.207500  \n",
       "\n",
       "[8 rows x 30 columns]"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1173f1ba8>"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 792x648 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "corr = df.corr()\n",
    "# Generate a mask for the upper triangle\n",
    "mask = np.zeros_like(corr, dtype=np.bool)\n",
    "mask[np.triu_indices_from(mask)] = True\n",
    "\n",
    "# Set up the matplotlib figure\n",
    "f, ax = plt.subplots(figsize=(11, 9))\n",
    "\n",
    "# Draw the heatmap with the mask and correct aspect ratio\n",
    "sns.heatmap(corr, mask=mask, vmax=.8, center=0,\n",
    "            square=True, linewidths=.5, cbar_kws={\"shrink\": .5})"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 標準化する\n",
    "\n",
    "分散を1にする必要はないがセンタリングは必須である。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import StandardScaler\n",
    "ss = StandardScaler()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "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>mean radius</th>\n",
       "      <th>mean texture</th>\n",
       "      <th>mean perimeter</th>\n",
       "      <th>mean area</th>\n",
       "      <th>mean smoothness</th>\n",
       "      <th>mean compactness</th>\n",
       "      <th>mean concavity</th>\n",
       "      <th>mean concave points</th>\n",
       "      <th>mean symmetry</th>\n",
       "      <th>mean fractal dimension</th>\n",
       "      <th>...</th>\n",
       "      <th>worst radius</th>\n",
       "      <th>worst texture</th>\n",
       "      <th>worst perimeter</th>\n",
       "      <th>worst area</th>\n",
       "      <th>worst smoothness</th>\n",
       "      <th>worst compactness</th>\n",
       "      <th>worst concavity</th>\n",
       "      <th>worst concave points</th>\n",
       "      <th>worst symmetry</th>\n",
       "      <th>worst fractal dimension</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>5.690000e+02</td>\n",
       "      <td>5.690000e+02</td>\n",
       "      <td>5.690000e+02</td>\n",
       "      <td>5.690000e+02</td>\n",
       "      <td>5.690000e+02</td>\n",
       "      <td>5.690000e+02</td>\n",
       "      <td>5.690000e+02</td>\n",
       "      <td>5.690000e+02</td>\n",
       "      <td>5.690000e+02</td>\n",
       "      <td>5.690000e+02</td>\n",
       "      <td>...</td>\n",
       "      <td>5.690000e+02</td>\n",
       "      <td>5.690000e+02</td>\n",
       "      <td>5.690000e+02</td>\n",
       "      <td>5.690000e+02</td>\n",
       "      <td>5.690000e+02</td>\n",
       "      <td>5.690000e+02</td>\n",
       "      <td>5.690000e+02</td>\n",
       "      <td>5.690000e+02</td>\n",
       "      <td>5.690000e+02</td>\n",
       "      <td>5.690000e+02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>-3.162867e-15</td>\n",
       "      <td>-6.530609e-15</td>\n",
       "      <td>-7.078891e-16</td>\n",
       "      <td>-8.799835e-16</td>\n",
       "      <td>6.132177e-15</td>\n",
       "      <td>-1.120369e-15</td>\n",
       "      <td>-4.421380e-16</td>\n",
       "      <td>9.732500e-16</td>\n",
       "      <td>-1.971670e-15</td>\n",
       "      <td>-1.453631e-15</td>\n",
       "      <td>...</td>\n",
       "      <td>-2.333224e-15</td>\n",
       "      <td>1.763674e-15</td>\n",
       "      <td>-1.198026e-15</td>\n",
       "      <td>5.049661e-16</td>\n",
       "      <td>-5.213170e-15</td>\n",
       "      <td>-2.174788e-15</td>\n",
       "      <td>6.856456e-16</td>\n",
       "      <td>-1.412656e-16</td>\n",
       "      <td>-2.289567e-15</td>\n",
       "      <td>2.575171e-15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>1.000880e+00</td>\n",
       "      <td>1.000880e+00</td>\n",
       "      <td>1.000880e+00</td>\n",
       "      <td>1.000880e+00</td>\n",
       "      <td>1.000880e+00</td>\n",
       "      <td>1.000880e+00</td>\n",
       "      <td>1.000880e+00</td>\n",
       "      <td>1.000880e+00</td>\n",
       "      <td>1.000880e+00</td>\n",
       "      <td>1.000880e+00</td>\n",
       "      <td>...</td>\n",
       "      <td>1.000880e+00</td>\n",
       "      <td>1.000880e+00</td>\n",
       "      <td>1.000880e+00</td>\n",
       "      <td>1.000880e+00</td>\n",
       "      <td>1.000880e+00</td>\n",
       "      <td>1.000880e+00</td>\n",
       "      <td>1.000880e+00</td>\n",
       "      <td>1.000880e+00</td>\n",
       "      <td>1.000880e+00</td>\n",
       "      <td>1.000880e+00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>-2.029648e+00</td>\n",
       "      <td>-2.229249e+00</td>\n",
       "      <td>-1.984504e+00</td>\n",
       "      <td>-1.454443e+00</td>\n",
       "      <td>-3.112085e+00</td>\n",
       "      <td>-1.610136e+00</td>\n",
       "      <td>-1.114873e+00</td>\n",
       "      <td>-1.261820e+00</td>\n",
       "      <td>-2.744117e+00</td>\n",
       "      <td>-1.819865e+00</td>\n",
       "      <td>...</td>\n",
       "      <td>-1.726901e+00</td>\n",
       "      <td>-2.223994e+00</td>\n",
       "      <td>-1.693361e+00</td>\n",
       "      <td>-1.222423e+00</td>\n",
       "      <td>-2.682695e+00</td>\n",
       "      <td>-1.443878e+00</td>\n",
       "      <td>-1.305831e+00</td>\n",
       "      <td>-1.745063e+00</td>\n",
       "      <td>-2.160960e+00</td>\n",
       "      <td>-1.601839e+00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>-6.893853e-01</td>\n",
       "      <td>-7.259631e-01</td>\n",
       "      <td>-6.919555e-01</td>\n",
       "      <td>-6.671955e-01</td>\n",
       "      <td>-7.109628e-01</td>\n",
       "      <td>-7.470860e-01</td>\n",
       "      <td>-7.437479e-01</td>\n",
       "      <td>-7.379438e-01</td>\n",
       "      <td>-7.032397e-01</td>\n",
       "      <td>-7.226392e-01</td>\n",
       "      <td>...</td>\n",
       "      <td>-6.749213e-01</td>\n",
       "      <td>-7.486293e-01</td>\n",
       "      <td>-6.895783e-01</td>\n",
       "      <td>-6.421359e-01</td>\n",
       "      <td>-6.912304e-01</td>\n",
       "      <td>-6.810833e-01</td>\n",
       "      <td>-7.565142e-01</td>\n",
       "      <td>-7.563999e-01</td>\n",
       "      <td>-6.418637e-01</td>\n",
       "      <td>-6.919118e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>-2.150816e-01</td>\n",
       "      <td>-1.046362e-01</td>\n",
       "      <td>-2.359800e-01</td>\n",
       "      <td>-2.951869e-01</td>\n",
       "      <td>-3.489108e-02</td>\n",
       "      <td>-2.219405e-01</td>\n",
       "      <td>-3.422399e-01</td>\n",
       "      <td>-3.977212e-01</td>\n",
       "      <td>-7.162650e-02</td>\n",
       "      <td>-1.782793e-01</td>\n",
       "      <td>...</td>\n",
       "      <td>-2.690395e-01</td>\n",
       "      <td>-4.351564e-02</td>\n",
       "      <td>-2.859802e-01</td>\n",
       "      <td>-3.411812e-01</td>\n",
       "      <td>-4.684277e-02</td>\n",
       "      <td>-2.695009e-01</td>\n",
       "      <td>-2.182321e-01</td>\n",
       "      <td>-2.234689e-01</td>\n",
       "      <td>-1.274095e-01</td>\n",
       "      <td>-2.164441e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>4.693926e-01</td>\n",
       "      <td>5.841756e-01</td>\n",
       "      <td>4.996769e-01</td>\n",
       "      <td>3.635073e-01</td>\n",
       "      <td>6.361990e-01</td>\n",
       "      <td>4.938569e-01</td>\n",
       "      <td>5.260619e-01</td>\n",
       "      <td>6.469351e-01</td>\n",
       "      <td>5.307792e-01</td>\n",
       "      <td>4.709834e-01</td>\n",
       "      <td>...</td>\n",
       "      <td>5.220158e-01</td>\n",
       "      <td>6.583411e-01</td>\n",
       "      <td>5.402790e-01</td>\n",
       "      <td>3.575891e-01</td>\n",
       "      <td>5.975448e-01</td>\n",
       "      <td>5.396688e-01</td>\n",
       "      <td>5.311411e-01</td>\n",
       "      <td>7.125100e-01</td>\n",
       "      <td>4.501382e-01</td>\n",
       "      <td>4.507624e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>3.971288e+00</td>\n",
       "      <td>4.651889e+00</td>\n",
       "      <td>3.976130e+00</td>\n",
       "      <td>5.250529e+00</td>\n",
       "      <td>4.770911e+00</td>\n",
       "      <td>4.568425e+00</td>\n",
       "      <td>4.243589e+00</td>\n",
       "      <td>3.927930e+00</td>\n",
       "      <td>4.484751e+00</td>\n",
       "      <td>4.910919e+00</td>\n",
       "      <td>...</td>\n",
       "      <td>4.094189e+00</td>\n",
       "      <td>3.885905e+00</td>\n",
       "      <td>4.287337e+00</td>\n",
       "      <td>5.930172e+00</td>\n",
       "      <td>3.955374e+00</td>\n",
       "      <td>5.112877e+00</td>\n",
       "      <td>4.700669e+00</td>\n",
       "      <td>2.685877e+00</td>\n",
       "      <td>6.046041e+00</td>\n",
       "      <td>6.846856e+00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 30 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        mean radius  mean texture  mean perimeter     mean area  \\\n",
       "count  5.690000e+02  5.690000e+02    5.690000e+02  5.690000e+02   \n",
       "mean  -3.162867e-15 -6.530609e-15   -7.078891e-16 -8.799835e-16   \n",
       "std    1.000880e+00  1.000880e+00    1.000880e+00  1.000880e+00   \n",
       "min   -2.029648e+00 -2.229249e+00   -1.984504e+00 -1.454443e+00   \n",
       "25%   -6.893853e-01 -7.259631e-01   -6.919555e-01 -6.671955e-01   \n",
       "50%   -2.150816e-01 -1.046362e-01   -2.359800e-01 -2.951869e-01   \n",
       "75%    4.693926e-01  5.841756e-01    4.996769e-01  3.635073e-01   \n",
       "max    3.971288e+00  4.651889e+00    3.976130e+00  5.250529e+00   \n",
       "\n",
       "       mean smoothness  mean compactness  mean concavity  mean concave points  \\\n",
       "count     5.690000e+02      5.690000e+02    5.690000e+02         5.690000e+02   \n",
       "mean      6.132177e-15     -1.120369e-15   -4.421380e-16         9.732500e-16   \n",
       "std       1.000880e+00      1.000880e+00    1.000880e+00         1.000880e+00   \n",
       "min      -3.112085e+00     -1.610136e+00   -1.114873e+00        -1.261820e+00   \n",
       "25%      -7.109628e-01     -7.470860e-01   -7.437479e-01        -7.379438e-01   \n",
       "50%      -3.489108e-02     -2.219405e-01   -3.422399e-01        -3.977212e-01   \n",
       "75%       6.361990e-01      4.938569e-01    5.260619e-01         6.469351e-01   \n",
       "max       4.770911e+00      4.568425e+00    4.243589e+00         3.927930e+00   \n",
       "\n",
       "       mean symmetry  mean fractal dimension           ...             \\\n",
       "count   5.690000e+02            5.690000e+02           ...              \n",
       "mean   -1.971670e-15           -1.453631e-15           ...              \n",
       "std     1.000880e+00            1.000880e+00           ...              \n",
       "min    -2.744117e+00           -1.819865e+00           ...              \n",
       "25%    -7.032397e-01           -7.226392e-01           ...              \n",
       "50%    -7.162650e-02           -1.782793e-01           ...              \n",
       "75%     5.307792e-01            4.709834e-01           ...              \n",
       "max     4.484751e+00            4.910919e+00           ...              \n",
       "\n",
       "       worst radius  worst texture  worst perimeter    worst area  \\\n",
       "count  5.690000e+02   5.690000e+02     5.690000e+02  5.690000e+02   \n",
       "mean  -2.333224e-15   1.763674e-15    -1.198026e-15  5.049661e-16   \n",
       "std    1.000880e+00   1.000880e+00     1.000880e+00  1.000880e+00   \n",
       "min   -1.726901e+00  -2.223994e+00    -1.693361e+00 -1.222423e+00   \n",
       "25%   -6.749213e-01  -7.486293e-01    -6.895783e-01 -6.421359e-01   \n",
       "50%   -2.690395e-01  -4.351564e-02    -2.859802e-01 -3.411812e-01   \n",
       "75%    5.220158e-01   6.583411e-01     5.402790e-01  3.575891e-01   \n",
       "max    4.094189e+00   3.885905e+00     4.287337e+00  5.930172e+00   \n",
       "\n",
       "       worst smoothness  worst compactness  worst concavity  \\\n",
       "count      5.690000e+02       5.690000e+02     5.690000e+02   \n",
       "mean      -5.213170e-15      -2.174788e-15     6.856456e-16   \n",
       "std        1.000880e+00       1.000880e+00     1.000880e+00   \n",
       "min       -2.682695e+00      -1.443878e+00    -1.305831e+00   \n",
       "25%       -6.912304e-01      -6.810833e-01    -7.565142e-01   \n",
       "50%       -4.684277e-02      -2.695009e-01    -2.182321e-01   \n",
       "75%        5.975448e-01       5.396688e-01     5.311411e-01   \n",
       "max        3.955374e+00       5.112877e+00     4.700669e+00   \n",
       "\n",
       "       worst concave points  worst symmetry  worst fractal dimension  \n",
       "count          5.690000e+02    5.690000e+02             5.690000e+02  \n",
       "mean          -1.412656e-16   -2.289567e-15             2.575171e-15  \n",
       "std            1.000880e+00    1.000880e+00             1.000880e+00  \n",
       "min           -1.745063e+00   -2.160960e+00            -1.601839e+00  \n",
       "25%           -7.563999e-01   -6.418637e-01            -6.919118e-01  \n",
       "50%           -2.234689e-01   -1.274095e-01            -2.164441e-01  \n",
       "75%            7.125100e-01    4.501382e-01             4.507624e-01  \n",
       "max            2.685877e+00    6.046041e+00             6.846856e+00  \n",
       "\n",
       "[8 rows x 30 columns]"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dfs = pd.DataFrame(ss.fit_transform(cancer.data), columns=cancer.feature_names)\n",
    "dfs.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 自力のPCA\n",
    "\n",
    "- 共分散行列を求めて固有値、固有ベクトルを計算する\n",
    "\n",
    "(cancer.data.shape[0]-1)としているのは次の共分散行列の定義による。\n",
    "- https://en.wikipedia.org/wiki/Estimation_of_covariance_matrices\n",
    "\n",
    "$$ \\Sigma = \\frac{1}{N-1} \\sum_{i}^{N} (x_i - \\bar{x}) (x_i - \\bar{x})^T  $$\n",
    "ただし$x$は縦ベクトル\n",
    "\n",
    "(プログラムを書くときは基本データは横ベクトルとなっているのでそこだけ注意したい)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [],
   "source": [
    "scatter_matrix = np.dot(dfs.T, dfs)/(cancer.data.shape[0]-1)\n",
    "la, v = np.linalg.eig(scatter_matrix)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "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>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>13.304991</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>5.701375</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2.822910</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1.984128</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.651633</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           0\n",
       "0  13.304991\n",
       "1   5.701375\n",
       "2   2.822910\n",
       "3   1.984128\n",
       "4   1.651633"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.DataFrame(la).head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 今回は2次元に落として可視化する。\n",
    "\n",
    "よって固有値を大きい方から２つ選び、それに対応する固有ベクトルを縦に並べた射影行列を作る   \n",
    "射影は固有ベクトルとデータの内積を計算するので\n",
    "- 各データ:　　　横ベクトル\n",
    "- 固有ベクトル:　縦ベクトル\n",
    "\n",
    "という形に注意するとnp.dot(dfs, proj)かnp.dot(proj.T, dfs.T).Tと射影すればよいことがわかる。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(569, 2)"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "proj = v[:,0:2]\n",
    "red = np.dot(dfs, proj)\n",
    "red.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.legend.Legend at 0x1a26714d30>"
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAr0AAAFyCAYAAAD4cmIkAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMi4yLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvhp/UCwAAIABJREFUeJzs3Xl8XNWVL/rfrkFVpalkS7Iky5OYZYQhjs3gBAeSACY8J5B0gHQSQj7hOdMlaTqBDu/eznTfDelOXujGuZCQ0Nwkl+4mhOHGAZspgE0YYhmwEcgTnmRZki3ZKk1VpRr2+2PVqUk1qqpUqtLv+/noI+mo6px9TsnWqnXWXltprUFEREREVM5MxR4AEREREVGhMeglIiIiorLHoJeIiIiIyh6DXiIiIiIqewx6iYiIiKjsMeglIiIiorLHoJeIiIiIyh6DXiKa05RSNyul3lZKTSil+pVS9yml6qJ+/n2llE8pNaaUGlZKvaKUuiTq55cppYKhn0d/XJLkeIeUUgNKqaqobbcopV6M+l4ppW5XSu1TSrmVUkeUUj9WStlSnMeLSilP6NiDSqnHlFItUT+/UCn1VOgcTiql/qqU+mLcPtpC53Jv1heSiGiWY9BLRHOWUupbAP4JwO0AnAAuBrAUwLNKqYqohz6sta4G0ADgBQCPxO3qmNa6Ou7j1RSHtgD4Zoqf3wNgA4CbANQAuBrAhwH8Ps0p/ZfQOM8CUAfg7tB5XgLgzwBeAnAGgHoAXw3tN9pNAE4BuDFVgE1EVIoY9BLRnKSUqgXwAwC3aq23aK19WutDAK6HBL6fi3+O1toP4CEArUqpxhwO/xMA347OKEeN60wAXwPwWa31q1prv9b6HQCfArBOKfXhdDvXWp8E8CiAjqjj/UZr/U9a60Etdmitr4976k0A/hsAH4D10z47IqJZiEEvEc1VawDYATwWvVFrPQZgM4Ar4p8Qyv7eBGAIkhGdrk4ALwL4doKffQTAUa31X+PG1QPgtUTjSjDOBkiQ/KZSqhLAJQD+kOY5lwJYBOA/IRnlm9KeBRFRCWHQS0RzVQOAwVD2Nl5f6OeG65VSwwDcAP5vAH8T97yFoVrZ6I8qpPZdALcmyBg3hI6fSPy44t0TGufO0GP/HsA8yP/1yfZp+AKAzVrrUwD+HcDVSqkFaZ5DRFQyGPQS0Vw1CKBBKWVJ8LOW0M8Nv9da1wFoAtAF4P1xjz+mta6L+xhPdXCtdReAPwH4ToJxtUx9RsJxxftG6NitWuvPaq1PQDLSwRT7hFLKAeDTkNINhOqRjwD421TnQERUShj0EtFc9SoAL4BPRm8MZWivBvB8/BO01oMAvgzg+9GdEXLwPUjmuDVq258BLFZKXRg3rsWQiXZTxpWK1noCcq6fSvGw6wDUArg31MGiPzQmljgQUdlg0EtEc5LW2gWZyLZRKbVOKWVVSi2DdGY4CuB3SZ63G8DTAO7Iwxj2A3gYwDeitu0F8AsADymlLlZKmZVS50Impj2ntX5uGoe6A8DNoTZo9QCglDpfKfWfoZ9/AcC/ATgPwAWhjw8AuEApdd40T4+IaFZh0EtEc5bW+p8B/D8AfgpgBMDrAHoAfERr7U3x1J8A2BBV87owQZ/eVJnVaD8EEF//+18A/BrA/wYwBmALZOJbpvuMobV+BdLy7MMADiilTgK4H8BTSqlWyOS5f9Fa90d97Agd9wvTOSYR0WyjtNbFHgMRERERUUEx00tEREREZY9BLxERERGVPQa9RERERFT2GPQSERERUdlj0EtEREREZS/RSkQ5a2ho0MuWLSvEromIiIiIwnbs2DGotY5f0n2KggS9y5YtQ2dnZyF2TUREREQUppQ6nMnjWN5ARERERGWPQS8RERERlT0GvURERERU9gpS00tEREREsXw+H44ePQqPx1PsoZQku92ORYsWwWq1Tuv5DHqJiIiIZsDRo0dRU1ODZcuWQSlV7OGUFK01hoaGcPToUbS1tU1rHyxvICIiIpoBHo8H9fX1DHinQSmF+vr6nLLkDHqJiIiIZggD3unL9dox6CUiIiKaI5RS+Na3vhX+/qc//Sm+//3v5/04P/rRj2K+X7NmTd6PkS0GvURERERzhM1mw2OPPYbBwcGCHic+6H3llVcKerxMMOglIiIimoW6+1y4+9m9+PYjO3H3s3vR3efKeZ8WiwUbNmzA3XffPeVnJ06cwKc+9SmsXr0aq1evxl/+8pfw9iuuuAIrV67El7/8ZSxdujQcNF977bV4//vfj3PPPRf3338/AOA73/kO3G43LrjgAnz2s58FAFRXVwMAbrjhBjz11FPhY95888149NFHEQgEcPvtt2P16tVYsWIFfvnLX+Z8rvEY9BIRERHNMt19Lty/9SBcbh9anHa43D7cv/VgXgLfr3/963jooYfgcsXu65vf/CZuu+02bN++HY8++ihuueUWAMAPfvADfPjDH8Ybb7yB6667DkeOHAk/59/+7d+wY8cOdHZ24p577sHQ0BB+/OMfw+Fw4K233sJDDz0Uc4wbb7wRDz/8MABgcnISzz//PD72sY/hgQcegNPpxPbt27F9+3b86le/wsGDB3M+12hsWUZEREQ0y2zpGoDTYYXTIT1pjc9bugbQ3uLMad+1tbW46aabcM8998DhcIS3P/fcc3j33XfD34+MjGB0dBQvv/wyHn/8cQDAunXrMG/evPBj7rnnnvDPenp6sG/fPtTX1yc99tVXX41vfOMb8Hq92LJlC9auXQuHw4FnnnkGu3btwh/+8AcAgMvlwr59+6bdniwRBr1ERJS7/i6gexPg6gGci4H29UBzR7FHRVSyeofdaHHaY7bV2C3oHXbnZf9/93d/h5UrV+KLX/xieFswGMSrr74aEwgD0iM3kRdffBHPPfccXn31VVRWVuKyyy5L21LMbrfjsssuw9NPP42HH34Yn/nMZ8LH2LhxI6666qoczyw5ljcQEVFu+ruAVzYC7mGgtlU+v7JRthPRtLTWOTDq8cdsG/X40VrnSPKM7MyfPx/XX389HnjggfC2K6+8Ej//+c/D37/11lsAgA9+8IP4/e9/DwB45plncOrUKQCSjZ03bx4qKyuxe/duvPbaa+HnWq1W+Hy+hMe+8cYb8eCDD2Lbtm3hIPeqq67CfffdF37O3r17MT4+npdzNTDoJSKi3HRvAux1gKMOUCb5bK+T7UQ0Les6muBy++By+xDUOvz1uo6mvB3jW9/6VkwXh3vuuQednZ1YsWIFli9fjl/84hcAgO9973t45plnsHLlSmzevBktLS2oqanBunXr4Pf7sWLFCvzjP/4jLr744vC+NmzYgBUrVoQnskW78sorsXXrVnz0ox9FRUUFAOCWW27B8uXLsXLlSnR0dODLX/4y/H7/lOfmQiVLWedi1apVurOzM+/7JSKiWeiJr0mGV0XlUXQQGOkFrr23eOMimmW6u7vR3t6e+eP7XNjSNYDeYTda6xxY19GUcz3vdHi9XpjNZlgsFrz66qv46le/Gs4Cz7RE11AptUNrvSrdc1nTS0REuXEulpIGR11km2dEthPRtLW3OIsS5MY7cuQIrr/+egSDQVRUVOBXv/pVsYc0LQx6iYgoN+3rpYYXAOy1EvB6hoGVny/uuIgoL84880y8+eabxR5GzljTS0REuWnuANbcKpnekV75vOZWdm8golmFmV4iIspdcweDXCKa1ZjpJSIiIqKyx6CXiIiIiMoeg14iIiKiOcJsNuOCCy5AR0cHPv3pT2NiYiLrfdxyyy3h5Yp/9KMfxfxszZo1eRlnITDoJSIiIpojHA4H3nrrLXR1daGioiK8AEU2fv3rX2P58uUApga9r7zySl7GWQgMeomIiIhmo/4u4IW7ZAGYF+7K+9Lel156Kfbv3w8A+NnPfoaOjg50dHTgX/7lXwAA4+PjuOaaa3D++eejo6MDDz/8MADgsssuQ2dnJ77zne/A7XbjggsuCK+8Vl1dDQC44YYb8NRTT4WPdfPNN+PRRx9FIBDA7bffjtWrV2PFihX45S9/mddzSoXdG4iIiIhmm/4u6X9tr5MVD93D8n2e2gH6/X5s3rwZ69atw44dO/Dggw/i9ddfh9YaF110ET70oQ/hwIEDWLhwIZ588kkAgMvlitnHj3/8Y/z85z9PuDrbjTfeiIcffhgf+9jHMDk5ieeffx733XcfHnjgATidTmzfvh1erxcf+MAHcOWVV6KtrS3nc0qHmV4iIiKi2aZ7kwS8jjpZ4ttRJ993b8ppt0ZmdtWqVViyZAm+9KUv4eWXX8Z1112HqqoqVFdX45Of/CS2bduG8847D8899xz+4R/+Adu2bYPTmfnqcFdffTX+/Oc/w+v1YvPmzVi7di0cDgeeeeYZ/Pa3v8UFF1yAiy66CENDQ9i3b19O55QpZnqJiIiIZhtXj2R4o9lrZXsOjJreaFrrhI8966yzsGPHDjz11FO48847ceWVV+K73/1uRsex2+247LLL8PTTT+Phhx/GZz7zmfCxNm7ciKuuuiqn85gOZnqJiIiIZhvnYlnSO5pnRLbn2dq1a/HEE09gYmIC4+PjePzxx3HppZfi2LFjqKysxOc+9zl8+9vfxhtvvDHluVarFT6fL+F+b7zxRjz44IPYtm1bOMi96qqrcN9994Wfs3fvXoyPj+f9nBJhppeIiIhotmlfLzW8gGR4PSOAZxhY+fm8H2rlypW4+eabceGFFwKQlmTve9/78PTTT+P222+HyWSC1WrFfffdN+W5GzZswIoVK7By5Uo89NBDMT+78sorcdNNN+HjH/84Kioqwvs+dOgQVq5cCa01Ghsb8cQTT+T9nBJRyVLauVi1apXu7OzM+36JiIiISlV3dzfa29szf0J/l9Twunokw9u+fs4v953oGiqldmitV6V7LjO9RERERLNRc8ecD3LziTW9RERERFT2GPQSERERUdlj0EtEREQ0Qwoxl2quyPXaMeglIiIimgF2ux1DQ0MMfKdBa42hoSHY7fZp74MT2YiIiIhmwKJFi3D06FGcOHGi2EMpSXa7HYsWLZr28xn0EhEREc0Aq9WKtra2Yg9jzmJ5AxERERGVPQa9RERERFT2GPQSERERUdlj0EtEREREZY9BLxERERGVPQa9RERERFT2GPQSERERUdljn14iIsqL7j4XtnQNoHfYjdY6B9Z1NKG9xVnsYRERAWCml4iI8qC7z4X7tx6Ey+1Di9MOl9uH+7ceRHefq9hDIyICwKCXiIjyYEvXAJwOK5wOK0xKhb/e0jVQ7KEREQFg0EtERHnQO+xGjT22Yq7GbkHvsLtIIyIiisWgl4iIctZa58Coxx+zbdTjR2udo0gjIiKKxaCXiIhytq6jCS63Dy63D0Gtw1+v62gq9tCIiAAw6CUiojxob3Fiw9o2OB1W9Lk8cDqs2LC2jd0biGjWYMsyIiLKi/YWJ4NcIpq1mOklIiIiorLHoJeIiIiIyh6DXiIiIiIqewx6iYiIiKjsMeglIiIiorLHoJeIiIiIyh6DXiIiIiIqewx6iYiIiKjscXEKIqJ4/V1A9ybA1QM4FwPt64HmjmKPioiIcsBMLxFRtP4u4JWNgHsYqG2Vz69slO1ERFSyGPQSEUXr3gTY6wBHHaBM8tleJ9uJiKhkMeglIorm6gHstbHb7LWynYiIShaDXiKiaM7FgGckdptnRLYTEVHJYtBLRBStfT3gGZZaXh2Uz55h2U5ERCWLQS8RUbTmDmDNrVLLO9Irn9fcyu4NREQlji3LiIjiNXcwyCUiKjPM9BIRERFR2WPQS0RERERlj0EvEREREZU9Br1EREREVPYY9BIRERFR2WP3BqJS0t8ly+G6emSxhPb17DJARESUAWZ6iUpFfxfwykZZLKG2VT6/slG2ExERUUoMeolKRfcmwF4niyUok3y218l2IiIiSolBL1GpcPUA9trYbfZa2U5EREQpsaaXqFQ4F0tJg6Muss0zItuJctTd58KWrgH0DrvRWufAuo4mtLc4iz0sIqK8YaaXqFS0rwc8wxL46qB89gzLdqIcdPe5cP/Wg3C5fWhx2uFy+3D/1oPo7nMVe2hERHnDoJeoVDR3AGtulUzvSK98XnMruzdQzrZ0DcDpsMLpsMKkVPjrLV0DxR4aEVHesLyBqJQ0dzDIpbzrHXajxWmP2VZjt6B32F2kERER5R+DXqJywP69lIX4+l2bWWHU44fTYQ0/ZtTjR2udo4ijJCLKL5Y3EJU69u+lLCSq3z3m8qDn5ARcbh+CWsPl9sHl9mFdR1Oxh0tElDcMeolKHfv3UhYS1e8ura9CU60NTocVfS4PnA4rNqxtY/cGIiorLG8gKnWuHsnwRmP/XkoiWf1un8uP2644q0ijIiIqPGZ6iUqdc7H0643G/r2URGudA6Mef8w21u8S0VzAoJcokf4u4IW7gCe+Jp9nc30s+/dSFtZ1NIVrdlm/S0RzCYNeonilNjGM/XspC+0tTmxY28b6XSKac1jTSxQvemIYEPncvWn2BpLs30tZaG9xMsglojmHQS9RvGwnhrFHLhER0azH8gaieNlMDCu1UggiIqI5ipleonjt6yVwBSTD6xmRiWErPz/1scUshWCGmYiIKGPM9BLFy2ZimKtHAuNoM9EjlxlmIiKirDDTS5RIphPDnIsl4DQyvMDM9Mgtxcl2RERERcRML1EuitUjt1gZZiIiohLFoJcoF8XqkctV2IiIiLLC8gaiXBWjR242k+2IiIiImV6iksRV2IiIiLLCTC9RqeIqbERERBlj0Es0F7CnLxERzXEMeonKndHT114X29M3XTkEA2UiIiojrOklKnfRPX2VST7b62R7Mlz8goiIygyDXqJyN52evtMJlImIiGYxBr1E5W46PX25+AUREZUZBr1E5W46q8Zx8QsiIiozDHqJyt10evoWa3llIiKiAmH3BqK5INuevkagHN29YeXnS6p7Q3efC1u6BtA77EZrnQPrOprQ3uIs9rCIiKhIkga9SqnzAPwKQCuAzQD+QWt9KvSzv2qtL5yZIRJRUZTw4hfdfS7cv/UgnA4rWpx2uNw+3L/1IDasbWPgS0Q0R6Uqb7gPwPcBnAdgL4CXlVKnh35mLfC4iIimbUvXAJwOK5wOK0xKhb/e0jVQ7KEREVGRpCpvqNZabwl9/VOl1A4AW5RSnwegCz80IqLp6R12o8Vpj9lWY7egd9hdpBEREVGxpcr0KqVU+D6g1voFAJ8C8DsASws9MCKi6Wqtc2DU44/ZNurxo7XOUaQRERFRsaUKev8JQHv0Bq31LgAfAfBYIQdFRJSLdR1NcLl9cLl9CGod/npdR1Oxh0ZEREWitM5/pcKqVat0Z2dn3vdLFKO/K7a7QPv6kp14RfnH7g1ERHODUmqH1npVusexZRmVpv4u4JWNsjRubav0kX1lY/r+szRntLc4GeQSEVEYF6eg0tS9SQJeRx2gTPLZXifbiYiIiOKkDXqVUh/IZBvRjHL1APba2G32WtlOREREFCeTTO/GDLcRzRznYsAzErvNMyLbiYiIiOKkWpHtEgBrADQqpf4+6ke1AMyFHhhRSu3rpYYXkAyvZwTwDMtSuURERERxUmV6KwBUQwLjmqiPEQB/U/ihEaXQ3CGT1hx1wEivfOYkNiIiIkoiaaZXa/0SgJeUUv9La314BsdElJnmDga5RBlg+zYiosxqem1KqfuVUs8opf5sfBR8ZERElLPuPhfu33oQLrcPLU47XG4f7t96EN19rmIPjYhoRmXSp/cRAL8A8GsAgcIOhygFLkZBlLUtXQNwOqxwOqwAEP68pWuA2V4imlMyCXr9Wuv7Cj4SolS4GAXNsHIpCegddqPFaY/ZVmO3oHfYXaQREREVRyZB7yal1NcAPA7Aa2zUWp8s2KiI4kUvRgFEPndvYtBrKFImvFyCw2hGSYDTYY0pCdiwtq3kzq21zgGX2xfO8ALAqMeP1jpHEUdFRDTzMqnp/QKA2wG8AmBH6KOzkIMimoKLUaRmZMLdw7GZ8P6ugh62XOtFo0sCTEqFv97SNVDsoWVtXUcTXG4fXG4fglqHv17X0VTsoVEZ6O5z4e5n9+Lbj+zE3c/uLfl/+1Te0ga9Wuu2BB+nzcTgiMK4GEVqRVqWuZyCw2i9w27U2GNvhJVqSUB7ixMb1rbB6bCiz+WB02EtyYw1zT7l+qaXylfa8galVCWAvwewRGu9QSl1JoCztdZ/KvjoiAxcjCI1V49keKPNQCa8XOtFy60koL3FySCX8o6TJKnUZFLe8CCAScjqbABwFMD/W7ARESXCxShSK1ImvLXOgVGPP2ZbKQeHBpYEEKVXTndEaG7IZCLb6VrrG5RSnwEArbVbKaUKPC6iqbgYRXJFyoSv62jC/VsPApA/dqMeP1xuH25Yvaigxy00oyQgeoLeDasXMXtFFKXc7ohQ+csk6J1USjkAaABQSp2OqC4OVCDsSUvZMDLh0b8zKz9fuN+Z0O9nu6sHd1Y2Yov/QuxyLSqr4JAlAUSpleubXipfSmud+gFKXQHgvwFYDuAZAB8AcLPW+sVkz1m1apXu7GSDh2mL7kkbnbXj7XyaDfj7SUQh5diykEqPUmqH1npVuselzfRqrZ9VSr0B4GIACsA3tdaDeRgjJcOetDSbFfr3k3c5iEoG74hQKclkIhsA2AGcAjACYLlSam3hhkTsSUuzWiF/P4vUb5iIiMpfJi3L/gnADQDeARAMbdYAthZwXHObc7H8sTcyaAB70hqYBSy+Qv5+8i4HEREVSCaZ3mshfXmv0VqvD318vNADm9Pa10uNpHsY0EH57BmW7XMZs4CzQyF/P6OyyCfGPHj1wBCeOTCBru4uNrwnIqKcZBL0HgBgTfsoyh/2pE2sSKuOUZw8/X4mXL401G/4xJgHOw4Pw+sLoN7ixQnTAq70REREOcmkZdkEgLeUUs8jqlWZ1vobBRsVsSdtIkVadYwSCP1+hmdub3OjtW5vxjO3jeVLnQ5rzPKlt557OU7b+yB6TmjYzQ7UqnHY/aN4Z+En4DRbk6/0VKJlL5z5TkQ0czLJ9P4RwH8H8AqAHVEfRDOrSKuOUWJG4Opy+2IC10yysdHLl5qUCn/9f/rmA2tuxQm/A/XBQXgttehc+DkMVZ+ZfKWnEi17yeX6ERFR9jJpWfYbpVQFgLNCm/ZorX2FHRZRAkVadYwSiw5cAYQ/J83GRukddqPFaY/ZFg5qm8/Hu2d9Ha9mutJTiU5+y+X6ERFR9jLp3nAZgN8AOATp07tYKfUFrTW7N9DMymXVsVS3vwt9a7xEb72nkzJwTSPd8qVZrfRUomUvuVw/IiLKXiY1vf8fgCu11nsAQCl1FoD/APD+Qg6MSlShA7zp1DpHryAWfft7za3y82Q/y9dCC4XcfxGlC1xTSRfUtrc4sWFtW0y9a9LljUu0xV8u14+IiLKXSdBrNQJeANBa71VKsZsDTVWoAC/XQDrV7W+gsLfGS/TWeyayysbGySSozXilpxIte8nl+hERUfYyCXo7lVIPAPhd6PvPghPZIsr01vW0FCLAMwLpgB8YOwYc7ZT9rb0D6Lg2s32ku/1dyFvjfbsA7zDgGZX9NpwNVDXM+lvvmcgqG5vk+XmpXc2l7KWIcr1+0dgFgogovUyC3q8C+DqAb0BqercCuLeQgyoZZXzrOqF0AX4haiu7N0nAO7gbMNuAynrJ5G37CdBwRmbXOd3t70LdGu/vAlxHZP1Cey3g8wBH/wo0nCNjNx5Twm+asglcCxqYlWiLv3wE/snav21Y28bAl4goStqWZVprL4CfA/gBgO8C+J+hbTSXFkvIpC1UIVqKuXokw2u2AVY7oJQEkAFf5tc51QpihVxdrHsT0NgOQAN+L2CxSQB8olv2X6KttqbDCMwOnhjDkaFxPLmrD7f95048uas36eOnLFxBCSVr/7ala6DYQyMimlXSBr1KqWsAvAfgXyHB736l1NWFHlhJiFoyNawEZo1PS3yAH5gEBvcBj38FeOEuCdQKEUA6FwPjQxIwGvxeyfhmep1TrSBWyNXvXD3A/DZg8UUSsHtDJQ7zlsr+59Cbpi1dAwgEgth7fAxefxDzq6yAAjb++b0pAW2p9a8tdoDeO+xGjT32ph27QGSm2K8dEc2sTLs3XK613g8ASqnTATwJYHMhB1YSSnTWeNb6u4DdTwJaAw4nUNkIDO2T7Ct0bFlHvmsr29fL/jwjEjD6vYDfA8w/LbvrnOr2d6FujRu/H9UL5AOI/X0p0VZb09E77Eb/iAc2iwl2qxkAUGu3YGh8ckpf2lLqXzsbSgvYBWJ6ZsNrR0QzK5MV2Y4bAW/IAQDHCzSe0lLIW+OzQX8XsOk24OHPAeODQNAvdalH/iLnqxRgd8ZmKJs7gMvvBK69Vz7nGkw2d8ikNQVgIpTxXbAcMJmzu879XZKRfuJrkcx0oaX7/ZhDK8y11jlwctwHmyXyX47XH0R9VcWUjGQpZS5nQ2nBuo4muNw+uNw+BLUOf72uo2nGxlCKZsNrR0QzK5Og9x2l1FNKqZuVUl8AsAnAdqXUJ5VSnyzw+Ga3Qt4aLzaj3rRvJ+CYJ0HtaB/gmwACAcBzCgh4pRsBUNgMZce1wHW/BM69TsoF6k/P7joXq3Y23e9Hub9pirKuowkWk8KIxw+tNTy+ALz+IFqc9ikZydY6B0Y9/phtsyVzGX87/J1jrqIH6EYXCKfDij6XB06HldnKDJTSmysiyo9MyhvsAAYAfCj0/QkA8wGsh0zLeawwQysRJTprPC2j3jQwCdhqAGso4JgcA8xmwO8DFl0YuW1f6AxlLte5mL1y05VVlGCrrelob3Hi1o+cjo1/fg9D45Oor6rAsvpKmEymKRnJ2dq/NtHt8KOn3Ki0mlFtt2D/iXGMefywmhXOXVg7o23E8tb+bQ5hWQjR3JM26NVaf3EmBkKzjFFvarTastqBynmA1wI0ngMcfxcwV0iGcrYvBjCba2fL9U1TAtesaMVpjdVpA8F89q9NJdugNFGt8dlN1dh5dBhmZUK1zQyLSQKn/cfH8NOn92Lx/ErWi85Ss/XNFREVTtqgVynVBuBWAMuiH6+1/njhhkVFZ0zCajhbessCMpHNXCFK5TO3AAAgAElEQVT1tGvvkNZbpZChnCsTDktAphnJQmcupzOJqXfYjRanPWbbkvoqvN3rQrXdgslAELV2K85b5ERX7wi8Y150tMq+ZvNkvLlqpt5cEdHskUl5wxMAHoDU8gYLOxyaNYylXe11QOsqoP9tqeM97XJg9ZdCAW6GK6IVW4kuU0uFY2RtJ/0BvH5wJFyW8LtXD+NHn1yR8DnJbofbrGasPasRJqXC2yf9w9DQMc9nvejsw7IQorklk6DXo7W+p+Ajodklvt70zCsiE6y6NwGv3Vs6K4jNodrZbM3V5Wt7h92wmIC3elywWaQ0wesL4OX9Q+jucyW8Bsluh79vcR1GPf6YYLjCMnWOMOtFiYiKS2mtUz9Aqb8FcCaAZwCEV2LTWr+R7DmrVq3SnZ2d+RojpTNTS9lGL7scnTEtl44Vc0z0Lf7oIG4u1J3e/exevLhHOi8afYM9vgAA4LKzF+C2K85K+LxEbxIATLmOh4fGYVIKi+dXzrlrO9Pm6hs3IopQSu3QWq9K97hMMr3nAfg8gA8jUt6gQ9/TTEoU3AKRQDS6HVc+A1HjuLuflJrelvMjK4gBM9MFgfKuEItAFDoAydf+13U04fE3e1HnsEBrDa8/CK8/iPctcaYsQUh2Ozy+NvSOddLKj/WihcUFJogoG5kEvdcBOE1rPVnowVAK0VnW6ODWWlmYdlxGoNu/Czh1GGhsl4ls0DKxzWhXlkkXBGNffbsAr0sWtGhekX1GeqYy2qUix+uRaGJWLnWnhQ5A8rn/9hYnLj2jHl3HRjDq9aPWbkVHay2sZjMW1FjT7yDB/hKNgYFXYZXS6n1EVHyZLE6xE0Bd2kdRYUX3mjWyrPY64Oh2CTyj5dqOK3oxB/cwAAUM7pauDVCy/PDgHnlsui4Ixr4G9wPDhwC3Czh5CBh6L7sFIrJZYKIYq6/NtDwsuJHvRSAKvcJVvvf/uUuW4rTGalzUVo8L2+bDajZzJbMSwwUmiCgbmWR6mwDsVkptR2xNL1uWZSM6c+pxATYn0JJFtjNZr1lAAs98tuOKDrC9o3IcvxfQAcDvkaDX44qsIJaqC4Kxr4G3AYtD+v36PMDoMaDpPGD7A5IxTpetzHSBiWQZ8XKrO87Dghv57lOa78xxofc/Ey2rWG9aWFxggoiykUnQ+72Cj6LcGYFYMCBZTmUC3KekNCHTgCxZr9lFqyXwBKbfjiv6NrnZBhzaCljsUoagTBLwWmwSAC++SJYmhpKxpOuCYATrnhFZ2Q2QfXlGJIA++BJw5lXpA9RMF5jo3iTXeeBtOYa9FqhZWB51x9GvU98uoPX9sT/PMMMfHYg5rCb4/AH0ufyRoE/1AC/cG/NGpFsvThu8FToAmc7+0wWdhWxZxXrTwuMCE2TgG0zKRNryBq31SwB2A6gJfXSHtlGmjKzc6DFZztfhlKznWJ9s796Ufh/t6yWYdQ/LKmhGlnX1lyRIdNQBI73yOZusZvRtcpMVOLQNGD8JBAKSkZ0ckwDdMwLYa2QiW8OZwHW/AC6/M7Ng3Qg+/aEbBX6vfN//NuCYP7VkI9H1MPYTLVFGu38XMPCOjN1WI58H3pHtmV6PZKUR/V04vul76Lr3s3j6f34Tv338SXT3uTLbb67iyxnMFcDhvwBjxyOPySDDbwRiLrcPLU47KixmTPiC+NIHl+G2K86SgDeubGL4+Z9h09PPhZ9jBG/x576uowk9Jyfw4p7jePqdPry45zh6Tk7krVxgXUcTXG4fXG4fglqHv062//hzTTbuQil0uQdFsvVOhxV9Lg+cDivfVMxBxf63TqUjkxXZrgfwEwAvAlAANiqlbtda/6HAYysfqbKdmdbfpus1O90sZvRt8kPbAFstYLIAE4NAxRLJ9vo88srb6jLL7kYzFoaobgFOvBsqkwgC808DejuBtg/FPj7Z9ch0gQmPSwJoa+g2uNUux/Rk8J9f1xPA1n8Ggn55fXrfAHY9LAtytH0Iwzv/iO5BQFc0oMHkRlPPb7HJ5QGu+mjh/8jGlzO0nC+vV99O4IyPAJ4RDJ86gT9612LXIzuTZjrSTvxJUDZxoOcUVuuX8ZbjvMTPiRIMtUBUUDHf50OicoTVy+qwpWsAD7x8aMo5F3uSU6HLPUhwgQkq9r91Kh2ZlDf8VwCrtdbHAUAp1QjgOQAMejNllCbYayWANAIxI3jLtP62uSP/t+ijywaMoNxiAwI+GafbJRPYrvvF9I4dHaz7JiLdG+pPl2OZK2Ifn+x6ZLrAhM0pmWmfR87D7wUQlO2p9HcB236C8EQ911HZXrVAAsujf8Ux/0Jo2yLYrGZMwgqbAlZ7XsaWrvOS/8ear44T8eUd1QuApR8AencAI704bm7E//Jdg2qvH58c+y0cfcdweM8C2C77DE7ruDj8tLSBWIIykkGfDS3qePLnhGzpGsDS+iqsWBQpwXG5fXn9wxMd4KQrHyh20Ml6U6KZUex/61Q6Mgl6TUbAGzKEzLo+kMHIUtYslFvtRiA2r634y+FG1wobQTkA1DQByy6N/CxRoJZpQJcsWDdu2QOZ1SNnEvS3rJBa6bG+SCZ9XhvQcEbq53VvkkC/sl7Ox2KTbtS+McBsBQI+VEz0o6J+SfgpXnM1GrwDyf9j7XpCAmljv/7J6U+qS1TTbbED51wDXH4nHnp2L6rt3bhs6D/hsdTAU9mCOs8IPC/9K9BQHT5e2kAswXEarF4M6gUxw0kUvM30H5502Z1iB52zsd60kHWP5VxTWc7nVg6K/W+dSkcmwesWpdTTSqmblVI3A3gSwObCDqvMGFnK+tOB+cukprdumQRixe4qEF0rXH8m4B2Rj/ozI3XDxiIY0fLQMit8XaZbj5zsfMwW6QzR+n4J4o/tkNrXVGNz9YQCU698KLNkuCfdEjhX1qMOI5j0B8NPsQXGMGhekPg/1v4uKZXQiOz3+LsyyS6TGu5E55Wopjv02vQOu3HB2FZ4LDXwWmoBZULQ7sRQwBFzvLR1sQmOc1q1H9vtH0xbS5vvFmjppGtXlW0NcL7NtnrTQtY9lnNNZfy5HRocw20P78Qtv9mOu5/dWxbnWOqK/W+dSkfaTK/W+nal1CcBfBBS2Xm/1vrxgo+s3BSiNCEf4ssGll0q2wNewNGcvH43k5ZZmWSC831djPPZ/oB0hnDMl7phc0XqLKtzsWRij78rAW/QLwGqMgENZwPeUVSNnYTyuuDVNahRbpgmXdheexXWJ/qPtXuT7KOyHlAqUmM80gtYKqY+PtPzSlLe0VrngKPvGDyVLeGnTPqDsFXWxdRIp23TleA4dSs/j/Wh7g3vHHNhxOOH02EJT8gynjvTmc102Z2ZaEmWzmyqNy1k3WM511RGn9vgmAd7BsYAACOhwIodOYpvNvxbp9KQyUS2NgBPaa0fC33vUEot01ofKvTgqACSBaLZBp7JWoj175KuB327ANcRWcltftvM9stt7pCa1zOvii0HAJK3LjNKUBYsB07skYU0TBZg6aUSMJvMcHz4TrQffBPHe/ajN9iAgcWfwPqLP5j4P1ZXD1BVD/i8kYDXYgMmhoC2tdM/ryTXbl1HEw7vWYA6zwiCdicm/UF4/EGc16Cm1EinDcQSHKc99PnIyQksmleJGrtlyh/8mf7Dk0mQPZuCzmIrZPlJOddURp/b/uPjsFlMsFlMGPMGyiq4L3X8t06ZyKSm9xEAa6K+D4S2rS7IiCi96U6OyufCDYlqTE8elCWLLZXAwC7AMwaMDkhN64Jz5DH57peb7FrEB+Vjx2VVudF++b6xHTjRHfs8I8NpqQAWrZLHBbwxHSsWdFyLBQDSnoFzsQS8g7vle6Nbh9mauFwkR+0tTtgu+ww8L/0rhiYkw3teg0K9yZ2342WSzZvJPzzM7mSnkHWP5VxTGX1uIx4famwWeP1BVIdKa8oluCeaCzIJei1a60njG631pFJqGvdnKS9yCVzzsIpXWKIWYie6pTXZ4G6pha2oAgKTwJG/ANDAxIlI0BkdqCcKXI1xpQrsU12L6KB87Dhw9K8ypsAksPM/5GeLLgRa3xf7vMvvzO46pLs+DecAY8eA8SHJHF96R8Ey3ad1XCyT1vLRLSKB2ZjNY3Ync4UsP5mNk/byJebcbBaMhOrWz10oK2IWI7jnxDqi6VE6TR9NpdSzADZqrf8Y+v4TAL6htf5IsuesWrVKd3Z25nWgFLLpNmmh5XFJFtJiCy1pfD6w/u7Uz/33zwDeYcATWlq44WygqkHqTK+9N/uxxAerfbtk/+OngNFeyfCaLFIba6sCqprkuM0rZLLUmltlP0bgagTPpw4CUMC8ZbFdHeID+xfumpptNr43gk57nWSdRwak93DtQllZbnICMJuBc9ZLKYTxvHwFvYmuTx4D0GK4+9m9U7J5xve3XXFWEUdGmWL3hukxzu3dPhd6htw4q6kaSxuqwsH9TNb0Rrfqi36DwbpimsuUUju01qvSPS6TTO9XADyklPp56PujAIrYY2uO6u+SyVlv/176yOqArKDmcwPKChx4QR6TLKjq75IaW41Ia7Kjf5VMZLp2XsnE136+cBfw1n8AvnHAVCFBb8AnE7q8JqBKA43nxGaYganZ56OD8vXCCyLboh+fyVK80ROyRvslw1u7EKicL3W1FZVy7Qb3SNCb6SIh2V6f6PEa4y9y4Dvd4CTbbN50jlPOgdNsUMjMeDln3eP7QxezpKacJw0SFVom3RveA3CxUqoakhkeLfywSsRMZfKM2/iD+4CKamkppoOAzSbdBbzD0gM4VZlC9yapYz0eWhXNWLjhRDdw6W35GWdjOzB+XDK7FptMAAv45GcmBSy+SAJMIDbIjJ8QF/BKcD52XIJSz4ic58SQrJDmmA80nxdZinfZpZH9Ri9uER2Uv/M44JgnX1tsoUVCHJGljZMtipHLa5zPGuo8SbegQyrZ1NBO5zi5jI1ophQ7uJ+NZUZEpSKTTC8AQGs9VsiBlJyZDGiMWtzApKwQ5j4lQaBvQupmJz0SBKbKVLp6pIuCrSYSSNprpy480fUEsP1+YLQPqGkBVm8AOq5NP8b+LmDvZgksJ07KWJVJ9jFxEtB+YPef5LG1C6UPcP3p8n18iYLZJuUHB1+Sc/R5JHusIcsXA8DR7bKP4+/ELMWbcHGL9vVyDY1zrqgOfe0E7DWRnrfxz8v1Nc5nDXWe5JolyvQP/nSOM1szWMw+02xSzpMGiQqNK6tNV3RAo0yhFc3qprfwQDquHgnW7LUy+98eOmbQB6l9XSqrc6Vazti5WAK96gWSGT3nGqmtbV4ReUzXE8Bz35Olh6ua5PNz35Pt6RjXY36bfFQvkEzs2IAErpMT0gcXSro8HP6LZIYTLbpQ1QBMjgLjg4DWEkBDAdCA+6S0ALPYZWLc0g/Iz1MtbtHcAay9Q3YxMSSB+aILZT+2uuTPy/U1Nl63aIUoo8hCugUdinmcmRpbNsp50QUqTVyIgWj6Ms70UpxkfWoLEdAYnQgazgZ6Xpe61MAkAC3lAx4XcGibBHbJbscn6rYQn93cfr9kQR2hLJbxefv9qbO9/V3A7iclQDWZZWwmi5RPBCZlcQaTDQh6gaBJlgm2OaW0ouPaBIsufBd45GYg4JdAGFqCzckxKe0AIi3AvGNTA8tEOq6V2uVkXSJeu3dq+UKur3Gitm7JyijyKUVJxkxliZIdx2ZWuPvZvQmzprMxgzVbs880d7FVH9H0JQ16Q6uwJWUsVjFn5TugSVU7Gt2JYNFqoP9tmcQWnJSuCLULJTjb+e8Idz1IdDs+xYpeAKSkoSouW2Crke2pxv3KRsnqQsvxfR7APQQgKBlSKMCsAItDJpA5F0vwagSPiRZdsNgBZ43U3Q4fkQDYYgMmx2X/Wsu23k65JpmUH8QfJ135Qq6vcSZvNPItzTnNVGupRMfpOTmBoNawWswJa3ZnY9urUqqfZBnG3FHsumKiUpUq05uqo70GMLeD3nwENEag279LFnVobAfqT5safMUHrGdeIZO8zBWxAdm+Z+VzfNeD7Q9IuYER7F78tcRBYU2LlDQ4ov4z9Y7K9mSMEoCW86UbhNFZQmvAVitL+vrGgWBQsr5+s2SAzbbUweOi1ZK9hpKJa8M9sl/nEvm555TU5DZ3RGqDs62ZTVdzm+trnMkbjXxLc07TyRJNJ5hKdJzJWhsqLOakWdNiZ7ASnedszD4nwkmARETpJQ16tdZfnMmBlJxcA5rojJx7GIAC+t4ETu6X7gfmCglWjd678VnKJ74mta/RknY9GJR+tKmyof1dQGUD0PcWMFYpga4OSknB2tuTn4dRAqBMUic7uAfwe+T7qkbJzp46DPgnJGi1VUmWd/5pqVcKW/0lqdMdH5Tn1TTL+VU3AUoDNe0SCFdUxT4vm/KDdOULxmu8/QFgz2bZtijLhQjz1bYs0y4SGZRkZJMlyrXbQ/Rjvv3ITtRXp67ZzUcGa7qt0hKd50fbG/Fc94nwWGdD9jkRlmEQEaWXUU2vUuoaAOcCCN/n01r/sFCDKohCtBdLdFs+U9EZOe+oBInuUzLpa16bBI6peu8muvVutsnze16X8gBbjbQ504FIN4VE2VAjAK9pAU77iHRGOHUAqD8D+OgPYut546+jOVRb66iTbHL1glC3hQk5njIDdUukRME3AVirZSLd6i/J/l64K7Kv+KWBz//b2O8b26VDhL1Ork/vm0DXo5LpXbhSjp1N+UGm5Qu+CZkwZ2R7s+ngkI8uH/1dGH7+ZzgwZsGgz4aGgYM47djPUPeRv5d9RL8mpw7JhEEj+53snDKUz2BqJrKm0w3Sk53n3oHxkqifLKUyDKKZwpIfipc26FVK/QJAJYDLAfwawN8A+GuBx5Vfs7BfajgjN3ZcbpmPD0qQqLVM/DJu6ye7VZ/o1ntVAzC0X2pnjT68AR9Q3RxZhMF4fHQ2NDoAd9QBTcsjwWB8wBt/HUd6ZawTNfL1xJAsRlHdJI8Z6QUmxgBnK3Dp7ZH9xe9r6D1g538CrasiJR57N8e+Ri/cFWnd1tsZ+toLuHol0KttlWAdSibWLVotwXWy1ziT8oVc247loW3Z8e2PoHsQ0LYqVNtNGPFbsHPQhfbtj2DBagCvbMRQ0IG9w3ZUjNhxev8rUG4fnK1n5VxHHB1MDY55sP/4OFzuSZiUKes/IDNRszvdID1V0Fis+sls/mBn8oaCAQDNJSz5oUQyaVm2Rmt9E4BTWusfALgEQIGnn+fZTLYXy5RzMTB0QOpgK6qllCDgl6ziiT3AyfckeOzfFXlOf5cEfk98TcZ+1tVyLka7ro98Vzo8OGole2y1SzszW2VkEQZgauYvk9Za/V3A5juAY28CA29LkO6ok6y0xSaLXkwMAVX1QMv7JMtsq5H2ZUs/IKUP+5+R8RuZSSOAPfwX6ck7OS7lHcleo/5d8rH7T3Isqw2oXSRvEnwTQO92CX5todZuh7YBz/9QjpeIUb4QfQ3j3wjl2nYsy+d397lw97N78e1HduLuZ/eiu8+F4z37oStqYLOaoZSCzWqGrqjB8Z79QPcmDAUd2N6v4fVreGvbcNi+HMePHcSp/kPJ27FlqLXOgVGPH4NjHuw4PAyPLwCb2QSrWWXdusuo2XU6rOhzeeB0WPP+Byi67dngmAevHRjCawcG8ey7AynHapxntGLW7mbbKi1dGyu2XqO5JvoNsEmp8NdbugaKPTQqokzKG4z7YxNKqYUAhgC0FW5IBTCT7cUy1b4eeGwDJKM7D6iokdZjwYCUOVQ2SBB46rD0yT34kpQ7GKuRJcqEAkDLithb9mPHJfiz1UpgnSjzl+42v5GVHR+U4/s8wIEX5RoG/XKMZWtjlzN2D0tAa7ZNHffzP5SgXkPOubIhlOE2ye35seNTlwbuegLo2S69iQOTgNkhGd6qRqDhTHm++5SMZ+SoBOLWahlzqqxquhKVXDs4ZPH8ZJmJyyfnodXuxiQiWbwa5UZvsAEdrh7sHbbDbtGwWc0AgImaJQhOWPGnxttx2+VnZTbOJIzs7IETY6gwKwCAN6CxcokTFRZz1mUOhc6aGhlPXyCAHYeHYbOYYDObAKVSZnkKnYXONsuabcY63SRA1vzSXMOSH0okk6D3T0qpOgA/AfAGJFT5dUFHlW/F6peaSnOHZGHdw6GsbKUsvGC0/QpMAuMnpI516z9Lja49tIxub6dkTu11UzszGHWvQGgxiwqZNGaUGiSacJfsNv+SSyQzu/tJ2Y/VIeMK+uXnfjdQ3SKB+ol35blGCYXfI4G6Y37suOefDpw8IAF9UMt2t1HaEZTSDKMUw3iN+ruAbT8Jjc0lZRu+MblmEyeAJRcD+5+PLC1srpAxTpwAgs7c3tzk2sEhi+cnC0xeMl+Cz0/+ETYFeM3VsAXGYJp0YWDxJwDnLviP7ENF5bzwfmyBMbgrF2b8n3uqgMwIpv7+9zsBDdQ4LDh3YS0aa+wIap3zH5DuPhf+96uH8WaPCxoa71tch89fsnTagdh0gnTj/Me8PvQOu1Frt+Dchc681e5O5zbrdP5gp3pDwQCA5ppS6bxCMytt0Ku1/u+hLx9VSv0JgF1rXVr3xIrRLzUTzSsiGdHdm0I9bSErhwU80jN35Kh0KAhMSrmAkj/kGNwjy/AefAk486pIje3ezVL2ED0BbOV3U2czE3WiWHJJZNKY1gC0BOeAtDXze6WzQ8AvWeqxE1J20HCmlFj0vy0Bb/y4j70h2VmtpauEJfSHOOCXLK6jXgLb6KWBuzeFapObZF8jfaGs7qQcw1wh3SGsDrl4SgHKIvucnJBsc6oJc6kmNebapSPF8+ODzXeOudDeElsKUWO34GjtWXhGX4/VnpfR4B3AoHkBttdehfUXfxBQS1H/7v/AiMcEba+FLTAGu38Urzmvyeg/90wCsvYWJ65c3pz3PyDdfS789Om9ODg4jmqbGQoKrx84iT6XB3esO3taAWe2QXr0+Z/TXBvO8Oaz3nU6WdZ8/8FmAEBzzWzs+03Fl8lEtq8DeEhrPay19iqlKpVSX9Na3zsD48uPTAOXQnR4SMUIxgf3AYGA3JLXAek/CxOg/RIAzluC8KIPVntkNTIjsIyfJHWiW/adTZus+Nv8xqQxR5307R0/KQHk5LhkWbUJqHBIEDp+HNAKsFiBSbeUU/gmgDOuAIb2xY7bOwZUNgI1TYCtGhgdkKysyQQ0rQSGdgPjbqDnNaBuqayU1rdLgmO/V94ANJwBeEYlc11RKWNsOBsYOSaBMkIZ5GCoRnPkmATGta3A4H6ZMLdotdQbZzKpMZcuHUmenyjYPHrKjUqrGW2N1eHHjXr8OHehE+s6PootXeeFA+T14aDMCfuHvokjL/4Hmib64K5ciNec12CfWooNGSxLmmlANp0/IOlu6W/pGsDgmBc1dgvsodIMKIWT45M53XbPJkifidv+08my5vsPNgOA6eHkv9JV7L7fNDsprXXqByj1ltb6grhtb2qt35fsOatWrdKdnZ15GmIeZBLMRncTiM4GF7rDQ38X8PhXANdRCQ4DPsCkpNWX1hJYnv5RGZPRiswogXCfBNo+JD1sDToo+7TXTv9cjDFpLQGvqgD63pDJYZPjsl0HZeU3vzsybgRl3Ba7HPe0yyXTGz3ukT4JdpddKsfqeV3OxWSWQBmIZGIBmQTX/7aUeuiglFJov1wCWw1ww+/knF64SzpADO2TIBcAKusl0F58ceQNwaFtkQU4jDEYpS+X35nDC5mdu5/dOyUoOzQ4hj39Y7j49PqYwCSTyV7T/eP87Ud2osVph8nIxAMIao0+lwc//fT50z5GdFAfvSJbU60NkwGN1joH3u1zoefkBGrtVqjQ8bXWEui3OqccPxuJjm9cSwDh83j32AjOX1yLBTWRYDjZ+U9Xotfa+P62K5LXXOc74Cp0AFduAWKq36FSPi+icqSU2qG1XpXucZnU9JqUUkqHomOllBlARa4DnDGZtivLQ2upaWnukKyjMYlNB0LBnVeWGq5bBkyOSjsyYwli9ykJKIHQ8r+ILEgxPijBY3Sgl825xC8r7PMAJ98BoCTgDUwCNqdkUb2j8lkHZdW1+WcAlfPkOWP90mnB7w0tS3xSyjcWXxhaka1CAuMFyyXAnRyXDHfL+XIettBt/qF9sm3fs7KohbVSsuIKscG+kTWvPzNU6zskgbS1OrZ7gmdEguXobhZFmNQYnf07MerB/hPjGHX74A0EMOkPoM/lzyozMd0JYtnc9s7mGPEZVF8ggIOD4xgc82LtWY1wuX3oGXIjqAGvPxjO9Hr9QVRYTDnfdk+W5QEQk2HfNzCK1w+cwiWnKzRU21Oe/3RNN8ua70l/hZxEWI7toTj5j6j8ZBL0Pg3g96F+vRrAVwBsKeio8inTYLbYHR4sNgkEjaAXFrm9v+RiCTQddZEliI1MdXRXhRPvAggtBqHMwMA7kn2dOBEJ9JQJ2HQbcHCrBJB2J7DgXKByvvS7dS6W4Dl6WeFAIJSBNctqaqiS8dnrZAKa0WrNWglUzZdzUUoC47EBeVyFQ8Zf1QCc+0mpQz78F3nsotXAdb+UMobaVjmXwX0AtNTiWuxSuhAIBc8Wu5R7LFwp18t4HZs7pJZ56z9LIF5VD1QvBAZ3S2s4o7OEvXbqUsszNKnRyIS9c8yFd/tGYA610Rnz+OCsrIDVrFBhscLtC2YVLOSSYSvUbe/4W/r7j0vdri+gw+2Dzmqqxtu9Lvg9GlprKABj3gCW1FeGW23lIlGQd/eze2MCmXMX1uL1AyfR1TuCtWfZCnLbfy7cZi3HAJGT/4jKTyZB7z8A+DKAr0Lya8+glLo3ZBrMFrPDQ8Art/H3PCXBo9Uutbo6KGMd6U18692oVd58h2SJq+ZJgDi4R2plD/9FVkOz1UgAOjYgAWXQJwHw6ECo7VcDcPqH5fwPvBApmVh0IbD/2dAEOw04Q4HA0AFgsj/SmWFon/xmeEalBMIzLC6/pjkAACAASURBVNlo7xjgGAVqF0oQ7R2VoHTZpcDZV0fKLgAJcN/dBIz2SfkCTIB3XALYdx4LnV+jjMvvkefEv44numXf0a+hUtJDuKoh1F2iRc55QXvyFm4FYGTCAoEgjp50w2YxYXDUixG3D0opWC0mmE0mvH+pE1Zz5q3Acs2wZRKQTSeojs8gj3h8qDApVNsj/+UsbajChC+AphpbuHvDRafNz6l7QzrxgUxjjR2r2+Zh51EX+lyetAHpdN9gFGuBi5lSjgEiJ/8RlZ9MujcEAdwX+ig9mQazxezwYIyx4czIpC+fR7K++5+XTO8LdyWuRW7ukNrapR+IdH8AZIGLgD+yMpt3BAhCygxM5lBbLx8AJZ+H9oUCxvlSQlHTLG3DzDbAWiWT10YHJPA0V0jgWVEdyu6eDkyclJKGmpbQ8UalPEOZZAli76g8PuifmnXf/oDU4Y4PAGYLEADgdUkHBrM5dC00UFUh1waQwN5cMXWRjfg3OPPbpPTCyJQ3nCHXMaa7RRbdGDIVV0e+fXgFnI5leLdvBDarCc5KKyrMJhw5OQGbxYSJyQAuO3s+GqqzawWWjwxbqoBsukF1fAa5wmzCWKhW12BM0ktV15pviQIZu9WCK5c3px1HOd7Cz5dyDBA5+Y+o/CQNepVSv9daX6+Uehvh6fARWusVBR1ZvmQazObamiqVdBPpjDFWt0iZgt8rJQXBUNC69AOpuwwYQfNon7QE845JjWxFtQSb9loJXoMjkt1UNvns9wJQ0pkhGJAscfN5Un7gHpZA1NUr47BVS3A8fESe23gOcM7H5Phjx4Ejr0mQbquS55nM0lnBbJVjTE7IPhecHTt2ey2wZ7Oc48n3AJ8b8J2U8ZrMEribzUDVAmmR5vNIsDs+mPkiG80rEmTKr0XBJKgjbz/0G+ilN+GvHieqbVK/ajVHJo95/cHw19kEC7lm2DLpsDCdoDo+g9yxsBbHXB5UWMwIhiarFSOAyCWQKcdb+PlSjgHiXChLIZprUmV6vxn6/H/NxEAKJptgNtfWVIkkm0gX30vX+N43IVnOgFdWams5P7LgA5B4Mlr7euDJ22V5YKM2WI1Lr9/5p8mt/OEjoV65JilF0BqS+lWSXVVm6aSwYHmk68KhrVJDq/0SIOuAlF8oE9AYFbxWLwCazpVs8UC3BLgVVfL4oF8e73cDwaDU2UYzJpQZC1v4PHJsQIJck5Ln252AySKZ3vFBKVeIfwMQ/wZn6IBc03lLk2fKo9+QmG1wnRyAZ2AffIEghupWoObSL+O0jouze80T1JGbK+uw5PjzqLZfD68vgKDWOHrKA4fVjKCWl6Pz0Cmc01wDk8mUcbCQS4Ytk8xlLkF1fAY5PsAuRgCRSyBTjrfw86VcA8RyL0shmmuSBr1a677QlyYAfVprDwAopRwAcp9lMpMKEcymEh1InToE1CyMvaU/PigrjC39YOyiEmtujWQkn/ia/Cy6ZCHZxLrmDlmcwWKXwNZSAcxrA0b7gZ6/SoCqTJI51abQQhChHrbQsr2qUTK4J7plYln3JlkMwmIPZXdDQbJ/UjK43lFpETbSK9lgr0vKGYwxKLNMpNPByHLEyy6UANs9HJt1X7Ravm44WybPGbW2Jgtgtsv3pw5JGUfTecnbr0W/wenbBbiOSBCfrB9v9BsSkxXePc/AOn4SbmsTTFY7Fg7vQP9T38MB/CC7wDdBmcXilib43tuH5iYb9g6MYXDMC2iNhho7JgNBVNks8PqC6Bvx4gcfXz4jE9EyyVzmett6NraxmolOF3ORcV2N1/yBlw/NmteciAiQgDadRyApQUMgtI0SMQIp93CkG8HAO1ICYBg7JgGho06CUUedBF7GIhKAZH+j22oBqSfWjZ+QLK/BYpfuD35PaPnhRcCSNUDjWRKc6lAG1uKQld+gAUct4FwiQaGrRzogjB+XfVXOk44MCHWXGHpPSilcvYB/XBan8HkkUx09QQ1KukO0rAA+dIcEnY46GZOjTr5f/SV5vLkCaF0VKqYJhjpCNEqJhM8tYwpMpl9I4vI75XhLPwjUn578GkdnZIf2wev1IGCywQE3AmYHfNZq1OkRDLz+h4xe+lSvXaNlEm1nnI22xmosmu8AFDCvugJ1VRVYc3o9PtrehKvPa8aS+ZVZBQhGhs3psKLP5YHTYc24xrR32I0ae+z73vjM5bqOJrjcPrjcPgS1Dn+dSXcFI5PscvtiMsndfaW1oKMhl2sxV0S/5hYT8OKe4/jy797Af31sV8m+7kRUPjLp3mDRWk8a32itJ5VSpdOnd6bF39quapAWWYN7ImUK40OycEK0+CxuNhPr+rsk2Jx0S5bVNyGlAfb5QNNy4Np7I8G41oD1qCzhCyXZXKtNsq3misi4nYsBnxfof1dKCvzeUCBrlmB+pFeC2cp5gGoATh4AtA/QFilF8E0AAbeUOJz9MQlsjeuTqLY5ugSltgWYtwYYPgycOiwtz2rPCbUtm8jsdYjOtho9jN0uuT7GcaMf4xkBAn4EzTZYgvLrHlAVqFBjMI8ejb3W6RY6SfLaLVhzK25rlslSiRYsmG7WsJCZy1xuW+erBna2ZItL5RZ+Ma+X8ZpP+gN4q8cFm8WEOocFXcdGOOmPiIouk6D3hFLq41rrPwKAUuoTAAYLO6wSFn9ru+FsWVJ3fDD2tn18l4H4LG42tcjbH5DyAT0eWcnNOy7Z5I98N/I4nxs4vE2+tlaFFpgYkUxu307pHmEE1UbgVtMCeE5FFs+w2iOro1XUACNHgfozJLiFku1WR6hkYoF8rl4AvPA/JIBtbAfqT5tabhBdgvLCXfJz95Bkao1uFvYaGcPmO6TUIdVS0caktugV4SwVMkbjuNGP8QzDrt0I+j3wmSvhCwTh97oxGgQOmeajps+FdtWT2UInGbx2s2HiT6ZjmG5QnY8a2NnWMSHRtchXkJmP/RT7ehmv+esHR2CzmGC3mmWVPa8fToeVk/6IqKgyCXq/AuAhpdTPIVOgegDcVNBRzXapsn3xHQSqFwCNy4GxvlCZwWJg7R3Azv+QVcb8XilLqGoEVv5j7HEyrUU+ul3qhu1O6eDgn5QSBsc8oOPaSJbXdVQmmJkrJHi01wITg8DJg7JYw/Jr5bxeuzcyuc5aCezdIoG0vU4+e05JcDt8ONIFwmSR4yqzBNPBoOw36JXjmizSTWJwd2TSGiABe/WC2GvZvh54/ofA8d2SmTVZpY7YeZ6UiuhA+o4WRtA+uE/eEAAS3C66MLKohXGckwcAaxVMZiuU341AwAuMD8KugF5TM96bfzle3XoQd1Y+jgUBv7yJMZY6dtTLOay/O6vXbjZkDdtbnPhoeyN+8+oRDIx40FRrxxcuWZK3MeSjBna2d0zIV5CZr/0U+3oZr/mYxx/uUuL1B1Frt3LSHxEVXSZ9et8DcLFSqhqA0lqPFn5Ys1i6ZY2NYGt8UGp3x4ck4Ft7hwSgxj6MLnDhrlV66nHS3UaPpiClFFUN8r3PLZleQIKywX0S3BndFAC57W+rBcyTUm7R+YCUORgTv4zJdQDw7v+RyWs6IEGj2S7LI5vtUvagzFJ7a7FJuzStpRwBiCxf7JsAzIsipR5+j7RHO/OqqZ0toEL9gL2RyvPhQzL2ynmROl0gcUcLI9v6+Ffk2hpLHFcvkEDd1SOPMequA5OwNJ4Bj3sc/uF+ODGGTvsa7F70adgXdMDp9sF1YAcWqGOy8IapQq75+IC8Kej/UtaTJYs9M7y7z4Xnuk9geUstLmqbj1GPH891n8BpjdV5GVc+stmzvWNCvoLMfO2n2NfLeM2tZgWvLwAoBa8/iI7WWk76I6KiSxv0KqVsAD4FYBkAi1ISpWmtf1jQkc1W6ZY1NpbD3fYTCTor6yWw2rtZFkZo7pDHzmsDFr4vsl/3cGQf6QLreItWA4e2AVBRi1GMymIT/V2yyppjngSRvgkJQsMdFrzS2my0X4LzoX1SUhB9XqP98v1kqHxCmSSIVWbA2fr/t3fmwXGc55l/vu65MRfuiyBBEKQIiiItmbQk67BkW7F8SHGceJ1s7MRbqVW83nWy2nJUm8rhZLccbzmu0qay0TpOXLFzeWN7bceKVrIlW5YY66IkiyREkCBFEgRJ3MBcwFzd8+0fbzfm4MxgZjAn8P6qVCDm6P66h2I/8/Tzvq8xiEIhQaxYAXc7jT9O6hQrUCwkthOrNBxDNf7azZ6iYRjXDav4CnVp8A5QNwfVTiI6MAV4eikyYlJsVHTfQWD/B4sPJ9HjwOh76Jgi83AsnsXSWgoWi4K5vR9Hyr0XAAkHEQsBIkTrMY8hpdPa8gnvJqdSoVXqbfhcN9umCrisSllV/bXumLDZSEG1RGa1ttPoDhPmZ/53L07hX88vod1lxc07acpgq/ftZRim9Smle8M/A/h5ABqA1Yz/mpPZccqEfu/T9HN2vLrbnzkJzJ0EzjxBQjMyn38c7q47gRt/Adh9N4nIzM4BwWl6TyaZ28gU1oU6D2Ry9DeoHy9A6wldI4EJkMvr7KBMrBYHoJBgkzoVs8UCgDAukEKh1mBmpwlzTfEgdXmwuQyxJ43euV6gc69RNOenPzv8FOXQYoBqhw4FMS2FGCxIQUKPBSibGw2QAO676frzEJ5JRyB2vIMyvakE5YO7D9DjkXk6/6f/mdZc6HMee8AYixwghzcaoN/HHqDnzU4LkXnK/iZjEFY7EtKKI9f+Hp2RcwBIOEiHz+ghbDTW1TX6aWuj81Trv3tVppTuDbmU25FhrJ8mrv3GncOIJlOwWtSyOjnUsmNCNbpLDPqdCMe0rMcqEZnV2k4zdJgY6/fhTz5yCH/5iVtwzw09SOooq6sIwzBMrSgl07tDSnl/zVdSDcp1SMvd9vGvAlMv0G187wAJySuvAF37ycU1yTcON1PUqvb0eGGHl5zLzJG6G70/c03rHQ8GSZhGl2ltfTfRNs/9AOg9BEwb61ZtGe3EABLBVurzK0FFaItn6amZE7RGLUaOpmoMvoAgF1uxAVP/Su6uq5NEtaoD3iEgcAlJ1YlUYhVCKAAEkrBC6BIR6YbP6Qf6DpPbe/W17PPg6Sch6vSTwHX3pAvOkmvA4nmaXAeF3GbPQOHPeaOisjzZ3w57Cq/q+2CRdowu/RgX1GFyz0ZuAS4vpNdisdMarS56r/F3b0HpxPTkRehv/DdMDP86jt52Z1Ne7CtxBSt1h6s12a2a2edqRAqqVZBYre00Q1Y8cy3N+PeeYZjtSymi9wUhxE1SylM1X81m2Sh6UCmmmF48B3j6qHetKaAkyNm96+H06wuNw/UN0bZC18hZTCWpuG1+ggTfB7+08ftz12QMVsDMCRrj6xnInuLm7KAOC3YfxRjiq0YMwWYMqJA0LU2qJHw9vRRnMN3eXXeQMF1dIGEamTN6+3ZRRwc9CXQMUVzCatyeFRogVGh6EprigE0moEgNmmLHefcRPDP0eTw8lgCu/Yy6R9g91G7t0jGgYw9w9CGKgwDZ7drMfPGTj5AIb2un82aK4kKfc7Gistzsr2KBw2bH25PnsRi3IxBzwbfLio8d3YEe8VEgdIbOm81Dmd54OJ2jdvixoDvw2uUAHJY2eJzA0Nwz+Mrzg03pclUitCq9DV/NyW7VohqRgmqJzGqKVRabpdMs7fAYhqkPpYjeOwF8UghxEUAc5hBbKQ/VdGWVkOuQRuapW0B4ln7fqBisEKaY1hPUm9bqAMJzdBu+c5TEabFxuJk9dicepy4GFhuQJHEIgIR0ofcvXyRh7dtJt827xyj3urpImVkzXgCFnN4rr1AswN1Dju/F5+h18YhRZKZTVEAodHtepuh3R0/6Vr1vKC2ehUKC1OYGDtxOIji6DNjd9LyS8dfIYgfWIsDoexA69xrcCEMXVmjCDg1W6I526DOnAMsk5Zq9g+Qsx0JUVOcdoIK/rtHC7mz7MInxUqbVlYKZ/V08T39fVDucbW0YUkMYEkHcdFMC6PMB8AHv+QNy/K8cp/cO30XxkpceA9q6cP7iChwWBXarioR0ozsx17StmioRWpVmRhudNa3lmqolMlms1pdSO2awMGaYrUMpovf9NV9Ftch0SCPzxkhbAO6+zUUdTDHt8FKkwdZGHQ7iYaDvULYjCxS/pf7SY9TVweEn1xgg4bm2lF0MZ75/9mR2f9ult4AT/4fe4x2gPKseJ7fU7iLHVLWnIwqzp8iZDM/Qc1IDYIwiFioVoFlc9FXG3UO9eq1OEsJXjqdjB7vuoBhCKkliGKDn9QStPaWnRxs7vMC7HsEPbFPYf+Wb2Bt5FVGrDwuuvYilLPhA+NvAjHGehJJ2pWWKnG/zHBb6nEpxwstl7AHgOw8hqxgQEkH3Xpx+4mv4v95PGBe8IYzltifLWFM4loTbTv9b2fUIwvb+puo2kEu5QqvS2/DN0Je4FdbE1I9S4i2N7nvMMEx1KVjIJoQwK63CBf5rPjKLlhbPGF3AJNC9f+NisGKYxU5dN9D258/Srfml88C5H5IgNZkdBx5/mG6Xn3mCBGhuH9/VpeyRwVqcMrGZTqU5TrfvELmJXaMkEMPXyHFFigSn1GkE8PIFIBamqEJilZzoS8coPuDsALw7aLKZaidnVggqSrN7jXhDisTsvvdTS66YETtYXaZzduEngMOL6a47cfryLI5dDOKE3INENAKsLWesRaehFACO3nYnloUfZz2345L/dqwoHQigDb29vVQcV86Y5UKfc77itEroO0gdLmIBipusziPo2oUXA144Vq9uXOhkrKnLEkUiqcGuheDQwjjXcW/DHc1qUunY482MS64VlaxpYiaIR5+exGe/dQKPPj3ZtKN1W2WdjaSUQs5MYawIsf7np8bn6r1chmGqQDGn9x8BfAjAayD5KDKekwBGariuysh0SMOz5PB27087iZXeAjfjBrpGAjURAlJG79eUDpz4x3Qh24/+O2VrhYWGOIx/m+IF7/5Dum0/9gCtLxai9WhxKhTrGMkv+HIjG6YY1Y33pVJAMkLP2T0knlfnyQl299GI4ZUpcqdTxhQ1IY33GWLXYgc+9Ge0PjM+sXgGWFuh1mOpFJCIIGjphnLsS0g6RqB6BrCipTCbcKDf4oJVUagATQiKPjz5CMbe/0X0dazhzJoXkbgGj8OKGwe96GyzAcm5dEHdRmOWi33OG02rK0RuH+TuMdq/ww/4dwJaHPH5SfRbk1jzDq9f8IAChU7GmnYc/xYunj+LoLMfp/ofxEWjCG4ruYeV3oZvxtv35aypVVy/VllnLvWOEZQSb2l032OGYapLQdErpfyQoKa875JSXq7jmjZH5m3xat0CN0XWk4+QUHR2UsGXrY3iDquLaQd5dYEKy1YXyFG1umi/z38x3af37keoj+/aEonUjhHK1JpOZaYgW7kEJONpUe3wAtGgEUW4gdxkU7h6B42WWqB1rS3QpDdbG4lrqZFQ7hwhJ1hR09ldc3BGcJqed3iB80+TeLa7ANWB04lu7JEaOlKLWBPDaJcBtOuLiKcErNDT2WJnBxC4Anz3N9GejOF2hw/YeRiADiweB6YWqfjrpo9RVrkS4VrqtLo8XBh/CbHn/gxLuhMWlx/7tDl0nvkXwN1PTroxJS+pSfTLi3iq49+tv7foBa/vIHoeOIilmSBeMC/eHmvDqueZ6tLoaWel0irrzKQRQr2UeEszZtEZhqmcopleKaUUQnwXwNvrtJ7qUayYrBL6DlIBVTRI2zOGdMBipwiB6SBrcfpdsRj9cKXRE1dLZ3bzFWqZEYjctmtaIl001TlC3RmCV8nBlinarsVOwnZtmUStqwfQpsihXV2k4jstTu6zTJJjbXFQdjd4mcYEn/sBHZ+ri86Vu4fW4Bui91odCK8lEbe1w6mtwJVYQn/4JKSiQmoaoGgUi7B76Dxra4D0UG545SKwcIbOSVs3FfG5+9MT3+o41GFiJoipn3wDfrRBdflgiS5iZekifNoULLEAgu2HEFqehRKfRyDlhG71YckYUAGUdsHLdA9N96qcgQxMNpU6gNVyDs3tfO+Nq+j12DHa40a3h9y/uKbh6dPLTVXk1IruZCOEeimFnJz7ZpitRSmFbC8JIY5KKY/XfDXVpBq3wHPxDQHzZ9ZFIACjN6097SDPnyE32GoII6mT2GzLk9nNt5bctmude+hn+BpFFTr3APs/RJGJC8+SgGzrocERwcskWm0uErWpFJCIUcbX5qJMsNVDDm8qQeNG4mskTGXSyNhKoH0E2PVOY4iE8Vj/YXjmVSwnu9GvR9C9ehaasGFN8cKvLBhFcVZykFMaiVtFpXZpnn5amxajNme73kmiP7fNWLmjlyvgqfE53JOaR8zVj7bkMgai44jDhlW40BYNIxI7i9m2g0h6u5EIL+PCqhWXFiPY2dlW9gWvkbeZm7HivJI1VXIOJ2aC+PsXp3DMmAg21u+p+Nxn7r/XY0copuH1ywHcstMPIYCXL6zA47DU9fPd6Dy2ojvZKKG+UbylmfoeMwyzeUoRvfcC+JQQ4hJoElvztizLZRO3wPMy9gBw7Q1g/jQ5sHqCzkbX/nQ04dob5GwmY+T06gkqkHIPlBatyDeYomM3idsPP5Z+bGEC2Ps+2v7F54BQgFzo5Bpledt6gNAMOdIpjQSp1QWMvjfd1/bsEzSYIpVIO9eKDQhNU7eH8Dw5xd5+QKawzyfxVlDgx72fxL3zX0dKTyGieODcOQbH8knqAaxaAKePRPviJLnK4VmKaCgKub0rl4CeseyMdS0Hi5jMjuPA5F9hIHoOemIKitShKXZIYcOq7oIllYCiCvQlL2NBd8Bvi+FF3wcwE4rDalHLvuA1wr2qpuCr9roq+QJgnsOkruOViyGEYknYVAV//+IUPv+R6/8JMvdzYSECv5P+eXtjOohbdvorah2X+Rnu7XXjtSnKoZ+fjyCupSAA3DjgLZr5ruYXkFLOYyu6k80s1Jsxi84wTGWUMob4/aCitXcDeABU3LaJMvkWpu8gcPhXDKGYBFQVaOslR9R8/j1/AAzfTflZPQn4dgD9N5MYLKW7gNkpIpN8WeR8o4wVNV1sF1kgZ1VKGkzhHUh3jDDfGw8bTrQx2Uzq5AhrCepMMfpe4MYPAxDA6e+h89ox7BnsRsI3gjfa7sBMxxH4DtwLX0cv5Xj1OInu1UXqgBBdoW3r8fTYXj1JhXWR+ezjmnicigLnTgFnn6SfKb2ybhv5MER1tyWKy84x2PUI/NFpCF2D0GKwWFSccxyCZnWjLbmAuMWLVwc+DtuOQ9jZ4cKXPnoYD9+3r6yLXyVjfjeDKYjGr4WyBF9C0xtecV5qFXxu14E3rwUR1zS8NhVALKnDY7dASolj55fydiQw95PQU3BYVTisKuwWBecXVis695mfYZfbgbfv8sPrsGAuHEdCT+Ho7vb1qANw/edbjVHH+Y6v2Hlsxk4ZG9EM45MZhtn6FHR6hRAOAJ8CMArgFICvSim1Qq/fNixMAKP3ZRfIZd6m7zsIfOzrG9+qL/R8vizyzEnKyJ76JkUlhCDRaHFQhtbs+bu2TA5tPExC0+YmEapFSdDuuoMeN/vc2j20HdUGcxoZZX8VcofNfsdCUMszpxedHg9+LfZ94F3vp0xu4E1q36bHyc21Oem9WgLpccUinW9OrtFxzZygnsBmxnr2JLB8iWIhdg855XNvAsnVyj+r3IJAzwCGBgbJrXO+DTdoL8CdmMWMbRiuXbcgGnHhajQA6TyKl3Y+BAAIR5MVu031dq+eGp+DrqfWRZfdosBlU3F+YRW37u5oaKazlNvX+VzMKytRTC2twmWzwGGlQS5CCLS78ru25n68DitiSX1d9EZiWkXnPvcz7HI7YFVV3G78Howms16fu49qu/2lxgBazZ3kGAHDMPWgWLzh6wCSAI6B3N4DAH67HotqavLFD/K1QisUrZgdp4lek08ZwlAHoAAnvwm853NU5JaZRY5HgMAlclJhFIVJUE42HqQuEe27aduKSrGGeGi9AwHad5KLa3WQSHb2pYV1137K4Gpxeq/FSnEJu5syyAANubA4aFuxcFrsX3yOssuXnqffhUqOt2oBnF1AZJbEc2wFEM50e7dEhIru9ER2dCEWNDLHxgXd6qB1xfI4YqVkf3PjEldeBdZW0L3Tg7fv8uP8vBWvxY9if/R1TFl2YzHsQK8tisVgEK92PYCUlJu+LVzv28xvXgviynIUqqDvF5qewvJqCpouG36ruJQvAPkE4g29bjx7dgG7O1VEYkksROKIaxI7/A68ee36vxvmfkZ72tajCJASVlVUdO43+gw3+nxfemsR0ytRrCZ0tNlVHB70YbTXU/EXkGaOAWyWVhPqDMO0HsXiDQeklB+XUv4lgF8CcFed1tTclBo/yIcpxKZeJPEXC1IONx6mSWQ//D16jen4+oaAyy+SW6pagNU5yuaqViAeSE90W3mLevM6u6hzgp6gXK3VSWJUtVHkwBzgYBb57Xg70HOAti0UEqM73kFt1NwD6WOz2I2BFQFqkXb5Rer2ELxC73G2k5Os2sgtToRpjf5dRlGeEcNQbZTlHb2Pxv5mClW7D0CKHF4p6SdSxuN5zmE0QOfi3NPAP32cBoLMjqdfl1kQKBRqkSYUYPEsut0OjPa0QbE5Me2/FS5fF0ToKn56Vcc3LT+PnwR7cGY2tOnbwvW+zRyKaYAAerwO6BIABAQk1hJ6w28Vl3L7Ol8cZGdnG7rcNkSTKVwJRCEgsMNPx3dlJXpdTMDcj1VVcfNOOs8rUQ03DngrOvfFPsONPt8nTl7FxGwYawkdLquCRDKFn761hJPTKxWL1M3EAHhgBcMw251iTu/6fTsppSaEKPLSbcRmWqGZQiy6ZPTTlVTcBZAgi8yTC3z0N9IupZ6g7hDBq5TRVWwUN9BiNATC7iWRqdiAmZ/RdgByhuNhEqZalJzWfe+/3hHtuxEYvIX+rBudKGxtwLXXm3VSlQAAIABJREFUyFWGEaVYXaB2aXYPsHiORG48RMVxKZ0EaHKV1pyMAv4hWldbL8UboFCLtc69+c9X/yHaVmQmPbijfXe6P3HuOdQTwNVXab2OdopLZBa+5TryXTcA0y+R+JcpTF+bgU+s4uTQr+EshvBaJAA4Aa/NggP93nUhsVmBWk/3yue0ILiWgCIU9PvsWAgnENdS6PbUJ9NZrGCrlNvXhVzM20c68dpUAP0+J7wOC+JaCrqWwg297utiAtn70XDPDT2b/hwLfYaZx2tTBRbDsazWdF9/8TI63TaEohpSErBZFGgpifFrYfzXD4zl2VNpa6kkBlBOIWEzdv5gGIapBsVE72EhhGlpCgBO43eze4O38Fu3MJtphZYpxLSkIXgFgBQAK/nuF5+nSMGqMcBBtZNYVCwUa5ApY7wyKN+rgARuysjQqjaKJ0hQflaolMftvZEyuKaIzLz1bwr3fUZO19NHDunsKRLoiVVqheZqp8iBnqQOEdoqieC1RXKDExEgsUbCu3MviW7vAHVviAfpuemX6BiC08DRh9JDMcwvE703ZX+ZyC3+M8/h1E/p3Fgd5AzHw+kx030H07llM47h7gE8gzRpbvzb8EY9eHPHL2PJvRfnLyzBblEo+xnXN527bJRoONDvg8uqYjYURyiWwnBXG/q8dgx3uWsubEoRVRt9ASgUJXjo7t14ayGCy8tRzASjcNstOLzDh52dbXljAvX4opF5vBYFePnCMiSAW0fa14/9wnwYVlWBnkohrklYFAGnVYUQoiYivBilZotbdZobwzBMKRSbyKbWcyEtRaWt0Ewh5h0wHEdpDHcW5JxaHCQgFZWEbDJGMYFYgJ5TbEAqToLWYqcOEnoSGLkHWL5A4jYRAXYcNaapgVzWnbel25SZ3RAyewGbP49/hUSn+bunj95z/hnA00OZXocXaN9Fa5Qa/XR10chi1U4dLbpuoH7CmVnb8e8Bz3yO4gp2D8U6nvkcPWcKX6uLxGwySsLdO5Ber7kd1Q6c/xEdr63NiC2otK7MbHWuI798EVg6B+y4FegcQejcFHYtPYegaxdCMQ88dnIQ3cbt9Uq7LGxGNGxWiJJoXMNYvzdLNObe+q6FsKlGwVYhFxMAAlENXqcVO9qdiGspXFhcg0VRsLvbXdF6N0vm8Z6eCa3/vbmwsIbbRjqxshrHakKH3QK4bBboKQktJeGwqVndHupFqQVwrTjNjWEYplRK6dPLVAtTiHWMAksX6Pa/KWBVOw2T8O8gRzUZIxfT3UtiMB4GLDrQNpDu3qBYqSNDzxiJ5WiQsrzmNDWrG0hGaKKbw0vua3Ca8rnRgOGOegFXN2WCZ0+SEO/eT9sA6HmrE+g9lBbD8xPApWMABGDbYbQ6cwL7P0DRjHxfCI5/hbpJOI0Lp/nz+FfIfTad58G3k/BNrFJRXma/XgAIXaNYhVBojPPqPGBtA3a/C4iFMK924x+ensTVgI5Dlgdxv/4KekJXabjH4JF1p3tooB+nL2gYmnsGHvtHKQ8L6rkKVF4cVKloqIYQLfXWdy2ETbWGC+RzMX/vOyeRSknMhmJYsaro9tgAACevBOBxWPDZb52o+234zOONxDS47eQRhGKUCpsJxuB1WhFN6EhoKVhVAT0lsRRJ4LM/t68ua8yk1AK4VpzmxjAMUyql9OllSmF2HHj2C8D3Pk0/M4uqTMxoRNco0HeIcrZ2L2DzUF7W6QGG3kFOqRajFmSRWfrP1QF86H8CnzkO/KdXgE/+CzDyLuriIFM01jcRoe3IFOVsA1PkmkZmSWS/9WPqBrEyRfEBu4f2ceFZIDBNYnruNLmr82dozbEQOcexAAnQ8CwN57C5qQexFiN39z1/BDzwaGEHPDxD+8vE7qHHM4vOls7RObF76c96gjLE3/0U8OQjtN+eA8ZoZ51cXqEA828iNHsOX1s6tN4T9YI6jC+s/QImbv0CjVjuHFnfdbfbgQO7B9GdmofPZQUksK/HjU63fVM9QivtzVtqH9tilOoU16J/8KDfiXAsu6NhNboKPHHyKh4/OYOFSBx2i4KkpuPychTJpIaYnoLVolal/225ZB6v28gZx7UUvA4SlUurCezqcOGOPZ2wWRWsJUn4ttkUPHt2se6FZKUWwNXqc2QYhmkG2Okth8xWWaox6MEs/gpdpcKrjaaJmdGIe3F96y2zZ67TT67s5Z9S9tfuJaFnZnLNbWRmi7tGyUlemDBanYUp/hAPkyOsWEkUL5yhCMOiMU45HiZ3d3WehHMyQmLywk8oW6zFgJF7Ke+7MEHdG+xeYPhw2g2OBqiFmbnvzDZi5jHGIxSP8A1SLAGgfXv6s7POphgHqJ1aNEDnN7lGLu/cOEU93P00pW7NyBzbvbgY92FtcH9+BzM34wug25JA99hB/NW9R68TjJX2CK20pdRmHbZynOJatL2qRXu2iZkg/vzHb8GmKlCEMVxQUdDbZkUoqqHP52jYbfjM4x3pcuH4xRVIAAcGPEb3CAV9Xgd2d7uxr8+LhXAML19YhrvOI4tN8t0FODrsx1Pjc1nFd604zY1hGKZUWPSWSmbfV8Vq3N4HxQtmTtAtd+8guY6msDKLqgqRmw029wGQCG3rpczvjndkZ3LN9+TNFn/YEJpPAIqdCty0KCBigLObhPWBEYotLJ4lwQhJwtI/SOI0PEsFbNEAsO99JMQnnySRbQpUkXGTQIsBF5/D0uA9mAw4oF0+h87Tn4fn8AMYmn+OztnQbeQoL1+kVmYyRSL87t8hsWwKUofXaFcG+kLh8FEBXDxEIlcT1OotpdM63L0UA9l1B+InTxV2MO8q3nWjWsVPlYqGzQjRiZkgPvf901iOJNDhtmG0u209N5pPBNZC2FRjuEDuF4/FcAxJPYVenx2zwTgsQkBVJELRJCJxHQcGsu8c5Bt2UauCwszjjcQ13DrSAQEgrkv0eKz4zLv34JmJBQSjSXgcFrx5LQQJ4OBg8ZHFtSTz73ixL0k8JIJhmK0Ki95SybwFf+kYuZ1A+ha83UMiMjMLO3OSog7FhihkkuneRmapkKwrJ1+bOwSj0FohqdBMNVqcpXQaFGFzkeBz96S3O/cmxQYAKiCLKNTzt60r3QvY3G4exxSzp7Bm8eL4rITDImFztSMUU2D96ZextOcWdDrNfrkCmH6FjqH3AAnegx8GZkfTgrRzL2V6gfSkuOgiFctZ7NSCDUb7vOBVKtSz+4DzP4LNvgvhmJZXOE7IXhwXD6L34g8xKK6gZ2gUPfmc+E1SqfirVIia4mUpEkeHy4p4UsfrlwMY6XJhMZLAXDi+vv1y2odVeuwbtfYqJD7zibBj55fgtatQFQX9PgeW1xKIJ1NISWB3Vxvslux/vi4vrWImFMdnv3UCdlXgWjCGXZ1t69v70g8m0eu1I6HLqojgjb4ojXS71487qUvcOtKOLnfhkcX1pFiuu9xx2wzDMK0Ci95SKXQL3uwpm4hmD61YugAELwP+nRtHHvJNGAOuF5elDsEITpNA1GIZDxodIlzGAAuA1u3up/1bjNZfWpycYXcfPQ+QO7xwhoT47nsoZoDhtGMaXcY562E4VAV2Y1SsdHjRHlrCZEDB7cZwN/SMAd03UBTkw4+ll5Yb1Rg25qBcOU7rdvhpAIYQVNwmjEhDKgG0j5CQj4cw4grCtXwGwY79WcLx6LDfEFTDWNj7abwY0xBcS+IhOYTKuqUWpxLXuFIh+vcvTuHCQgTBaBKRmIYerx1SSrx8cQXdHjt6PfaK2odVi1JjF/lEWLuLCsEUmYLdomCH30kFhxL4D/eM4JmJBQAkHi8vreL1ywHcPORHv8+B5ycXEIlp6Pc5oAgrkrqOi4urWIzEcfe+7rrECzLP8aNPT+LiQgQvLixR4ZvDgj6PvS7dJ/J96eCCNYZhtiMseouRKUZXLgHJOGVnM2/BO7xUeGa6vzJFQnBhgnK4uW3BciMPueNyTXFs9sw195FvCEahcby+IUDXgJRmDMEAFXzZ3UDn6PVZ4P7DwKl/onysq5NytimNjisyD0y/DECQ62u6r3qCxKtvCBi5F6GLQdhc6ciDXY9gzd4NbS0AoDu95kLCPV9Uwzw3i+cMAW8EO/d/kKbCRQPU0s3qBPrfBq9qw8+HXsUfzAxgLhRDr9eBX799J5beegMPrjyD7qV5zIluPKkdxcnEID73/dP44wcPNI2rVa4QnZgJ4tj5JfidFvR67bi2EsP0chQWBdBS1Mx5tMed5eKZP+vVQ7jUThH5RNhYvwcvvLWMm4d8mAnGsLSagFVV8Jn37MEHDw1mOakzoThuHvKvi8iEnoLbruL8wiq6PQ6cn1+F264iqcuy4gXVikjs623Dd16/gja7BR67ilA0iZlAFO+r8ZS8Ql86XFal4F2Rze6PB1swDNOssOgtRK4Y1RKG84jsW/B9N5EQ7NhDfWVNIdi+C+jYnb3NfPGEzNgEkP65MFF8CEYhsfzOz1ALr0QYgEIiUeoUdUilaEgEANz7u9nr8O+k9mHhGRLvFj8d1+xJkNgERS2cfgC76ae5jdlxdF7+PEIxBdLhhV2PwKGF8ULnL+LQ6gu0tnKn1wFpB/j4VykP7OygThKqjUTwvvdlxS8WwmsIzJzDgT1e3Lq7A+GYhjdffwl3Lv4j7O5OzKEToZVFfEB8G7LtF3EiMtTSjfefGp9Du4tEi9tmwWC7wEI4jpW1OLrcDtyy07+e7aVcaRCXl9fqOnigVEcxX6bZYbXgztFOdHscsFpU7O1xQwJ49uwiJudWcf/BXjx8H7X/+vd/exyzoRjOLUTgdVhhEQIS1E4MoFZiNkWs99MttI5MqtnPeHJuFbfs9BuDQ+g4b+h1Y3JuFR8sa0vlUehLR0Kj0dRAdQsPebAFwzDNDIveQuSK0c499DN8DbAOp2/B63HA2Qfc8gfZTuWzXygtnpA7LhdIi+NiQzAKieWJx4HJpyiukFyjx4Qx+S25RpnY7/4mcNfvpIdCzI6Tq9x7ExXmxULkbOuJ0rLFfQfheNdv4/JPvoHetRlEXQN4yfdBnBO78I4jR4GFZ8ufXpexbTzwaLar7eyjjhKqLeul0zNzWHP2Z13g3xb7V6yk2tCGNiyvxaGpHtiEgiPRn2La/2vrbcGa/aJc6Bb1WL8Hb0zTFxmXTUWf146YlsKRXe1ZQxDCMQ2hmIYd7a66djwotUCv2DS2sX5flqDqdFuyMroLkThenwrA67Cg22NHLKkjHNeg6Sl0uu1ISQmbqiAS03DjoK/oOjKpZj/jq4Eodna2YbgrHWdISVnzOEGhLx0zQa3quW4ebNGcsPvOMGlY9BYiOJ3u0mDmdjv3Ur/XzDxqIXInghVyOfMVhpWS3S0klmdPAkvnye21uoDoMhWxwRhlbI4dfv6L6fZneQX0MP286d+UtL6Rg7ch3jmW9Y/rQwd7MdLvA3DbxudrI4p1ujDOr74WwOVdD2a9rUufx0WrDzEthbWEDqdVQVh3oiM1h9HutqbNMWZeqGyqwFwojqEOV5aD5rQqsFlU3LLTj/MLq4jENFhVgTtGOqCqynrnAFNA+pyWqvfn3YhSC/Q2yjSbgiqh6Xj5YgiL4RiWV5Po9tjQ7rLBY1fX4w9+lxUOq4oYaNjITDCGgwNeXAvGYLOoSElZkrO5kUtdjpioRZu4Uii232rnujkn3Hyw+84w2bDoLYRqT+d07R7K8E79NO3wbkRucVYhl7NUcZxLIbEcC9Kwi5RGrbxU42KXSlH2VQjaz9pSOl9czG2+7dO0vtVFIHINWF0i8Xz3I9ctqV7FUQDynt+J4V/HRXUYmStYVHuww7WKoYFu/OTsAqIJHZ2WKFTvTnR76CLQbI33cy9Uz08uIBzT0OezQxFpJy1p3KL2Oa3rcQ7THQVwnYB8anyuqPCqhSNUToFesb8/VwOUVX5jOgi7RUEsqUNVgPlwAkk9hR6vA1aLgkhCg0VV4HVYsKPdiT/5yKGs81qOs1lMMJYrJjLFfyypYWImjJW1JO4a7cTETLBm/9/Us+9uo4Q9Uxh23xkmGxa9taRYPCHzNaWI41zGHgB+9N+BKwvUccFiB9q6qX3XjqM0LAIAoJAAhqC+vwC9vq0zHVEo5jb3HaSiumN/CuhJKnTzDqaL7IoNpCi1VVul5JzfozNB/CznAn/ccScesj4BPR5Eh9OC5WgAThHFCe/Pr0+larbG+7kXqqQuqShrfnW95VXuLeo3rwURimnwOS14anwuK+9qcmEhgj//0VvQUhIdbVb0eR1QVQUfO7qjpo5QNb4MDfqd+MnZedgtChxWFQldwqIIqAqdn7iWQrvLBquq474DvdeJr0rWUUwwlismTPH/dy9O4YW3ltHusuKO0Q5YLWpNnbdatafLBw+2aD7YfWeYbFj0FkKPU7516Vw63tB3Ez1eLXLF4W2fLlMcUoW+2bYWkOkOCyP3ANdep/UKBVCdgLubHGs9TtPjzIhC99j1olZRgZ23Uzb5zBPkfJtDMgBg8Ty9Z9ed+btO5Cuwq4XwzSDfBf7+970Xy0uDmPzJN9CbWoDs7MH34kfwxrUO3OnSm/I2X+6Fyu2wIJ7QEIol1x/LvEUNAJeX17Cj3QWPw5JXsE7MBPHMxAJu6HOvd0IIxTR85t17MNbvw6NPT1bFEapVfvD+g7347s+uwu+0QEoJVQgktBQG/A5Ek3rGGGBL1b7MFBOMX/3XS2WLibF+H7o9Drx7f891gryWzlu97sDUU2AzpcHuO8Nkw6K3EKb7mRlniAaoiKoaFOu+UIo4nHichOvAzdnr0xMUj/D0A4d/hQT77Emasra2RA5v+25AtZADaxaxde1PxxdiQeDQL6fFKyT18J1+GRi6lYRv5BqJ5NxCuuNfoYK4jVq11Yh8F/hHxzsQ3PnQ+j/8uwF0GBeCZrwg516oRrvb1kfY5sujluI6Zr7GLKYKRpPr3QOq4QjV2i2+a7QT49dCCMc19HjsCMc16BLoctvR73Pg7FwEXuMYqyW2CgnGRo2bbnbqGnFiNoTdd4bJhkVvISrN2pZKse4LpYjD2ZMkcuPhdK/gti5qmZYbl/jAn6a3nRs5ePYL6XV0jdLrogHg3FNp8erwkUNscaSnzq0aPX0zcXip5dmuO65/vJRJcjVgYiaIp0/PISVT8DltGO1pQ5fb0dRCI/dCZbOo2NnpwoDPgZlg7DoHrRQhtdFrShVxxZzcWucHP377rnVRbQ6kMIXucJcbn7pnT90EVyPGTTNMubD7zjDZsOgtRClZ281kV4sVj23E7DiwMgWaVmYMyph+mYZhdO7ZuNVZcNoYVVxkHZnitesG4MorFJuIBkkUm50gMomFyGGOhSqbJFdlTOfRqgpAUvHTa1MBvH2XH1ZVbVqhke9C9cj9N2yqM8BGrylFxG3k5Nbaxcw9L/UWusXWUutx0wxTKey+M0waFr3FKCYeNxtPqLRVGUCCtXsMWDyTLmLT4lRUdud/Lm+9Vld+kZopXt09lOedOUHdH5x+6t4w+eT1gyeOPrTxJLk6YTqPNw548frlAOwWAZsqMH41hJFud92FRjl513IuVKUIqY1es5GIm5gJ4nPfP43lSAIdbhtGu9vW+wCbTm49XMxSzku9+pLWc9w0wzAMs3lY9FbKZuMJm4lPBKeBzhF63+JZQ5x6Abu/vGEWa0vA1deAeIimnfXdRBGGfOJVtQFde7NFfddofie80ON1xnQeFWFd72UbjiYBIetewFbrvOtGQqrU1+Rbi7n2pUgcHS4r4kkdr18O4JadfnS67etObjO4mM3Ul7SQ+GbnjWEYpjGw6K2UzcQTgMpblQFpl9jdk+6mkOsab7TeyDww9yaNKN79LmD2FLU5G7k3LWw3Eq+FnPBSWrXVgUznsdvjWO/L24gCtlrnXUsRUpWKLXPtXW6aduawqgCA8wursFnSMZF6uJgbubilnudau8HNJL4ZhmEYgkVvpWwmnmBSqTisxCXOXe/iWWpl5mqnNmeevvTz5pqaRLxWSjM4jyatXLVvrn20pw2vTQUAADZVYDmSuO581tLFLEVIlnKeayVIM4X05eU19HvtPBSAYRimiVAavYCWZHacnNJzPwDOPU3twKIBEp5jD9R+/6ZL7PRTtwanf+Ms8dgDtL5oAJApmrCGFBWpmTSwy0ItMJ1Hn9MKOTuO9y38Df5Q/wuMnXmMPsM6Muh3IhzTsh5rlap9c+1dbgfevssPh1XF8loSHW5bXZ3LTBdXEWL9z0+Nz1231kxyz3Mp2ykXU0gHo0n0+xxYjiRwZjaMxUhs/TWt8iWnUUzMBPHo05P47LdO4NGnJzExE2z0khiG2WKw01sumQVhmbGAvsOAqwN46bHaTiEzyefCFusmkRunaOsC3P3peARQsy4L9SosysdYvw9jYhoI/5A+M8dwXQdmmMd+eiaI6aUo9vW6saurraWq9jMd8442O8b61fVxx/V0LUtxcUtx92vhuufGKjrcNoSiyawpeq3yJacRcByEYZh6wE5vuWQWhHn6gL33AYNHaHKbasvujFBPN9EU49FA4TX0HQTu/V3gw48B7/8iDagwnd8aOdW5Dph5Mauri5P5mQnF6D3sT7dtq9VuM459f58XN/S5MTkfwcRMCD6ntWUu6JmO+Uww1rC1l+LilrLWWrjuVwNReBxpD2G0uw2QwGIkjpSU61Pi7j/YW/E+tjK1cN8ZhmFyYae3XPIVsIWuAimtYVPI1vdVTjeJzRTSlUGtC7hKYrNFhxWSe+zDXW60t1HO8+H79tV039WmGToOlJrR3mittch657Zr6/Y4sK/XjdlwPO9AESabVs68MwzTOrDozUexmEC+AjZzvG8m9c7HViLs6lCoVs+LWcEYRTWKDiuAL+TVZazfh/eOdePrL17GXCiGXq8Dv377zqbolZtPSKuqgj9+8AAL3RLgSXUMw9QDjjfkslFMILcgLBoAVCvgHsjeTr2nkPmGaJ+NXEMe6lXAVTRGke8zq0PRYSsXrzUjEzNBPDOxgAP9Xjx4eAAH+r14ZmKhoqjMWL8PD9+3D1/66GE8fN++qvVKbnQEpFW5/2DvegSE4yAMw9QKdnpz2SgmkC8WcNfv5J9OVs8pZJsZdlFD6tU2LF+MYjkSx+e+fxo7O1w4ZHkQ9+uvoCd0tWpRjo0K9JqpZdpWoCmiMkVohghIq1LPSXWNLKxlGKaxsOjNpZSYQL5YQKOnkNUpo1su9bqY5UYJFsIxTM5FkEylcOvuDlyIDeMLa4NVc99KqTav1u34etHsYqDcuEizH0+z0CznqR5fGrhLBMNsb1j05lJp/rMZBjk0wxryUI+LWW4m8PzCKiCALrd9vRocqJ4rWIrrmHk7/tbdHQjHNDwzsYCRbnfTXWBbQQyUk/tsheNpBmp5nppFTGfS7HcLGIapLZzpzaVB+U9mc+RmApcjCUgpMdrTtv6aahaR5baoyrf9VmrD1AprLSf32QrH0wzU6jw1RavCPJTy/+1Wh4eAMNsZFr25VDLtjGk4uYVEHW4b9vd51gcDANUtIiulSK2VLrCVrrWeF9ByisVa6dw3klqdp2b90rHdi0ub9csIw9QLjjfko0ljAkxxMmMUmf+416KIrJQitVZqw1TJWhsRIciNypiiO/cWeiud+0ZSq/PUrO36tntxKcc7mO0OO73MlqTWLaRK2X4rtWGqZK31dPPyOcrFXKtWOveNpFbnqVkd1e3eWo7vgDDbHSGlrPpGjxw5Il999dWqb5dhWo1mLOYpRLlr/ey3TqDf54AixPpjKSkxE4zhSx89nLXNN68FEYpp8DktONDvK+s8ZDrKme6cy6rAalGzXErTtXz4vn0tde4bSS3OU6HPbDsJzGbk0acnr3P2M/+fYZhWRQjxmpTyyEav43gDw9SQVurdWu5aN7o1bgofXU/hynIUEEBwLQGXVcVXnl8rWQAVuiX7ysVlvGesJ+u1ma7VZs79dhLMtfg7Ws++u0zpbPd4B8Ow6GUYpiI2uoCaYvX0TAh2qwKHVUUsqWM2FMdYv7fkHGGhfKiERDimVT2PWq2s8nYSzvlopS982wX+MsJsd1j0MgxTERtdQE2xGolpcNtVAIDdoiAUS5aVIyzkKN885EcwmgRQXdeqGsU+mxXO210wVwM+h/nhLyPMdoZFL8MwFVPsAmqKVbfDgnhSh8OqIq6l4HVYy3JkCznKD929GwCq7lpVo/PAZoQzD9bYPHwOGYbJB4tehtnm1MoRM8Vqn8eOybkI4loKUkoMd7rKcmQ3cpSrLWKq0cZrM8KZ20ptHj6HDMPkg0Uvw2xjaumIZYrVtaS+3r1huMtdtrCu5y3ZahT7bEY4N2uP21aCzyHDMPngPr0Ms42pda/dMaM92Y0DPuzscJXdrqwRVKOX62b63zZrj9tWgs8hwzD5YKeXaTyz48DE40BwGvANAWMP8ES8OlFrR6xVs5WbdZY3UyXPbaU2D59DhmHywaKXaSyz48ALfw44/IB3EIgG6Pd3foaFbx2o9bje7ZytrFQ4c1upzcPnkGGYfLDoZRrLxOMkeJ1++t38OfE4i946UGtHrBWzlc3Q6orbSm0ePocMw+TCmV6msQSnAYc3+zGHlx5nak418qvFaLVspRnHCEaTWXGMiZlgo5fGMAzDbBJ2epnG4huiSIPp8AJALESPM3Whlo5Yq2Urt3Mcg2EYZqvDTi/TWMYeAGIBEr4yRT9jAXqcaXlq7SRXm6uBKDyObC+g2eMYDMMwTGmw08s0lr6DVLSW2b3hlk9wnncL0UrZyloX9jEMwzCNg0Uv03j6DrLIZZqCVotjMAzDMKXD8QaGYRiDVotjMAzDMKXDTi/DMAyub1X2G3cOs9hlGIbZQrDoZRhm29Oqk+NahWbofcwwDMPxBoZhtj2ZrcoUIdb//NT4XKOX1vJw72OGYZoFFr0Mw2x7uFVZ7eAvFAzDNAssehmG2fa02uS4VoK/UDCfsJB9AAAIeElEQVQM0yyw6GUYZttz/8FeBKNJBKNJpKRc//P9B3sbvbSWZWImiEefnsTpayE8P7mAhXBs/Tn+QsEwTCPgQjaGYbY9ZquyzGKrjx3dwcVWFZJZGHh4yIuXL6zg5QvLOLq7HQ6rZcv3PubCPYZpToSUsuobPXLkiHz11Vervl2GYRim+Xn06cmsyXaLkRjGr4aQ0FP4uQN9W1oEZgr+zAEn3AmEYWqHEOI1KeWRjV7HTi/DMAxTVa4Gouj3OdZ/73I7cPc+O2aCMTx8374Grqz2ZBbuAVj/+dT4HItehmkwnOllGIZhqsp2Lgzkwj2GaV5Y9DIMwzBVZTsXBm5nwc8wzQ6LXoZhGKaqmIWBPqcVM8EYfE7rtsm0bmfBzzDNDmd6GYZhmCyq0X1grN+3LURuLtwJhGGaFxa9DMMwzDqZ3QcyxwZvF6e2GmxXwc8wzQ7HGxiGYZh1eGwwwzBbFRa9DMMwzDrcfYBhmK0Ki16GYRhmHe4+wDDMVoVFL8MwDLMOdx9gGGarwqKXYRiGWWc7txtjGGZrw90bGIZhmCy4+wDDMFsRdnoZhmEYhmGYLQ+LXoZhGIZhGGbLw6KXYRiGYRiG2fJwppdhGKaBVGPkL8MwDLMx7PQyDMM0CHPkbzCazBr5OzETbPTSGIZhthwsehmGYRoEj/xlGIapHyx6GYZhGgSP/GUYhqkfLHoZhmEaBI/8ZRiGqR8sehmGYRoEj/xlGIapHyx6GYZhGgSP/GUYhqkf3LKMYRimgfDIX4ZhmPrATi/DMAzDMAyz5WHRyzAMwzAMw2x5WPQyDMMwDMMwWx7O9DIMwzAM01B4HDdTD9jpZRiGYRimYfA4bqZesOhlGIZhGKZh8Dhupl6w6GUYhmEYpmHwOG6mXnCml2EYhmGYhjHodyIYTcLntK4/xuO4W4dWymOz08swDMMwTMPgcdytS6vlsVn0MgzDMAzTMHgcd+vSanlsjjcwDMMwDNNQeBx3a3I1EEW/z5H1WDPnsdnpZRiGYRiGYcpm0O9EOKZlPdbMeWwWvQzDMAzDMEzZtFoem0UvwzAMwzAMUzatlsfmTC/DMAzDMAxTEa2Ux2anl2EYhmEYhtnysOhlGIZhGIZhtjwsehmGYRiGYZgtD4tehmEYhmEYZsvDopdhGIZhGIbZ8rDoZRiGYRiGYbY8LHoZhmEYhmGYLQ+LXoZhGIZhGGbLw6KXYRiGYRiG2fKw6GUYhmEYhmG2PEJKWf2NCrEAYKrqG2YYhmEYhmGYbHZJKbs3elFNRC/DMAzDMAzDNBMcb2AYhmEYhmG2PCx6GYZhGIZhmC0Pi16GYVoKIYQuhHhDCDEuhPiWEMJV4HX/Twjhr2D7A0KIb1e4tq8JIX6pkve2EkKIe4QQ7yzw3H4hxItCiLgQ4rP1XhvDMEwhWPQyDNNqRKWUb5NSHgSQAPCpzCcFoUgpPyClDJS7cSnlNSnllheum+QeAHlFL4BlAL8F4Et1Ww3DMEwJsOhlGKaVOQZgVAgxLISYEEI8BuB1AENCiEtCiK6M5/5KCPGmEOKHQggnAAghRoUQzwghTgghXhdC7DFeP248rwohviSEOCWEOCmE+Izx+B8KIY4bbvNXhBCi2CIL7EcIIf7U2MYpIcTHjNfeI4R4TgjxTSHEpBDifwghflUI8Yrxuj3G674mhPiyEOKY8boPGY87hBB/Y7z2Z0KIe43HPymE+I4Q4ikhxDkhxBcz1vdzhjv7uuGeu43HLwkh/th4/JTh4g6Dvmg8bDjud2Ueq5RyXkp5HEBysx8uwzBMNWHRyzBMSyKEsAB4P4BTxkM3APhbKeXNUsrclol7AfyFlPJGAAEAv2g8/g/G44dBzuVMzvseArAbwM1SykPG6wHgf0kpjxpusxPAhzZYbr79fATA2wAcBvBeAH8qhOg3Xn8YwG8DuAnAJwDsk1K+A8BfA/hMxnaHAbwLwAcBfFkI4QDwHwFASnkTgF8B8HXjcRj7+5ix3Y8JIYaEEF0Afh/Ae6WUtwB4FcB/ydjHovH4/wbwWSnlJQBfBvCo4bgf2+DYGYZhmgJLoxfAMAxTJk4hxBvGn48B+CqAAQBTUsqXCrznopTSfM9rAIaFEB4Ag1LK7wKAlDIGADmm7XsBfFlKqRmvWTYev1cI8QgAF4AOAG8CeDzfjovs504A35BS6gDmhBDPATgKIATguJRyxnjdWwB+aGzuFIB7Mzb/TSllCsA5IcQFAPsB3Angz419nRFCTAHYZ7z+R1LKoLHd0wB2AfADOADgp8ax2wC8mLGP72Sct4/kO0aGYZhWgEUvwzCtRlRK+bbMBwyxtlrkPfGMP+sgd7ZoJMHcNICsZuaGa/oYgCNSymkhxB8BcOR5b+Y2ynkcyF5vKuP3FLL/3c5ttC7L2K5ubEsAeFpK+SsbvMd8PcMwTEvC8QaGYbYlUsoQgCtCiA8DgBDCnqcTxA8BfMqIUkAI0YG0wF00sq9Fi96K7Od5UMRAFUJ0A7gbwCtlHsZHhRCKkfMdAXDW2O6vGvvaB2Cn8XghXgJwhxBi1HiPy3hfMcIAPGWulWEYpqGw6GUYZjvzCQC/JYQ4CeAFAH05z/81gMsATgohTgD4t0ZHiL8CRQ2+B+B4hfv5LoCTAE4A+DGAR6SUs2Wu/yyA5wA8CeBTRnTiMQCqEOIUgH8C8EkpZbzQBqSUCwA+CeAbxvpeAsUkivE4gF/IV8gmhOgTQlwB5YJ/XwhxRQjhLfO4GIZhqg6PIWYYhmlBhBBfA/AvUsqKegozDMNsN9jpZRiGYRiGYbY87PQyDMMwDMMwWx52ehmGYRiGYZgtD4tehmEYhmEYZsvDopdhGIZhGIbZ8rDoZRiGYRiGYbY8LHoZhmEYhmGYLQ+LXoZhGIZhGGbL8/8BX0g2Fjw3fqcAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 864x432 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig = plt.figure(figsize=(12,6))\n",
    "ax = fig.add_subplot(1,1,1,xticks=[], yticks=[])\n",
    "name = [\"Negative\", \"Positive\"]\n",
    "for i in [0,1]:\n",
    "    mask = cancer.target == i\n",
    "    ax.scatter(red[mask,0], red[mask,1], label=name[i], alpha=0.5)\n",
    "ax.set_title(\"ORE NO PCA\")\n",
    "ax.set_xlabel(\"Princical component 1\")\n",
    "ax.set_ylabel(\"Princical component 2\")\n",
    "ax.legend()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "各軸は固有ベクトルであることに注意してほしい。ただPCAを使うだけではこの座標の意味がわからないと思う。なぜなら軸がわからないからだ。   \n",
    "しかし、固有ベクトルへの射影がPCAであることを知っていると各軸は固有ベクトルであることが理解でき射影後の各データの座標自体にはそれほど意味はないとわかる。\n",
    "\n",
    "今回のようにラベル付けして位置関係を把握することに意味があるのだろう。そもそもPCAは可視化を目的としている気がする。"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 既存のPCA"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(569, 2)"
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.decomposition import PCA\n",
    "pca = PCA(n_components=2, whiten=True)\n",
    "pca.fit(dfs)\n",
    "_pca = pca.transform(dfs)\n",
    "_pca.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.legend.Legend at 0x1a2687cd68>"
      ]
     },
     "execution_count": 68,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x432 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig = plt.figure(figsize=(12,6))\n",
    "ax = fig.add_subplot(1,1,1,xticks=[], yticks=[])\n",
    "name = [\"Negative\", \"Positive\"]\n",
    "for i in [0,1]:\n",
    "    mask = cancer.target == i\n",
    "    ax.scatter(_pca[mask,0], _pca[mask,1], label=name[i], alpha=0.5)\n",
    "ax.set_title(\"sklearn NO PCA\")\n",
    "ax.set_xlabel(\"Princical component 1\")\n",
    "ax.set_ylabel(\"Princical component 2\")\n",
    "ax.legend()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# READMORE"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "今回は\n",
    "$$30 \\rightarrow 2$$\n",
    "へと次元削減を行なった。これは\n",
    "\n",
    "> **軸30個** の世界から **軸2個** の世界へ移動\n",
    "\n",
    "ですが、\n",
    "> **軸30個** の世界から **軸30個の世界を軸2個の世界と見た** の世界へ移動\n",
    "\n",
    "はどうなる？\n",
    "\n",
    "これは空間を維持した押しつぶしによる射影である。"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda env:py35]",
   "language": "python",
   "name": "conda-env-py35-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}