Skip to content

Instantly share code, notes, and snippets.

@kevindavenport
Last active July 21, 2021 18:51
Show Gist options
  • Star 28 You must be signed in to star a gist
  • Fork 4 You must be signed in to fork a gist
  • Save kevindavenport/ba71208cf06996d17d2b723f121a52bf to your computer and use it in GitHub Desktop.
Save kevindavenport/ba71208cf06996d17d2b723f121a52bf to your computer and use it in GitHub Desktop.
Display the source blob
Display the rendered blob
Raw
{
"cells": [
{
"cell_type": "code",
"execution_count": 93,
"metadata": {
"collapsed": false,
"hide_input": false
},
"outputs": [],
"source": [
"import time\n",
"import csv\n",
"import pickle\n",
"import random\n",
"import time\n",
"import numpy as np\n",
"import pandas as pd\n",
"import pylab as plt\n",
"import seaborn as sns\n",
"from functools import wraps\n",
"from matplotlib.font_manager import FontProperties\n",
"from scipy import interp\n",
"import matplotlib.pyplot as plt\n",
"from sklearn import cross_validation\n",
"from sklearn import neighbors\n",
"from sklearn import preprocessing\n",
"from sklearn import tree\n",
"from sklearn.ensemble import AdaBoostClassifier\n",
"from sklearn import svm\n",
"from sklearn.learning_curve import learning_curve\n",
"from sklearn.metrics import accuracy_score\n",
"from sklearn.cross_validation import train_test_split\n",
"from sklearn.metrics import roc_curve, auc\n",
"from sklearn.metrics import confusion_matrix\n",
"from sklearn.decomposition import PCA\n",
"\n",
"%matplotlib inline"
]
},
{
"cell_type": "code",
"execution_count": 94,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<!-- just to make a markdown table pretty -->\n",
"<style>table {float:left}</style>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"%%html\n",
"<!-- just to make a markdown table pretty -->\n",
"<style>table {float:left}</style>"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Our Example Data\n",
"\n",
"[This data](http://archive.ics.uci.edu/ml/datasets/Bank+Marketing) is from phone call based direct marketing campaigns of a Portuguese banking institution. The output is whether a customer signed up for the financial product. \n",
"\n",
"#### Why might this dataset be interesting?\n",
"There are progressively more platforms to reach customers such as social media, broadcast media, and physical advertisements. Due to the many input streams and the advancement of comparison shopping, conventional marketing campaigns have a reduced effect on the general public. Competition and budget constraints demand that marketing teams invest on highly refined and directed campaigns that maximize their Return On Investment. Modern campaigns can be created with the use of advanced analytics. \n",
"\n",
"This is a particularly interesting dataset as it seeks to optimize an older and conventional business medium, where as recent optimization involves mobile applications or ad-sponsored streaming media. *The data contains many interpretable social and economic features* thus it will be interesting to see if the stratifying effects of these nominal, ordinal, and numeric variables is intuitive.\n",
"\n",
"In the interest of time I won't step through our analysis and rationale of every single feature like I did in my [Lending Club Data Analysis Blog Post](http://kldavenport.com/lending-club-data-analysis-revisted-with-python/), but we will explore a few. Our pre-processing includes dropping predictors with no power, dummy encoding, and standardization. This is a binary classification problem. What our data will end up like after pre-processing:\n",
"\n",
"\n",
"| **State** | **Observations** | **Features** |\n",
"|------------------|--------------|----------|\n",
"| **Original** | 25211 | 20 |\n",
"| **Pre-processing** | 4119 | 63 |\n",
"\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 95,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Head of data\n",
"age 39\n",
"job services\n",
"marital single\n",
"education high.school\n",
"default no\n",
"housing no\n",
"loan no\n",
"contact telephone\n",
"month may\n",
"day_of_week fri\n",
"duration 346\n",
"campaign 4\n",
"pdays 999\n",
"previous 0\n",
"poutcome nonexistent\n",
"emp.var.rate 1.1\n",
"cons.price.idx 93.994\n",
"cons.conf.idx -36.4\n",
"euribor3m 4.855\n",
"nr.employed 5191\n",
"y no\n",
"Name: 1, dtype: object\n"
]
}
],
"source": [
"data = pd.read_csv('data/bank-additional1.csv')\n",
"# Data was already randomized by author\n",
"data_labels = pd.Series([0 if x == 'no' else 1 for x in data.ix[:,-1]])\n",
"\n",
"print(\"Head of data\")\n",
"print(data.ix[1])"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Exploratory Analysis\n",
"\n",
"The typical things I do in order are as follows:\n",
"\n",
"### 1. Histograms and Aggregation/Facets/Pivots\n",
"An easy place to start is to examine histograms (or scatterplots) of the features to discover characteristics such as sparsity, few unique values, distribution (is it heavy tailed or normally distributed).\n",
"\n",
"Some plots are pretty intuitive like this facetgrid which shows density plots of the respondant age faceted by outcome label (yes/no) and if they were contacted by cell or land line. We can expect a larger count of older respondents for land lines."
]
},
{
"cell_type": "code",
"execution_count": 96,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"<seaborn.axisgrid.FacetGrid at 0x121236f60>"
]
},
"execution_count": 96,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAa0AAAGqCAYAAAC4UxuPAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nEEJUDUlaQgghqsb/ByMTY3MtCLZyAAAAAElFTkSuQmCC\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x12123f9e8>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"g = sns.FacetGrid(data, row=\"contact\", col=\"y\", margin_titles=True)\n",
"g.map(sns.distplot, \"age\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Taking a look at the distribution of the ages in the dataset, it looks probably there wasn't a concerted effort to target a specific age class. The plot of the general workforce population might be similar."
]
},
{
"cell_type": "code",
"execution_count": 97,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"<matplotlib.axes._subplots.AxesSubplot at 0x120490320>"
]
},
"execution_count": 97,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAYAAAAECCAYAAAD3vwBsAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nA0CSCvX/AbtyyBcqZb/rAAAAAElFTkSuQmCC\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x12043c9e8>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"data.age.hist(alpha=.6)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Feature-Target Distributions\n",
"These class histograms conditioned on feature values help us identify features with predictive power.\n",
"Is there a telling difference between the age distribution? between respondents of different outcomes? Note that the histogram is expressed in densities and not in frequencies here for plotting purposes. We can tell very quickly that older respondents signed up for the solicited product more often in this sample. A box-plot could tell the same story."
]
},
{
"cell_type": "code",
"execution_count": 98,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAYUAAAECCAYAAAARlssoAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x12070bdd8>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"sns.kdeplot(data.query(\"y == 'no'\").age, shade=True, alpha=.2, label='No', color='salmon')\n",
"sns.kdeplot(data.query(\"y == 'yes'\").age, shade=True, alpha=.2, label='Yes',color='dodgerblue')\n",
"\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Let's examine our outcome variable pivoted by `poutcome` which describes the outcome of the previous marketing campaign/contact ('failure','nonexistent','success')."
]
},
{
"cell_type": "code",
"execution_count": 100,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"poutcome y \n",
"failure no 387\n",
" yes 67\n",
"nonexistent no 3231\n",
" yes 292\n",
"success no 50\n",
" yes 92\n",
"dtype: int64"
]
},
"execution_count": 100,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"gb = data.groupby(by=[\"poutcome\",\"y\"])\n",
"gbs = gb.size()\n",
"gbs"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Respondents that were a success before, were a success again at 10x the rate of previous failures."
]
},
{
"cell_type": "code",
"execution_count": 101,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"(0.1731266149870801, 0.090374497059733827, 1.8400000000000001)"
]
},
"execution_count": 101,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"gbs[1]/gbs[0] , gbs[3]/gbs[2], gbs[5]/gbs[4]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Imbalanced Data\n",
"If we examine the table above we see a severe distortion of outcomes which may distort the performance of the algorithms we choose to deploy. Test accuracy is not robust in this situation as most models will tend to fit the majority class better (more observations) which may indirectly bring up the overall accuracy. If we care more about recall than precision, that is more success identifying respondents that will sign up for the banking product versus our general ability to classify yes vs no respondents, we might want to use the ROC (Receiver Operating Characteristic) curve and AUC (Area Under Curve ) as a a performance measurement. More on this in other general posts, but to drive intuition I'll give an example: In this dataset 90% of the responses are 'No'. So if we created a naive model that always predicted 'No', we'd have ridiculously high accuracy.\n",
"\n",
"Another way to address this heavy biased data set is to create a new one with resampling such as\n",
"sampling with replacement from the group with less data until the number equals to the larger group and vice versa.\n",
"\n",
"[UnbalancedDataset](https://github.com/fmfn/UnbalancedDataset) is a python package offering a number of re-sampling techniques commonly used in datasets showing strong between-class imbalance. \n",
"\n",
"#### Missing Data\n",
"Although not necessary to produce a plot for, tabular views of the data can help us discover variables that may need imputation. For a quick look at data imputation methods in Pandas look [here](http://pandas.pydata.org/pandas-docs/stable/missing_data.html). We can go from simple imputation like columnwise mean filling, or polynomial approximation for time series, to linear regression (using what we know about other variables), to complex meta-methods (ignoring our class and using ML algos to predict the missing data).\n",
"\n",
"### 2. Correlation Structure\n",
"#### Feature-Target Correlation\n",
"Here we can use correlation measures like mutual information, pearson's correlation coefficient, or chi-squared, based on the type of feature and class we are examining (categorical or numeric)\n",
"\n",
"Below we use [Mutual Information](https://en.wikipedia.org/wiki/Mutual_information). There are many methods more advanced the typical mutual information \n",
"measure we used here which uses Kullback-Leibler divergence. For example there are versions based on quadratic divergence measures which don't require prior assumptions about class densities (assumption of independence). In this example we see a similar importance for `poutcome` as we did before with our simple aggregation table."
]
},
{
"cell_type": "code",
"execution_count": 102,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"[('poutcome', 0.065587942670630867),\n",
" ('contact', 0.015942038384609447),\n",
" ('duration', 0.014895700838497688),\n",
" ('job', 0.0031057910819885454),\n",
" ('campaign', 0.0014596269197607321),\n",
" ('education', 0.0011151723310124562),\n",
" ('marital', 0.00089561182867500366),\n",
" ('loan', -0.00018340180508122201)]"
]
},
"execution_count": 102,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from sklearn import metrics\n",
"f_list = ['education','job','marital','contact','campaign','duration','loan','poutcome']\n",
"sorted([(feature,metrics.adjusted_mutual_info_score(data[feature],data['y'])) for feature in f_list],\n",
" key=lambda x: x[1], reverse=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### How many features do we have really?\n",
"Here we can use PCA or another dimensionality reduction tool to examine structure. Sometimes this allows us to quickly discover the true dimensionality of the data, do we really have 500 features or is it really only 50? If using PCA I like to take a look at the sorted eigenvalues and examine if their values tend to decay slowly or rapidly. If I notice a fast drop off I can identify that there is a lot of structure in fewer features. In the case where the drop off is slower, I might have a harder time finding structure in the data.\n",
" \n",
"More concretely what we're doing is:\n",
"1. Obtaining Eigenvectors and Eigenvalues from the covariance or correlation matrix.\n",
"2. Sorting eigenvalues in descending order to choose the *k* eigenvectors which correspond to the *k* largest eigenvalues where *k* is the number of dimensions of the new feature subspace *(k≤d)*.\n",
"3. Construct the projection matrix *W* from the selected *k* eigenvectors.\n",
"4. Transform the original dataset *X* via *W* to obtain a k-dimensional feature subspace *Y*.\n",
"\n",
"*Note: Eigendecomposition of the covariance or correlation matrix may be more intuitiuve; however, most PCA implementations perform a Singular Vector Decomposition (SVD) to improve the computational efficiency*\n",
"\n",
"For a simple intuition to PCA see an execllent tutorial [here:](http://sebastianraschka.com/Articles/2015_pca_in_3_steps.html)\n",
"\n",
"Let's finish pre-processing our data to get a completely numerical representation of the feature space."
]
},
{
"cell_type": "code",
"execution_count": 103,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# Boiler Plate pre-processing\n",
"\n",
"test_size=.33\n",
"\n",
"pp_data = data.copy()\n",
"\n",
"# Scale numeric data\n",
"dts_cols = [0,10, 11, 12,13,15,16,17,18,19]\n",
"data_to_scale = pp_data.iloc[:, dts_cols].astype(np.float) # change int to float\n",
"scaler = preprocessing.StandardScaler().fit(data_to_scale)\n",
"pp_data.iloc[:, dts_cols] = scaler.transform(data_to_scale)\n",
"\n",
"# Create dummy encoding for categorical data\n",
"dtde_cols = [1, 2, 3, 4, 5, 6, 7, 8, 9, 14]\n",
"data_to_de = pp_data.iloc[:,dtde_cols]\n",
"de_data = pd.get_dummies(data_to_de)\n",
"pp_data.drop(pp_data.columns[dtde_cols], axis=1, inplace=True)\n",
"pp_data = pp_data.merge(de_data, how='inner',left_index=True, right_index=True, copy=False)\n",
"\n",
"pp_data.drop('y',1,inplace=True)\n",
"\n",
"X = pp_data.values\n",
"y = data_labels.values\n",
"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=test_size, random_state=42)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now back to where we were. We can see the features that contribute most to our two principal components. Interestingly enough nothing that we've done so far hints to the warning the dataset provides about the strength of the duration variable.: *\"duration: last contact duration, in seconds (numeric). Important note: this attribute highly affects the output target (e.g., if duration=0 then y='no'). Yet, the duration is not known before a call is performed. Also, after the end of the call y is obviously known. Thus, this input should only be included for benchmark purposes and should be discarded if the intention is to have a realistic predictive model.\"* \n",
"\n",
"If we stopped here with out examination we might not discover the flaw in using this feature until we got to our model training and tuning."
]
},
{
"cell_type": "code",
"execution_count": 104,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"pdays 0.598286\n",
"cons.price.idx 0.325123\n",
"previous 0.305417\n",
"emp.var.rate 0.158449\n",
"euribor3m 0.128620\n",
"poutcome_nonexistent 0.115631\n",
"contact_cellular 0.110780\n",
"cons.conf.idx 0.103740\n",
"contact_telephone 0.097095\n",
"poutcome_failure 0.073725\n",
"marital_single 0.049542\n",
"month_may 0.043885\n",
"default_no 0.040327\n",
"nr.employed 0.038772\n",
"poutcome_success 0.037754\n",
"month_apr 0.033660\n",
"month_jun 0.032950\n",
"duration 0.026043\n",
"default_unknown 0.021619\n",
"housing_yes 0.021206\n",
"job_blue-collar 0.021128\n",
"campaign 0.020842\n",
"marital_married 0.019902\n",
"month_aug 0.019134\n",
"education_high.school 0.017522\n",
"housing_no 0.016727\n",
"month_nov 0.015502\n",
"education_basic.9y 0.014443\n",
"age 0.013488\n",
"month_sep 0.013096\n",
" ... \n",
"day_of_week_wed 0.011663\n",
"month_jul 0.008897\n",
"job_retired 0.008825\n",
"month_mar 0.008493\n",
"job_student 0.008022\n",
"education_basic.4y 0.007861\n",
"day_of_week_thu 0.006818\n",
"day_of_week_mon 0.005996\n",
"loan_yes 0.005809\n",
"job_admin. 0.005244\n",
"month_dec 0.004605\n",
"job_management 0.003933\n",
"day_of_week_tue 0.003701\n",
"education_basic.6y 0.003571\n",
"job_housemaid 0.003172\n",
"marital_divorced 0.002248\n",
"education_professional.course 0.002034\n",
"job_unemployed 0.002003\n",
"education_unknown 0.001931\n",
"loan_no 0.001364\n",
"job_entrepreneur 0.001203\n",
"day_of_week_fri 0.001194\n",
"job_unknown 0.000768\n",
"loan_unknown 0.000733\n",
"housing_unknown 0.000733\n",
"education_illiterate 0.000159\n",
"job_self-employed 0.000154\n",
"marital_unknown 0.000148\n",
"job_technician 0.000055\n",
"default_yes 0.000036\n",
"dtype: float64"
]
},
"execution_count": 104,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pca = PCA(n_components=2)\n",
"pca.fit_transform(pp_data)\n",
"\n",
"pca_df = pd.DataFrame(pca.components_,columns=pp_data.columns,index = ['PC-1','PC-2'])\n",
"\n",
"np.abs(pca_df.max(axis=0)).sort_values(ascending=False) # regardless of sign"
]
},
{
"cell_type": "code",
"execution_count": 153,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"(array([ 0., 10., 20., 30., 40., 50., 60., 70.]),\n",
" <a list of 8 Text xticklabel objects>)"
]
},
"execution_count": 153,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAXIAAAFNCAYAAAAdCORxAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n7v8Dp9vK4KT15WgAAAAASUVORK5CYII=\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x121e71ac8>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"np.abs(pca_df.max(axis=0)).sort_values(ascending=False).plot()\n",
"plt.xticks(rotation='vertical')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Numeric Correlation\n",
"We have a lot of dummy encoded variables so I'm expecting the outcome of a straight numerical correlation won't be too telling. We usually examine our dataframes correlation matrix and drop highly correlated/redundant data to address multicollinearity."
]
},
{
"cell_type": "code",
"execution_count": 105,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"contact_telephone contact_cellular -1.000000\n",
"default_unknown default_no -0.999227\n",
"housing_yes housing_no -0.949959\n",
"poutcome_success pdays -0.940565\n",
"loan_yes loan_no -0.915086\n",
"poutcome_nonexistent poutcome_failure -0.855705\n",
" previous -0.854241\n",
"marital_single marital_married -0.778335\n",
"previous pdays -0.587941\n",
"contact_cellular cons.price.idx -0.574452\n",
"contact_telephone cons.price.idx 0.574452\n",
"euribor3m cons.price.idx 0.657159\n",
"poutcome_failure previous 0.661990\n",
"cons.price.idx emp.var.rate 0.755155\n",
"nr.employed emp.var.rate 0.897173\n",
" euribor3m 0.942589\n",
"euribor3m emp.var.rate 0.970308\n",
"loan_unknown housing_unknown 1.000000\n",
"dtype: float64"
]
},
"execution_count": 105,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cor = pp_data.corr()\n",
"cor.loc[:,:] = np.tril(cor, k=-1) # below main lower triangle of an array\n",
"cor = cor.stack()\n",
"(cor[(cor > 0.55) | (cor < -0.55)]).sort_values()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 3. Dimensional Reduction\n",
"If low dimensional structure, there are off the shelf sets of non-linear dimensionality reductions tools such as T-SNE, Isomap, LOE, variants of PCA or variants of multidimensional scaling with some interesting additional non-linearity. Sometimes these can help us find out manifold or cluster structure and can be helpful for identifying important variations."
]
},
{
"cell_type": "code",
"execution_count": 145,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"from sklearn.manifold import TSNE\n",
"\n",
"t_X = pp_data.ix[:,:10].values # lets only use the standard scaled data\n",
"\n",
"# perform t-SNE embedding\n",
"tsne = TSNE(n_components=2, init='random', random_state=0)\n",
"Y = tsne.fit_transform(t_X)"
]
},
{
"cell_type": "code",
"execution_count": 162,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x11b046f60>"
]
},
"execution_count": 162,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAXoAAAECCAYAAADw0Rw8AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nRU5ErkJggg==\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x1205f3f28>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"plt.scatter(Y[:, 0], Y[:, 1], c=y, cmap=plt.cm.Set3,s=30,alpha=.8)\n",
"# plt.axis('tight')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"I haven't used T-SNE in any meaningful way for years, but some key things to note are if we get a representation where regions overlap less compared to a standard post 2-dimension PCA plot. This might suggest that this dataset can be separated more effectively by non-linear methods that may focus on the local structure. We might find that 2-dimensions isn't enough to accurately represent the internal structure of the data (we might want to look at some 3-D plots)."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"### Conclusion\n",
"Thanks for reading! I might have spent more time on making the header image in photoshop than on the code :)\n",
"\n",
"Let me know via email or twitter if you have any sections you'd like me to expand on. Hope to see you at [PyCon 2016 in Oregon](https://us.pycon.org/2016/)!"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.5.1"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
@evanmiller29
Copy link

Hey mate, absolutely loving the post.

I'm just following through for my own benefit, but found it difficult to follow past the first few steps as the data from the UCI repository isn't the same as what you're using here.
That's cool, but maybe you could include a couple steps for people like me? I've written what I used to solve this problem..

  1. Download from UCI library bank-additional.zip
  2. Extract
  3. Input into Pandas using (the data isn't comma separated..):
    data = pd.read_csv('bank-additional.csv', sep=';')

Cheers, keep up the good work

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment