Skip to content

Instantly share code, notes, and snippets.

@Katba-Caroline

Katba-Caroline/Identify_Customer_Segments.ipynb

Created December 11, 2018 18:22
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save Katba-Caroline/29c0724d55aba66899d914d0764b7051 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save Katba-Caroline/29c0724d55aba66899d914d0764b7051 to your computer and use it in GitHub Desktop.
Download ZIP
Display the source blob
Display the rendered blob
Raw
Identify_Customer_Segments.ipynb
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Project: Identify Customer Segments\n",
"\n",
"In this project, you will apply unsupervised learning techniques to identify segments of the population that form the core customer base for a mail-order sales company in Germany. These segments can then be used to direct marketing campaigns towards audiences that will have the highest expected rate of returns. The data that you will use has been provided by our partners at Bertelsmann Arvato Analytics, and represents a real-life data science task.\n",
"\n",
"This notebook will help you complete this task by providing a framework within which you will perform your analysis steps. In each step of the project, you will see some text describing the subtask that you will perform, followed by one or more code cells for you to complete your work. **Feel free to add additional code and markdown cells as you go along so that you can explore everything in precise chunks.** The code cells provided in the base template will outline only the major tasks, and will usually not be enough to cover all of the minor tasks that comprise it.\n",
"\n",
"It should be noted that while there will be precise guidelines on how you should handle certain tasks in the project, there will also be places where an exact specification is not provided. **There will be times in the project where you will need to make and justify your own decisions on how to treat the data.** These are places where there may not be only one way to handle the data. In real-life tasks, there may be many valid ways to approach an analysis task. One of the most important things you can do is clearly document your approach so that other scientists can understand the decisions you've made.\n",
"\n",
"At the end of most sections, there will be a Markdown cell labeled **Discussion**. In these cells, you will report your findings for the completed section, as well as document the decisions that you made in your approach to each subtask. **Your project will be evaluated not just on the code used to complete the tasks outlined, but also your communication about your observations and conclusions at each stage.**"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"# import libraries here; add more as necessary\n",
"import numpy as np\n",
"import pandas as pd\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"import time\n",
"import pprint\n",
"import operator\n",
"from sklearn.cluster import KMeans\n",
"from sklearn.preprocessing import StandardScaler\n",
"from sklearn.decomposition import PCA \n",
"from sklearn.preprocessing import LabelEncoder\n",
"\n",
"# magic word for producing visualizations in notebook\n",
"%matplotlib inline"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Step 0: Load the Data\n",
"\n",
"There are four files associated with this project (not including this one):\n",
"\n",
"- `Udacity_AZDIAS_Subset.csv`: Demographics data for the general population of Germany; 891211 persons (rows) x 85 features (columns).\n",
"- `Udacity_CUSTOMERS_Subset.csv`: Demographics data for customers of a mail-order company; 191652 persons (rows) x 85 features (columns).\n",
"- `Data_Dictionary.md`: Detailed information file about the features in the provided datasets.\n",
"- `AZDIAS_Feature_Summary.csv`: Summary of feature attributes for demographics data; 85 features (rows) x 4 columns\n",
"\n",
"Each row of the demographics files represents a single person, but also includes information outside of individuals, including information about their household, building, and neighborhood. You will use this information to cluster the general population into groups with similar demographic properties. Then, you will see how the people in the customers dataset fit into those created clusters. The hope here is that certain clusters are over-represented in the customers data, as compared to the general population; those over-represented clusters will be assumed to be part of the core userbase. This information can then be used for further applications, such as targeting for a marketing campaign.\n",
"\n",
"To start off with, load in the demographics data for the general population into a pandas DataFrame, and do the same for the feature attributes summary. Note for all of the `.csv` data files in this project: they're semicolon (`;`) delimited, so you'll need an additional argument in your [`read_csv()`](https://pandas.pydata.org/pandas-docs/stable/generated/pandas.read_csv.html) call to read in the data properly. Also, considering the size of the main dataset, it may take some time for it to load completely.\n",
"\n",
"Once the dataset is loaded, it's recommended that you take a little bit of time just browsing the general structure of the dataset and feature summary file. You'll be getting deep into the innards of the cleaning in the first major step of the project, so gaining some general familiarity can help you get your bearings."
]
},
{
"cell_type": "code",
"execution_count": 153,
"metadata": {},
"outputs": [],
"source": [
"# Load in the general demographics data.\n",
"azdias = pd.read_csv('Udacity_AZDIAS_Subset.csv', delimiter=';')\n"
]
},
{
"cell_type": "code",
"execution_count": 233,
"metadata": {},
"outputs": [],
"source": [
"# Load in the feature summary file.\n",
"feat_info = pd.read_csv('AZDIAS_Feature_Summary.csv', delimiter=';')"
]
},
{
"cell_type": "code",
"execution_count": 155,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Number of columns: 85\n",
"Number of rows: 891221\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>AGER_TYP</th>\n",
" <th>ALTERSKATEGORIE_GROB</th>\n",
" <th>ANREDE_KZ</th>\n",
" <th>CJT_GESAMTTYP</th>\n",
" <th>FINANZ_MINIMALIST</th>\n",
" <th>FINANZ_SPARER</th>\n",
" <th>FINANZ_VORSORGER</th>\n",
" <th>FINANZ_ANLEGER</th>\n",
" <th>FINANZ_UNAUFFAELLIGER</th>\n",
" <th>FINANZ_HAUSBAUER</th>\n",
" <th>...</th>\n",
" <th>PLZ8_ANTG1</th>\n",
" <th>PLZ8_ANTG2</th>\n",
" <th>PLZ8_ANTG3</th>\n",
" <th>PLZ8_ANTG4</th>\n",
" <th>PLZ8_BAUMAX</th>\n",
" <th>PLZ8_HHZ</th>\n",
" <th>PLZ8_GBZ</th>\n",
" <th>ARBEIT</th>\n",
" <th>ORTSGR_KLS9</th>\n",
" <th>RELAT_AB</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>-1</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>2.0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>3</td>\n",
" <td>5</td>\n",
" <td>5</td>\n",
" <td>3</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>-1</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>5.0</td>\n",
" <td>1</td>\n",
" <td>5</td>\n",
" <td>2</td>\n",
" <td>5</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>...</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>-1</td>\n",
" <td>3</td>\n",
" <td>2</td>\n",
" <td>3.0</td>\n",
" <td>1</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>3</td>\n",
" <td>5</td>\n",
" <td>...</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2</td>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>2.0</td>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>5</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>...</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>-1</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>5.0</td>\n",
" <td>4</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>3</td>\n",
" <td>2</td>\n",
" <td>...</td>\n",
" <td>2.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>6.0</td>\n",
" <td>5.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 85 columns</p>\n",
"</div>"
],
"text/plain": [
" AGER_TYP ALTERSKATEGORIE_GROB ANREDE_KZ CJT_GESAMTTYP \\\n",
"0 -1 2 1 2.0 \n",
"1 -1 1 2 5.0 \n",
"2 -1 3 2 3.0 \n",
"3 2 4 2 2.0 \n",
"4 -1 3 1 5.0 \n",
"\n",
" FINANZ_MINIMALIST FINANZ_SPARER FINANZ_VORSORGER FINANZ_ANLEGER \\\n",
"0 3 4 3 5 \n",
"1 1 5 2 5 \n",
"2 1 4 1 2 \n",
"3 4 2 5 2 \n",
"4 4 3 4 1 \n",
"\n",
" FINANZ_UNAUFFAELLIGER FINANZ_HAUSBAUER ... PLZ8_ANTG1 PLZ8_ANTG2 \\\n",
"0 5 3 ... NaN NaN \n",
"1 4 5 ... 2.0 3.0 \n",
"2 3 5 ... 3.0 3.0 \n",
"3 1 2 ... 2.0 2.0 \n",
"4 3 2 ... 2.0 4.0 \n",
"\n",
" PLZ8_ANTG3 PLZ8_ANTG4 PLZ8_BAUMAX PLZ8_HHZ PLZ8_GBZ ARBEIT \\\n",
"0 NaN NaN NaN NaN NaN NaN \n",
"1 2.0 1.0 1.0 5.0 4.0 3.0 \n",
"2 1.0 0.0 1.0 4.0 4.0 3.0 \n",
"3 2.0 0.0 1.0 3.0 4.0 2.0 \n",
"4 2.0 1.0 2.0 3.0 3.0 4.0 \n",
"\n",
" ORTSGR_KLS9 RELAT_AB \n",
"0 NaN NaN \n",
"1 5.0 4.0 \n",
"2 5.0 2.0 \n",
"3 3.0 3.0 \n",
"4 6.0 5.0 \n",
"\n",
"[5 rows x 85 columns]"
]
},
"execution_count": 155,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Check the structure of the data after it's loaded (e.g. print the number of\n",
"# rows and columns, print the first few rows).\n",
"num_rows, num_cols = azdias.shape\n",
"print('Number of columns: {}'.format(num_cols))\n",
"print('Number of rows: {}'.format(num_rows))\n",
"azdias.head(5)\n"
]
},
{
"cell_type": "code",
"execution_count": 156,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>AGER_TYP</th>\n",
" <th>ALTERSKATEGORIE_GROB</th>\n",
" <th>ANREDE_KZ</th>\n",
" <th>CJT_GESAMTTYP</th>\n",
" <th>FINANZ_MINIMALIST</th>\n",
" <th>FINANZ_SPARER</th>\n",
" <th>FINANZ_VORSORGER</th>\n",
" <th>FINANZ_ANLEGER</th>\n",
" <th>FINANZ_UNAUFFAELLIGER</th>\n",
" <th>FINANZ_HAUSBAUER</th>\n",
" <th>...</th>\n",
" <th>PLZ8_ANTG1</th>\n",
" <th>PLZ8_ANTG2</th>\n",
" <th>PLZ8_ANTG3</th>\n",
" <th>PLZ8_ANTG4</th>\n",
" <th>PLZ8_BAUMAX</th>\n",
" <th>PLZ8_HHZ</th>\n",
" <th>PLZ8_GBZ</th>\n",
" <th>ARBEIT</th>\n",
" <th>ORTSGR_KLS9</th>\n",
" <th>RELAT_AB</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>891221.000000</td>\n",
" <td>891221.000000</td>\n",
" <td>891221.000000</td>\n",
" <td>886367.000000</td>\n",
" <td>891221.000000</td>\n",
" <td>891221.000000</td>\n",
" <td>891221.000000</td>\n",
" <td>891221.000000</td>\n",
" <td>891221.000000</td>\n",
" <td>891221.000000</td>\n",
" <td>...</td>\n",
" <td>774706.000000</td>\n",
" <td>774706.000000</td>\n",
" <td>774706.000000</td>\n",
" <td>774706.000000</td>\n",
" <td>774706.000000</td>\n",
" <td>774706.000000</td>\n",
" <td>774706.000000</td>\n",
" <td>794005.000000</td>\n",
" <td>794005.000000</td>\n",
" <td>794005.00000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
" <td>-0.358435</td>\n",
" <td>2.777398</td>\n",
" <td>1.522098</td>\n",
" <td>3.632838</td>\n",
" <td>3.074528</td>\n",
" <td>2.821039</td>\n",
" <td>3.401106</td>\n",
" <td>3.033328</td>\n",
" <td>2.874167</td>\n",
" <td>3.075121</td>\n",
" <td>...</td>\n",
" <td>2.253330</td>\n",
" <td>2.801858</td>\n",
" <td>1.595426</td>\n",
" <td>0.699166</td>\n",
" <td>1.943913</td>\n",
" <td>3.612821</td>\n",
" <td>3.381087</td>\n",
" <td>3.167854</td>\n",
" <td>5.293002</td>\n",
" <td>3.07222</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>1.198724</td>\n",
" <td>1.068775</td>\n",
" <td>0.499512</td>\n",
" <td>1.595021</td>\n",
" <td>1.321055</td>\n",
" <td>1.464749</td>\n",
" <td>1.322134</td>\n",
" <td>1.529603</td>\n",
" <td>1.486731</td>\n",
" <td>1.353248</td>\n",
" <td>...</td>\n",
" <td>0.972008</td>\n",
" <td>0.920309</td>\n",
" <td>0.986736</td>\n",
" <td>0.727137</td>\n",
" <td>1.459654</td>\n",
" <td>0.973967</td>\n",
" <td>1.111598</td>\n",
" <td>1.002376</td>\n",
" <td>2.303739</td>\n",
" <td>1.36298</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>-1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>...</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>0.000000</td>\n",
" <td>1.00000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>-1.000000</td>\n",
" <td>2.000000</td>\n",
" <td>1.000000</td>\n",
" <td>2.000000</td>\n",
" <td>2.000000</td>\n",
" <td>1.000000</td>\n",
" <td>3.000000</td>\n",
" <td>2.000000</td>\n",
" <td>2.000000</td>\n",
" <td>2.000000</td>\n",
" <td>...</td>\n",
" <td>1.000000</td>\n",
" <td>2.000000</td>\n",
" <td>1.000000</td>\n",
" <td>0.000000</td>\n",
" <td>1.000000</td>\n",
" <td>3.000000</td>\n",
" <td>3.000000</td>\n",
" <td>3.000000</td>\n",
" <td>4.000000</td>\n",
" <td>2.00000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>-1.000000</td>\n",
" <td>3.000000</td>\n",
" <td>2.000000</td>\n",
" <td>4.000000</td>\n",
" <td>3.000000</td>\n",
" <td>3.000000</td>\n",
" <td>3.000000</td>\n",
" <td>3.000000</td>\n",
" <td>3.000000</td>\n",
" <td>3.000000</td>\n",
" <td>...</td>\n",
" <td>2.000000</td>\n",
" <td>3.000000</td>\n",
" <td>2.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>4.000000</td>\n",
" <td>3.000000</td>\n",
" <td>3.000000</td>\n",
" <td>5.000000</td>\n",
" <td>3.00000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>-1.000000</td>\n",
" <td>4.000000</td>\n",
" <td>2.000000</td>\n",
" <td>5.000000</td>\n",
" <td>4.000000</td>\n",
" <td>4.000000</td>\n",
" <td>5.000000</td>\n",
" <td>5.000000</td>\n",
" <td>4.000000</td>\n",
" <td>4.000000</td>\n",
" <td>...</td>\n",
" <td>3.000000</td>\n",
" <td>3.000000</td>\n",
" <td>2.000000</td>\n",
" <td>1.000000</td>\n",
" <td>3.000000</td>\n",
" <td>4.000000</td>\n",
" <td>4.000000</td>\n",
" <td>4.000000</td>\n",
" <td>7.000000</td>\n",
" <td>4.00000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>3.000000</td>\n",
" <td>9.000000</td>\n",
" <td>2.000000</td>\n",
" <td>6.000000</td>\n",
" <td>5.000000</td>\n",
" <td>5.000000</td>\n",
" <td>5.000000</td>\n",
" <td>5.000000</td>\n",
" <td>5.000000</td>\n",
" <td>5.000000</td>\n",
" <td>...</td>\n",
" <td>4.000000</td>\n",
" <td>4.000000</td>\n",
" <td>3.000000</td>\n",
" <td>2.000000</td>\n",
" <td>5.000000</td>\n",
" <td>5.000000</td>\n",
" <td>5.000000</td>\n",
" <td>9.000000</td>\n",
" <td>9.000000</td>\n",
" <td>9.00000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>8 rows × 81 columns</p>\n",
"</div>"
],
"text/plain": [
" AGER_TYP ALTERSKATEGORIE_GROB ANREDE_KZ CJT_GESAMTTYP \\\n",
"count 891221.000000 891221.000000 891221.000000 886367.000000 \n",
"mean -0.358435 2.777398 1.522098 3.632838 \n",
"std 1.198724 1.068775 0.499512 1.595021 \n",
"min -1.000000 1.000000 1.000000 1.000000 \n",
"25% -1.000000 2.000000 1.000000 2.000000 \n",
"50% -1.000000 3.000000 2.000000 4.000000 \n",
"75% -1.000000 4.000000 2.000000 5.000000 \n",
"max 3.000000 9.000000 2.000000 6.000000 \n",
"\n",
" FINANZ_MINIMALIST FINANZ_SPARER FINANZ_VORSORGER FINANZ_ANLEGER \\\n",
"count 891221.000000 891221.000000 891221.000000 891221.000000 \n",
"mean 3.074528 2.821039 3.401106 3.033328 \n",
"std 1.321055 1.464749 1.322134 1.529603 \n",
"min 1.000000 1.000000 1.000000 1.000000 \n",
"25% 2.000000 1.000000 3.000000 2.000000 \n",
"50% 3.000000 3.000000 3.000000 3.000000 \n",
"75% 4.000000 4.000000 5.000000 5.000000 \n",
"max 5.000000 5.000000 5.000000 5.000000 \n",
"\n",
" FINANZ_UNAUFFAELLIGER FINANZ_HAUSBAUER ... PLZ8_ANTG1 \\\n",
"count 891221.000000 891221.000000 ... 774706.000000 \n",
"mean 2.874167 3.075121 ... 2.253330 \n",
"std 1.486731 1.353248 ... 0.972008 \n",
"min 1.000000 1.000000 ... 0.000000 \n",
"25% 2.000000 2.000000 ... 1.000000 \n",
"50% 3.000000 3.000000 ... 2.000000 \n",
"75% 4.000000 4.000000 ... 3.000000 \n",
"max 5.000000 5.000000 ... 4.000000 \n",
"\n",
" PLZ8_ANTG2 PLZ8_ANTG3 PLZ8_ANTG4 PLZ8_BAUMAX \\\n",
"count 774706.000000 774706.000000 774706.000000 774706.000000 \n",
"mean 2.801858 1.595426 0.699166 1.943913 \n",
"std 0.920309 0.986736 0.727137 1.459654 \n",
"min 0.000000 0.000000 0.000000 1.000000 \n",
"25% 2.000000 1.000000 0.000000 1.000000 \n",
"50% 3.000000 2.000000 1.000000 1.000000 \n",
"75% 3.000000 2.000000 1.000000 3.000000 \n",
"max 4.000000 3.000000 2.000000 5.000000 \n",
"\n",
" PLZ8_HHZ PLZ8_GBZ ARBEIT ORTSGR_KLS9 \\\n",
"count 774706.000000 774706.000000 794005.000000 794005.000000 \n",
"mean 3.612821 3.381087 3.167854 5.293002 \n",
"std 0.973967 1.111598 1.002376 2.303739 \n",
"min 1.000000 1.000000 1.000000 0.000000 \n",
"25% 3.000000 3.000000 3.000000 4.000000 \n",
"50% 4.000000 3.000000 3.000000 5.000000 \n",
"75% 4.000000 4.000000 4.000000 7.000000 \n",
"max 5.000000 5.000000 9.000000 9.000000 \n",
"\n",
" RELAT_AB \n",
"count 794005.00000 \n",
"mean 3.07222 \n",
"std 1.36298 \n",
"min 1.00000 \n",
"25% 2.00000 \n",
"50% 3.00000 \n",
"75% 4.00000 \n",
"max 9.00000 \n",
"\n",
"[8 rows x 81 columns]"
]
},
"execution_count": 156,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"azdias.describe()"
]
},
{
"cell_type": "code",
"execution_count": 157,
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'pandas.core.frame.DataFrame'>\n",
"RangeIndex: 891221 entries, 0 to 891220\n",
"Data columns (total 85 columns):\n",
"AGER_TYP 891221 non-null int64\n",
"ALTERSKATEGORIE_GROB 891221 non-null int64\n",
"ANREDE_KZ 891221 non-null int64\n",
"CJT_GESAMTTYP 886367 non-null float64\n",
"FINANZ_MINIMALIST 891221 non-null int64\n",
"FINANZ_SPARER 891221 non-null int64\n",
"FINANZ_VORSORGER 891221 non-null int64\n",
"FINANZ_ANLEGER 891221 non-null int64\n",
"FINANZ_UNAUFFAELLIGER 891221 non-null int64\n",
"FINANZ_HAUSBAUER 891221 non-null int64\n",
"FINANZTYP 891221 non-null int64\n",
"GEBURTSJAHR 891221 non-null int64\n",
"GFK_URLAUBERTYP 886367 non-null float64\n",
"GREEN_AVANTGARDE 891221 non-null int64\n",
"HEALTH_TYP 891221 non-null int64\n",
"LP_LEBENSPHASE_FEIN 886367 non-null float64\n",
"LP_LEBENSPHASE_GROB 886367 non-null float64\n",
"LP_FAMILIE_FEIN 886367 non-null float64\n",
"LP_FAMILIE_GROB 886367 non-null float64\n",
"LP_STATUS_FEIN 886367 non-null float64\n",
"LP_STATUS_GROB 886367 non-null float64\n",
"NATIONALITAET_KZ 891221 non-null int64\n",
"PRAEGENDE_JUGENDJAHRE 891221 non-null int64\n",
"RETOURTYP_BK_S 886367 non-null float64\n",
"SEMIO_SOZ 891221 non-null int64\n",
"SEMIO_FAM 891221 non-null int64\n",
"SEMIO_REL 891221 non-null int64\n",
"SEMIO_MAT 891221 non-null int64\n",
"SEMIO_VERT 891221 non-null int64\n",
"SEMIO_LUST 891221 non-null int64\n",
"SEMIO_ERL 891221 non-null int64\n",
"SEMIO_KULT 891221 non-null int64\n",
"SEMIO_RAT 891221 non-null int64\n",
"SEMIO_KRIT 891221 non-null int64\n",
"SEMIO_DOM 891221 non-null int64\n",
"SEMIO_KAEM 891221 non-null int64\n",
"SEMIO_PFLICHT 891221 non-null int64\n",
"SEMIO_TRADV 891221 non-null int64\n",
"SHOPPER_TYP 891221 non-null int64\n",
"SOHO_KZ 817722 non-null float64\n",
"TITEL_KZ 817722 non-null float64\n",
"VERS_TYP 891221 non-null int64\n",
"ZABEOTYP 891221 non-null int64\n",
"ALTER_HH 817722 non-null float64\n",
"ANZ_PERSONEN 817722 non-null float64\n",
"ANZ_TITEL 817722 non-null float64\n",
"HH_EINKOMMEN_SCORE 872873 non-null float64\n",
"KK_KUNDENTYP 306609 non-null float64\n",
"W_KEIT_KIND_HH 783619 non-null float64\n",
"WOHNDAUER_2008 817722 non-null float64\n",
"ANZ_HAUSHALTE_AKTIV 798073 non-null float64\n",
"ANZ_HH_TITEL 794213 non-null float64\n",
"GEBAEUDETYP 798073 non-null float64\n",
"KONSUMNAEHE 817252 non-null float64\n",
"MIN_GEBAEUDEJAHR 798073 non-null float64\n",
"OST_WEST_KZ 798073 non-null object\n",
"WOHNLAGE 798073 non-null float64\n",
"CAMEO_DEUG_2015 792242 non-null object\n",
"CAMEO_DEU_2015 792242 non-null object\n",
"CAMEO_INTL_2015 792242 non-null object\n",
"KBA05_ANTG1 757897 non-null float64\n",
"KBA05_ANTG2 757897 non-null float64\n",
"KBA05_ANTG3 757897 non-null float64\n",
"KBA05_ANTG4 757897 non-null float64\n",
"KBA05_BAUMAX 757897 non-null float64\n",
"KBA05_GBZ 757897 non-null float64\n",
"BALLRAUM 797481 non-null float64\n",
"EWDICHTE 797481 non-null float64\n",
"INNENSTADT 797481 non-null float64\n",
"GEBAEUDETYP_RASTER 798066 non-null float64\n",
"KKK 770025 non-null float64\n",
"MOBI_REGIO 757897 non-null float64\n",
"ONLINE_AFFINITAET 886367 non-null float64\n",
"REGIOTYP 770025 non-null float64\n",
"KBA13_ANZAHL_PKW 785421 non-null float64\n",
"PLZ8_ANTG1 774706 non-null float64\n",
"PLZ8_ANTG2 774706 non-null float64\n",
"PLZ8_ANTG3 774706 non-null float64\n",
"PLZ8_ANTG4 774706 non-null float64\n",
"PLZ8_BAUMAX 774706 non-null float64\n",
"PLZ8_HHZ 774706 non-null float64\n",
"PLZ8_GBZ 774706 non-null float64\n",
"ARBEIT 794005 non-null float64\n",
"ORTSGR_KLS9 794005 non-null float64\n",
"RELAT_AB 794005 non-null float64\n",
"dtypes: float64(49), int64(32), object(4)\n",
"memory usage: 578.0+ MB\n"
]
}
],
"source": [
"azdias.info()"
]
},
{
"cell_type": "code",
"execution_count": 158,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"AGER_TYP int64\n",
"ALTERSKATEGORIE_GROB int64\n",
"ANREDE_KZ int64\n",
"CJT_GESAMTTYP float64\n",
"FINANZ_MINIMALIST int64\n",
"FINANZ_SPARER int64\n",
"FINANZ_VORSORGER int64\n",
"FINANZ_ANLEGER int64\n",
"FINANZ_UNAUFFAELLIGER int64\n",
"FINANZ_HAUSBAUER int64\n",
"FINANZTYP int64\n",
"GEBURTSJAHR int64\n",
"GFK_URLAUBERTYP float64\n",
"GREEN_AVANTGARDE int64\n",
"HEALTH_TYP int64\n",
"LP_LEBENSPHASE_FEIN float64\n",
"LP_LEBENSPHASE_GROB float64\n",
"LP_FAMILIE_FEIN float64\n",
"LP_FAMILIE_GROB float64\n",
"LP_STATUS_FEIN float64\n",
"LP_STATUS_GROB float64\n",
"NATIONALITAET_KZ int64\n",
"PRAEGENDE_JUGENDJAHRE int64\n",
"RETOURTYP_BK_S float64\n",
"SEMIO_SOZ int64\n",
"SEMIO_FAM int64\n",
"SEMIO_REL int64\n",
"SEMIO_MAT int64\n",
"SEMIO_VERT int64\n",
"SEMIO_LUST int64\n",
" ... \n",
"OST_WEST_KZ object\n",
"WOHNLAGE float64\n",
"CAMEO_DEUG_2015 object\n",
"CAMEO_DEU_2015 object\n",
"CAMEO_INTL_2015 object\n",
"KBA05_ANTG1 float64\n",
"KBA05_ANTG2 float64\n",
"KBA05_ANTG3 float64\n",
"KBA05_ANTG4 float64\n",
"KBA05_BAUMAX float64\n",
"KBA05_GBZ float64\n",
"BALLRAUM float64\n",
"EWDICHTE float64\n",
"INNENSTADT float64\n",
"GEBAEUDETYP_RASTER float64\n",
"KKK float64\n",
"MOBI_REGIO float64\n",
"ONLINE_AFFINITAET float64\n",
"REGIOTYP float64\n",
"KBA13_ANZAHL_PKW float64\n",
"PLZ8_ANTG1 float64\n",
"PLZ8_ANTG2 float64\n",
"PLZ8_ANTG3 float64\n",
"PLZ8_ANTG4 float64\n",
"PLZ8_BAUMAX float64\n",
"PLZ8_HHZ float64\n",
"PLZ8_GBZ float64\n",
"ARBEIT float64\n",
"ORTSGR_KLS9 float64\n",
"RELAT_AB float64\n",
"Length: 85, dtype: object"
]
},
"execution_count": 158,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"azdias.dtypes"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"> **Tip**: Add additional cells to keep everything in reasonably-sized chunks! Keyboard shortcut `esc --> a` (press escape to enter command mode, then press the 'A' key) adds a new cell before the active cell, and `esc --> b` adds a new cell after the active cell. If you need to convert an active cell to a markdown cell, use `esc --> m` and to convert to a code cell, use `esc --> y`. \n",
"\n",
"## Step 1: Preprocessing\n",
"\n",
"### Step 1.1: Assess Missing Data\n",
"\n",
"The feature summary file contains a summary of properties for each demographics data column. You will use this file to help you make cleaning decisions during this stage of the project. First of all, you should assess the demographics data in terms of missing data. Pay attention to the following points as you perform your analysis, and take notes on what you observe. Make sure that you fill in the **Discussion** cell with your findings and decisions at the end of each step that has one!\n",
"\n",
"#### Step 1.1.1: Convert Missing Value Codes to NaNs\n",
"The fourth column of the feature attributes summary (loaded in above as `feat_info`) documents the codes from the data dictionary that indicate missing or unknown data. While the file encodes this as a list (e.g. `[-1,0]`), this will get read in as a string object. You'll need to do a little bit of parsing to make use of it to identify and clean the data. Convert data that matches a 'missing' or 'unknown' value code into a numpy NaN value. You might want to see how much data takes on a 'missing' or 'unknown' code, and how much data is naturally missing, as a point of interest.\n",
"\n",
"**As one more reminder, you are encouraged to add additional cells to break up your analysis into manageable chunks.**"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 159,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"Index(['AGER_TYP', 'ALTERSKATEGORIE_GROB', 'ANREDE_KZ', 'CJT_GESAMTTYP',\n",
" 'FINANZ_MINIMALIST', 'FINANZ_SPARER', 'FINANZ_VORSORGER',\n",
" 'FINANZ_ANLEGER', 'FINANZ_UNAUFFAELLIGER', 'FINANZ_HAUSBAUER',\n",
" 'FINANZTYP', 'GEBURTSJAHR', 'GFK_URLAUBERTYP', 'GREEN_AVANTGARDE',\n",
" 'HEALTH_TYP', 'LP_LEBENSPHASE_FEIN', 'LP_LEBENSPHASE_GROB',\n",
" 'LP_FAMILIE_FEIN', 'LP_FAMILIE_GROB', 'LP_STATUS_FEIN',\n",
" 'LP_STATUS_GROB', 'NATIONALITAET_KZ', 'PRAEGENDE_JUGENDJAHRE',\n",
" 'RETOURTYP_BK_S', 'SEMIO_SOZ', 'SEMIO_FAM', 'SEMIO_REL', 'SEMIO_MAT',\n",
" 'SEMIO_VERT', 'SEMIO_LUST', 'SEMIO_ERL', 'SEMIO_KULT', 'SEMIO_RAT',\n",
" 'SEMIO_KRIT', 'SEMIO_DOM', 'SEMIO_KAEM', 'SEMIO_PFLICHT', 'SEMIO_TRADV',\n",
" 'SHOPPER_TYP', 'SOHO_KZ', 'TITEL_KZ', 'VERS_TYP', 'ZABEOTYP',\n",
" 'ALTER_HH', 'ANZ_PERSONEN', 'ANZ_TITEL', 'HH_EINKOMMEN_SCORE',\n",
" 'KK_KUNDENTYP', 'W_KEIT_KIND_HH', 'WOHNDAUER_2008',\n",
" 'ANZ_HAUSHALTE_AKTIV', 'ANZ_HH_TITEL', 'GEBAEUDETYP', 'KONSUMNAEHE',\n",
" 'MIN_GEBAEUDEJAHR', 'OST_WEST_KZ', 'WOHNLAGE', 'CAMEO_DEUG_2015',\n",
" 'CAMEO_DEU_2015', 'CAMEO_INTL_2015', 'KBA05_ANTG1', 'KBA05_ANTG2',\n",
" 'KBA05_ANTG3', 'KBA05_ANTG4', 'KBA05_BAUMAX', 'KBA05_GBZ', 'BALLRAUM',\n",
" 'EWDICHTE', 'INNENSTADT', 'GEBAEUDETYP_RASTER', 'KKK', 'MOBI_REGIO',\n",
" 'ONLINE_AFFINITAET', 'REGIOTYP', 'KBA13_ANZAHL_PKW', 'PLZ8_ANTG1',\n",
" 'PLZ8_ANTG2', 'PLZ8_ANTG3', 'PLZ8_ANTG4', 'PLZ8_BAUMAX', 'PLZ8_HHZ',\n",
" 'PLZ8_GBZ', 'ARBEIT', 'ORTSGR_KLS9', 'RELAT_AB'],\n",
" dtype='object')"
]
},
"execution_count": 159,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"col_names = azdias.columns\n",
"col_names"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 160,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"--- Run time: 0.82 mins ---\n"
]
}
],
"source": [
"# turn missing_or_unknown to list \n",
"feat_info['missing_or_unknown'] = feat_info['missing_or_unknown'].apply(lambda x: x[1:-1].split(','))\n",
"\n",
"start_time = time.time()\n",
"\n",
"# Identify missing or unknown data values and convert them to NaNs.\n",
"for attrib, missing_values in zip(feat_info['attribute'], feat_info['missing_or_unknown']):\n",
" if missing_values[0] != '':\n",
" for value in missing_values:\n",
" if value.isnumeric() or value.lstrip('-').isnumeric():\n",
" value = int(value)\n",
" azdias.loc[azdias[attrib] == value, attrib] = np.nan\n",
" \n",
"print(\"--- Run time: %s mins ---\" % np.round(((time.time() - start_time)/60),2))"
]
},
{
"cell_type": "code",
"execution_count": 161,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>AGER_TYP</th>\n",
" <th>ALTERSKATEGORIE_GROB</th>\n",
" <th>ANREDE_KZ</th>\n",
" <th>CJT_GESAMTTYP</th>\n",
" <th>FINANZ_MINIMALIST</th>\n",
" <th>FINANZ_SPARER</th>\n",
" <th>FINANZ_VORSORGER</th>\n",
" <th>FINANZ_ANLEGER</th>\n",
" <th>FINANZ_UNAUFFAELLIGER</th>\n",
" <th>FINANZ_HAUSBAUER</th>\n",
" <th>...</th>\n",
" <th>PLZ8_ANTG1</th>\n",
" <th>PLZ8_ANTG2</th>\n",
" <th>PLZ8_ANTG3</th>\n",
" <th>PLZ8_ANTG4</th>\n",
" <th>PLZ8_BAUMAX</th>\n",
" <th>PLZ8_HHZ</th>\n",
" <th>PLZ8_GBZ</th>\n",
" <th>ARBEIT</th>\n",
" <th>ORTSGR_KLS9</th>\n",
" <th>RELAT_AB</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>NaN</td>\n",
" <td>2.0</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>5.0</td>\n",
" <td>3.0</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>NaN</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>1.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>5.0</td>\n",
" <td>...</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>NaN</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>...</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>...</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>NaN</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>1.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>...</td>\n",
" <td>2.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>6.0</td>\n",
" <td>5.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 85 columns</p>\n",
"</div>"
],
"text/plain": [
" AGER_TYP ALTERSKATEGORIE_GROB ANREDE_KZ CJT_GESAMTTYP \\\n",
"0 NaN 2.0 1.0 2.0 \n",
"1 NaN 1.0 2.0 5.0 \n",
"2 NaN 3.0 2.0 3.0 \n",
"3 2.0 4.0 2.0 2.0 \n",
"4 NaN 3.0 1.0 5.0 \n",
"\n",
" FINANZ_MINIMALIST FINANZ_SPARER FINANZ_VORSORGER FINANZ_ANLEGER \\\n",
"0 3.0 4.0 3.0 5.0 \n",
"1 1.0 5.0 2.0 5.0 \n",
"2 1.0 4.0 1.0 2.0 \n",
"3 4.0 2.0 5.0 2.0 \n",
"4 4.0 3.0 4.0 1.0 \n",
"\n",
" FINANZ_UNAUFFAELLIGER FINANZ_HAUSBAUER ... PLZ8_ANTG1 PLZ8_ANTG2 \\\n",
"0 5.0 3.0 ... NaN NaN \n",
"1 4.0 5.0 ... 2.0 3.0 \n",
"2 3.0 5.0 ... 3.0 3.0 \n",
"3 1.0 2.0 ... 2.0 2.0 \n",
"4 3.0 2.0 ... 2.0 4.0 \n",
"\n",
" PLZ8_ANTG3 PLZ8_ANTG4 PLZ8_BAUMAX PLZ8_HHZ PLZ8_GBZ ARBEIT \\\n",
"0 NaN NaN NaN NaN NaN NaN \n",
"1 2.0 1.0 1.0 5.0 4.0 3.0 \n",
"2 1.0 0.0 1.0 4.0 4.0 3.0 \n",
"3 2.0 0.0 1.0 3.0 4.0 2.0 \n",
"4 2.0 1.0 2.0 3.0 3.0 4.0 \n",
"\n",
" ORTSGR_KLS9 RELAT_AB \n",
"0 NaN NaN \n",
"1 5.0 4.0 \n",
"2 5.0 2.0 \n",
"3 3.0 3.0 \n",
"4 6.0 5.0 \n",
"\n",
"[5 rows x 85 columns]"
]
},
"execution_count": 161,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"azdias.head()"
]
},
{
"cell_type": "code",
"execution_count": 162,
"metadata": {},
"outputs": [],
"source": [
"azdias.to_csv('azdias_parsed.csv', sep=';', index = False)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# LOAD NEW DATA SET"
]
},
{
"cell_type": "code",
"execution_count": 205,
"metadata": {},
"outputs": [],
"source": [
"#load the post parsed data set and perform similar exploratory functions\n",
"azdiasPP = pd.read_csv('azdias_parsed.csv', delimiter=';')"
]
},
{
"cell_type": "code",
"execution_count": 164,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>AGER_TYP</th>\n",
" <th>ALTERSKATEGORIE_GROB</th>\n",
" <th>ANREDE_KZ</th>\n",
" <th>CJT_GESAMTTYP</th>\n",
" <th>FINANZ_MINIMALIST</th>\n",
" <th>FINANZ_SPARER</th>\n",
" <th>FINANZ_VORSORGER</th>\n",
" <th>FINANZ_ANLEGER</th>\n",
" <th>FINANZ_UNAUFFAELLIGER</th>\n",
" <th>FINANZ_HAUSBAUER</th>\n",
" <th>...</th>\n",
" <th>PLZ8_ANTG1</th>\n",
" <th>PLZ8_ANTG2</th>\n",
" <th>PLZ8_ANTG3</th>\n",
" <th>PLZ8_ANTG4</th>\n",
" <th>PLZ8_BAUMAX</th>\n",
" <th>PLZ8_HHZ</th>\n",
" <th>PLZ8_GBZ</th>\n",
" <th>ARBEIT</th>\n",
" <th>ORTSGR_KLS9</th>\n",
" <th>RELAT_AB</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>NaN</td>\n",
" <td>2.0</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>5.0</td>\n",
" <td>3.0</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>NaN</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>1.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>5.0</td>\n",
" <td>...</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>NaN</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>...</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>...</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>NaN</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>1.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>...</td>\n",
" <td>2.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>6.0</td>\n",
" <td>5.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 85 columns</p>\n",
"</div>"
],
"text/plain": [
" AGER_TYP ALTERSKATEGORIE_GROB ANREDE_KZ CJT_GESAMTTYP \\\n",
"0 NaN 2.0 1.0 2.0 \n",
"1 NaN 1.0 2.0 5.0 \n",
"2 NaN 3.0 2.0 3.0 \n",
"3 2.0 4.0 2.0 2.0 \n",
"4 NaN 3.0 1.0 5.0 \n",
"\n",
" FINANZ_MINIMALIST FINANZ_SPARER FINANZ_VORSORGER FINANZ_ANLEGER \\\n",
"0 3.0 4.0 3.0 5.0 \n",
"1 1.0 5.0 2.0 5.0 \n",
"2 1.0 4.0 1.0 2.0 \n",
"3 4.0 2.0 5.0 2.0 \n",
"4 4.0 3.0 4.0 1.0 \n",
"\n",
" FINANZ_UNAUFFAELLIGER FINANZ_HAUSBAUER ... PLZ8_ANTG1 PLZ8_ANTG2 \\\n",
"0 5.0 3.0 ... NaN NaN \n",
"1 4.0 5.0 ... 2.0 3.0 \n",
"2 3.0 5.0 ... 3.0 3.0 \n",
"3 1.0 2.0 ... 2.0 2.0 \n",
"4 3.0 2.0 ... 2.0 4.0 \n",
"\n",
" PLZ8_ANTG3 PLZ8_ANTG4 PLZ8_BAUMAX PLZ8_HHZ PLZ8_GBZ ARBEIT \\\n",
"0 NaN NaN NaN NaN NaN NaN \n",
"1 2.0 1.0 1.0 5.0 4.0 3.0 \n",
"2 1.0 0.0 1.0 4.0 4.0 3.0 \n",
"3 2.0 0.0 1.0 3.0 4.0 2.0 \n",
"4 2.0 1.0 2.0 3.0 3.0 4.0 \n",
"\n",
" ORTSGR_KLS9 RELAT_AB \n",
"0 NaN NaN \n",
"1 5.0 4.0 \n",
"2 5.0 2.0 \n",
"3 3.0 3.0 \n",
"4 6.0 5.0 \n",
"\n",
"[5 rows x 85 columns]"
]
},
"execution_count": 164,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#As you can see, all of our missing or unknown codes have been transformed to NaNs\n",
"azdiasPP.head()"
]
},
{
"cell_type": "code",
"execution_count": 165,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>AGER_TYP</th>\n",
" <th>ALTERSKATEGORIE_GROB</th>\n",
" <th>ANREDE_KZ</th>\n",
" <th>CJT_GESAMTTYP</th>\n",
" <th>FINANZ_MINIMALIST</th>\n",
" <th>FINANZ_SPARER</th>\n",
" <th>FINANZ_VORSORGER</th>\n",
" <th>FINANZ_ANLEGER</th>\n",
" <th>FINANZ_UNAUFFAELLIGER</th>\n",
" <th>FINANZ_HAUSBAUER</th>\n",
" <th>...</th>\n",
" <th>PLZ8_ANTG1</th>\n",
" <th>PLZ8_ANTG2</th>\n",
" <th>PLZ8_ANTG3</th>\n",
" <th>PLZ8_ANTG4</th>\n",
" <th>PLZ8_BAUMAX</th>\n",
" <th>PLZ8_HHZ</th>\n",
" <th>PLZ8_GBZ</th>\n",
" <th>ARBEIT</th>\n",
" <th>ORTSGR_KLS9</th>\n",
" <th>RELAT_AB</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>205378.000000</td>\n",
" <td>888340.000000</td>\n",
" <td>891221.000000</td>\n",
" <td>886367.000000</td>\n",
" <td>891221.000000</td>\n",
" <td>891221.000000</td>\n",
" <td>891221.000000</td>\n",
" <td>891221.000000</td>\n",
" <td>891221.000000</td>\n",
" <td>891221.000000</td>\n",
" <td>...</td>\n",
" <td>774706.000000</td>\n",
" <td>774706.000000</td>\n",
" <td>774706.000000</td>\n",
" <td>774706.000000</td>\n",
" <td>774706.000000</td>\n",
" <td>774706.000000</td>\n",
" <td>774706.000000</td>\n",
" <td>793846.000000</td>\n",
" <td>793947.000000</td>\n",
" <td>793846.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
" <td>1.743410</td>\n",
" <td>2.757217</td>\n",
" <td>1.522098</td>\n",
" <td>3.632838</td>\n",
" <td>3.074528</td>\n",
" <td>2.821039</td>\n",
" <td>3.401106</td>\n",
" <td>3.033328</td>\n",
" <td>2.874167</td>\n",
" <td>3.075121</td>\n",
" <td>...</td>\n",
" <td>2.253330</td>\n",
" <td>2.801858</td>\n",
" <td>1.595426</td>\n",
" <td>0.699166</td>\n",
" <td>1.943913</td>\n",
" <td>3.612821</td>\n",
" <td>3.381087</td>\n",
" <td>3.166686</td>\n",
" <td>5.293389</td>\n",
" <td>3.071033</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>0.674312</td>\n",
" <td>1.009951</td>\n",
" <td>0.499512</td>\n",
" <td>1.595021</td>\n",
" <td>1.321055</td>\n",
" <td>1.464749</td>\n",
" <td>1.322134</td>\n",
" <td>1.529603</td>\n",
" <td>1.486731</td>\n",
" <td>1.353248</td>\n",
" <td>...</td>\n",
" <td>0.972008</td>\n",
" <td>0.920309</td>\n",
" <td>0.986736</td>\n",
" <td>0.727137</td>\n",
" <td>1.459654</td>\n",
" <td>0.973967</td>\n",
" <td>1.111598</td>\n",
" <td>0.999072</td>\n",
" <td>2.303379</td>\n",
" <td>1.360532</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>...</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>1.000000</td>\n",
" <td>2.000000</td>\n",
" <td>1.000000</td>\n",
" <td>2.000000</td>\n",
" <td>2.000000</td>\n",
" <td>1.000000</td>\n",
" <td>3.000000</td>\n",
" <td>2.000000</td>\n",
" <td>2.000000</td>\n",
" <td>2.000000</td>\n",
" <td>...</td>\n",
" <td>1.000000</td>\n",
" <td>2.000000</td>\n",
" <td>1.000000</td>\n",
" <td>0.000000</td>\n",
" <td>1.000000</td>\n",
" <td>3.000000</td>\n",
" <td>3.000000</td>\n",
" <td>3.000000</td>\n",
" <td>4.000000</td>\n",
" <td>2.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>2.000000</td>\n",
" <td>3.000000</td>\n",
" <td>2.000000</td>\n",
" <td>4.000000</td>\n",
" <td>3.000000</td>\n",
" <td>3.000000</td>\n",
" <td>3.000000</td>\n",
" <td>3.000000</td>\n",
" <td>3.000000</td>\n",
" <td>3.000000</td>\n",
" <td>...</td>\n",
" <td>2.000000</td>\n",
" <td>3.000000</td>\n",
" <td>2.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>4.000000</td>\n",
" <td>3.000000</td>\n",
" <td>3.000000</td>\n",
" <td>5.000000</td>\n",
" <td>3.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>2.000000</td>\n",
" <td>4.000000</td>\n",
" <td>2.000000</td>\n",
" <td>5.000000</td>\n",
" <td>4.000000</td>\n",
" <td>4.000000</td>\n",
" <td>5.000000</td>\n",
" <td>5.000000</td>\n",
" <td>4.000000</td>\n",
" <td>4.000000</td>\n",
" <td>...</td>\n",
" <td>3.000000</td>\n",
" <td>3.000000</td>\n",
" <td>2.000000</td>\n",
" <td>1.000000</td>\n",
" <td>3.000000</td>\n",
" <td>4.000000</td>\n",
" <td>4.000000</td>\n",
" <td>4.000000</td>\n",
" <td>7.000000</td>\n",
" <td>4.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>3.000000</td>\n",
" <td>4.000000</td>\n",
" <td>2.000000</td>\n",
" <td>6.000000</td>\n",
" <td>5.000000</td>\n",
" <td>5.000000</td>\n",
" <td>5.000000</td>\n",
" <td>5.000000</td>\n",
" <td>5.000000</td>\n",
" <td>5.000000</td>\n",
" <td>...</td>\n",
" <td>4.000000</td>\n",
" <td>4.000000</td>\n",
" <td>3.000000</td>\n",
" <td>2.000000</td>\n",
" <td>5.000000</td>\n",
" <td>5.000000</td>\n",
" <td>5.000000</td>\n",
" <td>5.000000</td>\n",
" <td>9.000000</td>\n",
" <td>5.000000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>8 rows × 83 columns</p>\n",
"</div>"
],
"text/plain": [
" AGER_TYP ALTERSKATEGORIE_GROB ANREDE_KZ CJT_GESAMTTYP \\\n",
"count 205378.000000 888340.000000 891221.000000 886367.000000 \n",
"mean 1.743410 2.757217 1.522098 3.632838 \n",
"std 0.674312 1.009951 0.499512 1.595021 \n",
"min 1.000000 1.000000 1.000000 1.000000 \n",
"25% 1.000000 2.000000 1.000000 2.000000 \n",
"50% 2.000000 3.000000 2.000000 4.000000 \n",
"75% 2.000000 4.000000 2.000000 5.000000 \n",
"max 3.000000 4.000000 2.000000 6.000000 \n",
"\n",
" FINANZ_MINIMALIST FINANZ_SPARER FINANZ_VORSORGER FINANZ_ANLEGER \\\n",
"count 891221.000000 891221.000000 891221.000000 891221.000000 \n",
"mean 3.074528 2.821039 3.401106 3.033328 \n",
"std 1.321055 1.464749 1.322134 1.529603 \n",
"min 1.000000 1.000000 1.000000 1.000000 \n",
"25% 2.000000 1.000000 3.000000 2.000000 \n",
"50% 3.000000 3.000000 3.000000 3.000000 \n",
"75% 4.000000 4.000000 5.000000 5.000000 \n",
"max 5.000000 5.000000 5.000000 5.000000 \n",
"\n",
" FINANZ_UNAUFFAELLIGER FINANZ_HAUSBAUER ... PLZ8_ANTG1 \\\n",
"count 891221.000000 891221.000000 ... 774706.000000 \n",
"mean 2.874167 3.075121 ... 2.253330 \n",
"std 1.486731 1.353248 ... 0.972008 \n",
"min 1.000000 1.000000 ... 0.000000 \n",
"25% 2.000000 2.000000 ... 1.000000 \n",
"50% 3.000000 3.000000 ... 2.000000 \n",
"75% 4.000000 4.000000 ... 3.000000 \n",
"max 5.000000 5.000000 ... 4.000000 \n",
"\n",
" PLZ8_ANTG2 PLZ8_ANTG3 PLZ8_ANTG4 PLZ8_BAUMAX \\\n",
"count 774706.000000 774706.000000 774706.000000 774706.000000 \n",
"mean 2.801858 1.595426 0.699166 1.943913 \n",
"std 0.920309 0.986736 0.727137 1.459654 \n",
"min 0.000000 0.000000 0.000000 1.000000 \n",
"25% 2.000000 1.000000 0.000000 1.000000 \n",
"50% 3.000000 2.000000 1.000000 1.000000 \n",
"75% 3.000000 2.000000 1.000000 3.000000 \n",
"max 4.000000 3.000000 2.000000 5.000000 \n",
"\n",
" PLZ8_HHZ PLZ8_GBZ ARBEIT ORTSGR_KLS9 \\\n",
"count 774706.000000 774706.000000 793846.000000 793947.000000 \n",
"mean 3.612821 3.381087 3.166686 5.293389 \n",
"std 0.973967 1.111598 0.999072 2.303379 \n",
"min 1.000000 1.000000 1.000000 1.000000 \n",
"25% 3.000000 3.000000 3.000000 4.000000 \n",
"50% 4.000000 3.000000 3.000000 5.000000 \n",
"75% 4.000000 4.000000 4.000000 7.000000 \n",
"max 5.000000 5.000000 5.000000 9.000000 \n",
"\n",
" RELAT_AB \n",
"count 793846.000000 \n",
"mean 3.071033 \n",
"std 1.360532 \n",
"min 1.000000 \n",
"25% 2.000000 \n",
"50% 3.000000 \n",
"75% 4.000000 \n",
"max 5.000000 \n",
"\n",
"[8 rows x 83 columns]"
]
},
"execution_count": 165,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"azdiasPP.describe()"
]
},
{
"cell_type": "code",
"execution_count": 166,
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'pandas.core.frame.DataFrame'>\n",
"RangeIndex: 891221 entries, 0 to 891220\n",
"Data columns (total 85 columns):\n",
"AGER_TYP 205378 non-null float64\n",
"ALTERSKATEGORIE_GROB 888340 non-null float64\n",
"ANREDE_KZ 891221 non-null float64\n",
"CJT_GESAMTTYP 886367 non-null float64\n",
"FINANZ_MINIMALIST 891221 non-null float64\n",
"FINANZ_SPARER 891221 non-null float64\n",
"FINANZ_VORSORGER 891221 non-null float64\n",
"FINANZ_ANLEGER 891221 non-null float64\n",
"FINANZ_UNAUFFAELLIGER 891221 non-null float64\n",
"FINANZ_HAUSBAUER 891221 non-null float64\n",
"FINANZTYP 891221 non-null float64\n",
"GEBURTSJAHR 498903 non-null float64\n",
"GFK_URLAUBERTYP 886367 non-null float64\n",
"GREEN_AVANTGARDE 891221 non-null int64\n",
"HEALTH_TYP 780025 non-null float64\n",
"LP_LEBENSPHASE_FEIN 793589 non-null float64\n",
"LP_LEBENSPHASE_GROB 796649 non-null float64\n",
"LP_FAMILIE_FEIN 813429 non-null float64\n",
"LP_FAMILIE_GROB 813429 non-null float64\n",
"LP_STATUS_FEIN 886367 non-null float64\n",
"LP_STATUS_GROB 886367 non-null float64\n",
"NATIONALITAET_KZ 782906 non-null float64\n",
"PRAEGENDE_JUGENDJAHRE 783057 non-null float64\n",
"RETOURTYP_BK_S 886367 non-null float64\n",
"SEMIO_SOZ 891221 non-null float64\n",
"SEMIO_FAM 891221 non-null float64\n",
"SEMIO_REL 891221 non-null float64\n",
"SEMIO_MAT 891221 non-null float64\n",
"SEMIO_VERT 891221 non-null float64\n",
"SEMIO_LUST 891221 non-null float64\n",
"SEMIO_ERL 891221 non-null float64\n",
"SEMIO_KULT 891221 non-null float64\n",
"SEMIO_RAT 891221 non-null float64\n",
"SEMIO_KRIT 891221 non-null float64\n",
"SEMIO_DOM 891221 non-null float64\n",
"SEMIO_KAEM 891221 non-null float64\n",
"SEMIO_PFLICHT 891221 non-null float64\n",
"SEMIO_TRADV 891221 non-null float64\n",
"SHOPPER_TYP 780025 non-null float64\n",
"SOHO_KZ 817722 non-null float64\n",
"TITEL_KZ 2160 non-null float64\n",
"VERS_TYP 780025 non-null float64\n",
"ZABEOTYP 891221 non-null float64\n",
"ALTER_HH 580954 non-null float64\n",
"ANZ_PERSONEN 817722 non-null float64\n",
"ANZ_TITEL 817722 non-null float64\n",
"HH_EINKOMMEN_SCORE 872873 non-null float64\n",
"KK_KUNDENTYP 306609 non-null float64\n",
"W_KEIT_KIND_HH 743233 non-null float64\n",
"WOHNDAUER_2008 817722 non-null float64\n",
"ANZ_HAUSHALTE_AKTIV 791610 non-null float64\n",
"ANZ_HH_TITEL 794213 non-null float64\n",
"GEBAEUDETYP 798073 non-null float64\n",
"KONSUMNAEHE 817252 non-null float64\n",
"MIN_GEBAEUDEJAHR 798073 non-null float64\n",
"OST_WEST_KZ 798073 non-null object\n",
"WOHNLAGE 798073 non-null float64\n",
"CAMEO_DEUG_2015 791869 non-null float64\n",
"CAMEO_DEU_2015 791869 non-null object\n",
"CAMEO_INTL_2015 791869 non-null float64\n",
"KBA05_ANTG1 757897 non-null float64\n",
"KBA05_ANTG2 757897 non-null float64\n",
"KBA05_ANTG3 757897 non-null float64\n",
"KBA05_ANTG4 757897 non-null float64\n",
"KBA05_BAUMAX 414697 non-null float64\n",
"KBA05_GBZ 757897 non-null float64\n",
"BALLRAUM 797481 non-null float64\n",
"EWDICHTE 797481 non-null float64\n",
"INNENSTADT 797481 non-null float64\n",
"GEBAEUDETYP_RASTER 798066 non-null float64\n",
"KKK 733157 non-null float64\n",
"MOBI_REGIO 757897 non-null float64\n",
"ONLINE_AFFINITAET 886367 non-null float64\n",
"REGIOTYP 733157 non-null float64\n",
"KBA13_ANZAHL_PKW 785421 non-null float64\n",
"PLZ8_ANTG1 774706 non-null float64\n",
"PLZ8_ANTG2 774706 non-null float64\n",
"PLZ8_ANTG3 774706 non-null float64\n",
"PLZ8_ANTG4 774706 non-null float64\n",
"PLZ8_BAUMAX 774706 non-null float64\n",
"PLZ8_HHZ 774706 non-null float64\n",
"PLZ8_GBZ 774706 non-null float64\n",
"ARBEIT 793846 non-null float64\n",
"ORTSGR_KLS9 793947 non-null float64\n",
"RELAT_AB 793846 non-null float64\n",
"dtypes: float64(82), int64(1), object(2)\n",
"memory usage: 578.0+ MB\n"
]
}
],
"source": [
"azdiasPP.info()"
]
},
{
"cell_type": "code",
"execution_count": 167,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"AGER_TYP 685843\n",
"ALTERSKATEGORIE_GROB 2881\n",
"ANREDE_KZ 0\n",
"CJT_GESAMTTYP 4854\n",
"FINANZ_MINIMALIST 0\n",
"FINANZ_SPARER 0\n",
"FINANZ_VORSORGER 0\n",
"FINANZ_ANLEGER 0\n",
"FINANZ_UNAUFFAELLIGER 0\n",
"FINANZ_HAUSBAUER 0\n",
"FINANZTYP 0\n",
"GEBURTSJAHR 392318\n",
"GFK_URLAUBERTYP 4854\n",
"GREEN_AVANTGARDE 0\n",
"HEALTH_TYP 111196\n",
"LP_LEBENSPHASE_FEIN 97632\n",
"LP_LEBENSPHASE_GROB 94572\n",
"LP_FAMILIE_FEIN 77792\n",
"LP_FAMILIE_GROB 77792\n",
"LP_STATUS_FEIN 4854\n",
"LP_STATUS_GROB 4854\n",
"NATIONALITAET_KZ 108315\n",
"PRAEGENDE_JUGENDJAHRE 108164\n",
"RETOURTYP_BK_S 4854\n",
"SEMIO_SOZ 0\n",
"SEMIO_FAM 0\n",
"SEMIO_REL 0\n",
"SEMIO_MAT 0\n",
"SEMIO_VERT 0\n",
"SEMIO_LUST 0\n",
" ... \n",
"OST_WEST_KZ 93148\n",
"WOHNLAGE 93148\n",
"CAMEO_DEUG_2015 99352\n",
"CAMEO_DEU_2015 99352\n",
"CAMEO_INTL_2015 99352\n",
"KBA05_ANTG1 133324\n",
"KBA05_ANTG2 133324\n",
"KBA05_ANTG3 133324\n",
"KBA05_ANTG4 133324\n",
"KBA05_BAUMAX 476524\n",
"KBA05_GBZ 133324\n",
"BALLRAUM 93740\n",
"EWDICHTE 93740\n",
"INNENSTADT 93740\n",
"GEBAEUDETYP_RASTER 93155\n",
"KKK 158064\n",
"MOBI_REGIO 133324\n",
"ONLINE_AFFINITAET 4854\n",
"REGIOTYP 158064\n",
"KBA13_ANZAHL_PKW 105800\n",
"PLZ8_ANTG1 116515\n",
"PLZ8_ANTG2 116515\n",
"PLZ8_ANTG3 116515\n",
"PLZ8_ANTG4 116515\n",
"PLZ8_BAUMAX 116515\n",
"PLZ8_HHZ 116515\n",
"PLZ8_GBZ 116515\n",
"ARBEIT 97375\n",
"ORTSGR_KLS9 97274\n",
"RELAT_AB 97375\n",
"Length: 85, dtype: int64"
]
},
"execution_count": 167,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"azdiasPP.isnull().sum()"
]
},
{
"cell_type": "code",
"execution_count": 168,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"8373929"
]
},
"execution_count": 168,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"azdiasPP.isnull().sum().sum()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Step 1.1.2: Assess Missing Data in Each Column\n",
"\n",
"How much missing data is present in each column? There are a few columns that are outliers in terms of the proportion of values that are missing. You will want to use matplotlib's [`hist()`](https://matplotlib.org/api/_as_gen/matplotlib.pyplot.hist.html) function to visualize the distribution of missing value counts to find these columns. Identify and document these columns. While some of these columns might have justifications for keeping or re-encoding the data, for this project you should just remove them from the dataframe. (Feel free to make remarks about these outlier columns in the discussion, however!)\n",
"\n",
"For the remaining features, are there any patterns in which columns have, or share, missing data?"
]
},
{
"cell_type": "code",
"execution_count": 206,
"metadata": {},
"outputs": [],
"source": [
"# Perform an assessment of how much missing data there is in each column of the\n",
"# dataset.\n",
"missing_data = azdiasPP.isnull().sum()\n",
"#get the percentage\n",
"missing_data = missing_data[missing_data > 0]/(azdiasPP.shape[0]) * 100\n",
"#sort the values\n",
"missing_data.sort_values(inplace=True)\n"
]
},
{
"cell_type": "code",
"execution_count": 207,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x7f5edd16c0b8>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"#plot the data as specified/sorted above\n",
"\n",
"plt.hist(missing_data, bins = 25)\n",
"\n",
"plt.xlabel('Percentage of missing data(%)')\n",
"plt.ylabel('Counts')\n",
"plt.title('Histogram of number of missing data')\n",
"plt.grid(True)\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Discussion:\n",
"### In the histogram above, we can see that there are several columns with more than a quarter of the values missing. I want to have an understanding of the total percentage of missing values per column before I make a decision about removing columns from this analysis."
]
},
{
"cell_type": "code",
"execution_count": 208,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x7f5edd16c438>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"# Investigate patterns in the amount of missing data in each column.\n",
"missing_data.plot.barh(figsize=(15,30))\n",
"plt.xlabel('Column name with missing values')\n",
"plt.ylabel('Percentage of missing values')\n",
"\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 209,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"TITEL_KZ 99.757636\n",
"AGER_TYP 76.955435\n",
"KK_KUNDENTYP 65.596749\n",
"KBA05_BAUMAX 53.468668\n",
"GEBURTSJAHR 44.020282\n",
"ALTER_HH 34.813699\n",
"REGIOTYP 17.735668\n",
"KKK 17.735668\n",
"W_KEIT_KIND_HH 16.605084\n",
"KBA05_ANTG1 14.959701\n",
"KBA05_ANTG3 14.959701\n",
"KBA05_ANTG2 14.959701\n",
"KBA05_ANTG4 14.959701\n",
"MOBI_REGIO 14.959701\n",
"KBA05_GBZ 14.959701\n",
"PLZ8_ANTG1 13.073637\n",
"PLZ8_ANTG2 13.073637\n",
"PLZ8_ANTG3 13.073637\n",
"PLZ8_GBZ 13.073637\n",
"PLZ8_ANTG4 13.073637\n",
"PLZ8_BAUMAX 13.073637\n",
"PLZ8_HHZ 13.073637\n",
"SHOPPER_TYP 12.476816\n",
"VERS_TYP 12.476816\n",
"HEALTH_TYP 12.476816\n",
"NATIONALITAET_KZ 12.153551\n",
"PRAEGENDE_JUGENDJAHRE 12.136608\n",
"KBA13_ANZAHL_PKW 11.871354\n",
"ANZ_HAUSHALTE_AKTIV 11.176913\n",
"CAMEO_DEUG_2015 11.147852\n",
" ... \n",
"CAMEO_INTL_2015 11.147852\n",
"LP_LEBENSPHASE_FEIN 10.954859\n",
"RELAT_AB 10.926022\n",
"ARBEIT 10.926022\n",
"ORTSGR_KLS9 10.914689\n",
"ANZ_HH_TITEL 10.884842\n",
"LP_LEBENSPHASE_GROB 10.611509\n",
"INNENSTADT 10.518154\n",
"BALLRAUM 10.518154\n",
"EWDICHTE 10.518154\n",
"GEBAEUDETYP_RASTER 10.452514\n",
"MIN_GEBAEUDEJAHR 10.451729\n",
"OST_WEST_KZ 10.451729\n",
"WOHNLAGE 10.451729\n",
"GEBAEUDETYP 10.451729\n",
"LP_FAMILIE_GROB 8.728699\n",
"LP_FAMILIE_FEIN 8.728699\n",
"KONSUMNAEHE 8.299737\n",
"WOHNDAUER_2008 8.247000\n",
"ANZ_TITEL 8.247000\n",
"SOHO_KZ 8.247000\n",
"ANZ_PERSONEN 8.247000\n",
"HH_EINKOMMEN_SCORE 2.058749\n",
"LP_STATUS_GROB 0.544646\n",
"LP_STATUS_FEIN 0.544646\n",
"RETOURTYP_BK_S 0.544646\n",
"ONLINE_AFFINITAET 0.544646\n",
"GFK_URLAUBERTYP 0.544646\n",
"CJT_GESAMTTYP 0.544646\n",
"ALTERSKATEGORIE_GROB 0.323264\n",
"Length: 61, dtype: float64"
]
},
"execution_count": 209,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#just to see the numbers as portrayed above in the plot\n",
"missing_data.sort_values(ascending=False)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Discussion\n",
"### It appears that there is a stark difference between the columns with more than 25% missing data and the rest of the data set. because of this, I would like remove them so as not to skew the results too much. But first, let's see what those columns are."
]
},
{
"cell_type": "code",
"execution_count": 210,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['AGER_TYP', 'GEBURTSJAHR', 'TITEL_KZ', 'ALTER_HH', 'KK_KUNDENTYP', 'KBA05_BAUMAX']\n"
]
}
],
"source": [
"# find columns with more that 25% of data missing\n",
"missing_25P = [col for col in azdiasPP.columns \n",
" if (azdiasPP[col].isnull().sum()/azdiasPP.shape[0])\n",
" * 100 > 25]\n",
"\n",
"print(missing_25P)\n"
]
},
{
"cell_type": "code",
"execution_count": 211,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"TITEL_KZ 99.757636\n",
"AGER_TYP 76.955435\n",
"KK_KUNDENTYP 65.596749\n",
"KBA05_BAUMAX 53.468668\n",
"GEBURTSJAHR 44.020282\n",
"ALTER_HH 34.813699\n",
"REGIOTYP 17.735668\n",
"KKK 17.735668\n",
"W_KEIT_KIND_HH 16.605084\n",
"KBA05_ANTG1 14.959701\n",
"KBA05_ANTG3 14.959701\n",
"KBA05_ANTG2 14.959701\n",
"KBA05_ANTG4 14.959701\n",
"MOBI_REGIO 14.959701\n",
"KBA05_GBZ 14.959701\n",
"PLZ8_ANTG1 13.073637\n",
"PLZ8_ANTG2 13.073637\n",
"PLZ8_ANTG3 13.073637\n",
"PLZ8_GBZ 13.073637\n",
"PLZ8_ANTG4 13.073637\n",
"PLZ8_BAUMAX 13.073637\n",
"PLZ8_HHZ 13.073637\n",
"SHOPPER_TYP 12.476816\n",
"VERS_TYP 12.476816\n",
"HEALTH_TYP 12.476816\n",
"NATIONALITAET_KZ 12.153551\n",
"PRAEGENDE_JUGENDJAHRE 12.136608\n",
"KBA13_ANZAHL_PKW 11.871354\n",
"ANZ_HAUSHALTE_AKTIV 11.176913\n",
"CAMEO_DEUG_2015 11.147852\n",
" ... \n",
"CAMEO_INTL_2015 11.147852\n",
"LP_LEBENSPHASE_FEIN 10.954859\n",
"RELAT_AB 10.926022\n",
"ARBEIT 10.926022\n",
"ORTSGR_KLS9 10.914689\n",
"ANZ_HH_TITEL 10.884842\n",
"LP_LEBENSPHASE_GROB 10.611509\n",
"INNENSTADT 10.518154\n",
"BALLRAUM 10.518154\n",
"EWDICHTE 10.518154\n",
"GEBAEUDETYP_RASTER 10.452514\n",
"MIN_GEBAEUDEJAHR 10.451729\n",
"OST_WEST_KZ 10.451729\n",
"WOHNLAGE 10.451729\n",
"GEBAEUDETYP 10.451729\n",
"LP_FAMILIE_GROB 8.728699\n",
"LP_FAMILIE_FEIN 8.728699\n",
"KONSUMNAEHE 8.299737\n",
"WOHNDAUER_2008 8.247000\n",
"ANZ_TITEL 8.247000\n",
"SOHO_KZ 8.247000\n",
"ANZ_PERSONEN 8.247000\n",
"HH_EINKOMMEN_SCORE 2.058749\n",
"LP_STATUS_GROB 0.544646\n",
"LP_STATUS_FEIN 0.544646\n",
"RETOURTYP_BK_S 0.544646\n",
"ONLINE_AFFINITAET 0.544646\n",
"GFK_URLAUBERTYP 0.544646\n",
"CJT_GESAMTTYP 0.544646\n",
"ALTERSKATEGORIE_GROB 0.323264\n",
"Length: 61, dtype: float64"
]
},
"execution_count": 211,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"missing_data.sort_values(ascending=False)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Discussion\n",
"### Looking at the columns with more than 25% of their data missing, I don't think that our analysis would suffer much without those values. I will choose to drop them. "
]
},
{
"cell_type": "code",
"execution_count": 212,
"metadata": {},
"outputs": [],
"source": [
"# Remove the outlier columns from the dataset. (You'll perform other data\n",
"# engineering tasks such as re-encoding and imputation later.)\n",
"for col in missing_25P:\n",
" azdiasPP.drop(col, axis=1, inplace=True)\n"
]
},
{
"cell_type": "code",
"execution_count": 213,
"metadata": {},
"outputs": [],
"source": [
"#check to make sure that our code was successful\n",
"missing_data_check = azdiasPP.isnull().sum()\n",
"#get the percentage\n",
"missing_data_check = missing_data_check[missing_data_check > 0]/(azdiasPP.shape[0]) * 100\n",
"#sort the values\n",
"missing_data_check.sort_values(inplace=True)"
]
},
{
"cell_type": "code",
"execution_count": 214,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"REGIOTYP 17.735668\n",
"KKK 17.735668\n",
"W_KEIT_KIND_HH 16.605084\n",
"KBA05_ANTG2 14.959701\n",
"KBA05_ANTG3 14.959701\n",
"KBA05_ANTG4 14.959701\n",
"KBA05_GBZ 14.959701\n",
"MOBI_REGIO 14.959701\n",
"KBA05_ANTG1 14.959701\n",
"PLZ8_GBZ 13.073637\n",
"PLZ8_ANTG3 13.073637\n",
"PLZ8_BAUMAX 13.073637\n",
"PLZ8_ANTG2 13.073637\n",
"PLZ8_ANTG4 13.073637\n",
"PLZ8_ANTG1 13.073637\n",
"PLZ8_HHZ 13.073637\n",
"SHOPPER_TYP 12.476816\n",
"VERS_TYP 12.476816\n",
"HEALTH_TYP 12.476816\n",
"NATIONALITAET_KZ 12.153551\n",
"PRAEGENDE_JUGENDJAHRE 12.136608\n",
"KBA13_ANZAHL_PKW 11.871354\n",
"ANZ_HAUSHALTE_AKTIV 11.176913\n",
"CAMEO_INTL_2015 11.147852\n",
"CAMEO_DEU_2015 11.147852\n",
"CAMEO_DEUG_2015 11.147852\n",
"LP_LEBENSPHASE_FEIN 10.954859\n",
"ARBEIT 10.926022\n",
"RELAT_AB 10.926022\n",
"ORTSGR_KLS9 10.914689\n",
"ANZ_HH_TITEL 10.884842\n",
"LP_LEBENSPHASE_GROB 10.611509\n",
"EWDICHTE 10.518154\n",
"INNENSTADT 10.518154\n",
"BALLRAUM 10.518154\n",
"GEBAEUDETYP_RASTER 10.452514\n",
"WOHNLAGE 10.451729\n",
"GEBAEUDETYP 10.451729\n",
"MIN_GEBAEUDEJAHR 10.451729\n",
"OST_WEST_KZ 10.451729\n",
"LP_FAMILIE_GROB 8.728699\n",
"LP_FAMILIE_FEIN 8.728699\n",
"KONSUMNAEHE 8.299737\n",
"ANZ_TITEL 8.247000\n",
"SOHO_KZ 8.247000\n",
"WOHNDAUER_2008 8.247000\n",
"ANZ_PERSONEN 8.247000\n",
"HH_EINKOMMEN_SCORE 2.058749\n",
"ONLINE_AFFINITAET 0.544646\n",
"CJT_GESAMTTYP 0.544646\n",
"GFK_URLAUBERTYP 0.544646\n",
"LP_STATUS_FEIN 0.544646\n",
"LP_STATUS_GROB 0.544646\n",
"RETOURTYP_BK_S 0.544646\n",
"ALTERSKATEGORIE_GROB 0.323264\n",
"dtype: float64"
]
},
"execution_count": 214,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"missing_data_check.sort_values(ascending = False)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Discussion 1.1.2: Assess Missing Data in Each Column\n",
"\n",
"here we investigated the data and looked at the amount of missing data in each columns and chose to remove columns which had more than 25% of their data missing, those include:['AGER_TYP', 'GEBURTSJAHR', 'TITEL_KZ', 'ALTER_HH', 'KK_KUNDENTYP', 'KBA05_BAUMAX']"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Step 1.1.3: Assess Missing Data in Each Row\n",
"\n",
"Now, you'll perform a similar assessment for the rows of the dataset. How much data is missing in each row? As with the columns, you should see some groups of points that have a very different numbers of missing values. Divide the data into two subsets: one for data points that are above some threshold for missing values, and a second subset for points below that threshold.\n",
"\n",
"In order to know what to do with the outlier rows, we should see if the distribution of data values on columns that are not missing data (or are missing very little data) are similar or different between the two groups. Select at least five of these columns and compare the distribution of values.\n",
"- You can use seaborn's [`countplot()`](https://seaborn.pydata.org/generated/seaborn.countplot.html) function to create a bar chart of code frequencies and matplotlib's [`subplot()`](https://matplotlib.org/api/_as_gen/matplotlib.pyplot.subplot.html) function to put bar charts for the two subplots side by side.\n",
"- To reduce repeated code, you might want to write a function that can perform this comparison, taking as one of its arguments a column to be compared.\n",
"\n",
"Depending on what you observe in your comparison, this will have implications on how you approach your conclusions later in the analysis. If the distributions of non-missing features look similar between the data with many missing values and the data with few or no missing values, then we could argue that simply dropping those points from the analysis won't present a major issue. On the other hand, if the data with many missing values looks very different from the data with few or no missing values, then we should make a note on those data as special. We'll revisit these data later on. **Either way, you should continue your analysis for now using just the subset of the data with few or no missing values.**"
]
},
{
"cell_type": "code",
"execution_count": 215,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAZUAAAEWCAYAAACufwpNAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMS4wLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvpW3flQAAIABJREFUeJzt3XucHFWd9/HPl4RAJEC4meXqwCYiIIoQMCi4w+XBcFFYBYRFCYrGVVDQqIAXRBA3rqvgDXbzAAKKBETFGNDIExguCiEJtxCQJYZgIpeAJEC4ycDv+eOcIZWhe6ZnUj3dPfm+X69+TdWpU1XnVNXUr05V9WlFBGZmZmVYq9EFMDOzwcNBxczMSuOgYmZmpXFQMTOz0jiomJlZaRxUzMysNA4qLU7SfEntjS5HI0n6V0mLJa2Q9I7VXNbekh5Yjfm3yeUYsjrlqHFdx0m6pd7raUWSjpH0h0aXY03koNLEJC2StH+3tFVOJBGxU0R09LKcNkkhaWiditpo/wWcGBEjIuLO1VlQRNwcEduvxvx/zeV4ZXXKUTZJZ0j6WaPL0RerEzQj4rKIOKDsMlnvHFRstTVBsHoTML/BZbBBqgmO75bioNLiiq0ZSXtImiPpGUmPS/peznZT/rs835rZU9Jakr4q6WFJSyVdKmnDwnKPzdP+Lulr3dZzhqSrJP1M0jPAcXndt0paLulRST+SNKywvJD0aUkPSnpW0lmS/jnP84ykK4v5u9WxYlklrSNpBTAEuFvSX6rMX/O6JbVLWlKY9xRJf8vzPSBpv562dfdWoaSOvL4/5mX8QdKmtWznCvXYRNK0vM7bgX/uNv37+TbgM5LmSto7p48Hvgx8KO//u3P6RyXdn8u1UNInK623sPxPFPLfJ2nXnL5Drudypdux7y/M0yHp44XxVVofeVv9e943yyT9WMkOwH8De+YyL8/5D8rrfjbvly9UKWtN66kyb6Xjex1J50p6JH/OlbROzn+jpA/m4b3yug7K4/tLuisPj855n5b0pKQretreLSsi/GnSD7AI2L9b2nHALZXyALcCH8nDI4BxebgNCGBoYb6PAQuA7XLeXwE/zdN2BFYAewHDSLeXXi6s54w8fhjpwmQ4sBswDhia13c/cHJhfQFMAzYAdgJeAmbm9W8I3AdMqLIdqpa1sOzRPWzHmtcNtANL8vD2wGJgi8J2/Oe+bGugA/gL8Oa8nTqAybVs5wr1mApcCawHvBX4W7dj4cPAJnkfTAIeA9Yt7LOfdVvewaTAJOBfgOeBXaus+4i8vt1z/tGkFuLaed98OddhX+BZYPtC/T/ew/EbwHRgJLAN8AQwvlLenPYosHce3qiH8ta8ngrznsHrj+8zgduANwKbAX8Czsr5zwR+mIe/nPf3twvTvp+HLwe+kpe5LrBXo88x9fi4pdL8rs5XgMvz1dp5PeR9GRgtadOIWBERt/WQ9xjgexGxMCJWAKcBR+Ur7MOB30bELRHxD+B00j9l0a0RcXVEvBoRL0TE3Ii4LSI6I2IR8D+kE1XRtyPimYiYD9wL/CGv/2ngd0C1h+w9lbVW/Vn3K8A6wI6S1o6IRRHR1Rrqy7b+SUT8b0S8QAoKu+T0WrYzAEoP/j8InB4Rz0XEvcAlxTwR8bOI+HveB9/NZa/6fCgiromIv0RyI/AHYO8q2T8O/GdEzM75F0TEw6QLiRGkQPmPiLiedPI+uoft0d3kiFgeEX8FbmDl9qnkZdL+2CAilkXEHXVazyrHN+kYPDMilkbEE8A3gI/kvDey8lh/D/AfhfF/ydO7yv4m0kXKixExKF+ycFBpfodFxMiuD/DpHvIeT7oi/rOk2ZIO6SHvFsDDhfGHSVe4o/K0xV0TIuJ54O/d5l9cHJH0ZknTJT2Wbxl8C9i02zyPF4ZfqDA+oh9lrVWf1x0RC4CTSVeuSyVNlbRFntyXbf1YYfj5wrpq2c5dNiPVubjdi9sESZPy7amn8wXIhrx+HxTzHyjpNklP5fwH9ZB/a9IVeHdbAIsj4tVu5dqy2norqLZ9KvlgLufD+VbSnnVaz+Ju45WOwa5j4VbgzZJGkQLVpcDW+TbnHqy8/fwlUivv9nyb8GN9KHvLcFAZRCLiwYg4mtRE/zZwlaT1qHz1+wjpqqnLNkAn6WT7KLBV1wRJw0m3VVZZXbfx84E/A2MiYgPSbYCK96z7oaey1lVE/Dwi9srrD9J27Wlb90Ut27nLE6Q6b11I26Yw797AKcCRwEb5AuRpVu6DVfZXfh7wS9Itt1E5/7VU32eL6fYMJ3uEdAItnku2Id0qA3gOeENh2j9VWX4lrztuc0vpUNJ2v5rU8quH7uuudAw+ksv0PDAXOAm4N7c6/wR8HvhLRDyZ8z0WEZ+IiC2ATwLnSRpdp/I3jIPKICLpw5I2y1eNy3PyK6QT0qukZwhdLgc+J2lbSSNILYsrIqITuAp4n6R3KT3A/ga9B4j1gWeAFZLeAnyqtIr1XNa6kbS9pH3zCfhFUovmlTyt2rbui5q3c6RXlH8FnCHpDZJ2BCYUsqxPCjpPAEMlnU56htTlcaCtcPIfRro99gTQKelAoKdXcC8AviBpt/wgfbSkNwGzSIHjS5LWVvrO1PtIz38A7gI+kMs8mtTCq9XjwFZa+RLFMKXvn2wYES+TjreBenX7cuCrkjbLLZDTgeIr2jcCJ7LyVldHt3EkHSGp6yJiGSlwNdWr52VwUBlcxgPzld6I+j5wVL53+zxwNvDH/GxmHHAR8FNS0/wh0knzMwD5ucNnSCeGR0kPXpeSHnBX8wXg33Le/wuU+WZL1bLW2TrAZOBJ0q2TN5JaYFBlW/dl4f3YzieSbtk8BlwM/KQwbQbp2dD/km7NvMiqt3B+kf/+XdIdEfEs8FnSlf4y0r6b1kNZf0E6hn6ey3k1sHG+Kn8/cCBpO50HHBsRf86zngP8gxQgLgEuq7aOCq4nvSr+mKQnc9pHgEX5Fuu/k15OGAjfBOYA9wDzgDtyWpcbSYH9pirjkF5ymJWPmWnASRHxUJ3LPeAU4R/psp7l1sFy0q2tQfdP0Cy8nW0wcEvFKpL0vnzLYj3Sffd5pNeXrUTezjbYOKhYNYeSHkQ+Aowh3d5xs7Z83s42qPj2l5mZlcYtFTMzK80a11HapptuGm1tbVWnP/fcc6y3Xl+/btCcBktdXI/m4no0l4Gox9y5c5+MiM1qybvGBZW2tjbmzJlTdXpHRwft7e0DV6A6Gix1cT2ai+vRXAaiHpIe7j1X4ttfZmZWGgcVMzMrjYOKmZmVxkHFzMxK46BiZmalcVAxM7PSOKiYmVlpHFTMzKw0DipmZlaaNe4b9WZmzajt1Gv6lH/R5IPrVJLV45aKmZmVxkHFzMxK46BiZmalcVAxM7PSOKiYmVlpHFTMzKw0DipmZlYaf0+lDwbLe+RmZvXiloqZmZXGQcXMzErjoGJmZqVxUDEzs9I4qJiZWWkcVMzMrDQOKmZmVhoHFTMzK42DipmZlcZBxczMSuOgYmZmpXFQMTOz0jiomJlZaeoeVCQNkXSnpOl5fFtJsyQ9KOkKScNy+jp5fEGe3lZYxmk5/QFJ7y2kj89pCySdWu+6mJlZzwaipXIScH9h/NvAORExBlgGHJ/TjweWRcRo4JycD0k7AkcBOwHjgfNyoBoC/Bg4ENgRODrnNTOzBqlrUJG0FXAwcEEeF7AvcFXOcglwWB4+NI+Tp++X8x8KTI2IlyLiIWABsEf+LIiIhRHxD2BqzmtmZg1S7x/pOhf4ErB+Ht8EWB4RnXl8CbBlHt4SWAwQEZ2Sns75twRuKyyzOM/ibunvrFQISROBiQCjRo2io6OjaoFXrFhRdfqknTsrplfT03oGQk91aSWuR3NxPeqjv+eXZqtH3YKKpEOApRExV1J7V3KFrNHLtGrplVpZUSGNiJgCTAEYO3ZstLe3V8oGpB1Vbfpxff3lx2Oqr2cg9FSXVuJ6NBfXoz76e35ptnrUs6XybuD9kg4C1gU2ILVcRkoamlsrWwGP5PxLgK2BJZKGAhsCTxXSuxTnqZZuZmYNULdnKhFxWkRsFRFtpAft10fEMcANwOE52wTgN3l4Wh4nT78+IiKnH5XfDtsWGAPcDswGxuS3yYbldUyrV33MzKx39X6mUskpwFRJ3wTuBC7M6RcCP5W0gNRCOQogIuZLuhK4D+gEToiIVwAknQjMAIYAF0XE/AGtiZmZrWJAgkpEdAAdeXgh6c2t7nleBI6oMv/ZwNkV0q8Fri2xqGZmthr8jXozMyuNg4qZmZWmEc9UrCRtvbyCOGnnzlVeU1w0+eB6F8nM1nBuqZiZWWkcVMzMrDQOKmZmVhoHFTMzK42DipmZlcZBxczMSuOgYmZmpXFQMTOz0vjLj02kty8zmpk1O7dUzMysNA4qZmZWGgcVMzMrjYOKmZmVxkHFzMxK46BiZmalcVAxM7PSOKiYmVlpHFTMzKw0DipmZlYaBxUzMyuNg4qZmZXGQcXMzErjoGJmZqVxUDEzs9I4qJiZWWkcVMzMrDQOKmZmVhoHFTMzK42DipmZlcZBxczMSuOgYmZmpXFQMTOz0jiomJlZaeoWVCStK+l2SXdLmi/pGzl9W0mzJD0o6QpJw3L6Onl8QZ7eVljWaTn9AUnvLaSPz2kLJJ1ar7qYmVlt6tlSeQnYNyLeDuwCjJc0Dvg2cE5EjAGWAcfn/McDyyJiNHBOzoekHYGjgJ2A8cB5koZIGgL8GDgQ2BE4Ouc1M7MGGVqvBUdEACvy6Nr5E8C+wL/l9EuAM4DzgUPzMMBVwI8kKadPjYiXgIckLQD2yPkWRMRCAElTc9776lWnvmo79ZpGF8HMbEDVLagA5NbEXGA0qVXxF2B5RHTmLEuALfPwlsBigIjolPQ0sElOv62w2OI8i7ulv7NKOSYCEwFGjRpFR0dH1TKvWLGi6vRJO3dWTG9Wo4avWuae6t3MetonrcT1aC7NVo++nl+6yt5s9ahrUImIV4BdJI0Efg3sUClb/qsq06qlV7p1FxXSiIgpwBSAsWPHRnt7e9Uyd3R0UG36cS3W8pi0cyffnbdyFy86pr1xhVkNPe2TVuJ6NJdmq0dfzy9d/8/NVo8BefsrIpYDHcA4YKSkrjPdVsAjeXgJsDVAnr4h8FQxvds81dLNzKxB6vn212a5hYKk4cD+wP3ADcDhOdsE4Dd5eFoeJ0+/Pj+XmQYcld8O2xYYA9wOzAbG5LfJhpEe5k+rV33MzKx39bz9tTlwSX6ushZwZURMl3QfMFXSN4E7gQtz/guBn+YH8U+RggQRMV/SlaQH8J3ACfm2GpJOBGYAQ4CLImJ+HetjZma9qOfbX/cA76iQvpCVb28V018EjqiyrLOBsyukXwtcu9qFNTOzUvgb9WZmVhoHFTMzK42DipmZlcZBxczMSuOgYmZmpXFQMTOz0tS1mxYzs8GgP53DLpp8cB1K0vz63FKRtJGkt9WjMGZm1tpqCiqSOiRtIGlj4G7gJ5K+V9+imZlZq6m1pbJhRDwDfAD4SUTsRurLy8zM7DW1BpWhkjYHjgSm17E8ZmbWwmoNKt8gddy4ICJmS9oOeLB+xTIzs1ZU69tfj0bEaw/nI2Khn6mYmVl3tbZUflhjmpmZrcF6bKlI2hN4F7CZpM8XJm1A+g0TMzOz1/R2+2sYMCLnW7+Q/gwrf73RzMwM6CWoRMSNwI2SLo6IhweoTGZm1qJqfVC/jqQpQFtxnojYtx6FMjOz1lRrUPkF8N/ABcAr9SuOmZm1slqDSmdEnF/XkpiZWcur9ZXi30r6tKTNJW3c9alryczMrOXU2lKZkP9+sZAWwHblFsfMzFpZTUElIratd0HMzKz11RRUJB1bKT0iLi23OGZm1spqvf21e2F4XWA/4A7AQcXMzF5T6+2vzxTHJW0I/LQuJTIzs5bV558Tzp4HxpRZEDMza321PlP5LeltL0gdSe4AXFmvQpmZWWuq9ZnKfxWGO4GHI2JJHcpjZmYtrKbbX7ljyT+TeireCPhHPQtlZmatqaagIulI4HbgCNLv1M+S5K7vzcxsFbXe/voKsHtELAWQtBnw/4Cr6lUwMzNrPbW+/bVWV0DJ/t6Hec3MbA1Ra0vl95JmAJfn8Q8B19anSGZm1qp6+4360cCoiPiipA8AewECbgUuG4DymZlZC+ntFta5wLMAEfGriPh8RHyO1Eo5t96FMzOz1tJbUGmLiHu6J0bEHNJPC5uZmb2mt6Cybg/Thvc0o6StJd0g6X5J8yWdlNM3lnSdpAfz341yuiT9QNICSfdI2rWwrAk5/4OSJhTSd5M0L8/zA0nqvcpmZlYvvQWV2ZI+0T1R0vHA3F7m7QQmRcQOwDjgBEk7AqcCMyNiDDAzjwMcSOpPbAwwETg/r2tj4OvAO4E9gK93BaKcZ2JhvvG9lMnMzOqot7e/TgZ+LekYVgaRscAw4F97mjEiHgUezcPPSrof2BI4FGjP2S4BOoBTcvqlERHAbZJGSto8570uIp4CkHQdMF5SB7BBRNya0y8FDgN+V0vFzcysfErn8F4ySfsAb82j8yPi+j6tRGoDbsrL+GtEjCxMWxYRG0maDkyOiFty+kxSsGkH1o2Ib+b0rwEvkILR5IjYP6fvDZwSEYdUWP9EUouGUaNG7TZ16tSqZV2xYgUjRoyoOG3e357uS7UbbtRwePyFleM7b7lh4wqzGnraJ63E9WgufalHf/73+/r/1td1dC1/IPbHPvvsMzcixtaSt9bfU7kBuKE/hZE0AvglcHJEPNPDY49KE6If6a9PjJgCTAEYO3ZstLe3Vy1vR0cH1aYfd+o1VedrRpN27uS781bu4kXHtDeuMKuhp33SSlyP5tKXevTnf7+v/299XUfX8pttf9T1W/GS1iYFlMsi4lc5+fF8W4v8t+ub+kuArQuzbwU80kv6VhXSzcysQeoWVPKbWBcC90fE9wqTpgFdb3BNAH5TSD82vwU2Dng6P5eZARwgaaP8gP4AYEae9qykcXldxxaWZWZmDVBrNy398W7gI8A8SXfltC8Dk4Er8xtkfyX1fAzpC5UHAQtIvyz5UYCIeErSWcDsnO/Mrof2wKeAi0mvN/8OP6Q3M2uougWV/MC92gOU/SrkD+CEKsu6CLioQvocVr5AYGZmDeaehs3MrDQOKmZmVhoHFTMzK42DipmZlcZBxczMSuOgYmZmpXFQMTOz0jiomJlZaRxUzMysNA4qZmZWGgcVMzMrjYOKmZmVxkHFzMxK46BiZmalcVAxM7PSOKiYmVlpHFTMzKw0DipmZlaaev5GvZkZAG2nXtOn/IsmH1ynkli9uaViZmalcVAxM7PSOKiYmVlpHFTMzKw0DipmZlYaBxUzMyuNg4qZmZXGQcXMzErjoGJmZqVxUDEzs9I4qJiZWWkcVMzMrDQOKmZmVhoHFTMzK42DipmZlcZBxczMSuOgYmZmpalbUJF0kaSlku4tpG0s6TpJD+a/G+V0SfqBpAWS7pG0a2GeCTn/g5ImFNJ3kzQvz/MDSapXXczMrDb1bKlcDIzvlnYqMDMixgAz8zjAgcCY/JkInA8pCAFfB94J7AF8vSsQ5TwTC/N1X5eZmQ2wugWViLgJeKpb8qHAJXn4EuCwQvqlkdwGjJS0OfBe4LqIeCoilgHXAePztA0i4taICODSwrLMzKxBlM7JdVq41AZMj4i35vHlETGyMH1ZRGwkaTowOSJuyekzgVOAdmDdiPhmTv8a8ALQkfPvn9P3Bk6JiEOqlGMiqVXDqFGjdps6dWrVMq9YsYIRI0ZUnDbvb0/XWvWmMGo4PP7CyvGdt9ywcYVZDT3tk1ayJtejr/87A3Gs9qUe/fnf72sd+ruNBuK42meffeZGxNha8g6ta0lqV+l5SPQjvaKImAJMARg7dmy0t7dXLUhHRwfVph936jVV52tGk3bu5LvzVu7iRce0N64wq6GnfdJK1uR69PV/ZyCO1b7Uoz//+32tQ3+3UbMdVwP99tfj+dYV+e/SnL4E2LqQbyvgkV7St6qQbmZmDTTQQWUa0PUG1wTgN4X0Y/NbYOOApyPiUWAGcICkjfID+gOAGXnas5LG5be+ji0sy8zMGqRut78kXU56JrKppCWkt7gmA1dKOh74K3BEzn4tcBCwAHge+ChARDwl6Sxgds53ZkR0Pfz/FOkNs+HA7/LHzMwaqG5BJSKOrjJpvwp5AzihynIuAi6qkD4HeOvqlNHMzMrlb9SbmVlpmuXtLxsAbf15g2XywXUoiZkNVm6pmJlZaRxUzMysNA4qZmZWGgcVMzMrjYOKmZmVxm9/WUPV8kbapJ07X+sXyW+jmTU3t1TMzKw0DipmZlYaBxUzMyuNg4qZmZXGQcXMzErjoGJmZqVxUDEzs9L4eypWqv70hGxmg4dbKmZmVhoHFTMzK42DipmZlcZBxczMSuOgYmZmpXFQMTOz0jiomJlZaRxUzMysNA4qZmZWGn+j3sz6zD0nWDVuqZiZWWkcVMzMrDQOKmZmVhoHFTMzK42DipmZlcZvf1mP/JaPmfWFWypmZlYat1RsUOtPS2vR5IPrUBKzNYNbKmZmVhq3VKyl+BmPWXNzS8XMzErT8i0VSeOB7wNDgAsiYnKDi2Rmq6mvLdJmfA62praqWzqoSBoC/Bj4P8ASYLakaRFxX2NLZmYDqT8n8Ek7d3LcGnrir6eWDirAHsCCiFgIIGkqcCjgoGL9Vq8rzK6TWF+vqgfDVbutORQRjS5Dv0k6HBgfER/P4x8B3hkRJ3bLNxGYmEe3Bx7oYbGbAk/WobiNMFjq4no0F9ejuQxEPd4UEZvVkrHVWyqqkPa6KBkRU4ApNS1QmhMRY1e3YM1gsNTF9WgurkdzabZ6tPrbX0uArQvjWwGPNKgsZmZrvFYPKrOBMZK2lTQMOAqY1uAymZmtsVr69ldEdEo6EZhBeqX4ooiYv5qLrek2WYsYLHVxPZqL69FcmqoeLf2g3szMmkur3/4yM7Mm4qBiZmalcVApkDRe0gOSFkg6tdHlqZWkiyQtlXRvIW1jSddJejD/3aiRZayFpK0l3SDpfknzJZ2U01uqLpLWlXS7pLtzPb6R07eVNCvX44r8cknTkzRE0p2SpufxlquHpEWS5km6S9KcnNZSxxWApJGSrpL05/x/smez1cNBJSt0+XIgsCNwtKQdG1uqml0MjO+WdiowMyLGADPzeLPrBCZFxA7AOOCEvA9arS4vAftGxNuBXYDxksYB3wbOyfVYBhzfwDL2xUnA/YXxVq3HPhGxS+E7Ha12XEHq5/D3EfEW4O2k/dJc9YgIf9LLCnsCMwrjpwGnNbpcfSh/G3BvYfwBYPM8vDnwQKPL2I86/YbUr1vL1gV4A3AH8E7St56H5vRVjrdm/ZC++zUT2BeYTvrCcSvWYxGwabe0ljqugA2Ah8gvWDVrPdxSWWlLYHFhfElOa1WjIuJRgPz3jQ0uT59IagPeAcyiBeuSbxndBSwFrgP+AiyPiM6cpVWOr3OBLwGv5vFNaM16BPAHSXNzt03QesfVdsATwE/y7cgLJK1Hk9XDQWWlmrp8sfqTNAL4JXByRDzT6PL0R0S8EhG7kK709wB2qJRtYEvVN5IOAZZGxNxicoWsTV2P7N0RsSvp9vYJkt7T6AL1w1BgV+D8iHgH8ByNvtVVgYPKSoOty5fHJW0OkP8ubXB5aiJpbVJAuSwifpWTW7IuABGxHOggPSMaKanrC8etcHy9G3i/pEXAVNItsHNpvXoQEY/kv0uBX5MCfasdV0uAJRExK49fRQoyTVUPB5WVBluXL9OACXl4Aun5RFOTJOBC4P6I+F5hUkvVRdJmkkbm4eHA/qQHqjcAh+dsTV+PiDgtIraKiDbS/8P1EXEMLVYPSetJWr9rGDgAuJcWO64i4jFgsaTtc9J+pJ/5aKp6+Bv1BZIOIl2JdXX5cnaDi1QTSZcD7aQusB8Hvg5cDVwJbAP8FTgiIp5qVBlrIWkv4GZgHivv4X+Z9FylZeoi6W3AJaTjaC3gyog4U9J2pCv+jYE7gQ9HxEuNK2ntJLUDX4iIQ1qtHrm8v86jQ4GfR8TZkjahhY4rAEm7ABcAw4CFwEfJxxhNUg8HFTMzK41vf5mZWWkcVMzMrDQOKmZmVhoHFTMzK42DipmZlcZBxWom6ZXcy+u9kn4h6Q0NKsfJjVp3Xv93cu/D3+nn/Bf0tbNSSe9vsZ6zOySN7SVPv/ajpHO7vhEv6TJJ90j6VmH61yQdWhg/pKunaKs/v1JsNZO0IiJG5OHLgLndvqTY07xDIuKVksqxCBgbEU+Wsbx+rP8ZYLNm/m5GrSQNLfTjVeZyO0jfa5nTQ55F9HE/StoYuDYixuXvA50SEcdIuhk4hNSB55SIeF9hHpE69Xx3RDzfrwpZzdxSsf66GRgNIOnD+fdD7pL0P/lnBJC0QtKZkmYBe0raXdKflH5n5HZJ6+eOF78jaXa+4vxknrc9X+12/XbEZUo+C2wB3CDphpz3fElzVPjtkpx+UJ73Fkk/0MrfA1lP6TdoZueO+Q6lm7yu7+RW2TxJH8rp04D1gFldaYV5zpB0iaQ/KP1+xwck/Wee//dKXdC8dhWf635xYR2fy9M/K+m+vD2m5rTjJP0oD1+c6/MnSQslHZ7T15J0Xt4O0yVd2zWtWzk7JH1L0o3ASZLeJGlmXt9MSdvksi3M22GkpFcLrYObJY3utszhkqbmZVwBDC9Me93+6ct+7OZw4Pd5+GVguKS1SF8GfAU4Ezi9OEOkK+cOUtCxemt0d87+tM4HWJH/DiV1BfEpUkeJvwXWztPOA47NwwEcmYe7vgG8ex7fIC9nIvDVnLYOMAfYltRDwNOkvqXWAm4F9sr5FlHoxhzYOP8dQjp5vA1Yl9Tr9LZ52uXA9Dz8LdK3wAFGAv8LrNetrh8k9S48BBhF+qby5sXtUGH7nAHcAqxN+q2L54ED87RfA4fl4Q5gLLAbcF1h/pH57yPAOt3SjgN+lIcvBn6Rt8uOwIKcfjhwbU7/J9JvnRxeoZwdwHmF8d8CE/Lwx4Cr8/DvgZ1IJ+PZwFfyPnqowjI/T+qFgrz9O0mtkIr7p9b9WGE9lwDvK4yfC9wFTCL9ds0FVfbNMcBmOrXVAAAD6UlEQVQPG/0/tCZ83FKxvhiu1J37HNJJ9kJS/0O7AbPztP1IXXRDunL8ZR7eHng0ImYDRMQzkW67HAAcm+edRepafUye5/aIWBIRr5JOHG1VynWkpDtIXYbsRDrRvgVYGBEP5TyXF/IfAJya19lBCkDbdFvmXsDlkXobfhy4Edi9903E7yLiZVJXM0NYeVU9r0L5FwLbSfqhpPFAV4/M9wCXSfow6eRcydUR8WpE3EcKel1l/kVOf4zUR1c1VxSG9wR+nod/mpcDqTX6nvz5j5y+OynAdPce4GcAEXFPrkOXSvunklrybU7q/p28rpMj/fDWd4GzgNMlfUXSlZI+UZhvKallZHU2tPcsZq95IVJ37q+RJOCSiDitQv4XY+VzFFG5i3QBn4mIGd2W2076BcUur1DheJW0LfAFUgtomaSLSUGiUhftxXV+MCIe6CVPf7wEEBGvSno58mUyqS+zVcqfy/t24L3ACcCRpJbCwaST9PuBr0naqdp6upW1L2V+rodpXWW+Gfh30sn4dOCLpBbkTb3Mt7Jg1fdPv/IBL1SZ/1DSxc56wFsj4khJN0m6LNJzlHXzvFZnbqnY6poJHC7pjfDa736/qUK+PwNbSNo951tfqfv0GcCnCs8b3qzUk2xPngXWz8MbkE6QT0saRfq9jK71baf0Y18AxecfM4DP5ICIpHdUWMdNwIfys4XNSCf523spV59I2hRYKyJ+CXwN2DU/H9g6Im4g/TjWSGBEjYu8BfhgfrYyihQAavEnUi/EkG4T3ZKHZwHvAl6NiBdJrcVPkoJNdzfleZH0VtItMKi+f6C2/djd/eRneV3ysXMS8B3Sg/qu4Nb1rAXgzaSeia3O3FKx1RIR90n6KulX9dYiPTw9AXi4W75/5AfbP1TqDv4FUpfwF5BuC92RT/JPAIf1stopwO8kPRoR+0i6E5hPup30x7y+FyR9Gvi9pCdZNSCcRboXf09e5yJe/xD316TbQneTTlJfyreUyrQl6Vf8ui7uTiPdMvuZpA1JLY9zImJ5jn+9+SXp9uO9pOdEs0jPpXrzWeAiSV8kbf+PAkTES5IWA7flfDcDR5Nu5XV3fq7LPaTgc3text2V9k/W636s4BpSYLugkHYCqbX8fF6/JM0jvSW2POfZh7R9rc78SrENWpJGRMSKHDh+DDwYEec0ulz1VKjzJqQT+7vrEAwbStItwCGFgNFb/lGk7u73q2/JDNxSscHtE5ImkG6B3An8T4PLMxCmK/1A2DDgrMEWULJJpBcragoqOe+k+hXHitxSMTOz0vhBvZmZlcZBxczMSuOgYmZmpXFQMTOz0jiomJlZaf4/6LSWW6rvT1IAAAAASUVORK5CYII=\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x7f5eddce38d0>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"# How much data is missing in each row of the dataset?\n",
"missing_row_data = azdiasPP.isnull().sum(axis=1)\n",
"missing_row_data = missing_row_data[missing_row_data > 0]/(len(azdiasPP.columns)) * 100\n",
"missing_row_data.sort_values(inplace=True)\n",
"\n",
"plt.hist(missing_row_data, bins=25)\n",
"\n",
"\n",
"plt.xlabel('Percentage of missing row data (%)')\n",
"plt.ylabel('Counts')\n",
"plt.title('Histogram of missing data counts in rows')\n",
"plt.grid(True)\n",
"plt.show()\n"
]
},
{
"cell_type": "code",
"execution_count": 216,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"643174 49\n",
"732775 49\n",
"472919 48\n",
"183108 47\n",
"139316 47\n",
"691141 47\n",
"691142 47\n",
"691171 47\n",
"691183 47\n",
"139332 47\n",
"691197 47\n",
"139323 47\n",
"691212 47\n",
"691122 47\n",
"139267 47\n",
"139255 47\n",
"139250 47\n",
"139248 47\n",
"139245 47\n",
"139243 47\n",
"691317 47\n",
"691129 47\n",
"691118 47\n",
"139236 47\n",
"139478 47\n",
"690871 47\n",
"690876 47\n",
"690878 47\n",
"690887 47\n",
"139521 47\n",
" ..\n",
"540246 0\n",
"540244 0\n",
"540243 0\n",
"540242 0\n",
"540241 0\n",
"540240 0\n",
"540239 0\n",
"540269 0\n",
"540271 0\n",
"540300 0\n",
"540289 0\n",
"540299 0\n",
"540298 0\n",
"540296 0\n",
"540295 0\n",
"540293 0\n",
"540292 0\n",
"540291 0\n",
"540290 0\n",
"540287 0\n",
"540273 0\n",
"540286 0\n",
"540284 0\n",
"540283 0\n",
"540281 0\n",
"540280 0\n",
"540277 0\n",
"540275 0\n",
"540274 0\n",
"445610 0\n",
"Length: 891221, dtype: int64"
]
},
"execution_count": 216,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"missing_row_counts = azdiasPP.isnull().sum(axis=1)\n",
"missing_row_counts.sort_values(ascending=False)"
]
},
{
"cell_type": "code",
"execution_count": 217,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"5035304"
]
},
"execution_count": 217,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"missing_row_counts.sum()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Discussion\n",
"### It appears that we have rows that have up to 50 missing values. I think that that number is severe and directly impacts our work. My inclination is to remove rows with more than 10 values missing."
]
},
{
"cell_type": "code",
"execution_count": 218,
"metadata": {},
"outputs": [],
"source": [
"# Write code to divide the data into two subsets based on the number of missing\n",
"# values in each row.\n",
"\n",
"# We use the drop parameter to avoid the old index being added as a column\n",
"## link ^ https://pandas.pydata.org/pandas-docs/stable/generated/pandas.DataFrame.reset_index.html\n",
"few_missing = azdiasPP[azdiasPP.isnull().sum(axis=1) < 10].reset_index(drop=True)\n",
"\n",
"many_missing = azdiasPP[azdiasPP.isnull().sum(axis=1) >= 10].reset_index(drop=True)\n"
]
},
{
"cell_type": "code",
"execution_count": 219,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x7f5eddf24b00>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"plt.figure(figsize=(25,25))\n",
"for i, col in enumerate(azdiasPP.columns[:10]):\n",
" plt.subplot(5, 2, i+1)\n",
" sns.distplot(few_missing[col][few_missing[col].notnull()], label='few_missing')\n",
" sns.distplot(many_missing[col][many_missing[col].notnull()], label='many_missing')\n",
" plt.title('Distribution for column: {}'.format(col))\n",
" plt.legend();"
]
},
{
"cell_type": "code",
"execution_count": 220,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x7f5ebea424e0>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"# Compare the distribution of values for at least five columns where there are\n",
"# no or few missing values, between the two subsets.\n",
"#check here for some more example of code: https://jakevdp.github.io/PythonDataScienceHandbook/04.08-multiple-subplots.html\n",
"\n",
"col_names_few = few_missing.columns\n",
"\n",
"def print_countplot(cols,num):\n",
" \n",
" fig, axs = plt.subplots(num,2, figsize=(20, 25))\n",
" \n",
" # adjust the spacing between these plots\n",
" fig.subplots_adjust(hspace =2 , wspace=.2)\n",
" \n",
" \n",
" #This function returns a flattened one-dimensional array.\n",
" #A copy is made only if needed. The returned array will have \n",
" #the same type as that of the input array.\n",
" #Read more here: https://www.tutorialspoint.com/numpy/numpy_ndarray_ravel.htm\n",
" axs = axs.ravel()\n",
"\n",
" for i in range(num):\n",
" \n",
" sns.countplot(few_missing[cols[i]], ax=axs[i*2])\n",
" axs[i*2].set_title('few_missing')\n",
" \n",
" sns.countplot(many_missing[cols[i]], ax=axs[i*2+1])\n",
" axs[i*2+1].set_title('many_missing')\n",
" \n",
" \n",
"print_countplot(col_names_few,8)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Discussion\n",
"### The data with many missing rows is significantly different from the data with few missing rows. I am a little concerned about dropping the data with many missing rows because of this vast difference. In addition dropping the data can result in a significant decerease in the number of data rendering our culstering algorithm obsolete.\n",
"\n",
"### However, I will choose to drop rows with many missing data points and fill the few missing data points (ie. less than 10). \n",
"\n",
"### Nevertheless, it is important to keep the following in mind: filling in the data with the mean or the median of the overall column might create a significant challenge and not help our clustering algorithms. So i will choose to interpolate the data, aka imputation based on the mean of the values directly near it. Keep in mind that this might be dangerous if we have very big outliers."
]
},
{
"attachments": {
"image.png": {
"image/png": "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"
}
},
"cell_type": "markdown",
"metadata": {},
"source": [
"## check out this cool image for handling missing data\n",
"https://medium.com/ibm-data-science-experience/missing-data-conundrum-exploration-and-imputation-techniques-9f40abe0fd87\n",
"![image.png](attachment:image.png)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### check exactly how many missing rows will be dropped and save them. this step is not absolutely necessary but it is good practice."
]
},
{
"cell_type": "code",
"execution_count": 221,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"rows with many missing values: 116478 or 13.07 % of all data\n"
]
}
],
"source": [
"#many_missing = missing_row_counts[missing_row_counts > 10]\n",
"print('rows with many missing values:', many_missing.shape[0], 'or', \\\n",
" np.round(many_missing.shape[0]*100/missing_row_counts.shape[0],2), \n",
" '% of all data')"
]
},
{
"cell_type": "code",
"execution_count": 222,
"metadata": {},
"outputs": [],
"source": [
"# Save data with many missing rows \n",
"azdiasPP_many_missing = azdiasPP.iloc[many_missing.index]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### fill in the missing values in the few_missing data set. Interpolation fills the missing value with the mean of the value before it and after it. I used the director in both ways to fill in any NaNs at the top of the columns. "
]
},
{
"cell_type": "code",
"execution_count": 223,
"metadata": {
"scrolled": false
},
"outputs": [],
"source": [
"#filling missing values in the few missing with the mean of the value, before and after\n",
"for col in few_missing.columns:\n",
" few_missing[col] = few_missing[col].interpolate(limit_direction='both')"
]
},
{
"cell_type": "code",
"execution_count": 224,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"774743"
]
},
"execution_count": 224,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"few_missing[col].interpolate().count()"
]
},
{
"cell_type": "code",
"execution_count": 225,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<matplotlib.axes._subplots.AxesSubplot at 0x7f5ede045470>"
]
},
"execution_count": 225,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x7f5edde423c8>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"few_missing[col].interpolate().plot()"
]
},
{
"cell_type": "code",
"execution_count": 226,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>ALTERSKATEGORIE_GROB</th>\n",
" <th>ANREDE_KZ</th>\n",
" <th>CJT_GESAMTTYP</th>\n",
" <th>FINANZ_MINIMALIST</th>\n",
" <th>FINANZ_SPARER</th>\n",
" <th>FINANZ_VORSORGER</th>\n",
" <th>FINANZ_ANLEGER</th>\n",
" <th>FINANZ_UNAUFFAELLIGER</th>\n",
" <th>FINANZ_HAUSBAUER</th>\n",
" <th>FINANZTYP</th>\n",
" <th>...</th>\n",
" <th>PLZ8_ANTG1</th>\n",
" <th>PLZ8_ANTG2</th>\n",
" <th>PLZ8_ANTG3</th>\n",
" <th>PLZ8_ANTG4</th>\n",
" <th>PLZ8_BAUMAX</th>\n",
" <th>PLZ8_HHZ</th>\n",
" <th>PLZ8_GBZ</th>\n",
" <th>ARBEIT</th>\n",
" <th>ORTSGR_KLS9</th>\n",
" <th>RELAT_AB</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>1.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>5.0</td>\n",
" <td>1.0</td>\n",
" <td>...</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>1.0</td>\n",
" <td>...</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>6.0</td>\n",
" <td>...</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>1.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>...</td>\n",
" <td>2.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>6.0</td>\n",
" <td>5.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>...</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>5.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 79 columns</p>\n",
"</div>"
],
"text/plain": [
" ALTERSKATEGORIE_GROB ANREDE_KZ CJT_GESAMTTYP FINANZ_MINIMALIST \\\n",
"0 1.0 2.0 5.0 1.0 \n",
"1 3.0 2.0 3.0 1.0 \n",
"2 4.0 2.0 2.0 4.0 \n",
"3 3.0 1.0 5.0 4.0 \n",
"4 1.0 2.0 2.0 3.0 \n",
"\n",
" FINANZ_SPARER FINANZ_VORSORGER FINANZ_ANLEGER FINANZ_UNAUFFAELLIGER \\\n",
"0 5.0 2.0 5.0 4.0 \n",
"1 4.0 1.0 2.0 3.0 \n",
"2 2.0 5.0 2.0 1.0 \n",
"3 3.0 4.0 1.0 3.0 \n",
"4 1.0 5.0 2.0 2.0 \n",
"\n",
" FINANZ_HAUSBAUER FINANZTYP ... PLZ8_ANTG1 PLZ8_ANTG2 PLZ8_ANTG3 \\\n",
"0 5.0 1.0 ... 2.0 3.0 2.0 \n",
"1 5.0 1.0 ... 3.0 3.0 1.0 \n",
"2 2.0 6.0 ... 2.0 2.0 2.0 \n",
"3 2.0 5.0 ... 2.0 4.0 2.0 \n",
"4 5.0 2.0 ... 2.0 3.0 1.0 \n",
"\n",
" PLZ8_ANTG4 PLZ8_BAUMAX PLZ8_HHZ PLZ8_GBZ ARBEIT ORTSGR_KLS9 RELAT_AB \n",
"0 1.0 1.0 5.0 4.0 3.0 5.0 4.0 \n",
"1 0.0 1.0 4.0 4.0 3.0 5.0 2.0 \n",
"2 0.0 1.0 3.0 4.0 2.0 3.0 3.0 \n",
"3 1.0 2.0 3.0 3.0 4.0 6.0 5.0 \n",
"4 1.0 1.0 5.0 5.0 2.0 3.0 3.0 \n",
"\n",
"[5 rows x 79 columns]"
]
},
"execution_count": 226,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"few_missing.head()"
]
},
{
"cell_type": "code",
"execution_count": 227,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"ALTERSKATEGORIE_GROB 0\n",
"ANREDE_KZ 0\n",
"CJT_GESAMTTYP 0\n",
"FINANZ_MINIMALIST 0\n",
"FINANZ_SPARER 0\n",
"FINANZ_VORSORGER 0\n",
"FINANZ_ANLEGER 0\n",
"FINANZ_UNAUFFAELLIGER 0\n",
"FINANZ_HAUSBAUER 0\n",
"FINANZTYP 0\n",
"GFK_URLAUBERTYP 0\n",
"GREEN_AVANTGARDE 0\n",
"HEALTH_TYP 0\n",
"LP_LEBENSPHASE_FEIN 0\n",
"LP_LEBENSPHASE_GROB 0\n",
"LP_FAMILIE_FEIN 0\n",
"LP_FAMILIE_GROB 0\n",
"LP_STATUS_FEIN 0\n",
"LP_STATUS_GROB 0\n",
"NATIONALITAET_KZ 0\n",
"PRAEGENDE_JUGENDJAHRE 0\n",
"RETOURTYP_BK_S 0\n",
"SEMIO_SOZ 0\n",
"SEMIO_FAM 0\n",
"SEMIO_REL 0\n",
"SEMIO_MAT 0\n",
"SEMIO_VERT 0\n",
"SEMIO_LUST 0\n",
"SEMIO_ERL 0\n",
"SEMIO_KULT 0\n",
" ... \n",
"MIN_GEBAEUDEJAHR 0\n",
"OST_WEST_KZ 0\n",
"WOHNLAGE 0\n",
"CAMEO_DEUG_2015 0\n",
"CAMEO_DEU_2015 3456\n",
"CAMEO_INTL_2015 0\n",
"KBA05_ANTG1 0\n",
"KBA05_ANTG2 0\n",
"KBA05_ANTG3 0\n",
"KBA05_ANTG4 0\n",
"KBA05_GBZ 0\n",
"BALLRAUM 0\n",
"EWDICHTE 0\n",
"INNENSTADT 0\n",
"GEBAEUDETYP_RASTER 0\n",
"KKK 0\n",
"MOBI_REGIO 0\n",
"ONLINE_AFFINITAET 0\n",
"REGIOTYP 0\n",
"KBA13_ANZAHL_PKW 0\n",
"PLZ8_ANTG1 0\n",
"PLZ8_ANTG2 0\n",
"PLZ8_ANTG3 0\n",
"PLZ8_ANTG4 0\n",
"PLZ8_BAUMAX 0\n",
"PLZ8_HHZ 0\n",
"PLZ8_GBZ 0\n",
"ARBEIT 0\n",
"ORTSGR_KLS9 0\n",
"RELAT_AB 0\n",
"Length: 79, dtype: int64"
]
},
"execution_count": 227,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#check for any null values\n",
"few_missing.isnull().sum()"
]
},
{
"cell_type": "code",
"execution_count": 228,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"3456"
]
},
"execution_count": 228,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"few_missing.isnull().sum().sum()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### It appears that we have a column that has a significant number of missing points. I chose to drop this column, however if the client asked to keep it, We could fill it using the mode or mean. "
]
},
{
"cell_type": "code",
"execution_count": 229,
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"few_missing.drop(['CAMEO_DEU_2015'], axis=1, inplace=True)"
]
},
{
"cell_type": "code",
"execution_count": 230,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0"
]
},
"execution_count": 230,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"few_missing.isnull().sum().sum()"
]
},
{
"cell_type": "code",
"execution_count": 231,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"ALTERSKATEGORIE_GROB 0\n",
"ANREDE_KZ 0\n",
"CJT_GESAMTTYP 0\n",
"FINANZ_MINIMALIST 0\n",
"FINANZ_SPARER 0\n",
"FINANZ_VORSORGER 0\n",
"FINANZ_ANLEGER 0\n",
"FINANZ_UNAUFFAELLIGER 0\n",
"FINANZ_HAUSBAUER 0\n",
"FINANZTYP 0\n",
"GFK_URLAUBERTYP 0\n",
"GREEN_AVANTGARDE 0\n",
"HEALTH_TYP 0\n",
"LP_LEBENSPHASE_FEIN 0\n",
"LP_LEBENSPHASE_GROB 0\n",
"LP_FAMILIE_FEIN 0\n",
"LP_FAMILIE_GROB 0\n",
"LP_STATUS_FEIN 0\n",
"LP_STATUS_GROB 0\n",
"NATIONALITAET_KZ 0\n",
"PRAEGENDE_JUGENDJAHRE 0\n",
"RETOURTYP_BK_S 0\n",
"SEMIO_SOZ 0\n",
"SEMIO_FAM 0\n",
"SEMIO_REL 0\n",
"SEMIO_MAT 0\n",
"SEMIO_VERT 0\n",
"SEMIO_LUST 0\n",
"SEMIO_ERL 0\n",
"SEMIO_KULT 0\n",
" ..\n",
"KONSUMNAEHE 0\n",
"MIN_GEBAEUDEJAHR 0\n",
"OST_WEST_KZ 0\n",
"WOHNLAGE 0\n",
"CAMEO_DEUG_2015 0\n",
"CAMEO_INTL_2015 0\n",
"KBA05_ANTG1 0\n",
"KBA05_ANTG2 0\n",
"KBA05_ANTG3 0\n",
"KBA05_ANTG4 0\n",
"KBA05_GBZ 0\n",
"BALLRAUM 0\n",
"EWDICHTE 0\n",
"INNENSTADT 0\n",
"GEBAEUDETYP_RASTER 0\n",
"KKK 0\n",
"MOBI_REGIO 0\n",
"ONLINE_AFFINITAET 0\n",
"REGIOTYP 0\n",
"KBA13_ANZAHL_PKW 0\n",
"PLZ8_ANTG1 0\n",
"PLZ8_ANTG2 0\n",
"PLZ8_ANTG3 0\n",
"PLZ8_ANTG4 0\n",
"PLZ8_BAUMAX 0\n",
"PLZ8_HHZ 0\n",
"PLZ8_GBZ 0\n",
"ARBEIT 0\n",
"ORTSGR_KLS9 0\n",
"RELAT_AB 0\n",
"Length: 78, dtype: int64"
]
},
"execution_count": 231,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"few_missing.isnull().sum()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Wunderbar! "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Discussion 1.1.3: Assess Missing Data in Each Row\n",
"There were many rows with missing data, I chose to create a cut off around 10 missing values per row, deleted any rows with more than that, which lost us about 13% of the data set. I also chose to interpolate the rest of the values and deleted the columns that presisted with a significant number of empty values. now the data is clean and is void of any null vlaues. "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Step 1.2: Select and Re-Encode Features\n",
"\n",
"Checking for missing data isn't the only way in which you can prepare a dataset for analysis. Since the unsupervised learning techniques to be used will only work on data that is encoded numerically, you need to make a few encoding changes or additional assumptions to be able to make progress. In addition, while almost all of the values in the dataset are encoded using numbers, not all of them represent numeric values. Check the third column of the feature summary (`feat_info`) for a summary of types of measurement.\n",
"- For numeric and interval data, these features can be kept without changes.\n",
"- Most of the variables in the dataset are ordinal in nature. While ordinal values may technically be non-linear in spacing, make the simplifying assumption that the ordinal variables can be treated as being interval in nature (that is, kept without any changes).\n",
"- Special handling may be necessary for the remaining two variable types: categorical, and 'mixed'.\n",
"\n",
"In the first two parts of this sub-step, you will perform an investigation of the categorical and mixed-type features and make a decision on each of them, whether you will keep, drop, or re-encode each. Then, in the last part, you will create a new data frame with only the selected and engineered columns.\n",
"\n",
"Data wrangling is often the trickiest part of the data analysis process, and there's a lot of it to be done here. But stick with it: once you're done with this step, you'll be ready to get to the machine learning parts of the project!"
]
},
{
"cell_type": "code",
"execution_count": 234,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>information_level</th>\n",
" <th>type</th>\n",
" <th>missing_or_unknown</th>\n",
" </tr>\n",
" <tr>\n",
" <th>attribute</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>AGER_TYP</th>\n",
" <td>person</td>\n",
" <td>categorical</td>\n",
" <td>[-1,0]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>ALTERSKATEGORIE_GROB</th>\n",
" <td>person</td>\n",
" <td>ordinal</td>\n",
" <td>[-1,0,9]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>ANREDE_KZ</th>\n",
" <td>person</td>\n",
" <td>categorical</td>\n",
" <td>[-1,0]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>CJT_GESAMTTYP</th>\n",
" <td>person</td>\n",
" <td>categorical</td>\n",
" <td>[0]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>FINANZ_MINIMALIST</th>\n",
" <td>person</td>\n",
" <td>ordinal</td>\n",
" <td>[-1]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>FINANZ_SPARER</th>\n",
" <td>person</td>\n",
" <td>ordinal</td>\n",
" <td>[-1]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>FINANZ_VORSORGER</th>\n",
" <td>person</td>\n",
" <td>ordinal</td>\n",
" <td>[-1]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>FINANZ_ANLEGER</th>\n",
" <td>person</td>\n",
" <td>ordinal</td>\n",
" <td>[-1]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>FINANZ_UNAUFFAELLIGER</th>\n",
" <td>person</td>\n",
" <td>ordinal</td>\n",
" <td>[-1]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>FINANZ_HAUSBAUER</th>\n",
" <td>person</td>\n",
" <td>ordinal</td>\n",
" <td>[-1]</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" information_level type missing_or_unknown\n",
"attribute \n",
"AGER_TYP person categorical [-1,0]\n",
"ALTERSKATEGORIE_GROB person ordinal [-1,0,9]\n",
"ANREDE_KZ person categorical [-1,0]\n",
"CJT_GESAMTTYP person categorical [0]\n",
"FINANZ_MINIMALIST person ordinal [-1]\n",
"FINANZ_SPARER person ordinal [-1]\n",
"FINANZ_VORSORGER person ordinal [-1]\n",
"FINANZ_ANLEGER person ordinal [-1]\n",
"FINANZ_UNAUFFAELLIGER person ordinal [-1]\n",
"FINANZ_HAUSBAUER person ordinal [-1]"
]
},
"execution_count": 234,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#set the attribute as the index\n",
"feat_info.set_index('attribute', inplace=True)\n",
"\n",
"feat_info.head(n=10)"
]
},
{
"cell_type": "code",
"execution_count": 235,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>information_level</th>\n",
" <th>type</th>\n",
" <th>missing_or_unknown</th>\n",
" <th>col_names</th>\n",
" </tr>\n",
" <tr>\n",
" <th>attribute</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>AGER_TYP</th>\n",
" <td>person</td>\n",
" <td>categorical</td>\n",
" <td>[-1,0]</td>\n",
" <td>AGER_TYP</td>\n",
" </tr>\n",
" <tr>\n",
" <th>ALTERSKATEGORIE_GROB</th>\n",
" <td>person</td>\n",
" <td>ordinal</td>\n",
" <td>[-1,0,9]</td>\n",
" <td>ALTERSKATEGORIE_GROB</td>\n",
" </tr>\n",
" <tr>\n",
" <th>ANREDE_KZ</th>\n",
" <td>person</td>\n",
" <td>categorical</td>\n",
" <td>[-1,0]</td>\n",
" <td>ANREDE_KZ</td>\n",
" </tr>\n",
" <tr>\n",
" <th>CJT_GESAMTTYP</th>\n",
" <td>person</td>\n",
" <td>categorical</td>\n",
" <td>[0]</td>\n",
" <td>CJT_GESAMTTYP</td>\n",
" </tr>\n",
" <tr>\n",
" <th>FINANZ_MINIMALIST</th>\n",
" <td>person</td>\n",
" <td>ordinal</td>\n",
" <td>[-1]</td>\n",
" <td>FINANZ_MINIMALIST</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" information_level type missing_or_unknown \\\n",
"attribute \n",
"AGER_TYP person categorical [-1,0] \n",
"ALTERSKATEGORIE_GROB person ordinal [-1,0,9] \n",
"ANREDE_KZ person categorical [-1,0] \n",
"CJT_GESAMTTYP person categorical [0] \n",
"FINANZ_MINIMALIST person ordinal [-1] \n",
"\n",
" col_names \n",
"attribute \n",
"AGER_TYP AGER_TYP \n",
"ALTERSKATEGORIE_GROB ALTERSKATEGORIE_GROB \n",
"ANREDE_KZ ANREDE_KZ \n",
"CJT_GESAMTTYP CJT_GESAMTTYP \n",
"FINANZ_MINIMALIST FINANZ_MINIMALIST "
]
},
"execution_count": 235,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"feat_info['col_names'] = feat_info.index\n",
"feat_info.head()"
]
},
{
"cell_type": "code",
"execution_count": 236,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'ordinal': 49, 'categorical': 17, 'mixed': 6, 'numeric': 6}"
]
},
"execution_count": 236,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# How many features are there of each data type?\n",
"\n",
"dtype={}\n",
"for col in few_missing.columns:\n",
" data_type = feat_info.loc[col].type\n",
" if data_type not in dtype:\n",
" dtype[data_type] = 1\n",
" else:\n",
" dtype[data_type] += 1\n",
" \n",
"dtype\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Step 1.2.1: Re-Encode Categorical Features\n",
"\n",
"For categorical data, you would ordinarily need to encode the levels as dummy variables. Depending on the number of categories, perform one of the following:\n",
"- For binary (two-level) categoricals that take numeric values, you can keep them without needing to do anything.\n",
"- There is one binary variable that takes on non-numeric values. For this one, you need to re-encode the values as numbers or create a dummy variable.\n",
"- For multi-level categoricals (three or more values), you can choose to encode the values using multiple dummy variables (e.g. via [OneHotEncoder](http://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.OneHotEncoder.html)), or (to keep things straightforward) just drop them from the analysis. As always, document your choices in the Discussion section."
]
},
{
"cell_type": "code",
"execution_count": 237,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"ANREDE_KZ 2 float64\n",
"CJT_GESAMTTYP 6 float64\n",
"FINANZTYP 6 float64\n",
"GFK_URLAUBERTYP 12 float64\n",
"GREEN_AVANTGARDE 2 int64\n",
"LP_FAMILIE_FEIN 68 float64\n",
"LP_FAMILIE_GROB 28 float64\n",
"LP_STATUS_FEIN 10 float64\n",
"LP_STATUS_GROB 5 float64\n",
"NATIONALITAET_KZ 20 float64\n",
"SHOPPER_TYP 28 float64\n",
"SOHO_KZ 2 float64\n",
"VERS_TYP 13 float64\n",
"ZABEOTYP 6 float64\n",
"GEBAEUDETYP 7 float64\n",
"OST_WEST_KZ 2 object\n",
"CAMEO_DEUG_2015 61 float64\n"
]
}
],
"source": [
"# Assess categorical variables: which are binary, which are multi-level, and\n",
"# which one needs to be re-encoded?\n",
"for col in few_missing.columns:\n",
" if feat_info.loc[col].type == 'categorical':\n",
" print(col, len(few_missing[col].unique()), few_missing[col].dtype)\n"
]
},
{
"cell_type": "code",
"execution_count": 238,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['CJT_GESAMTTYP',\n",
" 'FINANZTYP',\n",
" 'GFK_URLAUBERTYP',\n",
" 'LP_FAMILIE_FEIN',\n",
" 'LP_FAMILIE_GROB',\n",
" 'LP_STATUS_FEIN',\n",
" 'LP_STATUS_GROB',\n",
" 'NATIONALITAET_KZ',\n",
" 'SHOPPER_TYP',\n",
" 'VERS_TYP',\n",
" 'ZABEOTYP',\n",
" 'GEBAEUDETYP',\n",
" 'CAMEO_DEUG_2015']"
]
},
"execution_count": 238,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#extract categorical columns with more than 2 categories\n",
"non_binary_type = []\n",
"for col in few_missing.columns:\n",
" if feat_info.loc[col].type == 'categorical' and len(few_missing[col].unique()) > 2:\n",
" non_binary_type.append(col)\n",
"non_binary_type"
]
},
{
"cell_type": "code",
"execution_count": 239,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['LP_LEBENSPHASE_FEIN',\n",
" 'LP_LEBENSPHASE_GROB',\n",
" 'PRAEGENDE_JUGENDJAHRE',\n",
" 'WOHNLAGE',\n",
" 'CAMEO_INTL_2015',\n",
" 'PLZ8_BAUMAX']"
]
},
"execution_count": 239,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Find the column names for mixed type columns\n",
"mixed_type = []\n",
"for col in few_missing.columns:\n",
" if feat_info.loc[col].type == 'mixed':\n",
" mixed_type.append(col)\n",
" \n",
"mixed_type"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### I think that the shopper type will be of value to the client so I choose to reencode it, but first, we must round the values up. those decimal values were the result of the interpolation."
]
},
{
"cell_type": "code",
"execution_count": 241,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"1.000000 246213\n",
"2.000000 210053\n",
"3.000000 175154\n",
"0.000000 126348\n",
"1.500000 7786\n",
"2.500000 3998\n",
"0.500000 3235\n",
"2.333333 279\n",
"1.666667 244\n",
"1.666667 222\n",
"1.333333 192\n",
"1.333333 189\n",
"2.666667 179\n",
"0.666667 150\n",
"0.666667 146\n",
"2.333333 113\n",
"0.333333 89\n",
"0.333333 79\n",
"1.250000 17\n",
"1.750000 17\n",
"2.250000 13\n",
"0.750000 9\n",
"2.750000 9\n",
"0.250000 5\n",
"1.800000 1\n",
"2.200000 1\n",
"1.400000 1\n",
"2.600000 1\n",
"Name: SHOPPER_TYP, dtype: int64"
]
},
"execution_count": 241,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"few_missing['SHOPPER_TYP'].value_counts()"
]
},
{
"cell_type": "code",
"execution_count": 246,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"0 3.0\n",
"1 2.0\n",
"2 1.0\n",
"3 2.0\n",
"4 0.0\n",
"5 1.0\n",
"6 0.0\n",
"7 3.0\n",
"8 3.0\n",
"9 2.0\n",
"10 1.0\n",
"11 3.0\n",
"12 1.0\n",
"13 2.0\n",
"14 1.0\n",
"15 2.0\n",
"16 1.0\n",
"17 1.0\n",
"18 0.0\n",
"19 0.0\n",
"20 0.0\n",
"21 1.0\n",
"22 1.0\n",
"23 1.0\n",
"24 0.0\n",
"25 1.0\n",
"26 2.0\n",
"27 2.0\n",
"28 2.0\n",
"29 1.0\n",
" ... \n",
"774713 0.0\n",
"774714 3.0\n",
"774715 0.0\n",
"774716 2.0\n",
"774717 0.0\n",
"774718 3.0\n",
"774719 1.0\n",
"774720 2.0\n",
"774721 1.0\n",
"774722 2.0\n",
"774723 3.0\n",
"774724 2.0\n",
"774725 3.0\n",
"774726 0.0\n",
"774727 2.0\n",
"774728 0.0\n",
"774729 3.0\n",
"774730 3.0\n",
"774731 2.0\n",
"774732 2.0\n",
"774733 1.0\n",
"774734 2.0\n",
"774735 1.0\n",
"774736 3.0\n",
"774737 1.0\n",
"774738 3.0\n",
"774739 2.0\n",
"774740 2.0\n",
"774741 0.0\n",
"774742 2.0\n",
"Name: SHOPPER_TYP, Length: 774743, dtype: float64"
]
},
"execution_count": 246,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"few_missing['SHOPPER_TYP'] = few_missing['SHOPPER_TYP'].round()\n",
"few_missing['SHOPPER_TYP']"
]
},
{
"cell_type": "code",
"execution_count": 247,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"1.0 246917\n",
"2.0 222727\n",
"3.0 175343\n",
"0.0 129756\n",
"Name: SHOPPER_TYP, dtype: int64"
]
},
"execution_count": 247,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"few_missing['SHOPPER_TYP'].value_counts()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### re encode the categorical variable OST_WEST_KZ"
]
},
{
"cell_type": "code",
"execution_count": 248,
"metadata": {},
"outputs": [],
"source": [
"# Re-encode categorical variable(s) to be kept in the analysis.\n",
"# we did not encode the others given that they are already binary.\n",
"#Onehot encoding for the one binary variable that takes on non-numeric values\n",
"# This will create an extra unecessary column:\n",
"##few_missing = pd.get_dummies(data=few_missing, columns=['OST_WEST_KZ'])\n",
"few_missing.loc[:, 'OST_WEST_KZ'].replace({'W':0, 'O':1}, inplace=True);"
]
},
{
"cell_type": "code",
"execution_count": 249,
"metadata": {},
"outputs": [],
"source": [
"# Reencode Shopper type\n",
"few_missing = pd.get_dummies(data=few_missing, columns=['SHOPPER_TYP'])"
]
},
{
"cell_type": "code",
"execution_count": 251,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>ALTERSKATEGORIE_GROB</th>\n",
" <th>ANREDE_KZ</th>\n",
" <th>CJT_GESAMTTYP</th>\n",
" <th>FINANZ_MINIMALIST</th>\n",
" <th>FINANZ_SPARER</th>\n",
" <th>FINANZ_VORSORGER</th>\n",
" <th>FINANZ_ANLEGER</th>\n",
" <th>FINANZ_UNAUFFAELLIGER</th>\n",
" <th>FINANZ_HAUSBAUER</th>\n",
" <th>FINANZTYP</th>\n",
" <th>...</th>\n",
" <th>PLZ8_BAUMAX</th>\n",
" <th>PLZ8_HHZ</th>\n",
" <th>PLZ8_GBZ</th>\n",
" <th>ARBEIT</th>\n",
" <th>ORTSGR_KLS9</th>\n",
" <th>RELAT_AB</th>\n",
" <th>SHOPPER_TYP_0.0</th>\n",
" <th>SHOPPER_TYP_1.0</th>\n",
" <th>SHOPPER_TYP_2.0</th>\n",
" <th>SHOPPER_TYP_3.0</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>1.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>5.0</td>\n",
" <td>1.0</td>\n",
" <td>...</td>\n",
" <td>1.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>1.0</td>\n",
" <td>...</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>6.0</td>\n",
" <td>...</td>\n",
" <td>1.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>1.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>...</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>6.0</td>\n",
" <td>5.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>...</td>\n",
" <td>1.0</td>\n",
" <td>5.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 81 columns</p>\n",
"</div>"
],
"text/plain": [
" ALTERSKATEGORIE_GROB ANREDE_KZ CJT_GESAMTTYP FINANZ_MINIMALIST \\\n",
"0 1.0 2.0 5.0 1.0 \n",
"1 3.0 2.0 3.0 1.0 \n",
"2 4.0 2.0 2.0 4.0 \n",
"3 3.0 1.0 5.0 4.0 \n",
"4 1.0 2.0 2.0 3.0 \n",
"\n",
" FINANZ_SPARER FINANZ_VORSORGER FINANZ_ANLEGER FINANZ_UNAUFFAELLIGER \\\n",
"0 5.0 2.0 5.0 4.0 \n",
"1 4.0 1.0 2.0 3.0 \n",
"2 2.0 5.0 2.0 1.0 \n",
"3 3.0 4.0 1.0 3.0 \n",
"4 1.0 5.0 2.0 2.0 \n",
"\n",
" FINANZ_HAUSBAUER FINANZTYP ... PLZ8_BAUMAX PLZ8_HHZ \\\n",
"0 5.0 1.0 ... 1.0 5.0 \n",
"1 5.0 1.0 ... 1.0 4.0 \n",
"2 2.0 6.0 ... 1.0 3.0 \n",
"3 2.0 5.0 ... 2.0 3.0 \n",
"4 5.0 2.0 ... 1.0 5.0 \n",
"\n",
" PLZ8_GBZ ARBEIT ORTSGR_KLS9 RELAT_AB SHOPPER_TYP_0.0 SHOPPER_TYP_1.0 \\\n",
"0 4.0 3.0 5.0 4.0 0 0 \n",
"1 4.0 3.0 5.0 2.0 0 0 \n",
"2 4.0 2.0 3.0 3.0 0 1 \n",
"3 3.0 4.0 6.0 5.0 0 0 \n",
"4 5.0 2.0 3.0 3.0 1 0 \n",
"\n",
" SHOPPER_TYP_2.0 SHOPPER_TYP_3.0 \n",
"0 0 1 \n",
"1 1 0 \n",
"2 0 0 \n",
"3 1 0 \n",
"4 0 0 \n",
"\n",
"[5 rows x 81 columns]"
]
},
"execution_count": 251,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#check the columns for the newly re-encoded categorical values\n",
"few_missing.head()"
]
},
{
"cell_type": "code",
"execution_count": 252,
"metadata": {},
"outputs": [],
"source": [
"#remove categorical columns with more than 2 categories\n",
"non_binary_cols = ['CJT_GESAMTTYP',\n",
" 'FINANZTYP',\n",
" 'GFK_URLAUBERTYP',\n",
" 'LP_FAMILIE_FEIN',\n",
" 'LP_FAMILIE_GROB',\n",
" 'LP_STATUS_FEIN',\n",
" 'LP_STATUS_GROB',\n",
" 'NATIONALITAET_KZ',\n",
" 'VERS_TYP',\n",
" 'ZABEOTYP',\n",
" 'GEBAEUDETYP',\n",
" 'CAMEO_DEUG_2015']\n",
"\n",
"for col in non_binary_cols:\n",
" few_missing.drop(col, axis=1, inplace=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Discussion 1.2.1: Re-Encode Categorical Features\n",
"I checked the values and I have a significant number of ordinal values, catgeorical and several mixed ones too. I rencoded the categorical variable for easier wrangling and less uncessary columns. I also reencoded the shopper type and dummied it out. I deleted the remaining non-binary columns, I chose to drop them for ease of analysis. Obviosuly if the client wanted them encoded, that could also be done. I looked at the mixed ones as well to prepare for their engineering below. "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Step 1.2.2: Engineer Mixed-Type Features\n",
"\n",
"There are a handful of features that are marked as \"mixed\" in the feature summary that require special treatment in order to be included in the analysis. There are two in particular that deserve attention; the handling of the rest are up to your own choices:\n",
"- \"PRAEGENDE_JUGENDJAHRE\" combines information on three dimensions: generation by decade, movement (mainstream vs. avantgarde), and nation (east vs. west). While there aren't enough levels to disentangle east from west, you should create two new variables to capture the other two dimensions: an interval-type variable for decade, and a binary variable for movement.\n",
"- \"CAMEO_INTL_2015\" combines information on two axes: wealth and life stage. Break up the two-digit codes by their 'tens'-place and 'ones'-place digits into two new ordinal variables (which, for the purposes of this project, is equivalent to just treating them as their raw numeric values).\n",
"- If you decide to keep or engineer new features around the other mixed-type features, make sure you note your steps in the Discussion section.\n",
"\n",
"Be sure to check `Data_Dictionary.md` for the details needed to finish these tasks."
]
},
{
"cell_type": "code",
"execution_count": 253,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0 14.0\n",
"1 15.0\n",
"2 8.0\n",
"3 8.0\n",
"4 3.0\n",
"Name: PRAEGENDE_JUGENDJAHRE, dtype: float64"
]
},
"execution_count": 253,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Investigate \"PRAEGENDE_JUGENDJAHRE\" and engineer two new variables.\n",
"few_missing['PRAEGENDE_JUGENDJAHRE'].head()\n"
]
},
{
"cell_type": "code",
"execution_count": 254,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0 51.0\n",
"1 24.0\n",
"2 12.0\n",
"3 43.0\n",
"4 54.0\n",
"Name: CAMEO_INTL_2015, dtype: float64"
]
},
"execution_count": 254,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"few_missing['CAMEO_INTL_2015'].head()"
]
},
{
"cell_type": "code",
"execution_count": 255,
"metadata": {},
"outputs": [],
"source": [
"# this information is based on the dictionary document\n",
"#Map generation \n",
"gen_dict = {0: [1, 2], \n",
" 1: [3, 4],\n",
" 2: [5, 6, 7],\n",
" 3: [8, 9],\n",
" 4: [10, 11, 12, 13], \n",
" 5:[14, 15]}\n",
"\n",
"def map_gen(x):\n",
" try:\n",
" for key, array in gen_dict.items():\n",
" if x in array:\n",
" return key\n",
" except ValueError:\n",
" return np.nan\n",
" \n",
"# Map movement \n",
"mainstream = [1, 3, 5, 8, 10, 12, 14]\n",
"\n",
"def map_mov(x):\n",
" try:\n",
" if x in mainstream:\n",
" return 0\n",
" else:\n",
" return 1\n",
" except ValueError:\n",
" return np.nan"
]
},
{
"cell_type": "code",
"execution_count": 256,
"metadata": {},
"outputs": [],
"source": [
"\n",
"# Create generation column\n",
"few_missing['PRAEGENDE_JUGENDJAHRE_decade'] = few_missing['PRAEGENDE_JUGENDJAHRE'].apply(map_gen)\n",
"\n",
"# Create movement column\n",
"few_missing['PRAEGENDE_JUGENDJAHRE_movement'] = few_missing['PRAEGENDE_JUGENDJAHRE'].apply(map_mov)"
]
},
{
"cell_type": "code",
"execution_count": 257,
"metadata": {},
"outputs": [],
"source": [
"# drop the original column\n",
"few_missing.drop(['PRAEGENDE_JUGENDJAHRE'], axis = 1, inplace=True)"
]
},
{
"cell_type": "code",
"execution_count": 258,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>ALTERSKATEGORIE_GROB</th>\n",
" <th>ANREDE_KZ</th>\n",
" <th>FINANZ_MINIMALIST</th>\n",
" <th>FINANZ_SPARER</th>\n",
" <th>FINANZ_VORSORGER</th>\n",
" <th>FINANZ_ANLEGER</th>\n",
" <th>FINANZ_UNAUFFAELLIGER</th>\n",
" <th>FINANZ_HAUSBAUER</th>\n",
" <th>GREEN_AVANTGARDE</th>\n",
" <th>HEALTH_TYP</th>\n",
" <th>...</th>\n",
" <th>PLZ8_GBZ</th>\n",
" <th>ARBEIT</th>\n",
" <th>ORTSGR_KLS9</th>\n",
" <th>RELAT_AB</th>\n",
" <th>SHOPPER_TYP_0.0</th>\n",
" <th>SHOPPER_TYP_1.0</th>\n",
" <th>SHOPPER_TYP_2.0</th>\n",
" <th>SHOPPER_TYP_3.0</th>\n",
" <th>PRAEGENDE_JUGENDJAHRE_decade</th>\n",
" <th>PRAEGENDE_JUGENDJAHRE_movement</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>1.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>5.0</td>\n",
" <td>0</td>\n",
" <td>3.0</td>\n",
" <td>...</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>5.0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>1</td>\n",
" <td>3.0</td>\n",
" <td>...</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>5.0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>0</td>\n",
" <td>2.0</td>\n",
" <td>...</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>3.0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>1.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>0</td>\n",
" <td>3.0</td>\n",
" <td>...</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>6.0</td>\n",
" <td>5.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>3.0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>0</td>\n",
" <td>3.0</td>\n",
" <td>...</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1.0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 70 columns</p>\n",
"</div>"
],
"text/plain": [
" ALTERSKATEGORIE_GROB ANREDE_KZ FINANZ_MINIMALIST FINANZ_SPARER \\\n",
"0 1.0 2.0 1.0 5.0 \n",
"1 3.0 2.0 1.0 4.0 \n",
"2 4.0 2.0 4.0 2.0 \n",
"3 3.0 1.0 4.0 3.0 \n",
"4 1.0 2.0 3.0 1.0 \n",
"\n",
" FINANZ_VORSORGER FINANZ_ANLEGER FINANZ_UNAUFFAELLIGER FINANZ_HAUSBAUER \\\n",
"0 2.0 5.0 4.0 5.0 \n",
"1 1.0 2.0 3.0 5.0 \n",
"2 5.0 2.0 1.0 2.0 \n",
"3 4.0 1.0 3.0 2.0 \n",
"4 5.0 2.0 2.0 5.0 \n",
"\n",
" GREEN_AVANTGARDE HEALTH_TYP ... PLZ8_GBZ \\\n",
"0 0 3.0 ... 4.0 \n",
"1 1 3.0 ... 4.0 \n",
"2 0 2.0 ... 4.0 \n",
"3 0 3.0 ... 3.0 \n",
"4 0 3.0 ... 5.0 \n",
"\n",
" ARBEIT ORTSGR_KLS9 RELAT_AB SHOPPER_TYP_0.0 SHOPPER_TYP_1.0 \\\n",
"0 3.0 5.0 4.0 0 0 \n",
"1 3.0 5.0 2.0 0 0 \n",
"2 2.0 3.0 3.0 0 1 \n",
"3 4.0 6.0 5.0 0 0 \n",
"4 2.0 3.0 3.0 1 0 \n",
"\n",
" SHOPPER_TYP_2.0 SHOPPER_TYP_3.0 PRAEGENDE_JUGENDJAHRE_decade \\\n",
"0 0 1 5.0 \n",
"1 1 0 5.0 \n",
"2 0 0 3.0 \n",
"3 1 0 3.0 \n",
"4 0 0 1.0 \n",
"\n",
" PRAEGENDE_JUGENDJAHRE_movement \n",
"0 0 \n",
"1 1 \n",
"2 0 \n",
"3 0 \n",
"4 0 \n",
"\n",
"[5 rows x 70 columns]"
]
},
"execution_count": 258,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"few_missing.head()"
]
},
{
"cell_type": "code",
"execution_count": 259,
"metadata": {},
"outputs": [],
"source": [
"# Map wealth \n",
"def map_wealth(x):\n",
" # Check of nan first, or it will convert nan to string 'nan'\n",
" try:\n",
" if pd.isnull(x):\n",
" return np.nan\n",
" else:\n",
" return int(str(x)[0])\n",
" except ValueError:\n",
" return np.nan\n",
"\n",
"# Map life stage\n",
"def map_lifestage(x):\n",
" try:\n",
" if pd.isnull(x):\n",
" return np.nan\n",
" else:\n",
" return int(str(x)[1])\n",
" except ValueError:\n",
" return np.nan"
]
},
{
"cell_type": "code",
"execution_count": 260,
"metadata": {},
"outputs": [],
"source": [
"# Create wealth column\n",
"few_missing['CAMEO_INTL_2015_wealth'] = few_missing['CAMEO_INTL_2015'].apply(map_wealth)\n",
"\n",
"# Create life stage column\n",
"few_missing['CAMEO_INTL_2015_lifestage'] = few_missing['CAMEO_INTL_2015'].apply(map_lifestage)"
]
},
{
"cell_type": "code",
"execution_count": 261,
"metadata": {},
"outputs": [],
"source": [
"# drop the original column\n",
"few_missing.drop(['CAMEO_INTL_2015'], axis = 1, inplace=True)"
]
},
{
"cell_type": "code",
"execution_count": 262,
"metadata": {},
"outputs": [],
"source": [
"#Map WOHNLAGE\n",
"\n",
"# Map Rural\n",
" \n",
"rural = [7,8]\n",
"\n",
"def map_rur(x):\n",
" try:\n",
" if x in rural:\n",
" return 0\n",
" else:\n",
" return 1\n",
" except ValueError:\n",
" return np.nan\n",
" \n",
" \n",
"# Map Neigh\n",
"\n",
"neigh = [1,2,3,4,5]\n",
"\n",
"def map_neigh(x):\n",
" try: \n",
" if x in neigh:\n",
" return 0\n",
" else:\n",
" return 1\n",
" except ValueError:\n",
" return np.nan"
]
},
{
"cell_type": "code",
"execution_count": 263,
"metadata": {},
"outputs": [],
"source": [
"# Create rural column\n",
"few_missing['WOHNLAGE_rural'] = few_missing['WOHNLAGE'].apply(map_rur)\n",
"# Create neighborhood column\n",
"few_missing['WOHNLAGE_neigh'] = few_missing['WOHNLAGE'].apply(map_neigh)\n"
]
},
{
"cell_type": "code",
"execution_count": 264,
"metadata": {},
"outputs": [],
"source": [
"# drop the original column\n",
"few_missing.drop(['WOHNLAGE'], axis = 1, inplace=True)"
]
},
{
"cell_type": "code",
"execution_count": 265,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>ALTERSKATEGORIE_GROB</th>\n",
" <th>ANREDE_KZ</th>\n",
" <th>FINANZ_MINIMALIST</th>\n",
" <th>FINANZ_SPARER</th>\n",
" <th>FINANZ_VORSORGER</th>\n",
" <th>FINANZ_ANLEGER</th>\n",
" <th>FINANZ_UNAUFFAELLIGER</th>\n",
" <th>FINANZ_HAUSBAUER</th>\n",
" <th>GREEN_AVANTGARDE</th>\n",
" <th>HEALTH_TYP</th>\n",
" <th>...</th>\n",
" <th>SHOPPER_TYP_0.0</th>\n",
" <th>SHOPPER_TYP_1.0</th>\n",
" <th>SHOPPER_TYP_2.0</th>\n",
" <th>SHOPPER_TYP_3.0</th>\n",
" <th>PRAEGENDE_JUGENDJAHRE_decade</th>\n",
" <th>PRAEGENDE_JUGENDJAHRE_movement</th>\n",
" <th>CAMEO_INTL_2015_wealth</th>\n",
" <th>CAMEO_INTL_2015_lifestage</th>\n",
" <th>WOHNLAGE_rural</th>\n",
" <th>WOHNLAGE_neigh</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>1.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>5.0</td>\n",
" <td>0</td>\n",
" <td>3.0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>5.0</td>\n",
" <td>0</td>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>1</td>\n",
" <td>3.0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>5.0</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>0</td>\n",
" <td>2.0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>3.0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>1.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>0</td>\n",
" <td>3.0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>3.0</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>0</td>\n",
" <td>3.0</td>\n",
" <td>...</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1.0</td>\n",
" <td>0</td>\n",
" <td>5</td>\n",
" <td>4</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 72 columns</p>\n",
"</div>"
],
"text/plain": [
" ALTERSKATEGORIE_GROB ANREDE_KZ FINANZ_MINIMALIST FINANZ_SPARER \\\n",
"0 1.0 2.0 1.0 5.0 \n",
"1 3.0 2.0 1.0 4.0 \n",
"2 4.0 2.0 4.0 2.0 \n",
"3 3.0 1.0 4.0 3.0 \n",
"4 1.0 2.0 3.0 1.0 \n",
"\n",
" FINANZ_VORSORGER FINANZ_ANLEGER FINANZ_UNAUFFAELLIGER FINANZ_HAUSBAUER \\\n",
"0 2.0 5.0 4.0 5.0 \n",
"1 1.0 2.0 3.0 5.0 \n",
"2 5.0 2.0 1.0 2.0 \n",
"3 4.0 1.0 3.0 2.0 \n",
"4 5.0 2.0 2.0 5.0 \n",
"\n",
" GREEN_AVANTGARDE HEALTH_TYP ... SHOPPER_TYP_0.0 \\\n",
"0 0 3.0 ... 0 \n",
"1 1 3.0 ... 0 \n",
"2 0 2.0 ... 0 \n",
"3 0 3.0 ... 0 \n",
"4 0 3.0 ... 1 \n",
"\n",
" SHOPPER_TYP_1.0 SHOPPER_TYP_2.0 SHOPPER_TYP_3.0 \\\n",
"0 0 0 1 \n",
"1 0 1 0 \n",
"2 1 0 0 \n",
"3 0 1 0 \n",
"4 0 0 0 \n",
"\n",
" PRAEGENDE_JUGENDJAHRE_decade PRAEGENDE_JUGENDJAHRE_movement \\\n",
"0 5.0 0 \n",
"1 5.0 1 \n",
"2 3.0 0 \n",
"3 3.0 0 \n",
"4 1.0 0 \n",
"\n",
" CAMEO_INTL_2015_wealth CAMEO_INTL_2015_lifestage WOHNLAGE_rural \\\n",
"0 5 1 1 \n",
"1 2 4 1 \n",
"2 1 2 0 \n",
"3 4 3 1 \n",
"4 5 4 0 \n",
"\n",
" WOHNLAGE_neigh \n",
"0 0 \n",
"1 0 \n",
"2 1 \n",
"3 0 \n",
"4 1 \n",
"\n",
"[5 rows x 72 columns]"
]
},
"execution_count": 265,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"few_missing.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Discussion\n",
"### After mapping WOHNLAGE in addition to the others, I am opting to drop the other mixed categories, they were too fine and something tells me that because there were lumped like this anyway, that means that they didn't matter that much anyway!"
]
},
{
"cell_type": "code",
"execution_count": 266,
"metadata": {},
"outputs": [],
"source": [
"# dropping the other mixed columns\n",
"mixed = ['LP_LEBENSPHASE_FEIN', 'LP_LEBENSPHASE_GROB','PLZ8_BAUMAX']\n",
"for col in mixed:\n",
" few_missing.drop(col, axis=1, inplace=True)"
]
},
{
"cell_type": "code",
"execution_count": 267,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>ALTERSKATEGORIE_GROB</th>\n",
" <th>ANREDE_KZ</th>\n",
" <th>FINANZ_MINIMALIST</th>\n",
" <th>FINANZ_SPARER</th>\n",
" <th>FINANZ_VORSORGER</th>\n",
" <th>FINANZ_ANLEGER</th>\n",
" <th>FINANZ_UNAUFFAELLIGER</th>\n",
" <th>FINANZ_HAUSBAUER</th>\n",
" <th>GREEN_AVANTGARDE</th>\n",
" <th>HEALTH_TYP</th>\n",
" <th>...</th>\n",
" <th>SHOPPER_TYP_0.0</th>\n",
" <th>SHOPPER_TYP_1.0</th>\n",
" <th>SHOPPER_TYP_2.0</th>\n",
" <th>SHOPPER_TYP_3.0</th>\n",
" <th>PRAEGENDE_JUGENDJAHRE_decade</th>\n",
" <th>PRAEGENDE_JUGENDJAHRE_movement</th>\n",
" <th>CAMEO_INTL_2015_wealth</th>\n",
" <th>CAMEO_INTL_2015_lifestage</th>\n",
" <th>WOHNLAGE_rural</th>\n",
" <th>WOHNLAGE_neigh</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>1.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>5.0</td>\n",
" <td>0</td>\n",
" <td>3.0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>5.0</td>\n",
" <td>0</td>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>1</td>\n",
" <td>3.0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>5.0</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>0</td>\n",
" <td>2.0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>3.0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>1.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>0</td>\n",
" <td>3.0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>3.0</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>0</td>\n",
" <td>3.0</td>\n",
" <td>...</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1.0</td>\n",
" <td>0</td>\n",
" <td>5</td>\n",
" <td>4</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 69 columns</p>\n",
"</div>"
],
"text/plain": [
" ALTERSKATEGORIE_GROB ANREDE_KZ FINANZ_MINIMALIST FINANZ_SPARER \\\n",
"0 1.0 2.0 1.0 5.0 \n",
"1 3.0 2.0 1.0 4.0 \n",
"2 4.0 2.0 4.0 2.0 \n",
"3 3.0 1.0 4.0 3.0 \n",
"4 1.0 2.0 3.0 1.0 \n",
"\n",
" FINANZ_VORSORGER FINANZ_ANLEGER FINANZ_UNAUFFAELLIGER FINANZ_HAUSBAUER \\\n",
"0 2.0 5.0 4.0 5.0 \n",
"1 1.0 2.0 3.0 5.0 \n",
"2 5.0 2.0 1.0 2.0 \n",
"3 4.0 1.0 3.0 2.0 \n",
"4 5.0 2.0 2.0 5.0 \n",
"\n",
" GREEN_AVANTGARDE HEALTH_TYP ... SHOPPER_TYP_0.0 \\\n",
"0 0 3.0 ... 0 \n",
"1 1 3.0 ... 0 \n",
"2 0 2.0 ... 0 \n",
"3 0 3.0 ... 0 \n",
"4 0 3.0 ... 1 \n",
"\n",
" SHOPPER_TYP_1.0 SHOPPER_TYP_2.0 SHOPPER_TYP_3.0 \\\n",
"0 0 0 1 \n",
"1 0 1 0 \n",
"2 1 0 0 \n",
"3 0 1 0 \n",
"4 0 0 0 \n",
"\n",
" PRAEGENDE_JUGENDJAHRE_decade PRAEGENDE_JUGENDJAHRE_movement \\\n",
"0 5.0 0 \n",
"1 5.0 1 \n",
"2 3.0 0 \n",
"3 3.0 0 \n",
"4 1.0 0 \n",
"\n",
" CAMEO_INTL_2015_wealth CAMEO_INTL_2015_lifestage WOHNLAGE_rural \\\n",
"0 5 1 1 \n",
"1 2 4 1 \n",
"2 1 2 0 \n",
"3 4 3 1 \n",
"4 5 4 0 \n",
"\n",
" WOHNLAGE_neigh \n",
"0 0 \n",
"1 0 \n",
"2 1 \n",
"3 0 \n",
"4 1 \n",
"\n",
"[5 rows x 69 columns]"
]
},
"execution_count": 267,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"few_missing.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Discussion 1.2.2: Engineer Mixed-Type Features\n",
"\n",
"To reingineer those mixed type values, it was helpful that they were assigned a numeric value. I was interested in reeingineering the LP_LEBENSPHASE_FEIN column, but unfortunately, it was too fine and had more than 3-4 vlaues per person and no clear code. if I had more time, I would have looked at it more deeply, but for now, I chose to drop the other mixed variables, including: 'LP_LEBENSPHASE_FEIN', 'LP_LEBENSPHASE_GROB','WOHNLAGE','KBA05_BAUMAX','PLZ8_BAUMAX'."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Step 1.2.3: Complete Feature Selection\n",
"\n",
"In order to finish this step up, you need to make sure that your data frame now only has the columns that you want to keep. To summarize, the dataframe should consist of the following:\n",
"- All numeric, interval, and ordinal type columns from the original dataset.\n",
"- Binary categorical features (all numerically-encoded).\n",
"- Engineered features from other multi-level categorical features and mixed features.\n",
"\n",
"Make sure that for any new columns that you have engineered, that you've excluded the original columns from the final dataset. Otherwise, their values will interfere with the analysis later on the project. For example, you should not keep \"PRAEGENDE_JUGENDJAHRE\", since its values won't be useful for the algorithm: only the values derived from it in the engineered features you created should be retained. As a reminder, your data should only be from **the subset with few or no missing values**."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# If there are other re-engineering tasks you need to perform, make sure you\n",
"# take care of them here. (Dealing with missing data will come in step 2.1.)\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 268,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"ALTERSKATEGORIE_GROB 0\n",
"ANREDE_KZ 0\n",
"FINANZ_MINIMALIST 0\n",
"FINANZ_SPARER 0\n",
"FINANZ_VORSORGER 0\n",
"FINANZ_ANLEGER 0\n",
"FINANZ_UNAUFFAELLIGER 0\n",
"FINANZ_HAUSBAUER 0\n",
"GREEN_AVANTGARDE 0\n",
"HEALTH_TYP 0\n",
"RETOURTYP_BK_S 0\n",
"SEMIO_SOZ 0\n",
"SEMIO_FAM 0\n",
"SEMIO_REL 0\n",
"SEMIO_MAT 0\n",
"SEMIO_VERT 0\n",
"SEMIO_LUST 0\n",
"SEMIO_ERL 0\n",
"SEMIO_KULT 0\n",
"SEMIO_RAT 0\n",
"SEMIO_KRIT 0\n",
"SEMIO_DOM 0\n",
"SEMIO_KAEM 0\n",
"SEMIO_PFLICHT 0\n",
"SEMIO_TRADV 0\n",
"SOHO_KZ 0\n",
"ANZ_PERSONEN 0\n",
"ANZ_TITEL 0\n",
"HH_EINKOMMEN_SCORE 0\n",
"W_KEIT_KIND_HH 0\n",
" ... \n",
"KBA05_ANTG4 0\n",
"KBA05_GBZ 0\n",
"BALLRAUM 0\n",
"EWDICHTE 0\n",
"INNENSTADT 0\n",
"GEBAEUDETYP_RASTER 0\n",
"KKK 0\n",
"MOBI_REGIO 0\n",
"ONLINE_AFFINITAET 0\n",
"REGIOTYP 0\n",
"KBA13_ANZAHL_PKW 0\n",
"PLZ8_ANTG1 0\n",
"PLZ8_ANTG2 0\n",
"PLZ8_ANTG3 0\n",
"PLZ8_ANTG4 0\n",
"PLZ8_HHZ 0\n",
"PLZ8_GBZ 0\n",
"ARBEIT 0\n",
"ORTSGR_KLS9 0\n",
"RELAT_AB 0\n",
"SHOPPER_TYP_0.0 0\n",
"SHOPPER_TYP_1.0 0\n",
"SHOPPER_TYP_2.0 0\n",
"SHOPPER_TYP_3.0 0\n",
"PRAEGENDE_JUGENDJAHRE_decade 11896\n",
"PRAEGENDE_JUGENDJAHRE_movement 0\n",
"CAMEO_INTL_2015_wealth 0\n",
"CAMEO_INTL_2015_lifestage 0\n",
"WOHNLAGE_rural 0\n",
"WOHNLAGE_neigh 0\n",
"Length: 69, dtype: int64"
]
},
"execution_count": 268,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#check again for missing values\n",
"few_missing.isnull().sum()"
]
},
{
"cell_type": "code",
"execution_count": 269,
"metadata": {},
"outputs": [],
"source": [
"# interpolate one more time to clear the empty values from the newly created columns\n",
"\n",
"for col in few_missing.columns:\n",
" few_missing[col] = few_missing[col].interpolate(limit_direction='both')\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 270,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0"
]
},
"execution_count": 270,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"few_missing.isnull().sum().sum()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#this could also work to clear the data from NaNs\n",
"\n",
"from sklearn.preprocessing import Imputer\n",
"imputer = Imputer(missing_values=float(\"NaN\"), \n",
" strategy=\"mean/most frequent/median\",\n",
" axis=1, copy = False)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Step 1.3: Create a Cleaning Function\n",
"\n",
"Even though you've finished cleaning up the general population demographics data, it's important to look ahead to the future and realize that you'll need to perform the same cleaning steps on the customer demographics data. In this substep, complete the function below to execute the main feature selection, encoding, and re-engineering steps you performed above. Then, when it comes to looking at the customer data in Step 3, you can just run this function on that DataFrame to get the trimmed dataset in a single step."
]
},
{
"cell_type": "code",
"execution_count": 325,
"metadata": {},
"outputs": [],
"source": [
"def clean_data(df):\n",
" \"\"\"\n",
" Perform feature trimming, re-encoding, and engineering for demographics\n",
" data\n",
" \n",
" INPUT: Demographics DataFrame\n",
" OUTPUT: Trimmed and cleaned demographics DataFrame\n",
" \"\"\"\n",
" \n",
" # Put in code here to execute all main cleaning steps:\n",
" # convert missing value codes into NaNs, ...\n",
" feat_info = pd.read_csv('AZDIAS_Feature_Summary.csv', delimiter=';')\n",
" feat_info['missing_or_unknown'] = feat_info['missing_or_unknown'].apply(lambda x: x[1:-1].split(','))\n",
"\n",
"\n",
"\n",
" # Identify missing or unknown data values and convert them to NaNs.\n",
" for attrib, missing_values in zip(feat_info['attribute'], feat_info['missing_or_unknown']):\n",
" if missing_values[0] != '':\n",
" for value in missing_values:\n",
" if value.isnumeric() or value.lstrip('-').isnumeric():\n",
" value = int(value)\n",
" azdias.loc[azdias[attrib] == value, attrib] = np.nan\n",
" # remove selected columns and rows, ...\n",
"\n",
" #Columns\n",
" columns_removed = ['AGER_TYP', 'GEBURTSJAHR', 'TITEL_KZ', \n",
" 'ALTER_HH', 'KK_KUNDENTYP', 'KBA05_BAUMAX',\n",
" 'CAMEO_DEU_2015']\n",
" \n",
" \n",
" for col in columns_removed:\n",
" df.drop(col, axis=1, inplace=True)\n",
" \n",
" #Rows\n",
" few_missing = df[df.isnull().sum(axis=1) < 10].reset_index(drop=True)\n",
" \n",
" #interpolate and impute the NaNs\n",
" for col in few_missing.columns:\n",
" few_missing[col] = few_missing[col].interpolate(limit_direction='both')\n",
" \n",
" # select, re-encode, and engineer column values.\n",
" #drop non categorical\n",
" non_binary_cols = ['CJT_GESAMTTYP','FINANZTYP','GFK_URLAUBERTYP','LP_FAMILIE_FEIN',\n",
" 'LP_FAMILIE_GROB','LP_STATUS_FEIN','LP_STATUS_GROB','NATIONALITAET_KZ',\n",
" 'VERS_TYP','ZABEOTYP','GEBAEUDETYP','CAMEO_DEUG_2015']\n",
" \n",
" for col in non_binary_cols:\n",
" few_missing.drop(col, axis=1, inplace=True)\n",
" \n",
" \n",
" #Reencode the categorical and get dummies for the shopper type\n",
" few_missing.loc[:, 'OST_WEST_KZ'].replace({'W':0, 'O':1}, inplace=True);\n",
" few_missing['SHOPPER_TYP'] = few_missing['SHOPPER_TYP'].round()\n",
" few_missing = pd.get_dummies(data=few_missing, columns=['SHOPPER_TYP'])\n",
" \n",
" # Complete the mapping process of mixed features\n",
" few_missing['PRAEGENDE_JUGENDJAHRE_decade'] = few_missing['PRAEGENDE_JUGENDJAHRE'].apply(map_gen)\n",
" few_missing['PRAEGENDE_JUGENDJAHRE_movement'] = few_missing['PRAEGENDE_JUGENDJAHRE'].apply(map_mov)\n",
" few_missing.drop('PRAEGENDE_JUGENDJAHRE', axis=1, inplace=True) \n",
" \n",
" few_missing['CAMEO_INTL_2015_wealth'] = few_missing['CAMEO_INTL_2015'].apply(map_wealth)\n",
" few_missing['CAMEO_INTL_2015_lifestage'] = few_missing['CAMEO_INTL_2015'].apply(map_lifestage)\n",
" few_missing.drop('CAMEO_INTL_2015', axis=1, inplace=True)\n",
" \n",
" few_missing['WOHNLAGE_rural'] = few_missing['WOHNLAGE'].apply(map_rur)\n",
" few_missing['WOHNLAGE_neigh'] = few_missing['WOHNLAGE'].apply(map_neigh)\n",
" few_missing.drop('WOHNLAGE', axis=1, inplace=True)\n",
" \n",
" #drop mixed\n",
" mixed = ['LP_LEBENSPHASE_FEIN','LP_LEBENSPHASE_GROB','PLZ8_BAUMAX']\n",
" for col in mixed:\n",
" few_missing.drop(col, axis=1, inplace=True)\n",
" \n",
" # interpolate again to clean the data set\n",
" for col in few_missing.columns:\n",
" few_missing[col] = few_missing[col].interpolate(limit_direction='both')\n",
" \n",
" # Return the cleaned dataframe.\n",
" return few_missing\n",
"\n",
" "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step 2: Feature Transformation\n",
"\n",
"### Step 2.1: Apply Feature Scaling\n",
"\n",
"Before we apply dimensionality reduction techniques to the data, we need to perform feature scaling so that the principal component vectors are not influenced by the natural differences in scale for features. Starting from this part of the project, you'll want to keep an eye on the [API reference page for sklearn](http://scikit-learn.org/stable/modules/classes.html) to help you navigate to all of the classes and functions that you'll need. In this substep, you'll need to check the following:\n",
"\n",
"- sklearn requires that data not have missing values in order for its estimators to work properly. So, before applying the scaler to your data, make sure that you've cleaned the DataFrame of the remaining missing values. This can be as simple as just removing all data points with missing data, or applying an [Imputer](http://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.Imputer.html) to replace all missing values. You might also try a more complicated procedure where you temporarily remove missing values in order to compute the scaling parameters before re-introducing those missing values and applying imputation. Think about how much missing data you have and what possible effects each approach might have on your analysis, and justify your decision in the discussion section below.\n",
"- For the actual scaling function, a [StandardScaler](http://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.StandardScaler.html) instance is suggested, scaling each feature to mean 0 and standard deviation 1.\n",
"- For these classes, you can make use of the `.fit_transform()` method to both fit a procedure to the data as well as apply the transformation to the data at the same time. Don't forget to keep the fit sklearn objects handy, since you'll be applying them to the customer demographics data towards the end of the project."
]
},
{
"cell_type": "code",
"execution_count": 272,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"--- Run time: 0.63 mins ---\n"
]
}
],
"source": [
"# Apply feature scaling to the general population demographics data.\n",
"# use .as_matrix to convert a pandas data frame to a numpy matrix for scikit-learn\n",
"\n",
"start_time = time.time()\n",
"\n",
"scaler = StandardScaler()\n",
"few_missing[few_missing.columns] = scaler.fit_transform(few_missing[few_missing.columns].as_matrix())\n",
"\n",
"print(\"--- Run time: %s mins ---\" % np.round(((time.time() - start_time)/60),2))"
]
},
{
"cell_type": "code",
"execution_count": 273,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>ALTERSKATEGORIE_GROB</th>\n",
" <th>ANREDE_KZ</th>\n",
" <th>FINANZ_MINIMALIST</th>\n",
" <th>FINANZ_SPARER</th>\n",
" <th>FINANZ_VORSORGER</th>\n",
" <th>FINANZ_ANLEGER</th>\n",
" <th>FINANZ_UNAUFFAELLIGER</th>\n",
" <th>FINANZ_HAUSBAUER</th>\n",
" <th>GREEN_AVANTGARDE</th>\n",
" <th>HEALTH_TYP</th>\n",
" <th>...</th>\n",
" <th>SHOPPER_TYP_0.0</th>\n",
" <th>SHOPPER_TYP_1.0</th>\n",
" <th>SHOPPER_TYP_2.0</th>\n",
" <th>SHOPPER_TYP_3.0</th>\n",
" <th>PRAEGENDE_JUGENDJAHRE_decade</th>\n",
" <th>PRAEGENDE_JUGENDJAHRE_movement</th>\n",
" <th>CAMEO_INTL_2015_wealth</th>\n",
" <th>CAMEO_INTL_2015_lifestage</th>\n",
" <th>WOHNLAGE_rural</th>\n",
" <th>WOHNLAGE_neigh</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>7.747430e+05</td>\n",
" <td>7.747430e+05</td>\n",
" <td>7.747430e+05</td>\n",
" <td>7.747430e+05</td>\n",
" <td>7.747430e+05</td>\n",
" <td>7.747430e+05</td>\n",
" <td>7.747430e+05</td>\n",
" <td>7.747430e+05</td>\n",
" <td>7.747430e+05</td>\n",
" <td>7.747430e+05</td>\n",
" <td>...</td>\n",
" <td>7.747430e+05</td>\n",
" <td>7.747430e+05</td>\n",
" <td>7.747430e+05</td>\n",
" <td>7.747430e+05</td>\n",
" <td>7.747430e+05</td>\n",
" <td>7.747430e+05</td>\n",
" <td>7.747430e+05</td>\n",
" <td>7.747430e+05</td>\n",
" <td>7.747430e+05</td>\n",
" <td>7.747430e+05</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
" <td>1.825462e-16</td>\n",
" <td>-3.738236e-17</td>\n",
" <td>-1.041864e-16</td>\n",
" <td>8.767796e-17</td>\n",
" <td>4.510462e-17</td>\n",
" <td>1.162742e-16</td>\n",
" <td>-3.250321e-17</td>\n",
" <td>1.707152e-16</td>\n",
" <td>6.704246e-17</td>\n",
" <td>-1.624794e-16</td>\n",
" <td>...</td>\n",
" <td>-4.706729e-17</td>\n",
" <td>-4.792940e-17</td>\n",
" <td>8.034089e-18</td>\n",
" <td>9.776643e-18</td>\n",
" <td>2.685367e-17</td>\n",
" <td>-7.713092e-18</td>\n",
" <td>8.872349e-17</td>\n",
" <td>6.403426e-17</td>\n",
" <td>-1.279768e-16</td>\n",
" <td>-4.325201e-17</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>1.000001e+00</td>\n",
" <td>1.000001e+00</td>\n",
" <td>1.000001e+00</td>\n",
" <td>1.000001e+00</td>\n",
" <td>1.000001e+00</td>\n",
" <td>1.000001e+00</td>\n",
" <td>1.000001e+00</td>\n",
" <td>1.000001e+00</td>\n",
" <td>1.000001e+00</td>\n",
" <td>1.000001e+00</td>\n",
" <td>...</td>\n",
" <td>1.000001e+00</td>\n",
" <td>1.000001e+00</td>\n",
" <td>1.000001e+00</td>\n",
" <td>1.000001e+00</td>\n",
" <td>1.000001e+00</td>\n",
" <td>1.000001e+00</td>\n",
" <td>1.000001e+00</td>\n",
" <td>1.000001e+00</td>\n",
" <td>1.000001e+00</td>\n",
" <td>1.000001e+00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>-1.763460e+00</td>\n",
" <td>-1.043381e+00</td>\n",
" <td>-1.488785e+00</td>\n",
" <td>-1.151076e+00</td>\n",
" <td>-1.770775e+00</td>\n",
" <td>-1.247929e+00</td>\n",
" <td>-1.171961e+00</td>\n",
" <td>-1.533358e+00</td>\n",
" <td>-5.311360e-01</td>\n",
" <td>-1.612046e+00</td>\n",
" <td>...</td>\n",
" <td>-4.485266e-01</td>\n",
" <td>-6.839591e-01</td>\n",
" <td>-6.352002e-01</td>\n",
" <td>-5.408612e-01</td>\n",
" <td>-2.297786e+00</td>\n",
" <td>-5.676484e-01</td>\n",
" <td>-1.552736e+00</td>\n",
" <td>-1.916286e+00</td>\n",
" <td>-1.811996e+00</td>\n",
" <td>-5.577290e-01</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>-7.820297e-01</td>\n",
" <td>-1.043381e+00</td>\n",
" <td>-7.627794e-01</td>\n",
" <td>-1.151076e+00</td>\n",
" <td>-1.044684e+00</td>\n",
" <td>-1.247929e+00</td>\n",
" <td>-1.171961e+00</td>\n",
" <td>-8.182165e-01</td>\n",
" <td>-5.311360e-01</td>\n",
" <td>-2.732270e-01</td>\n",
" <td>...</td>\n",
" <td>-4.485266e-01</td>\n",
" <td>-6.839591e-01</td>\n",
" <td>-6.352002e-01</td>\n",
" <td>-5.408612e-01</td>\n",
" <td>-9.150856e-01</td>\n",
" <td>-5.676484e-01</td>\n",
" <td>-8.698078e-01</td>\n",
" <td>-1.250972e+00</td>\n",
" <td>5.518776e-01</td>\n",
" <td>-5.577290e-01</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>1.994002e-01</td>\n",
" <td>9.584224e-01</td>\n",
" <td>-3.677339e-02</td>\n",
" <td>1.944708e-01</td>\n",
" <td>4.074985e-01</td>\n",
" <td>1.103059e-01</td>\n",
" <td>-4.542929e-01</td>\n",
" <td>-1.030746e-01</td>\n",
" <td>-5.311360e-01</td>\n",
" <td>-2.732270e-01</td>\n",
" <td>...</td>\n",
" <td>-4.485266e-01</td>\n",
" <td>-6.839591e-01</td>\n",
" <td>-6.352002e-01</td>\n",
" <td>-5.408612e-01</td>\n",
" <td>-2.237354e-01</td>\n",
" <td>-5.676484e-01</td>\n",
" <td>4.960489e-01</td>\n",
" <td>7.965636e-02</td>\n",
" <td>5.518776e-01</td>\n",
" <td>-5.577290e-01</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>1.180830e+00</td>\n",
" <td>9.584224e-01</td>\n",
" <td>6.892326e-01</td>\n",
" <td>8.672441e-01</td>\n",
" <td>1.133590e+00</td>\n",
" <td>7.894232e-01</td>\n",
" <td>9.810433e-01</td>\n",
" <td>6.120673e-01</td>\n",
" <td>-5.311360e-01</td>\n",
" <td>1.065592e+00</td>\n",
" <td>...</td>\n",
" <td>-4.485266e-01</td>\n",
" <td>1.462076e+00</td>\n",
" <td>1.574307e+00</td>\n",
" <td>-5.408612e-01</td>\n",
" <td>1.158965e+00</td>\n",
" <td>-5.676484e-01</td>\n",
" <td>1.178977e+00</td>\n",
" <td>7.449705e-01</td>\n",
" <td>5.518776e-01</td>\n",
" <td>-5.577290e-01</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>1.180830e+00</td>\n",
" <td>9.584224e-01</td>\n",
" <td>1.415239e+00</td>\n",
" <td>1.540017e+00</td>\n",
" <td>1.133590e+00</td>\n",
" <td>1.468541e+00</td>\n",
" <td>1.698711e+00</td>\n",
" <td>1.327209e+00</td>\n",
" <td>1.882757e+00</td>\n",
" <td>1.065592e+00</td>\n",
" <td>...</td>\n",
" <td>2.229522e+00</td>\n",
" <td>1.462076e+00</td>\n",
" <td>1.574307e+00</td>\n",
" <td>1.848903e+00</td>\n",
" <td>1.158965e+00</td>\n",
" <td>1.761654e+00</td>\n",
" <td>1.178977e+00</td>\n",
" <td>4.071541e+00</td>\n",
" <td>5.518776e-01</td>\n",
" <td>1.792986e+00</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>8 rows × 69 columns</p>\n",
"</div>"
],
"text/plain": [
" ALTERSKATEGORIE_GROB ANREDE_KZ FINANZ_MINIMALIST FINANZ_SPARER \\\n",
"count 7.747430e+05 7.747430e+05 7.747430e+05 7.747430e+05 \n",
"mean 1.825462e-16 -3.738236e-17 -1.041864e-16 8.767796e-17 \n",
"std 1.000001e+00 1.000001e+00 1.000001e+00 1.000001e+00 \n",
"min -1.763460e+00 -1.043381e+00 -1.488785e+00 -1.151076e+00 \n",
"25% -7.820297e-01 -1.043381e+00 -7.627794e-01 -1.151076e+00 \n",
"50% 1.994002e-01 9.584224e-01 -3.677339e-02 1.944708e-01 \n",
"75% 1.180830e+00 9.584224e-01 6.892326e-01 8.672441e-01 \n",
"max 1.180830e+00 9.584224e-01 1.415239e+00 1.540017e+00 \n",
"\n",
" FINANZ_VORSORGER FINANZ_ANLEGER FINANZ_UNAUFFAELLIGER \\\n",
"count 7.747430e+05 7.747430e+05 7.747430e+05 \n",
"mean 4.510462e-17 1.162742e-16 -3.250321e-17 \n",
"std 1.000001e+00 1.000001e+00 1.000001e+00 \n",
"min -1.770775e+00 -1.247929e+00 -1.171961e+00 \n",
"25% -1.044684e+00 -1.247929e+00 -1.171961e+00 \n",
"50% 4.074985e-01 1.103059e-01 -4.542929e-01 \n",
"75% 1.133590e+00 7.894232e-01 9.810433e-01 \n",
"max 1.133590e+00 1.468541e+00 1.698711e+00 \n",
"\n",
" FINANZ_HAUSBAUER GREEN_AVANTGARDE HEALTH_TYP ... \\\n",
"count 7.747430e+05 7.747430e+05 7.747430e+05 ... \n",
"mean 1.707152e-16 6.704246e-17 -1.624794e-16 ... \n",
"std 1.000001e+00 1.000001e+00 1.000001e+00 ... \n",
"min -1.533358e+00 -5.311360e-01 -1.612046e+00 ... \n",
"25% -8.182165e-01 -5.311360e-01 -2.732270e-01 ... \n",
"50% -1.030746e-01 -5.311360e-01 -2.732270e-01 ... \n",
"75% 6.120673e-01 -5.311360e-01 1.065592e+00 ... \n",
"max 1.327209e+00 1.882757e+00 1.065592e+00 ... \n",
"\n",
" SHOPPER_TYP_0.0 SHOPPER_TYP_1.0 SHOPPER_TYP_2.0 SHOPPER_TYP_3.0 \\\n",
"count 7.747430e+05 7.747430e+05 7.747430e+05 7.747430e+05 \n",
"mean -4.706729e-17 -4.792940e-17 8.034089e-18 9.776643e-18 \n",
"std 1.000001e+00 1.000001e+00 1.000001e+00 1.000001e+00 \n",
"min -4.485266e-01 -6.839591e-01 -6.352002e-01 -5.408612e-01 \n",
"25% -4.485266e-01 -6.839591e-01 -6.352002e-01 -5.408612e-01 \n",
"50% -4.485266e-01 -6.839591e-01 -6.352002e-01 -5.408612e-01 \n",
"75% -4.485266e-01 1.462076e+00 1.574307e+00 -5.408612e-01 \n",
"max 2.229522e+00 1.462076e+00 1.574307e+00 1.848903e+00 \n",
"\n",
" PRAEGENDE_JUGENDJAHRE_decade PRAEGENDE_JUGENDJAHRE_movement \\\n",
"count 7.747430e+05 7.747430e+05 \n",
"mean 2.685367e-17 -7.713092e-18 \n",
"std 1.000001e+00 1.000001e+00 \n",
"min -2.297786e+00 -5.676484e-01 \n",
"25% -9.150856e-01 -5.676484e-01 \n",
"50% -2.237354e-01 -5.676484e-01 \n",
"75% 1.158965e+00 -5.676484e-01 \n",
"max 1.158965e+00 1.761654e+00 \n",
"\n",
" CAMEO_INTL_2015_wealth CAMEO_INTL_2015_lifestage WOHNLAGE_rural \\\n",
"count 7.747430e+05 7.747430e+05 7.747430e+05 \n",
"mean 8.872349e-17 6.403426e-17 -1.279768e-16 \n",
"std 1.000001e+00 1.000001e+00 1.000001e+00 \n",
"min -1.552736e+00 -1.916286e+00 -1.811996e+00 \n",
"25% -8.698078e-01 -1.250972e+00 5.518776e-01 \n",
"50% 4.960489e-01 7.965636e-02 5.518776e-01 \n",
"75% 1.178977e+00 7.449705e-01 5.518776e-01 \n",
"max 1.178977e+00 4.071541e+00 5.518776e-01 \n",
"\n",
" WOHNLAGE_neigh \n",
"count 7.747430e+05 \n",
"mean -4.325201e-17 \n",
"std 1.000001e+00 \n",
"min -5.577290e-01 \n",
"25% -5.577290e-01 \n",
"50% -5.577290e-01 \n",
"75% -5.577290e-01 \n",
"max 1.792986e+00 \n",
"\n",
"[8 rows x 69 columns]"
]
},
"execution_count": 273,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#check the stats, mean, etc\n",
"f
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment