You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
595 lines
44 KiB
595 lines
44 KiB
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"___\n",
|
|
"\n",
|
|
"<a href='http://www.pieriandata.com'><img src='../Pierian_Data_Logo.png'/></a>\n",
|
|
"___\n",
|
|
"<center><em>Copyright by Pierian Data Inc.</em></center>\n",
|
|
"<center><em>For more information, visit us at <a href='http://www.pieriandata.com'>www.pieriandata.com</a></em></center>"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Seaborn Exercises"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Imports\n",
|
|
"\n",
|
|
"Run the cell below to import the libraries"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import numpy as np\n",
|
|
"import pandas as pd\n",
|
|
"import seaborn as sns\n",
|
|
"\n",
|
|
"import matplotlib.pyplot as plt"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## The Data\n",
|
|
"\n",
|
|
"DATA SOURCE: https://www.kaggle.com/rikdifos/credit-card-approval-prediction\n",
|
|
"\n",
|
|
"Data Information:\n",
|
|
"\n",
|
|
"Credit score cards are a common risk control method in the financial industry. It uses personal information and data submitted by credit card applicants to predict the probability of future defaults and credit card borrowings. The bank is able to decide whether to issue a credit card to the applicant. Credit scores can objectively quantify the magnitude of risk."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"Feature Information:\n",
|
|
"\n",
|
|
"<table>\n",
|
|
"<thead>\n",
|
|
"<tr>\n",
|
|
"<th>application_record.csv</th>\n",
|
|
"<th></th>\n",
|
|
"<th></th>\n",
|
|
"</tr>\n",
|
|
"</thead>\n",
|
|
"<tbody>\n",
|
|
"<tr>\n",
|
|
"<td>Feature name</td>\n",
|
|
"<td>Explanation</td>\n",
|
|
"<td>Remarks</td>\n",
|
|
"</tr>\n",
|
|
"<tr>\n",
|
|
"<td><code>ID</code></td>\n",
|
|
"<td>Client number</td>\n",
|
|
"<td></td>\n",
|
|
"</tr>\n",
|
|
"<tr>\n",
|
|
"<td><code>CODE_GENDER</code></td>\n",
|
|
"<td>Gender</td>\n",
|
|
"<td></td>\n",
|
|
"</tr>\n",
|
|
"<tr>\n",
|
|
"<td><code>FLAG_OWN_CAR</code></td>\n",
|
|
"<td>Is there a car</td>\n",
|
|
"<td></td>\n",
|
|
"</tr>\n",
|
|
"<tr>\n",
|
|
"<td><code>FLAG_OWN_REALTY</code></td>\n",
|
|
"<td>Is there a property</td>\n",
|
|
"<td></td>\n",
|
|
"</tr>\n",
|
|
"<tr>\n",
|
|
"<td><code>CNT_CHILDREN</code></td>\n",
|
|
"<td>Number of children</td>\n",
|
|
"<td></td>\n",
|
|
"</tr>\n",
|
|
"<tr>\n",
|
|
"<td><code>AMT_INCOME_TOTAL</code></td>\n",
|
|
"<td>Annual income</td>\n",
|
|
"<td></td>\n",
|
|
"</tr>\n",
|
|
"<tr>\n",
|
|
"<td><code>NAME_INCOME_TYPE</code></td>\n",
|
|
"<td>Income category</td>\n",
|
|
"<td></td>\n",
|
|
"</tr>\n",
|
|
"<tr>\n",
|
|
"<td><code>NAME_EDUCATION_TYPE</code></td>\n",
|
|
"<td>Education level</td>\n",
|
|
"<td></td>\n",
|
|
"</tr>\n",
|
|
"<tr>\n",
|
|
"<td><code>NAME_FAMILY_STATUS</code></td>\n",
|
|
"<td>Marital status</td>\n",
|
|
"<td></td>\n",
|
|
"</tr>\n",
|
|
"<tr>\n",
|
|
"<td><code>NAME_HOUSING_TYPE</code></td>\n",
|
|
"<td>Way of living</td>\n",
|
|
"<td></td>\n",
|
|
"</tr>\n",
|
|
"<tr>\n",
|
|
"<td><code>DAYS_BIRTH</code></td>\n",
|
|
"<td>Birthday</td>\n",
|
|
"<td>Count backwards from current day (0), -1 means yesterday</td>\n",
|
|
"</tr>\n",
|
|
"<tr>\n",
|
|
"<td><code>DAYS_EMPLOYED</code></td>\n",
|
|
"<td>Start date of employment</td>\n",
|
|
"<td>Count backwards from current day(0). If positive, it means the person currently unemployed.</td>\n",
|
|
"</tr>\n",
|
|
"<tr>\n",
|
|
"<td><code>FLAG_MOBIL</code></td>\n",
|
|
"<td>Is there a mobile phone</td>\n",
|
|
"<td></td>\n",
|
|
"</tr>\n",
|
|
"<tr>\n",
|
|
"<td><code>FLAG_WORK_PHONE</code></td>\n",
|
|
"<td>Is there a work phone</td>\n",
|
|
"<td></td>\n",
|
|
"</tr>\n",
|
|
"<tr>\n",
|
|
"<td><code>FLAG_PHONE</code></td>\n",
|
|
"<td>Is there a phone</td>\n",
|
|
"<td></td>\n",
|
|
"</tr>\n",
|
|
"<tr>\n",
|
|
"<td><code>FLAG_EMAIL</code></td>\n",
|
|
"<td>Is there an email</td>\n",
|
|
"<td></td>\n",
|
|
"</tr>\n",
|
|
"<tr>\n",
|
|
"<td><code>OCCUPATION_TYPE</code></td>\n",
|
|
"<td>Occupation</td>\n",
|
|
"<td></td>\n",
|
|
"</tr>\n",
|
|
"<tr>\n",
|
|
"<td><code>CNT_FAM_MEMBERS</code></td>\n",
|
|
"<td>Family size</td>\n",
|
|
"<td></td>\n",
|
|
"</tr>\n",
|
|
"</tbody>\n",
|
|
"</table>"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"df = pd.read_csv('application_record.csv')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {
|
|
"scrolled": true
|
|
},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<div>\n",
|
|
"<style scoped>\n",
|
|
" .dataframe tbody tr th:only-of-type {\n",
|
|
" vertical-align: middle;\n",
|
|
" }\n",
|
|
"\n",
|
|
" .dataframe tbody tr th {\n",
|
|
" vertical-align: top;\n",
|
|
" }\n",
|
|
"\n",
|
|
" .dataframe thead th {\n",
|
|
" text-align: right;\n",
|
|
" }\n",
|
|
"</style>\n",
|
|
"<table border=\"1\" class=\"dataframe\">\n",
|
|
" <thead>\n",
|
|
" <tr style=\"text-align: right;\">\n",
|
|
" <th></th>\n",
|
|
" <th>ID</th>\n",
|
|
" <th>CODE_GENDER</th>\n",
|
|
" <th>FLAG_OWN_CAR</th>\n",
|
|
" <th>FLAG_OWN_REALTY</th>\n",
|
|
" <th>CNT_CHILDREN</th>\n",
|
|
" <th>AMT_INCOME_TOTAL</th>\n",
|
|
" <th>NAME_INCOME_TYPE</th>\n",
|
|
" <th>NAME_EDUCATION_TYPE</th>\n",
|
|
" <th>NAME_FAMILY_STATUS</th>\n",
|
|
" <th>NAME_HOUSING_TYPE</th>\n",
|
|
" <th>DAYS_BIRTH</th>\n",
|
|
" <th>DAYS_EMPLOYED</th>\n",
|
|
" <th>FLAG_MOBIL</th>\n",
|
|
" <th>FLAG_WORK_PHONE</th>\n",
|
|
" <th>FLAG_PHONE</th>\n",
|
|
" <th>FLAG_EMAIL</th>\n",
|
|
" <th>OCCUPATION_TYPE</th>\n",
|
|
" <th>CNT_FAM_MEMBERS</th>\n",
|
|
" </tr>\n",
|
|
" </thead>\n",
|
|
" <tbody>\n",
|
|
" <tr>\n",
|
|
" <th>0</th>\n",
|
|
" <td>5008804</td>\n",
|
|
" <td>M</td>\n",
|
|
" <td>Y</td>\n",
|
|
" <td>Y</td>\n",
|
|
" <td>0</td>\n",
|
|
" <td>427500.0</td>\n",
|
|
" <td>Working</td>\n",
|
|
" <td>Higher education</td>\n",
|
|
" <td>Civil marriage</td>\n",
|
|
" <td>Rented apartment</td>\n",
|
|
" <td>-12005</td>\n",
|
|
" <td>-4542</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>0</td>\n",
|
|
" <td>0</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>2.0</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>1</th>\n",
|
|
" <td>5008805</td>\n",
|
|
" <td>M</td>\n",
|
|
" <td>Y</td>\n",
|
|
" <td>Y</td>\n",
|
|
" <td>0</td>\n",
|
|
" <td>427500.0</td>\n",
|
|
" <td>Working</td>\n",
|
|
" <td>Higher education</td>\n",
|
|
" <td>Civil marriage</td>\n",
|
|
" <td>Rented apartment</td>\n",
|
|
" <td>-12005</td>\n",
|
|
" <td>-4542</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>0</td>\n",
|
|
" <td>0</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>2.0</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2</th>\n",
|
|
" <td>5008806</td>\n",
|
|
" <td>M</td>\n",
|
|
" <td>Y</td>\n",
|
|
" <td>Y</td>\n",
|
|
" <td>0</td>\n",
|
|
" <td>112500.0</td>\n",
|
|
" <td>Working</td>\n",
|
|
" <td>Secondary / secondary special</td>\n",
|
|
" <td>Married</td>\n",
|
|
" <td>House / apartment</td>\n",
|
|
" <td>-21474</td>\n",
|
|
" <td>-1134</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>0</td>\n",
|
|
" <td>0</td>\n",
|
|
" <td>0</td>\n",
|
|
" <td>Security staff</td>\n",
|
|
" <td>2.0</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>3</th>\n",
|
|
" <td>5008808</td>\n",
|
|
" <td>F</td>\n",
|
|
" <td>N</td>\n",
|
|
" <td>Y</td>\n",
|
|
" <td>0</td>\n",
|
|
" <td>270000.0</td>\n",
|
|
" <td>Commercial associate</td>\n",
|
|
" <td>Secondary / secondary special</td>\n",
|
|
" <td>Single / not married</td>\n",
|
|
" <td>House / apartment</td>\n",
|
|
" <td>-19110</td>\n",
|
|
" <td>-3051</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>0</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>Sales staff</td>\n",
|
|
" <td>1.0</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>4</th>\n",
|
|
" <td>5008809</td>\n",
|
|
" <td>F</td>\n",
|
|
" <td>N</td>\n",
|
|
" <td>Y</td>\n",
|
|
" <td>0</td>\n",
|
|
" <td>270000.0</td>\n",
|
|
" <td>Commercial associate</td>\n",
|
|
" <td>Secondary / secondary special</td>\n",
|
|
" <td>Single / not married</td>\n",
|
|
" <td>House / apartment</td>\n",
|
|
" <td>-19110</td>\n",
|
|
" <td>-3051</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>0</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>Sales staff</td>\n",
|
|
" <td>1.0</td>\n",
|
|
" </tr>\n",
|
|
" </tbody>\n",
|
|
"</table>\n",
|
|
"</div>"
|
|
],
|
|
"text/plain": [
|
|
" ID CODE_GENDER FLAG_OWN_CAR FLAG_OWN_REALTY CNT_CHILDREN \\\n",
|
|
"0 5008804 M Y Y 0 \n",
|
|
"1 5008805 M Y Y 0 \n",
|
|
"2 5008806 M Y Y 0 \n",
|
|
"3 5008808 F N Y 0 \n",
|
|
"4 5008809 F N Y 0 \n",
|
|
"\n",
|
|
" AMT_INCOME_TOTAL NAME_INCOME_TYPE NAME_EDUCATION_TYPE \\\n",
|
|
"0 427500.0 Working Higher education \n",
|
|
"1 427500.0 Working Higher education \n",
|
|
"2 112500.0 Working Secondary / secondary special \n",
|
|
"3 270000.0 Commercial associate Secondary / secondary special \n",
|
|
"4 270000.0 Commercial associate Secondary / secondary special \n",
|
|
"\n",
|
|
" NAME_FAMILY_STATUS NAME_HOUSING_TYPE DAYS_BIRTH DAYS_EMPLOYED \\\n",
|
|
"0 Civil marriage Rented apartment -12005 -4542 \n",
|
|
"1 Civil marriage Rented apartment -12005 -4542 \n",
|
|
"2 Married House / apartment -21474 -1134 \n",
|
|
"3 Single / not married House / apartment -19110 -3051 \n",
|
|
"4 Single / not married House / apartment -19110 -3051 \n",
|
|
"\n",
|
|
" FLAG_MOBIL FLAG_WORK_PHONE FLAG_PHONE FLAG_EMAIL OCCUPATION_TYPE \\\n",
|
|
"0 1 1 0 0 NaN \n",
|
|
"1 1 1 0 0 NaN \n",
|
|
"2 1 0 0 0 Security staff \n",
|
|
"3 1 0 1 1 Sales staff \n",
|
|
"4 1 0 1 1 Sales staff \n",
|
|
"\n",
|
|
" CNT_FAM_MEMBERS \n",
|
|
"0 2.0 \n",
|
|
"1 2.0 \n",
|
|
"2 2.0 \n",
|
|
"3 1.0 \n",
|
|
"4 1.0 "
|
|
]
|
|
},
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"df.head()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"<class 'pandas.core.frame.DataFrame'>\n",
|
|
"RangeIndex: 438557 entries, 0 to 438556\n",
|
|
"Data columns (total 18 columns):\n",
|
|
" # Column Non-Null Count Dtype \n",
|
|
"--- ------ -------------- ----- \n",
|
|
" 0 ID 438557 non-null int64 \n",
|
|
" 1 CODE_GENDER 438557 non-null object \n",
|
|
" 2 FLAG_OWN_CAR 438557 non-null object \n",
|
|
" 3 FLAG_OWN_REALTY 438557 non-null object \n",
|
|
" 4 CNT_CHILDREN 438557 non-null int64 \n",
|
|
" 5 AMT_INCOME_TOTAL 438557 non-null float64\n",
|
|
" 6 NAME_INCOME_TYPE 438557 non-null object \n",
|
|
" 7 NAME_EDUCATION_TYPE 438557 non-null object \n",
|
|
" 8 NAME_FAMILY_STATUS 438557 non-null object \n",
|
|
" 9 NAME_HOUSING_TYPE 438557 non-null object \n",
|
|
" 10 DAYS_BIRTH 438557 non-null int64 \n",
|
|
" 11 DAYS_EMPLOYED 438557 non-null int64 \n",
|
|
" 12 FLAG_MOBIL 438557 non-null int64 \n",
|
|
" 13 FLAG_WORK_PHONE 438557 non-null int64 \n",
|
|
" 14 FLAG_PHONE 438557 non-null int64 \n",
|
|
" 15 FLAG_EMAIL 438557 non-null int64 \n",
|
|
" 16 OCCUPATION_TYPE 304354 non-null object \n",
|
|
" 17 CNT_FAM_MEMBERS 438557 non-null float64\n",
|
|
"dtypes: float64(2), int64(8), object(8)\n",
|
|
"memory usage: 60.2+ MB\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"df.info()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## TASKS \n",
|
|
"\n",
|
|
"### Recreate the plots shown in the markdown image cells. Each plot also contains a brief description of what it is trying to convey. Note, these are meant to be quite challenging. Start by first replicating the most basic form of the plot, then attempt to adjust its styling and parameters to match the given image.\n",
|
|
"\n",
|
|
"In general do not worry about coloring,styling, or sizing matching up exactly. Instead focus on the content of the plot itself. Our goal is not to test you on recognizing figsize=(10,8) , its to test your understanding of being able to see a requested plot, and reproducing it.\n",
|
|
"\n",
|
|
"**NOTE: You may need to perform extra calculations on the pandas dataframe before calling seaborn to create the plot.**"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"----\n",
|
|
"----\n",
|
|
"### TASK: Recreate the Scatter Plot shown below\n",
|
|
"\n",
|
|
"**The scatterplot attempts to show the relationship between the days employed versus the age of the person (DAYS_BIRTH) for people who were not unemployed. Note, to reproduce this chart you must remove unemployed people from the dataset first. Also note the sign of the axis, they are both transformed to be positive. Finally, feel free to adjust the *alpha* and *linewidth* parameters in the scatterplot since there are so many points stacked on top of each other.** \n",
|
|
"\n",
|
|
"<img src=\"task_one.jpg\">\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# CODE HERE TO RECREATE THE PLOT SHOWN ABOVE"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"-----\n",
|
|
"### TASK: Recreate the Distribution Plot shown below:\n",
|
|
"\n",
|
|
"<img src=\"DistPlot_solution.png\">\n",
|
|
"\n",
|
|
"**Note, you will need to figure out how to calculate \"Age in Years\" from one of the columns in the DF. Think carefully about this. Don't worry too much if you are unable to replicate the styling exactly.**"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# CODE HERE TO RECREATE THE PLOT SHOWN ABOVE"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"-----\n",
|
|
"### TASK: Recreate the Categorical Plot shown below:\n",
|
|
"\n",
|
|
"<img src='catplot_solution.png'>\n",
|
|
"\n",
|
|
"**This plot shows information only for the *bottom half* of income earners in the data set. It shows the boxplots for each category of NAME_FAMILY_STATUS column for displaying their distribution of their total income. Note: You will need to adjust or only take part of the dataframe *before* recreating this plot. You may want to explore the *order* parameter to get the xticks in the exact order shown here**"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 52,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# CODE HERE"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"### TASK: Recreate the Heat Map shown below:\n",
|
|
"\n",
|
|
"<img src='heatmap_solution.png'>"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"**This heatmap shows the correlation between the columns in the dataframe. You can get correlation with .corr() , also note that the FLAG_MOBIL column has NaN correlation with every other column, so you should drop it before calling .corr().**"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# CODE HERE"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 22,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"<AxesSubplot:>"
|
|
]
|
|
},
|
|
"execution_count": 22,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
},
|
|
{
|
|
"data": {
|
|
"image/png": "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\n",
|
|
"text/plain": [
|
|
"<Figure size 432x288 with 2 Axes>"
|
|
]
|
|
},
|
|
"metadata": {
|
|
"needs_background": "light"
|
|
},
|
|
"output_type": "display_data"
|
|
}
|
|
],
|
|
"source": []
|
|
}
|
|
],
|
|
"metadata": {
|
|
"anaconda-cloud": {},
|
|
"kernelspec": {
|
|
"display_name": "Python 3",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.7.6"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 1
|
|
}
|