51194507011_stu_ecnu_edu_cn
/
Intel_AI
1
0
Fork 0
Code Issues 0 Pull Requests 0 Releases 0 Wiki Activity
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.
4 Commits
1 Branch
9.7 MiB
 
Branch: master
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'master'
${ noResults }
Intel_AI/第4节/LinearRegression-Employee A...

1482 lines
177 KiB
Raw Permalink Blame History file_download

{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "uClORbqu8Kd_"
},
"source": [
"# 基于线性回归的Employee Attrition Rate\n",
"\n",
"## 项目背景\n",
"\n",
"Artificial intelligence is commonly used in various trade circles to automate processes, gather insights on business, and speed up processes. You will use Python to study the usage of artificial intelligence in real-life scenarios - how AI actually impacts industries. \n",
"\n",
"Employees are the most important entities in an organization. Successful employees offer a lot to organisations. In this notebook, we will use AI to predict the attrition rate of employees or how often a company can retain employees.\n",
"\n",
"## Context\n",
"\n",
"We will be working with the dataset containing employee attrition rates, which is collected by Hackerearth and uploaded at [Kaggle](https://www.kaggle.com/blurredmachine/hackerearth-employee-attrition). We will use regression to predict attrition rates and see how successful is our model.\n",
"\n",
"\n",
"\n",
"## 使用Python打开csv 文件\n",
"\n",
"We will use the [scikit-learn](https://scikit-learn.org/stable/) and [pandas](https://pandas.pydata.org/) to work with our dataset. Scikit-learn is a very useful machine learning library that provides efficient tools for predictive data analysis. Pandas is a popular Python library for data science. It offers powerful and flexible data structures to make data manipulation and analysis easier.\n",
"\n",
"\n",
"## 包含模块\n"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 72
},
"colab_type": "code",
"id": "R4ARBxgN-zWr",
"outputId": "e026843f-d7c7-4ef9-fb04-8fdd9e482e99"
},
"outputs": [],
"source": [
"%matplotlib inline\n",
"import pandas as pd\n",
"import seaborn as sns\n",
"import matplotlib.pyplot as plt\n",
"\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.linear_model import LinearRegression \n",
"from sklearn import metrics\n",
"from sklearn.metrics import mean_squared_error"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "6xBB32V___tL"
},
"source": [
"### 导入数据集\n",
"The dataset contains employee attrition rates. Let us visualize the dataset."
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"colab": {},
"colab_type": "code",
"id": "de2cFC5p-6kq"
},
"outputs": [],
"source": [
"\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "rVP7JXphAuqC"
},
"source": [
"## 任务 1: Print the columns of the training set"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 138
},
"colab_type": "code",
"id": "Rb_JYsztAZ51",
"outputId": "44e74eab-2051-429c-b25e-98b4e6fe370e"
},
"outputs": [
{
"data": {
"text/plain": [
"Index(['Employee_ID', 'Gender', 'Age', 'Education_Level',\n",
" 'Relationship_Status', 'Hometown', 'Unit', 'Decision_skill_possess',\n",
" 'Time_of_service', 'Time_since_promotion', 'growth_rate', 'Travel_Rate',\n",
" 'Post_Level', 'Pay_Scale', 'Compensation_and_Benefits',\n",
" 'Work_Life_balance', 'VAR1', 'VAR2', 'VAR3', 'VAR4', 'VAR5', 'VAR6',\n",
" 'VAR7', 'Attrition_rate'],\n",
" dtype='object')"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\n"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 274
},
"colab_type": "code",
"id": "B3SY7OdMA-Dg",
"outputId": "4e97fef7-b7a6-45d7-982e-a048585bb375"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(7000, 24)\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Employee_ID</th>\n",
" <th>Gender</th>\n",
" <th>Age</th>\n",
" <th>Education_Level</th>\n",
" <th>Relationship_Status</th>\n",
" <th>Hometown</th>\n",
" <th>Unit</th>\n",
" <th>Decision_skill_possess</th>\n",
" <th>Time_of_service</th>\n",
" <th>Time_since_promotion</th>\n",
" <th>...</th>\n",
" <th>Compensation_and_Benefits</th>\n",
" <th>Work_Life_balance</th>\n",
" <th>VAR1</th>\n",
" <th>VAR2</th>\n",
" <th>VAR3</th>\n",
" <th>VAR4</th>\n",
" <th>VAR5</th>\n",
" <th>VAR6</th>\n",
" <th>VAR7</th>\n",
" <th>Attrition_rate</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>EID_23371</td>\n",
" <td>F</td>\n",
" <td>42.0</td>\n",
" <td>4</td>\n",
" <td>Married</td>\n",
" <td>Franklin</td>\n",
" <td>IT</td>\n",
" <td>Conceptual</td>\n",
" <td>4.0</td>\n",
" <td>4</td>\n",
" <td>...</td>\n",
" <td>type2</td>\n",
" <td>3.0</td>\n",
" <td>4</td>\n",
" <td>0.7516</td>\n",
" <td>1.8688</td>\n",
" <td>2.0</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>3</td>\n",
" <td>0.1841</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>EID_18000</td>\n",
" <td>M</td>\n",
" <td>24.0</td>\n",
" <td>3</td>\n",
" <td>Single</td>\n",
" <td>Springfield</td>\n",
" <td>Logistics</td>\n",
" <td>Analytical</td>\n",
" <td>5.0</td>\n",
" <td>4</td>\n",
" <td>...</td>\n",
" <td>type2</td>\n",
" <td>4.0</td>\n",
" <td>3</td>\n",
" <td>-0.9612</td>\n",
" <td>-0.4537</td>\n",
" <td>2.0</td>\n",
" <td>3</td>\n",
" <td>5</td>\n",
" <td>3</td>\n",
" <td>0.0670</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>EID_3891</td>\n",
" <td>F</td>\n",
" <td>58.0</td>\n",
" <td>3</td>\n",
" <td>Married</td>\n",
" <td>Clinton</td>\n",
" <td>Quality</td>\n",
" <td>Conceptual</td>\n",
" <td>27.0</td>\n",
" <td>3</td>\n",
" <td>...</td>\n",
" <td>type2</td>\n",
" <td>1.0</td>\n",
" <td>4</td>\n",
" <td>-0.9612</td>\n",
" <td>-0.4537</td>\n",
" <td>3.0</td>\n",
" <td>3</td>\n",
" <td>8</td>\n",
" <td>3</td>\n",
" <td>0.0851</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>EID_17492</td>\n",
" <td>F</td>\n",
" <td>26.0</td>\n",
" <td>3</td>\n",
" <td>Single</td>\n",
" <td>Lebanon</td>\n",
" <td>Human Resource Management</td>\n",
" <td>Behavioral</td>\n",
" <td>4.0</td>\n",
" <td>3</td>\n",
" <td>...</td>\n",
" <td>type2</td>\n",
" <td>1.0</td>\n",
" <td>3</td>\n",
" <td>-1.8176</td>\n",
" <td>-0.4537</td>\n",
" <td>NaN</td>\n",
" <td>3</td>\n",
" <td>7</td>\n",
" <td>3</td>\n",
" <td>0.0668</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>EID_22534</td>\n",
" <td>F</td>\n",
" <td>31.0</td>\n",
" <td>1</td>\n",
" <td>Married</td>\n",
" <td>Springfield</td>\n",
" <td>Logistics</td>\n",
" <td>Conceptual</td>\n",
" <td>5.0</td>\n",
" <td>4</td>\n",
" <td>...</td>\n",
" <td>type3</td>\n",
" <td>3.0</td>\n",
" <td>1</td>\n",
" <td>0.7516</td>\n",
" <td>-0.4537</td>\n",
" <td>2.0</td>\n",
" <td>2</td>\n",
" <td>8</td>\n",
" <td>2</td>\n",
" <td>0.1827</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 24 columns</p>\n",
"</div>"
],
"text/plain": [
" Employee_ID Gender Age Education_Level Relationship_Status Hometown \\\n",
"0 EID_23371 F 42.0 4 Married Franklin \n",
"1 EID_18000 M 24.0 3 Single Springfield \n",
"2 EID_3891 F 58.0 3 Married Clinton \n",
"3 EID_17492 F 26.0 3 Single Lebanon \n",
"4 EID_22534 F 31.0 1 Married Springfield \n",
"\n",
" Unit Decision_skill_possess Time_of_service \\\n",
"0 IT Conceptual 4.0 \n",
"1 Logistics Analytical 5.0 \n",
"2 Quality Conceptual 27.0 \n",
"3 Human Resource Management Behavioral 4.0 \n",
"4 Logistics Conceptual 5.0 \n",
"\n",
" Time_since_promotion ... Compensation_and_Benefits \\\n",
"0 4 ... type2 \n",
"1 4 ... type2 \n",
"2 3 ... type2 \n",
"3 3 ... type2 \n",
"4 4 ... type3 \n",
"\n",
" Work_Life_balance VAR1 VAR2 VAR3 VAR4 VAR5 VAR6 VAR7 \\\n",
"0 3.0 4 0.7516 1.8688 2.0 4 5 3 \n",
"1 4.0 3 -0.9612 -0.4537 2.0 3 5 3 \n",
"2 1.0 4 -0.9612 -0.4537 3.0 3 8 3 \n",
"3 1.0 3 -1.8176 -0.4537 NaN 3 7 3 \n",
"4 3.0 1 0.7516 -0.4537 2.0 2 8 2 \n",
"\n",
" Attrition_rate \n",
"0 0.1841 \n",
"1 0.0670 \n",
"2 0.0851 \n",
"3 0.0668 \n",
"4 0.1827 \n",
"\n",
"[5 rows x 24 columns]"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "puSoD2YOBSto"
},
"source": [
"### 数据描述\n",
"\n",
"Let us see how the data is distributed. We can visualize the mean, max, and min value of each column alongside other characteristics."
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 314
},
"colab_type": "code",
"id": "7pvRvVWrBB6d",
"outputId": "913e3dbe-1d1d-4089-e9f7-7d28492cc4ec"
},
"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>Age</th>\n",
" <th>Education_Level</th>\n",
" <th>Time_of_service</th>\n",
" <th>Time_since_promotion</th>\n",
" <th>growth_rate</th>\n",
" <th>Travel_Rate</th>\n",
" <th>Post_Level</th>\n",
" <th>Pay_Scale</th>\n",
" <th>Work_Life_balance</th>\n",
" <th>VAR1</th>\n",
" <th>VAR2</th>\n",
" <th>VAR3</th>\n",
" <th>VAR4</th>\n",
" <th>VAR5</th>\n",
" <th>VAR6</th>\n",
" <th>VAR7</th>\n",
" <th>Attrition_rate</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>6588.000000</td>\n",
" <td>7000.000000</td>\n",
" <td>6856.000000</td>\n",
" <td>7000.000000</td>\n",
" <td>7000.000000</td>\n",
" <td>7000.000000</td>\n",
" <td>7000.000000</td>\n",
" <td>6991.000000</td>\n",
" <td>6989.000000</td>\n",
" <td>7000.000000</td>\n",
" <td>6423.000000</td>\n",
" <td>7000.000000</td>\n",
" <td>6344.000000</td>\n",
" <td>7000.000000</td>\n",
" <td>7000.000000</td>\n",
" <td>7000.000000</td>\n",
" <td>7000.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
" <td>39.622799</td>\n",
" <td>3.187857</td>\n",
" <td>13.385064</td>\n",
" <td>2.367143</td>\n",
" <td>47.064286</td>\n",
" <td>0.817857</td>\n",
" <td>2.798000</td>\n",
" <td>6.006294</td>\n",
" <td>2.387895</td>\n",
" <td>3.098571</td>\n",
" <td>-0.008126</td>\n",
" <td>-0.013606</td>\n",
" <td>1.891078</td>\n",
" <td>2.834143</td>\n",
" <td>7.101286</td>\n",
" <td>3.257000</td>\n",
" <td>0.189376</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>13.606920</td>\n",
" <td>1.065102</td>\n",
" <td>10.364188</td>\n",
" <td>1.149395</td>\n",
" <td>15.761406</td>\n",
" <td>0.648205</td>\n",
" <td>1.163721</td>\n",
" <td>2.058435</td>\n",
" <td>1.122786</td>\n",
" <td>0.836377</td>\n",
" <td>0.989850</td>\n",
" <td>0.986933</td>\n",
" <td>0.529403</td>\n",
" <td>0.938945</td>\n",
" <td>1.164262</td>\n",
" <td>0.925319</td>\n",
" <td>0.185753</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>19.000000</td>\n",
" <td>1.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>20.000000</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>-1.817600</td>\n",
" <td>-2.776200</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>5.000000</td>\n",
" <td>1.000000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>27.000000</td>\n",
" <td>3.000000</td>\n",
" <td>5.000000</td>\n",
" <td>1.000000</td>\n",
" <td>33.000000</td>\n",
" <td>0.000000</td>\n",
" <td>2.000000</td>\n",
" <td>5.000000</td>\n",
" <td>1.000000</td>\n",
" <td>3.000000</td>\n",
" <td>-0.961200</td>\n",
" <td>-0.453700</td>\n",
" <td>2.000000</td>\n",
" <td>2.000000</td>\n",
" <td>6.000000</td>\n",
" <td>3.000000</td>\n",
" <td>0.070400</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>37.000000</td>\n",
" <td>3.000000</td>\n",
" <td>10.000000</td>\n",
" <td>2.000000</td>\n",
" <td>47.000000</td>\n",
" <td>1.000000</td>\n",
" <td>3.000000</td>\n",
" <td>6.000000</td>\n",
" <td>2.000000</td>\n",
" <td>3.000000</td>\n",
" <td>-0.104800</td>\n",
" <td>-0.453700</td>\n",
" <td>2.000000</td>\n",
" <td>3.000000</td>\n",
" <td>7.000000</td>\n",
" <td>3.000000</td>\n",
" <td>0.142650</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>52.000000</td>\n",
" <td>4.000000</td>\n",
" <td>21.000000</td>\n",
" <td>3.000000</td>\n",
" <td>61.000000</td>\n",
" <td>1.000000</td>\n",
" <td>3.000000</td>\n",
" <td>8.000000</td>\n",
" <td>3.000000</td>\n",
" <td>3.000000</td>\n",
" <td>0.751600</td>\n",
" <td>0.707500</td>\n",
" <td>2.000000</td>\n",
" <td>3.000000</td>\n",
" <td>8.000000</td>\n",
" <td>4.000000</td>\n",
" <td>0.235000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>65.000000</td>\n",
" <td>5.000000</td>\n",
" <td>43.000000</td>\n",
" <td>4.000000</td>\n",
" <td>74.000000</td>\n",
" <td>2.000000</td>\n",
" <td>5.000000</td>\n",
" <td>10.000000</td>\n",
" <td>5.000000</td>\n",
" <td>5.000000</td>\n",
" <td>1.608100</td>\n",
" <td>1.868800</td>\n",
" <td>3.000000</td>\n",
" <td>5.000000</td>\n",
" <td>9.000000</td>\n",
" <td>5.000000</td>\n",
" <td>0.995900</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Age Education_Level Time_of_service Time_since_promotion \\\n",
"count 6588.000000 7000.000000 6856.000000 7000.000000 \n",
"mean 39.622799 3.187857 13.385064 2.367143 \n",
"std 13.606920 1.065102 10.364188 1.149395 \n",
"min 19.000000 1.000000 0.000000 0.000000 \n",
"25% 27.000000 3.000000 5.000000 1.000000 \n",
"50% 37.000000 3.000000 10.000000 2.000000 \n",
"75% 52.000000 4.000000 21.000000 3.000000 \n",
"max 65.000000 5.000000 43.000000 4.000000 \n",
"\n",
" growth_rate Travel_Rate Post_Level Pay_Scale Work_Life_balance \\\n",
"count 7000.000000 7000.000000 7000.000000 6991.000000 6989.000000 \n",
"mean 47.064286 0.817857 2.798000 6.006294 2.387895 \n",
"std 15.761406 0.648205 1.163721 2.058435 1.122786 \n",
"min 20.000000 0.000000 1.000000 1.000000 1.000000 \n",
"25% 33.000000 0.000000 2.000000 5.000000 1.000000 \n",
"50% 47.000000 1.000000 3.000000 6.000000 2.000000 \n",
"75% 61.000000 1.000000 3.000000 8.000000 3.000000 \n",
"max 74.000000 2.000000 5.000000 10.000000 5.000000 \n",
"\n",
" VAR1 VAR2 VAR3 VAR4 VAR5 \\\n",
"count 7000.000000 6423.000000 7000.000000 6344.000000 7000.000000 \n",
"mean 3.098571 -0.008126 -0.013606 1.891078 2.834143 \n",
"std 0.836377 0.989850 0.986933 0.529403 0.938945 \n",
"min 1.000000 -1.817600 -2.776200 1.000000 1.000000 \n",
"25% 3.000000 -0.961200 -0.453700 2.000000 2.000000 \n",
"50% 3.000000 -0.104800 -0.453700 2.000000 3.000000 \n",
"75% 3.000000 0.751600 0.707500 2.000000 3.000000 \n",
"max 5.000000 1.608100 1.868800 3.000000 5.000000 \n",
"\n",
" VAR6 VAR7 Attrition_rate \n",
"count 7000.000000 7000.000000 7000.000000 \n",
"mean 7.101286 3.257000 0.189376 \n",
"std 1.164262 0.925319 0.185753 \n",
"min 5.000000 1.000000 0.000000 \n",
"25% 6.000000 3.000000 0.070400 \n",
"50% 7.000000 3.000000 0.142650 \n",
"75% 8.000000 4.000000 0.235000 \n",
"max 9.000000 5.000000 0.995900 "
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": []
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "0pNp0HwvC4cV"
},
"source": [
"## 任务2: Get information about the training data set using the describe function"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 314
},
"colab_type": "code",
"id": "9ySxpstZBibr",
"outputId": "b3c6575e-c78b-43af-dd51-5ece6d163d21"
},
"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>Age</th>\n",
" <th>Education_Level</th>\n",
" <th>Time_of_service</th>\n",
" <th>Time_since_promotion</th>\n",
" <th>growth_rate</th>\n",
" <th>Travel_Rate</th>\n",
" <th>Post_Level</th>\n",
" <th>Pay_Scale</th>\n",
" <th>Work_Life_balance</th>\n",
" <th>VAR1</th>\n",
" <th>VAR2</th>\n",
" <th>VAR3</th>\n",
" <th>VAR4</th>\n",
" <th>VAR5</th>\n",
" <th>VAR6</th>\n",
" <th>VAR7</th>\n",
" <th>Attrition_rate</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>6588.000000</td>\n",
" <td>7000.000000</td>\n",
" <td>6856.000000</td>\n",
" <td>7000.000000</td>\n",
" <td>7000.000000</td>\n",
" <td>7000.000000</td>\n",
" <td>7000.000000</td>\n",
" <td>6991.000000</td>\n",
" <td>6989.000000</td>\n",
" <td>7000.000000</td>\n",
" <td>6423.000000</td>\n",
" <td>7000.000000</td>\n",
" <td>6344.000000</td>\n",
" <td>7000.000000</td>\n",
" <td>7000.000000</td>\n",
" <td>7000.000000</td>\n",
" <td>7000.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
" <td>39.622799</td>\n",
" <td>3.187857</td>\n",
" <td>13.385064</td>\n",
" <td>2.367143</td>\n",
" <td>47.064286</td>\n",
" <td>0.817857</td>\n",
" <td>2.798000</td>\n",
" <td>6.006294</td>\n",
" <td>2.387895</td>\n",
" <td>3.098571</td>\n",
" <td>-0.008126</td>\n",
" <td>-0.013606</td>\n",
" <td>1.891078</td>\n",
" <td>2.834143</td>\n",
" <td>7.101286</td>\n",
" <td>3.257000</td>\n",
" <td>0.189376</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>13.606920</td>\n",
" <td>1.065102</td>\n",
" <td>10.364188</td>\n",
" <td>1.149395</td>\n",
" <td>15.761406</td>\n",
" <td>0.648205</td>\n",
" <td>1.163721</td>\n",
" <td>2.058435</td>\n",
" <td>1.122786</td>\n",
" <td>0.836377</td>\n",
" <td>0.989850</td>\n",
" <td>0.986933</td>\n",
" <td>0.529403</td>\n",
" <td>0.938945</td>\n",
" <td>1.164262</td>\n",
" <td>0.925319</td>\n",
" <td>0.185753</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>19.000000</td>\n",
" <td>1.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>20.000000</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>-1.817600</td>\n",
" <td>-2.776200</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>5.000000</td>\n",
" <td>1.000000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>27.000000</td>\n",
" <td>3.000000</td>\n",
" <td>5.000000</td>\n",
" <td>1.000000</td>\n",
" <td>33.000000</td>\n",
" <td>0.000000</td>\n",
" <td>2.000000</td>\n",
" <td>5.000000</td>\n",
" <td>1.000000</td>\n",
" <td>3.000000</td>\n",
" <td>-0.961200</td>\n",
" <td>-0.453700</td>\n",
" <td>2.000000</td>\n",
" <td>2.000000</td>\n",
" <td>6.000000</td>\n",
" <td>3.000000</td>\n",
" <td>0.070400</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>37.000000</td>\n",
" <td>3.000000</td>\n",
" <td>10.000000</td>\n",
" <td>2.000000</td>\n",
" <td>47.000000</td>\n",
" <td>1.000000</td>\n",
" <td>3.000000</td>\n",
" <td>6.000000</td>\n",
" <td>2.000000</td>\n",
" <td>3.000000</td>\n",
" <td>-0.104800</td>\n",
" <td>-0.453700</td>\n",
" <td>2.000000</td>\n",
" <td>3.000000</td>\n",
" <td>7.000000</td>\n",
" <td>3.000000</td>\n",
" <td>0.142650</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>52.000000</td>\n",
" <td>4.000000</td>\n",
" <td>21.000000</td>\n",
" <td>3.000000</td>\n",
" <td>61.000000</td>\n",
" <td>1.000000</td>\n",
" <td>3.000000</td>\n",
" <td>8.000000</td>\n",
" <td>3.000000</td>\n",
" <td>3.000000</td>\n",
" <td>0.751600</td>\n",
" <td>0.707500</td>\n",
" <td>2.000000</td>\n",
" <td>3.000000</td>\n",
" <td>8.000000</td>\n",
" <td>4.000000</td>\n",
" <td>0.235000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>65.000000</td>\n",
" <td>5.000000</td>\n",
" <td>43.000000</td>\n",
" <td>4.000000</td>\n",
" <td>74.000000</td>\n",
" <td>2.000000</td>\n",
" <td>5.000000</td>\n",
" <td>10.000000</td>\n",
" <td>5.000000</td>\n",
" <td>5.000000</td>\n",
" <td>1.608100</td>\n",
" <td>1.868800</td>\n",
" <td>3.000000</td>\n",
" <td>5.000000</td>\n",
" <td>9.000000</td>\n",
" <td>5.000000</td>\n",
" <td>0.995900</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Age Education_Level Time_of_service Time_since_promotion \\\n",
"count 6588.000000 7000.000000 6856.000000 7000.000000 \n",
"mean 39.622799 3.187857 13.385064 2.367143 \n",
"std 13.606920 1.065102 10.364188 1.149395 \n",
"min 19.000000 1.000000 0.000000 0.000000 \n",
"25% 27.000000 3.000000 5.000000 1.000000 \n",
"50% 37.000000 3.000000 10.000000 2.000000 \n",
"75% 52.000000 4.000000 21.000000 3.000000 \n",
"max 65.000000 5.000000 43.000000 4.000000 \n",
"\n",
" growth_rate Travel_Rate Post_Level Pay_Scale Work_Life_balance \\\n",
"count 7000.000000 7000.000000 7000.000000 6991.000000 6989.000000 \n",
"mean 47.064286 0.817857 2.798000 6.006294 2.387895 \n",
"std 15.761406 0.648205 1.163721 2.058435 1.122786 \n",
"min 20.000000 0.000000 1.000000 1.000000 1.000000 \n",
"25% 33.000000 0.000000 2.000000 5.000000 1.000000 \n",
"50% 47.000000 1.000000 3.000000 6.000000 2.000000 \n",
"75% 61.000000 1.000000 3.000000 8.000000 3.000000 \n",
"max 74.000000 2.000000 5.000000 10.000000 5.000000 \n",
"\n",
" VAR1 VAR2 VAR3 VAR4 VAR5 \\\n",
"count 7000.000000 6423.000000 7000.000000 6344.000000 7000.000000 \n",
"mean 3.098571 -0.008126 -0.013606 1.891078 2.834143 \n",
"std 0.836377 0.989850 0.986933 0.529403 0.938945 \n",
"min 1.000000 -1.817600 -2.776200 1.000000 1.000000 \n",
"25% 3.000000 -0.961200 -0.453700 2.000000 2.000000 \n",
"50% 3.000000 -0.104800 -0.453700 2.000000 3.000000 \n",
"75% 3.000000 0.751600 0.707500 2.000000 3.000000 \n",
"max 5.000000 1.608100 1.868800 3.000000 5.000000 \n",
"\n",
" VAR6 VAR7 Attrition_rate \n",
"count 7000.000000 7000.000000 7000.000000 \n",
"mean 7.101286 3.257000 0.189376 \n",
"std 1.164262 0.925319 0.185753 \n",
"min 5.000000 1.000000 0.000000 \n",
"25% 6.000000 3.000000 0.070400 \n",
"50% 7.000000 3.000000 0.142650 \n",
"75% 8.000000 4.000000 0.235000 \n",
"max 9.000000 5.000000 0.995900 "
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#Here is the description of the train data too\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 450
},
"colab_type": "code",
"id": "VNSgkpGhBylQ",
"outputId": "6defceaa-82af-4dde-bbf2-b1aae1e4cc47"
},
"outputs": [
{
"data": {
"text/plain": [
"Employee_ID False\n",
"Gender False\n",
"Age True\n",
"Education_Level False\n",
"Relationship_Status False\n",
"Hometown False\n",
"Unit False\n",
"Decision_skill_possess False\n",
"Time_of_service True\n",
"Time_since_promotion False\n",
"growth_rate False\n",
"Travel_Rate False\n",
"Post_Level False\n",
"Pay_Scale True\n",
"Compensation_and_Benefits False\n",
"Work_Life_balance True\n",
"VAR1 False\n",
"VAR2 True\n",
"VAR3 False\n",
"VAR4 True\n",
"VAR5 False\n",
"VAR6 False\n",
"VAR7 False\n",
"Attrition_rate False\n",
"dtype: bool"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Let's see if training set has any missing values\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "onO3KLorD8R8"
},
"source": [
"### 数据可视化\n",
"\n",
"Now, let us see the correlation matrix to see how related are the features."
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 714
},
"colab_type": "code",
"id": "7AD5fiGICINO",
"outputId": "2d70ce07-915c-4fe8-a060-5f537cbb6404"
},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 1296x720 with 2 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"<Figure size 432x288 with 0 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "UMn9li18E7CU"
},
"source": [
"### 模型准备\n",
"\n",
"Now we will finalize the data for the training and prepare the model."
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"colab": {},
"colab_type": "code",
"id": "UlskIaq1EIct"
},
"outputs": [],
"source": [
"#Attrition_rate is the label or output to be predicted\n",
"#features will be used to predict Attrition_rate\n",
"\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
},
"colab_type": "code",
"id": "-8gY91pCFQZR",
"outputId": "07d3981b-3084-4bb1-a6c1-a713fc657d8c"
},
"outputs": [
{
"data": {
"text/plain": [
"(6856, 12)"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\n",
"#We will drop the columns here which have missing values using dropna function\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"colab": {},
"colab_type": "code",
"id": "8KBBjKtlFTIf"
},
"outputs": [],
"source": [
"\n"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"colab": {},
"colab_type": "code",
"id": "WqzHfmYFFl6o"
},
"outputs": [],
"source": [
"#Here the training and test data are split 55% to 45% as test size is 0.55\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"colab": {},
"colab_type": "code",
"id": "rHA8vcJgFcMA"
},
"outputs": [],
"source": [
"df = LinearRegression()\n",
"\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
},
"colab_type": "code",
"id": "P-OSoWuGFh_2",
"outputId": "978d7bb9-bfe5-43a9-c310-8da5a111662d"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"96.72970811621633\n"
]
}
],
"source": [
"#Let's print the accuracy now\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 202
},
"colab_type": "code",
"id": "jhB__hobF0QG",
"outputId": "2ff5c861-2142-4378-bdd9-7eb42bcf0d0c"
},
"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>Employee_ID</th>\n",
" <th>Attrition_rate</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>EID_22713</td>\n",
" <td>0.18662</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>EID_9658</td>\n",
" <td>0.20435</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>EID_22203</td>\n",
" <td>0.20973</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>EID_7652</td>\n",
" <td>0.20025</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>EID_6516</td>\n",
" <td>0.17774</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Employee_ID Attrition_rate\n",
"0 EID_22713 0.18662\n",
"1 EID_9658 0.20435\n",
"2 EID_22203 0.20973\n",
"3 EID_7652 0.20025\n",
"4 EID_6516 0.17774"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#Predicting\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "kB06o_GGF7zn"
},
"source": [
"## 任务 3: Print the first 20 columns of predictions\n"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 662
},
"colab_type": "code",
"id": "fIQY5JWcF5kV",
"outputId": "5484a0dc-adda-4a16-8f60-11b8a0272bf0"
},
"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>Employee_ID</th>\n",
" <th>Attrition_rate</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>EID_22713</td>\n",
" <td>0.18662</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>EID_9658</td>\n",
" <td>0.20435</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>EID_22203</td>\n",
" <td>0.20973</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>EID_7652</td>\n",
" <td>0.20025</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>EID_6516</td>\n",
" <td>0.17774</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>EID_20283</td>\n",
" <td>0.20274</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>EID_21014</td>\n",
" <td>0.18806</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>EID_7693</td>\n",
" <td>0.18530</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>EID_13232</td>\n",
" <td>0.18676</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>EID_6515</td>\n",
" <td>0.20339</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>EID_13639</td>\n",
" <td>0.21399</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>EID_14669</td>\n",
" <td>0.20041</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>EID_16537</td>\n",
" <td>0.18771</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>EID_5782</td>\n",
" <td>0.16481</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>EID_20157</td>\n",
" <td>0.21093</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>EID_1855</td>\n",
" <td>0.19392</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>EID_20748</td>\n",
" <td>0.20191</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>EID_23179</td>\n",
" <td>0.17694</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>EID_12838</td>\n",
" <td>0.18062</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>EID_21656</td>\n",
" <td>0.17483</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Employee_ID Attrition_rate\n",
"0 EID_22713 0.18662\n",
"1 EID_9658 0.20435\n",
"2 EID_22203 0.20973\n",
"3 EID_7652 0.20025\n",
"4 EID_6516 0.17774\n",
"5 EID_20283 0.20274\n",
"6 EID_21014 0.18806\n",
"7 EID_7693 0.18530\n",
"8 EID_13232 0.18676\n",
"9 EID_6515 0.20339\n",
"10 EID_13639 0.21399\n",
"11 EID_14669 0.20041\n",
"12 EID_16537 0.18771\n",
"13 EID_5782 0.16481\n",
"14 EID_20157 0.21093\n",
"15 EID_1855 0.19392\n",
"16 EID_20748 0.20191\n",
"17 EID_23179 0.17694\n",
"18 EID_12838 0.18062\n",
"19 EID_21656 0.17483"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": []
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "ZGdw47ChGG8I"
},
"source": [
"### 结论\n",
"\n",
"In this notebook, we have seen how AI can be used by companies to predict which employess would be loyal to them. We have bulit a linear regression model to predict the attrition rate."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"colab": {
"name": "[Jupyter - Coach] Module 11 Predicting Employee Attrition Rate.ipynb",
"provenance": [],
"toc_visible": true
},
"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": "3.6.5"
},
"toc": {
"base_numbering": 1,
"nav_menu": {},
"number_sections": true,
"sideBar": true,
"skip_h1_title": false,
"title_cell": "Table of Contents",
"title_sidebar": "Contents",
"toc_cell": false,
"toc_position": {},
"toc_section_display": true,
"toc_window_display": false
}
},
"nbformat": 4,
"nbformat_minor": 1
}