In [1]:

!pip install pandas numpy matplotlib seaborn

Requirement already satisfied: pandas in c:\users\luke holmes\anaconda3\lib\site-packages (1.5.3)
Requirement already satisfied: numpy in c:\users\luke holmes\anaconda3\lib\site-packages (1.24.3)
Requirement already satisfied: matplotlib in c:\users\luke holmes\anaconda3\lib\site-packages (3.7.1)
Requirement already satisfied: seaborn in c:\users\luke holmes\anaconda3\lib\site-packages (0.12.2)
Requirement already satisfied: python-dateutil>=2.8.1 in c:\users\luke holmes\anaconda3\lib\site-packages (from pandas) (2.8.2)
Requirement already satisfied: pytz>=2020.1 in c:\users\luke holmes\anaconda3\lib\site-packages (from pandas) (2022.7)
Requirement already satisfied: contourpy>=1.0.1 in c:\users\luke holmes\anaconda3\lib\site-packages (from matplotlib) (1.0.5)
Requirement already satisfied: cycler>=0.10 in c:\users\luke holmes\anaconda3\lib\site-packages (from matplotlib) (0.11.0)
Requirement already satisfied: fonttools>=4.22.0 in c:\users\luke holmes\anaconda3\lib\site-packages (from matplotlib) (4.25.0)
Requirement already satisfied: kiwisolver>=1.0.1 in c:\users\luke holmes\anaconda3\lib\site-packages (from matplotlib) (1.4.4)
Requirement already satisfied: packaging>=20.0 in c:\users\luke holmes\anaconda3\lib\site-packages (from matplotlib) (23.0)
Requirement already satisfied: pillow>=6.2.0 in c:\users\luke holmes\anaconda3\lib\site-packages (from matplotlib) (9.4.0)
Requirement already satisfied: pyparsing>=2.3.1 in c:\users\luke holmes\anaconda3\lib\site-packages (from matplotlib) (3.0.9)
Requirement already satisfied: six>=1.5 in c:\users\luke holmes\anaconda3\lib\site-packages (from python-dateutil>=2.8.1->pandas) (1.16.0)

In [2]:

# Importing necessary libraries
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

In [3]:

import pandas as pd

pd.set_option('display.max_rows', 100)  
pd.set_option('display.max_columns', 100)  

In [4]:

pd.set_option('display.max_columns', None)
pd.set_option('display.width', 1000)

In [5]:

file_path = 'Employee_Attrition.csv'
data = pd.read_csv(file_path)

In [6]:

print(data.head())

         Age Attrition     BusinessTravel    DailyRate              Department  DistanceFromHome  Education EducationField  EmployeeCount  EmployeeNumber  EnvironmentSatisfaction  Gender  HourlyRate  JobInvolvement  JobLevel                JobRole  JobSatisfaction MaritalStatus  MonthlyIncome   MonthlyRate  NumCompaniesWorked Over18 OverTime  PercentSalaryHike  PerformanceRating  RelationshipSatisfaction  StandardHours  StockOptionLevel  TotalWorkingYears  TrainingTimesLastYear  WorkLifeBalance  YearsAtCompany  YearsInCurrentRole  YearsSinceLastPromotion  YearsWithCurrManager
0  41.920786       Yes      Travel_Rarely   990.110009                   Sales          1.016716   1.770313  Life Sciences       1.033298        1.054148                 2.146294    Male   93.827486        3.426960  2.464492        Sales Executive         3.397665        Single    6438.949336  20845.103714            7.077818      Y      Yes           9.898765           2.844897                  1.012832      95.612654          0.000000           8.063833               0.000000         1.052104        5.795945            3.993896                 0.000000              4.594972
1  51.589037        No  Travel_Frequently   276.776030  Research & Development               NaN   1.035333  Life Sciences       0.944859        2.107031                 3.470803    Male   52.304157        1.813458  1.788697     Research Scientist         1.584059       Married    4457.659622  24877.898697            1.114423      Y       No                NaN           4.120281                  4.312008      85.370868          1.104642           8.965059               3.264952         2.526470       10.070232            7.937505                 1.032295              5.901207
2  33.131540       Yes      Travel_Rarely  1204.158501  Research & Development          2.198662   2.118801          Other       0.810809        4.008125                 3.979420    Male   87.271332        1.877226  0.833488  Laboratory Technician         3.301009        Single    2124.545220   2262.942954            5.539591      Y      Yes          15.401596           2.781168                  2.332558      76.248084          0.000000           8.427238               3.004521         2.924784        0.000000            0.000000                 0.000000              0.000000
3  34.707073        No  Travel_Frequently  1352.752432                   Sales          2.937851   3.670674  Life Sciences       0.822976        4.587269                 3.734705  Female   56.378982        2.932646  1.095372     Research Scientist         3.220844       Married    2771.699080  27189.905714            0.772793    NaN      Yes           9.757546           2.769576                  3.029591      75.888697          0.000000           7.662606               2.856001         3.117053        8.435324            5.563667                 2.845429              0.000000
4  24.790188        No      Travel_Rarely   485.053333  Research & Development          1.988953   1.120496        Medical            NaN        7.228740                 1.079412    Male   40.433887        3.117739  0.937746  Laboratory Technician         1.697330       Married    3254.601575  17675.541599           10.118125    NaN      NaN          11.920147           3.282183                       NaN      72.670937          0.953012           6.241733               2.814719         3.112317        2.040124            1.970786                 2.495949              2.219353

In [7]:

print("\nBasic Descriptive Statistics:")
print(data.describe())

Basic Descriptive Statistics:
               Age    DailyRate  DistanceFromHome    Education  EmployeeCount  EmployeeNumber  EnvironmentSatisfaction   HourlyRate  JobInvolvement     JobLevel  JobSatisfaction  MonthlyIncome   MonthlyRate  NumCompaniesWorked  PercentSalaryHike  PerformanceRating  RelationshipSatisfaction  StandardHours  StockOptionLevel  TotalWorkingYears  TrainingTimesLastYear  WorkLifeBalance  YearsAtCompany  YearsInCurrentRole  YearsSinceLastPromotion  YearsWithCurrManager
count  1323.000000  1323.000000       1323.000000  1323.000000    1323.000000     1323.000000              1323.000000  1323.000000     1323.000000  1323.000000      1323.000000    1323.000000   1323.000000         1323.000000        1323.000000        1323.000000               1323.000000    1323.000000       1323.000000        1323.000000            1323.000000      1323.000000     1323.000000         1323.000000              1323.000000           1323.000000
mean     36.635268   802.030050          9.091097     2.923447       0.999325     1026.679166                 2.726443    65.647722        2.743028     2.058270         2.715272    6544.718401  14364.334764            2.654394          15.295717           3.149344                  2.720431      80.241313          0.814757          11.426152               2.811756         2.762825        6.933624            4.233363                 2.160710              4.117695
std       9.882161   414.031025          8.177870     1.072203       0.099656      610.480802                 1.129679    21.469709        0.765568     1.127018         1.146786    4766.580903   7269.420895            2.508952           3.995702           0.476027                  1.115959       8.022535          0.863076           8.075870               1.329044         0.761802        6.046798            3.658111                 3.221481              3.594053
min      14.544608    86.828045          0.750112     0.770362       0.628985        1.054148                 0.759655    23.855272        0.722008     0.715172         0.724192     891.481007   1567.502382            0.000000           7.684723           2.116951                  0.720696      53.793059          0.000000           0.000000               0.000000         0.799138        0.000000            0.000000                 0.000000              0.000000
25%      29.624982   456.479553          2.147069     2.122706       0.931146      501.854842                 1.894818    47.701897        2.177638     1.045228         1.846039    2961.844066   8138.576694            0.948843          12.195197           2.845502                  1.909010      74.882946          0.000000           5.953221               1.967328         2.193390        2.673269            1.824392                 0.000000              1.687177
50%      34.951950   782.958705          6.920808     3.015658       0.998949     1022.025017                 2.887313    64.934490        2.859143     1.936150         2.895032    4957.070475  14258.293365            1.708812          14.495151           3.064551                  2.891235      80.351400          0.913651           9.306742               2.690934         2.899807        5.422160            2.968874                 0.967140              2.939240
75%      42.748741  1130.577949         13.584900     3.700560       1.067371     1533.811096                 3.676600    83.038355        3.179128     2.609707         3.676663    8268.002496  20322.279885            3.959710          17.745736           3.335525                  3.639961      85.664169          1.082523          15.324548               3.366949         3.206117        9.238005            7.052591                 2.586631              6.987964
max      69.402515  1784.394456         33.684424     6.285161       1.290613     2530.919375                 5.254672   123.200439        5.241968     5.942269         5.251277   22858.020388  32751.715800           10.855733          29.797261           5.013371                  5.092280     107.378705          3.474319          47.641892               7.503201         4.856086       36.848408           19.091844                17.273662             19.976003

In [8]:

print(data.head().T)

                                        0                       1                       2                   3                       4
Age                             41.920786               51.589037                33.13154           34.707073               24.790188
Attrition                             Yes                      No                     Yes                  No                      No
BusinessTravel              Travel_Rarely       Travel_Frequently           Travel_Rarely   Travel_Frequently           Travel_Rarely
DailyRate                      990.110009               276.77603             1204.158501         1352.752432              485.053333
Department                          Sales  Research & Development  Research & Development               Sales  Research & Development
DistanceFromHome                 1.016716                     NaN                2.198662            2.937851                1.988953
Education                        1.770313                1.035333                2.118801            3.670674                1.120496
EducationField              Life Sciences           Life Sciences                   Other       Life Sciences                 Medical
EmployeeCount                    1.033298                0.944859                0.810809            0.822976                     NaN
EmployeeNumber                   1.054148                2.107031                4.008125            4.587269                 7.22874
EnvironmentSatisfaction          2.146294                3.470803                 3.97942            3.734705                1.079412
Gender                               Male                    Male                    Male              Female                    Male
HourlyRate                      93.827486               52.304157               87.271332           56.378982               40.433887
JobInvolvement                    3.42696                1.813458                1.877226            2.932646                3.117739
JobLevel                         2.464492                1.788697                0.833488            1.095372                0.937746
JobRole                   Sales Executive      Research Scientist   Laboratory Technician  Research Scientist   Laboratory Technician
JobSatisfaction                  3.397665                1.584059                3.301009            3.220844                 1.69733
MaritalStatus                      Single                 Married                  Single             Married                 Married
MonthlyIncome                 6438.949336             4457.659622              2124.54522          2771.69908             3254.601575
MonthlyRate                  20845.103714            24877.898697             2262.942954        27189.905714            17675.541599
NumCompaniesWorked               7.077818                1.114423                5.539591            0.772793               10.118125
Over18                                  Y                       Y                       Y                 NaN                     NaN
OverTime                              Yes                      No                     Yes                 Yes                     NaN
PercentSalaryHike                9.898765                     NaN               15.401596            9.757546               11.920147
PerformanceRating                2.844897                4.120281                2.781168            2.769576                3.282183
RelationshipSatisfaction         1.012832                4.312008                2.332558            3.029591                     NaN
StandardHours                   95.612654               85.370868               76.248084           75.888697               72.670937
StockOptionLevel                      0.0                1.104642                     0.0                 0.0                0.953012
TotalWorkingYears                8.063833                8.965059                8.427238            7.662606                6.241733
TrainingTimesLastYear                 0.0                3.264952                3.004521            2.856001                2.814719
WorkLifeBalance                  1.052104                 2.52647                2.924784            3.117053                3.112317
YearsAtCompany                   5.795945               10.070232                     0.0            8.435324                2.040124
YearsInCurrentRole               3.993896                7.937505                     0.0            5.563667                1.970786
YearsSinceLastPromotion               0.0                1.032295                     0.0            2.845429                2.495949
YearsWithCurrManager             4.594972                5.901207                     0.0                 0.0                2.219353

In [9]:

from IPython.display import display
display(data.describe())

	Age	DailyRate	DistanceFromHome	Education	EmployeeCount	EmployeeNumber	EnvironmentSatisfaction	HourlyRate	JobInvolvement	JobLevel	JobSatisfaction	MonthlyIncome	MonthlyRate	NumCompaniesWorked	PercentSalaryHike	PerformanceRating	RelationshipSatisfaction	StandardHours	StockOptionLevel	TotalWorkingYears	TrainingTimesLastYear	WorkLifeBalance	YearsAtCompany	YearsInCurrentRole	YearsSinceLastPromotion	YearsWithCurrManager
count	1323.000000	1323.000000	1323.000000	1323.000000	1323.000000	1323.000000	1323.000000	1323.000000	1323.000000	1323.000000	1323.000000	1323.000000	1323.000000	1323.000000	1323.000000	1323.000000	1323.000000	1323.000000	1323.000000	1323.000000	1323.000000	1323.000000	1323.000000	1323.000000	1323.000000	1323.000000
mean	36.635268	802.030050	9.091097	2.923447	0.999325	1026.679166	2.726443	65.647722	2.743028	2.058270	2.715272	6544.718401	14364.334764	2.654394	15.295717	3.149344	2.720431	80.241313	0.814757	11.426152	2.811756	2.762825	6.933624	4.233363	2.160710	4.117695
std	9.882161	414.031025	8.177870	1.072203	0.099656	610.480802	1.129679	21.469709	0.765568	1.127018	1.146786	4766.580903	7269.420895	2.508952	3.995702	0.476027	1.115959	8.022535	0.863076	8.075870	1.329044	0.761802	6.046798	3.658111	3.221481	3.594053
min	14.544608	86.828045	0.750112	0.770362	0.628985	1.054148	0.759655	23.855272	0.722008	0.715172	0.724192	891.481007	1567.502382	0.000000	7.684723	2.116951	0.720696	53.793059	0.000000	0.000000	0.000000	0.799138	0.000000	0.000000	0.000000	0.000000
25%	29.624982	456.479553	2.147069	2.122706	0.931146	501.854842	1.894818	47.701897	2.177638	1.045228	1.846039	2961.844066	8138.576694	0.948843	12.195197	2.845502	1.909010	74.882946	0.000000	5.953221	1.967328	2.193390	2.673269	1.824392	0.000000	1.687177
50%	34.951950	782.958705	6.920808	3.015658	0.998949	1022.025017	2.887313	64.934490	2.859143	1.936150	2.895032	4957.070475	14258.293365	1.708812	14.495151	3.064551	2.891235	80.351400	0.913651	9.306742	2.690934	2.899807	5.422160	2.968874	0.967140	2.939240
75%	42.748741	1130.577949	13.584900	3.700560	1.067371	1533.811096	3.676600	83.038355	3.179128	2.609707	3.676663	8268.002496	20322.279885	3.959710	17.745736	3.335525	3.639961	85.664169	1.082523	15.324548	3.366949	3.206117	9.238005	7.052591	2.586631	6.987964
max	69.402515	1784.394456	33.684424	6.285161	1.290613	2530.919375	5.254672	123.200439	5.241968	5.942269	5.251277	22858.020388	32751.715800	10.855733	29.797261	5.013371	5.092280	107.378705	3.474319	47.641892	7.503201	4.856086	36.848408	19.091844	17.273662	19.976003

In [10]:

display(data.head())

	Age	Attrition	BusinessTravel	DailyRate	Department	DistanceFromHome	Education	EducationField	EmployeeCount	EmployeeNumber	EnvironmentSatisfaction	Gender	HourlyRate	JobInvolvement	JobLevel	JobRole	JobSatisfaction	MaritalStatus	MonthlyIncome	MonthlyRate	NumCompaniesWorked	Over18	OverTime	PercentSalaryHike	PerformanceRating	RelationshipSatisfaction	StandardHours	StockOptionLevel	TotalWorkingYears	TrainingTimesLastYear	WorkLifeBalance	YearsAtCompany	YearsInCurrentRole	YearsSinceLastPromotion	YearsWithCurrManager
0	41.920786	Yes	Travel_Rarely	990.110009	Sales	1.016716	1.770313	Life Sciences	1.033298	1.054148	2.146294	Male	93.827486	3.426960	2.464492	Sales Executive	3.397665	Single	6438.949336	20845.103714	7.077818	Y	Yes	9.898765	2.844897	1.012832	95.612654	0.000000	8.063833	0.000000	1.052104	5.795945	3.993896	0.000000	4.594972
1	51.589037	No	Travel_Frequently	276.776030	Research & Development	NaN	1.035333	Life Sciences	0.944859	2.107031	3.470803	Male	52.304157	1.813458	1.788697	Research Scientist	1.584059	Married	4457.659622	24877.898697	1.114423	Y	No	NaN	4.120281	4.312008	85.370868	1.104642	8.965059	3.264952	2.526470	10.070232	7.937505	1.032295	5.901207
2	33.131540	Yes	Travel_Rarely	1204.158501	Research & Development	2.198662	2.118801	Other	0.810809	4.008125	3.979420	Male	87.271332	1.877226	0.833488	Laboratory Technician	3.301009	Single	2124.545220	2262.942954	5.539591	Y	Yes	15.401596	2.781168	2.332558	76.248084	0.000000	8.427238	3.004521	2.924784	0.000000	0.000000	0.000000	0.000000
3	34.707073	No	Travel_Frequently	1352.752432	Sales	2.937851	3.670674	Life Sciences	0.822976	4.587269	3.734705	Female	56.378982	2.932646	1.095372	Research Scientist	3.220844	Married	2771.699080	27189.905714	0.772793	NaN	Yes	9.757546	2.769576	3.029591	75.888697	0.000000	7.662606	2.856001	3.117053	8.435324	5.563667	2.845429	0.000000
4	24.790188	No	Travel_Rarely	485.053333	Research & Development	1.988953	1.120496	Medical	NaN	7.228740	1.079412	Male	40.433887	3.117739	0.937746	Laboratory Technician	1.697330	Married	3254.601575	17675.541599	10.118125	NaN	NaN	11.920147	3.282183	NaN	72.670937	0.953012	6.241733	2.814719	3.112317	2.040124	1.970786	2.495949	2.219353

In [11]:

print("\nMissing Values:")
print(data.isnull().sum())

Missing Values:
Age                         147
Attrition                   147
BusinessTravel              147
DailyRate                   147
Department                  147
DistanceFromHome            147
Education                   147
EducationField              147
EmployeeCount               147
EmployeeNumber              147
EnvironmentSatisfaction     147
Gender                      147
HourlyRate                  147
JobInvolvement              147
JobLevel                    147
JobRole                     147
JobSatisfaction             147
MaritalStatus               147
MonthlyIncome               147
MonthlyRate                 147
NumCompaniesWorked          147
Over18                      147
OverTime                    147
PercentSalaryHike           147
PerformanceRating           147
RelationshipSatisfaction    147
StandardHours               147
StockOptionLevel            147
TotalWorkingYears           147
TrainingTimesLastYear       147
WorkLifeBalance             147
YearsAtCompany              147
YearsInCurrentRole          147
YearsSinceLastPromotion     147
YearsWithCurrManager        147
dtype: int64

In [12]:

data.shape

Out[12]:

(1470, 35)

In [13]:

data_cleaned = data.dropna()
print("New Data Shape:", data_cleaned.shape)

New Data Shape: (40, 35)

In [14]:

for col in data.select_dtypes(include=np.number).columns:
    data[col].fillna(data[col].mean(), inplace=True)

for col in data.select_dtypes(include='object').columns:
    data[col].fillna(data[col].mode()[0], inplace=True)

print("Data Shape after Imputation:", data.shape)

Data Shape after Imputation: (1470, 35)

In [15]:

print("Missing values after imputation:", data.isnull().sum().sum())

Missing values after imputation: 0

In [18]:

numerical_features = data.select_dtypes(include=np.number).columns.tolist()
categorical_features = data.select_dtypes(include='object').columns.tolist()

print("Numerical features:", numerical_features)
print("Categorical features:", categorical_features)

Numerical features: ['Age', 'DailyRate', 'DistanceFromHome', 'Education', 'EmployeeCount', 'EmployeeNumber', 'EnvironmentSatisfaction', 'HourlyRate', 'JobInvolvement', 'JobLevel', 'JobSatisfaction', 'MonthlyIncome', 'MonthlyRate', 'NumCompaniesWorked', 'PercentSalaryHike', 'PerformanceRating', 'RelationshipSatisfaction', 'StandardHours', 'StockOptionLevel', 'TotalWorkingYears', 'TrainingTimesLastYear', 'WorkLifeBalance', 'YearsAtCompany', 'YearsInCurrentRole', 'YearsSinceLastPromotion', 'YearsWithCurrManager']
Categorical features: ['Attrition', 'BusinessTravel', 'Department', 'EducationField', 'Gender', 'JobRole', 'MaritalStatus', 'Over18', 'OverTime']

In [19]:

In [22]:

for col in numerical_features:
    plt.figure(figsize=(8, 4))
    sns.histplot(data[col], kde=True)
    plt.title(f'Distribution of {col}')
    plt.xlabel(col)
    plt.ylabel('Frequency')
    plt.show()

In [24]:

for col in categorical_features:
    plt.figure(figsize=(8, 4))
    sns.countplot(x=col, data=data)
    plt.title(f'Distribution of {col}')
    plt.xticks(rotation=45)
    plt.xlabel(col)
    plt.ylabel('Count')
    plt.show()

In [ ]:

In [25]:

from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.compose import ColumnTransformer

preprocessor = ColumnTransformer(
    transformers=[
        ('num', StandardScaler(), numerical_features),
        ('cat', OneHotEncoder(), categorical_features)
    ])

data_processed = preprocessor.fit_transform(data)

In [29]:

cat_features = preprocessor.named_transformers_['cat'].get_feature_names_out(categorical_features)

all_features = numerical_features + cat_features.tolist()

data_processed_df = pd.DataFrame(data_processed, columns=all_features)

In [30]:

print(data_processed_df.describe())

                Age     DailyRate  DistanceFromHome     Education  EmployeeCount  EmployeeNumber  EnvironmentSatisfaction    HourlyRate  JobInvolvement      JobLevel  JobSatisfaction  MonthlyIncome   MonthlyRate  NumCompaniesWorked  PercentSalaryHike  PerformanceRating  RelationshipSatisfaction  StandardHours  StockOptionLevel  TotalWorkingYears  TrainingTimesLastYear  WorkLifeBalance  YearsAtCompany  YearsInCurrentRole  YearsSinceLastPromotion  YearsWithCurrManager  Attrition_No  Attrition_Yes  BusinessTravel_Non-Travel  BusinessTravel_Travel_Frequently  BusinessTravel_Travel_Rarely  Department_Human Resources  Department_Research & Development  Department_Sales  EducationField_Human Resources  EducationField_Life Sciences  EducationField_Marketing  EducationField_Medical  EducationField_Other  EducationField_Technical Degree  Gender_Female  Gender_Male  JobRole_Healthcare Representative  JobRole_Human Resources  JobRole_Laboratory Technician  JobRole_Manager  \
count  1.470000e+03  1.470000e+03      1.470000e+03  1.470000e+03   1.470000e+03    1.470000e+03             1.470000e+03  1.470000e+03    1.470000e+03  1.470000e+03     1.470000e+03   1.470000e+03  1.470000e+03        1.470000e+03       1.470000e+03       1.470000e+03              1.470000e+03   1.470000e+03      1.470000e+03       1.470000e+03           1.470000e+03     1.470000e+03    1.470000e+03        1.470000e+03             1.470000e+03          1.470000e+03   1470.000000    1470.000000                1470.000000                       1470.000000                   1470.000000                 1470.000000                        1470.000000       1470.000000                     1470.000000                   1470.000000               1470.000000             1470.000000           1470.000000                      1470.000000    1470.000000  1470.000000                        1470.000000              1470.000000                    1470.000000      1470.000000   
mean   4.326094e-16  9.667248e-18      1.377583e-16 -1.885113e-16   7.540454e-16    1.546760e-16             1.933450e-17 -8.700523e-17    2.477232e-16  2.392644e-16    -2.513485e-16  -3.746059e-17  0.000000e+00       -5.075305e-17       8.338001e-17       1.595096e-16             -2.368476e-16   1.457338e-15     -1.933450e-17      -9.667248e-18           1.413835e-16     7.250436e-18    1.836777e-16       -8.338001e-17             5.316986e-17         -3.456041e-16      0.824490       0.175510                   0.104762                          0.189796                      0.705442                    0.072109                           0.660544          0.267347                        0.033333                      0.442857                  0.101361                0.270068              0.056463                         0.095918       0.367347     0.632653                           0.080272                 0.040816                       0.155782         0.068707   
std    1.000340e+00  1.000340e+00      1.000340e+00  1.000340e+00   1.000340e+00    1.000340e+00             1.000340e+00  1.000340e+00    1.000340e+00  1.000340e+00     1.000340e+00   1.000340e+00  1.000340e+00        1.000340e+00       1.000340e+00       1.000340e+00              1.000340e+00   1.000340e+00      1.000340e+00       1.000340e+00           1.000340e+00     1.000340e+00    1.000340e+00        1.000340e+00             1.000340e+00          1.000340e+00      0.380532       0.380532                   0.306351                          0.392273                      0.455999                    0.258756                           0.473686          0.442726                        0.179567                      0.496893                  0.301908                0.444146              0.230891                         0.294579       0.482246     0.482246                           0.271806                 0.197932                       0.362772         0.253042   
min   -2.357218e+00 -1.821540e+00     -1.075524e+00 -2.117518e+00  -3.918668e+00   -1.771575e+00            -1.835884e+00 -2.052649e+00   -2.783746e+00 -1.256666e+00    -1.830835e+00  -1.250643e+00 -1.856289e+00       -1.115619e+00      -2.008590e+00      -2.286948e+00             -1.889588e+00  -3.476389e+00     -9.954557e-01      -1.491948e+00          -2.230906e+00    -2.718147e+00   -1.209143e+00       -1.220314e+00            -7.072677e-01         -1.208127e+00      0.000000       0.000000                   0.000000                          0.000000                      0.000000                    0.000000                           0.000000          0.000000                        0.000000                      0.000000                  0.000000                0.000000              0.000000                         0.000000       0.000000     0.000000                           0.000000                 0.000000                       0.000000         0.000000   
25%   -6.698885e-01 -7.624073e-01     -8.801388e-01 -7.106715e-01  -6.436999e-01   -8.417690e-01            -7.190978e-01 -8.163050e-01   -6.644049e-01 -9.287072e-01    -7.166879e-01  -7.448754e-01 -8.133326e-01       -7.092988e-01      -7.476689e-01      -6.092411e-01             -7.110232e-01  -6.288545e-01     -9.954557e-01      -6.643384e-01          -6.341142e-01    -6.566636e-01   -6.900668e-01       -6.737752e-01            -7.072677e-01         -6.762744e-01      1.000000       0.000000                   0.000000                          0.000000                      0.000000                    0.000000                           0.000000          0.000000                        0.000000                      0.000000                  0.000000                0.000000              0.000000                         0.000000       0.000000     0.000000                           0.000000                 0.000000                       0.000000         0.000000   
50%   -3.979301e-02  2.895478e-16     -1.572434e-01 -4.367532e-16   1.174756e-15    0.000000e+00             0.000000e+00  0.000000e+00    5.007715e-02 -5.525191e-02     1.392373e-02  -2.320246e-01  2.638598e-16       -2.457437e-01      -7.684195e-02      -7.601347e-02              2.714607e-02   1.867891e-15      5.094126e-02      -1.828699e-01           0.000000e+00     6.701606e-02   -1.713352e-01       -2.132420e-01            -3.683742e-01         -2.082280e-01      1.000000       0.000000                   0.000000                          0.000000                      1.000000                    0.000000                           1.000000          0.000000                        0.000000                      0.000000                  0.000000                0.000000              0.000000                         0.000000       0.000000     1.000000                           0.000000                 0.000000                       0.000000         0.000000   
75%    5.420049e-01  7.616039e-01      3.138841e-01  6.636076e-01   6.382783e-01    7.653682e-01             7.239376e-01  7.769248e-01    5.457430e-01  2.357327e-01     7.701983e-01   2.309499e-01  7.748776e-01        4.373216e-01       4.802629e-01       3.401735e-01              7.136293e-01   6.185459e-01      2.966171e-01       3.619964e-01           3.578518e-01     5.629550e-01    3.250412e-01        7.273780e-01             0.000000e+00          7.691807e-01      1.000000       0.000000                   0.000000                          0.000000                      1.000000                    0.000000                           1.000000          1.000000                        0.000000                      1.000000                  0.000000                1.000000              0.000000                         0.000000       1.000000     1.000000                           0.000000                 0.000000                       0.000000         0.000000   
max    3.496479e+00  2.501973e+00      3.171174e+00  3.306181e+00   3.082195e+00    2.598293e+00             2.359958e+00  2.826719e+00    3.442032e+00  3.634052e+00     2.331904e+00   3.608925e+00  2.667246e+00        3.446954e+00       3.827049e+00       4.129180e+00              2.241205e+00   3.566970e+00      3.249407e+00       4.728800e+00           3.722291e+00     2.897504e+00    5.216790e+00        4.283122e+00             4.946940e+00          4.652810e+00      1.000000       1.000000                   1.000000                          1.000000                      1.000000                    1.000000                           1.000000          1.000000                        1.000000                      1.000000                  1.000000                1.000000              1.000000                         1.000000       1.000000     1.000000                           1.000000                 1.000000                       1.000000         1.000000   

       JobRole_Manufacturing Director  JobRole_Research Director  JobRole_Research Scientist  JobRole_Sales Executive  JobRole_Sales Representative  MaritalStatus_Divorced  MaritalStatus_Married  MaritalStatus_Single  Over18_Y  OverTime_No  OverTime_Yes  
count                     1470.000000                1470.000000                 1470.000000              1470.000000                   1470.000000             1470.000000            1470.000000           1470.000000    1470.0  1470.000000   1470.000000  
mean                         0.082993                   0.054422                    0.174830                 0.291156                      0.051020                0.202721               0.505442              0.291837       1.0     0.731973      0.268027  
std                          0.275966                   0.226925                    0.379951                 0.454450                      0.220114                0.402163               0.500141              0.454762       0.0     0.443083      0.443083  
min                          0.000000                   0.000000                    0.000000                 0.000000                      0.000000                0.000000               0.000000              0.000000       1.0     0.000000      0.000000  
25%                          0.000000                   0.000000                    0.000000                 0.000000                      0.000000                0.000000               0.000000              0.000000       1.0     0.000000      0.000000  
50%                          0.000000                   0.000000                    0.000000                 0.000000                      0.000000                0.000000               1.000000              0.000000       1.0     1.000000      0.000000  
75%                          0.000000                   0.000000                    0.000000                 1.000000                      0.000000                0.000000               1.000000              1.000000       1.0     1.000000      1.000000  
max                          1.000000                   1.000000                    1.000000                 1.000000                      1.000000                1.000000               1.000000              1.000000       1.0     1.000000      1.000000

In [31]:

pd.set_option('display.float_format', lambda x: '%.2f' % x)
data_processed_df.describe()

Out[31]:

	Age	DailyRate	DistanceFromHome	Education	EmployeeCount	EmployeeNumber	EnvironmentSatisfaction	HourlyRate	JobInvolvement	JobLevel	JobSatisfaction	MonthlyIncome	MonthlyRate	NumCompaniesWorked	PercentSalaryHike	PerformanceRating	RelationshipSatisfaction	StandardHours	StockOptionLevel	TotalWorkingYears	TrainingTimesLastYear	WorkLifeBalance	YearsAtCompany	YearsInCurrentRole	YearsSinceLastPromotion	YearsWithCurrManager	Attrition_No	Attrition_Yes	BusinessTravel_Non-Travel	BusinessTravel_Travel_Frequently	BusinessTravel_Travel_Rarely	Department_Human Resources	Department_Research & Development	Department_Sales	EducationField_Human Resources	EducationField_Life Sciences	EducationField_Marketing	EducationField_Medical	EducationField_Other	EducationField_Technical Degree	Gender_Female	Gender_Male	JobRole_Healthcare Representative	JobRole_Human Resources	JobRole_Laboratory Technician	JobRole_Manager	JobRole_Manufacturing Director	JobRole_Research Director	JobRole_Research Scientist	JobRole_Sales Executive	JobRole_Sales Representative	MaritalStatus_Divorced	MaritalStatus_Married	MaritalStatus_Single	Over18_Y	OverTime_No	OverTime_Yes
count	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00
mean	0.00	0.00	0.00	-0.00	0.00	0.00	0.00	-0.00	0.00	0.00	-0.00	-0.00	0.00	-0.00	0.00	0.00	-0.00	0.00	-0.00	-0.00	0.00	0.00	0.00	-0.00	0.00	-0.00	0.82	0.18	0.10	0.19	0.71	0.07	0.66	0.27	0.03	0.44	0.10	0.27	0.06	0.10	0.37	0.63	0.08	0.04	0.16	0.07	0.08	0.05	0.17	0.29	0.05	0.20	0.51	0.29	1.00	0.73	0.27
std	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	0.38	0.38	0.31	0.39	0.46	0.26	0.47	0.44	0.18	0.50	0.30	0.44	0.23	0.29	0.48	0.48	0.27	0.20	0.36	0.25	0.28	0.23	0.38	0.45	0.22	0.40	0.50	0.45	0.00	0.44	0.44
min	-2.36	-1.82	-1.08	-2.12	-3.92	-1.77	-1.84	-2.05	-2.78	-1.26	-1.83	-1.25	-1.86	-1.12	-2.01	-2.29	-1.89	-3.48	-1.00	-1.49	-2.23	-2.72	-1.21	-1.22	-0.71	-1.21	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	1.00	0.00	0.00
25%	-0.67	-0.76	-0.88	-0.71	-0.64	-0.84	-0.72	-0.82	-0.66	-0.93	-0.72	-0.74	-0.81	-0.71	-0.75	-0.61	-0.71	-0.63	-1.00	-0.66	-0.63	-0.66	-0.69	-0.67	-0.71	-0.68	1.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	1.00	0.00	0.00
50%	-0.04	0.00	-0.16	-0.00	0.00	0.00	0.00	0.00	0.05	-0.06	0.01	-0.23	0.00	-0.25	-0.08	-0.08	0.03	0.00	0.05	-0.18	0.00	0.07	-0.17	-0.21	-0.37	-0.21	1.00	0.00	0.00	0.00	1.00	0.00	1.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	1.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	1.00	0.00	1.00	1.00	0.00
75%	0.54	0.76	0.31	0.66	0.64	0.77	0.72	0.78	0.55	0.24	0.77	0.23	0.77	0.44	0.48	0.34	0.71	0.62	0.30	0.36	0.36	0.56	0.33	0.73	0.00	0.77	1.00	0.00	0.00	0.00	1.00	0.00	1.00	1.00	0.00	1.00	0.00	1.00	0.00	0.00	1.00	1.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	1.00	0.00	0.00	1.00	1.00	1.00	1.00	1.00
max	3.50	2.50	3.17	3.31	3.08	2.60	2.36	2.83	3.44	3.63	2.33	3.61	2.67	3.45	3.83	4.13	2.24	3.57	3.25	4.73	3.72	2.90	5.22	4.28	4.95	4.65	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00

In [32]:

selected_columns = ['Age', 'DailyRate', 'DistanceFromHome', 'MonthlyIncome', 'Attrition_No', 'Attrition_Yes']
data_processed_df[selected_columns].describe()

Out[32]:

	Age	DailyRate	DistanceFromHome	MonthlyIncome	Attrition_No	Attrition_Yes
count	1470.00	1470.00	1470.00	1470.00	1470.00	1470.00
mean	0.00	0.00	0.00	-0.00	0.82	0.18
std	1.00	1.00	1.00	1.00	0.38	0.38
min	-2.36	-1.82	-1.08	-1.25	0.00	0.00
25%	-0.67	-0.76	-0.88	-0.74	1.00	0.00
50%	-0.04	0.00	-0.16	-0.23	1.00	0.00
75%	0.54	0.76	0.31	0.23	1.00	0.00
max	3.50	2.50	3.17	3.61	1.00	1.00

In [33]:

import seaborn as sns
import matplotlib.pyplot as plt

# Age Distribution
sns.histplot(data['Age'], kde=True)
plt.title('Age Distribution')
plt.xlabel('Age')
plt.ylabel('Count')
plt.show()

In [34]:

# Job Role Distribution
plt.figure(figsize=(10, 6))
sns.countplot(data=data, y='JobRole')
plt.title('Job Role Distribution')
plt.xlabel('Count')
plt.ylabel('Job Role')
plt.show()

In [35]:

# Job Role Distribution
plt.figure(figsize=(10, 6))
sns.countplot(data=data, y='JobRole')
plt.title('Job Role Distribution')
plt.xlabel('Count')
plt.ylabel('Job Role')
plt.show()

In [36]:

# Monthly Income Distribution
sns.histplot(data['MonthlyIncome'], kde=True)
plt.title('Monthly Income Distribution')
plt.xlabel('Monthly Income')
plt.ylabel('Count')
plt.show()

In [39]:

# Attrition Rate
sns.countplot(data=data, x='Attrition')
plt.title('Attrition Rate')
plt.xlabel('Attrition')
plt.ylabel('Count')
plt.show()

In [40]:

from sklearn.discriminant_analysis import LinearDiscriminantAnalysis as LDA
import matplotlib.pyplot as plt

In [42]:

lda = LDA(n_components=1) 
data_lda = lda.fit_transform(data_processed, class_labels)

plt.hist(data_lda[class_labels == 'Yes'], color='red', alpha=0.5, label='Attrition Yes')
plt.hist(data_lda[class_labels == 'No'], color='blue', alpha=0.5, label='Attrition No')
plt.title('LDA with 1 Component')
plt.xlabel('LD1')
plt.ylabel('Frequency')
plt.legend()
plt.show()

In [44]:

print(data_lda[:10])

[[ 2.20817721]
 [ 0.41066158]
 [ 1.61055669]
 [ 0.96858941]
 [ 1.04417906]
 [ 0.79475395]
 [ 0.56639182]
 [ 0.40650383]
 [ 0.99770173]
 [-0.33157394]]

In [45]:

from sklearn.decomposition import PCA

In [46]:

pca = PCA(n_components=2)
data_pca = pca.fit_transform(data_processed)

In [47]:

plt.figure(figsize=(8, 6))
plt.scatter(data_pca[:, 0], data_pca[:, 1], c=class_labels.map({'Yes': 1, 'No': 0}), cmap='rainbow', alpha=0.7)
plt.title('PCA with 2 Components')
plt.xlabel('PC1')
plt.ylabel('PC2')
plt.colorbar()
plt.show()

Statistical Analysis

Descriptive Statistics: Highlight key insights, such as average monthly income, typical job satisfaction scores, and other notable findings. Correlation Analysis: Point out any strong correlations that might influence employee satisfaction or productivity. Hypothesis Testing: Discuss whether the t-test and ANOVA results reveal significant differences that the company should consider. Regression Analysis: Explain how factors like years at the company are predictive of monthly income. Use Clear Visualizations: Include graphs and charts that clearly demonstrate your findings. Use Appropriate Terminology: Explain statistical terms in a way that's accessible to stakeholders without a statistical background.