[Pandas][DataFrame]S2_13_FeatureEngineering

Human_Resources_Employee.csv

0.22MB

 

 

 

Feature Engineering and Dealing with Missing Dataset¶

 

 

https://www.kaggle.com/datasets/rishikeshkonapure/hr-analytics-prediction?resource=download

위 데이터의 일부를 Null 처리함

 

In [46]:

import pandas as pd

 

In [48]:

employee_df = pd.read_csv('Human_Resources_Employee.csv')
employee_df.head()

 

Out[48]:

	Age	Attrition	BusinessTravel	DailyRate	Department	DistanceFromHome	Education	EducationField	EmployeeCount	EmployeeNumber	...	RelationshipSatisfaction	StandardHours	StockOptionLevel	TotalWorkingYears	TrainingTimesLastYear	WorkLifeBalance	YearsAtCompany	YearsInCurrentRole	YearsSinceLastPromotion	YearsWithCurrManager
0	41	Yes	Travel_Rarely	1102	Sales	1	2	Life Sciences	1	1.0	...	1	80	0	8	0	1	6	4	0	5
1	49	No	Travel_Frequently	279	Research & Development	8	1	Life Sciences	1	2.0	...	4	80	1	10	3	3	10	7	1	7
2	37	Yes	Travel_Rarely	1373	Research & Development	2	2	Other	1	4.0	...	2	80	0	7	3	3	0	0	0	0
3	33	No	Travel_Frequently	1392	Research & Development	3	4	Life Sciences	1	5.0	...	3	80	0	8	3	3	8	7	3	0
4	27	No	Travel_Rarely	591	Research & Development	2	1	Medical	1	7.0	...	4	80	1	6	3	3	2	2	2	2

5 rows × 35 columns

 

In [ ]:

employee_df.shape

 

In [49]:

# Null values
employee_df.isnull().sum()

 

Out[49]:

Age                         0
Attrition                   0
BusinessTravel              0
DailyRate                   0
Department                  1
DistanceFromHome            0
Education                   0
EducationField              1
EmployeeCount               0
EmployeeNumber              1
EnvironmentSatisfaction     0
Gender                      1
HourlyRate                  0
JobInvolvement              0
JobLevel                    0
JobRole                     1
JobSatisfaction             0
MaritalStatus               1
MonthlyIncome               3
MonthlyRate                 2
NumCompaniesWorked          0
Over18                      0
OverTime                    0
PercentSalaryHike           1
PerformanceRating           1
RelationshipSatisfaction    0
StandardHours               0
StockOptionLevel            0
TotalWorkingYears           0
TrainingTimesLastYear       0
WorkLifeBalance             0
YearsAtCompany              0
YearsInCurrentRole          0
YearsSinceLastPromotion     0
YearsWithCurrManager        0
dtype: int64

 

In [50]:

employee_df.loc[employee_df['Department'].isnull()]

 

Out[50]:

	Age	Attrition	BusinessTravel	DailyRate	Department	DistanceFromHome	Education	EducationField	EmployeeCount	EmployeeNumber	...	RelationshipSatisfaction	StandardHours	StockOptionLevel	TotalWorkingYears	TrainingTimesLastYear	WorkLifeBalance	YearsAtCompany	YearsInCurrentRole	YearsSinceLastPromotion	YearsWithCurrManager
7	30	No	Travel_Rarely	1358	NaN	24	1	Life Sciences	1	11.0	...	2	80	1	1	2	3	1	0	0	0

1 rows × 35 columns

 

In [51]:

# Drop any tow that contains a Null value
employee_df.dropna(how='any', inplace=True)

 

In [52]:

# 7 rows are gone
employee_df.shape

 

Out[52]:

(1463, 35)

 

In [53]:

# re-data
employee_df = pd.read_csv('Human_Resources_Employee.csv')

 

In [54]:

# indicate which columns are interested in
employee_df.dropna(how='any', inplace=True, subset = ['MonthlyIncome','PercentSalaryHike'])

 

In [55]:

employee_df.shape

 

Out[55]:

(1467, 35)

 

In [56]:

# filling na data
employee_df = pd.read_csv('Human_Resources_Employee.csv')

 

In [57]:

# Calculate the average monthly income
employee_df['MonthlyIncome'].mean()

 

Out[57]:

6505.155419222904

 

In [58]:

employee_df['MonthlyIncome'].fillna(employee_df['MonthlyIncome'].mean(), inplace=True)