Employee Retention Prediction in Logistic Regression in ML

Program 1

Machine Learning Dataset

import pandas as pd
from matplotlib import pyplot as plt


df = pd.read_csv("D://scikit_data/Employee/HR_comma_sep.csv")


df.head(10)


left = df[df.left==1]
left.shape


left.shape


left


retained = df[df.left==0]
retained.shape


retained


pd.crosstab(df.salary,df.left).plot(kind='bar')


pd.crosstab(df.Department,df.left).plot(kind='bar')


subdf = df[['satisfaction_level','average_montly_hours','promotion_last_5years','salary']]
subdf.head()


salary_dummies = pd.get_dummies(subdf.salary, prefix="salary")


salary_dummies


df_with_dummies = pd.concat([subdf,salary_dummies],axis='columns')


df_with_dummies.head()


df_with_dummies.drop('salary',axis='columns',inplace=True)
df_with_dummies.head()


x = df_with_dummies  # Independed variables
x.head()


y = df.left  # Depended variable


from sklearn.model_selection import train_test_split


x_train,x_test, y_train, y_test = train_test_split(x,y,train_size=0.3)


len(x_train)


len(x_test)

from sklearn.linear_model import LogisticRegression


model=LogisticRegression()


model.fit(x_train,y_train)


model.predict(x_test)


model


x=model.predict(x_test)


print(x)


model.score(x_test,y_test)


model.score(x_train,y_train)


x_test


model.predict(x_test)



model.predict([[0,0,0,0,0,1]])


model.predict([[0,0,0,1,0,0]])


model.predict([[1,0,1,0,0,1]])


model.predict([[0,0,1,1,0,0]])


model.predict([[1,0,0,0,1,0]])