logistic_regression.html

# -*- coding: utf-8 -*-
"""Logistic_Regression.ipynb

Automatically generated by Colaboratory.

Original file is located at
https://colab.research.google.com/drive/1evsgNOvajsenWB5spLxNCrIiuTqemzB2
"""

import numpy as np
import pandas as pd
import os
import math
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report
from sklearn.metrics import accuracy_score
from sklearn.metrics import confusion_matrix
from sklearn.metrics import f1_score
from sklearn.metrics import precision_score
import matplotlib.pyplot as plt

df = pd.read_csv('HR Employee Attrition.csv',na_values= "?")
df.head(25)

df.shape

lb = LabelEncoder()
df['EducationField'] = lb.fit_transform(df['EducationField'])
df['BusinessTravel'] = lb.fit_transform(df['BusinessTravel'])
df['Attrition'] = lb.fit_transform(df['Attrition'])
df['Department'] = lb.fit_transform(df['Department'])
df['Gender'] = lb.fit_transform(df['Gender'])
df['JobRole'] = lb.fit_transform(df['JobRole'])
df['MaritalStatus'] = lb.fit_transform(df['MaritalStatus'])
df['OverTime'] = lb.fit_transform(df['OverTime'])
df['Over18'] = lb.fit_transform(df['Over18'])

d = df.drop(['Attrition'], axis=1)

df.shape

Y = df['Attrition']
X = d

X_train, X_test, y_train, y_test = train_test_split(X,Y,test_size=0.3,random_state=42)
X_train.shape
X_test.shape
y_train.shape
y_test.shape

ss = StandardScaler()
X_train = ss.fit_transform(X_train)
X_test = ss.transform(X_test)

lr = LogisticRegression(C = 1.0, penalty='l2', tol=0.01)

lr.fit(X_train,y_train)
lr_y_predict = lr.predict(X_test)

lr.score(X_test,y_test)
classification_report(y_test, lr_y_predict,target_names=['good','bad'])

clf = LogisticRegression(verbose = 3)
clf_trained = clf.fit(X_train,y_train)

clf_trained.score(X_train,y_train)

predictions = clf_trained.predict(X_test)
classification_report(y_test,predictions)

accuracy_score(y_test, predictions)

confusion_matrix(y_test, predictions)

f1_score(y_test, predictions)

precision_score(y_test, predictions, pos_label = 0)