aniruddha27

import pandas as pd 
import numpy as np 
import matplotlib.pyplot as plt 
plt.style.use('seaborn')

aniruddha27

# Import library for VIF
from statsmodels.stats.outliers_influence import variance_inflation_factor

def calc_vif(X):

    # Calculating VIF
    vif = pd.DataFrame()
    vif["variables"] = X.columns
    vif["VIF"] = [variance_inflation_factor(X.values, i) for i in range(X.shape[1])]

aniruddha27

X = df.iloc[:,:-1]
calc_vif(X)

aniruddha27

X = df.drop(['Age','Salary'],axis=1)
calc_vif(X)

aniruddha27

df2 = df.copy()
df2['Age_at_joining'] = df.apply(lambda x: x['Age'] - x['Years of service'],axis=1)
X = df2.drop(['Age','Years of service','Salary'],axis=1)
calc_vif(X)

aniruddha27

#import linear regression 
from sklearn.linear_model import LinearRegression 

#fit on training data 
lr=LinearRegression() 
lr.fit(X_train,y_train) 

#accuracy 
print('Training accuracy =',lr.score(X_train,y_train)) 
print('Testing accuracy =',lr.score(X_test,y_test)) 

aniruddha27

#import ridge model 
from sklearn.linear_model import Ridge 

#fit on training data with regularization of 0.3 
ridge = Ridge(alpha = 0.3) 
ridge.fit(X_train,y_train) 

#accuracy 
print('Train',ridge.score(X_train,y_train)) 
print('Test',ridge.score(X_test,y_test)) 

aniruddha27

#import lasso 
from sklearn.linear_model import Lasso 

#fit on training dataset 
ls = Lasso(alpha=0.08) 
ls.fit(X_train, y_train) 

#accuracy 
print('Training score =', ls.score(X_train, y_train)) 
print('Testing score=', ls.score(X_test, y_test)) 

aniruddha27

df_meal = pd.read_csv('C:\\Users\Dell\\Desktop\\train_food\\meal_info.csv')
df_meal.head()

aniruddha27

df_center = pd.read_csv('C:\\Users\Dell\\Desktop\\train_food\\fulfilment_center_info.csv') 
df_center.head()