Alakhator

# Creating DataFrame out of Advertising.csv 
df = pd.read_csv("Advertising.csv") 
df.drop("Unnamed: 0", axis=1,inplace=True) 
# Separating Independent and dependent variables 
X=df.drop(['sales’'],axis=1) Y=df.sales 
# Fit Linear Regression 
lr = LinearRegression() 
model=lr.fit(X,Y) 
y_pred1 = model.predict(X) 
print("R-squared: {0}".format(metrics..r2_score(Y,ypred1)))

Alakhator

plt.scatter(ypred, (Y-ypred1)) 
plt.xlabel("Fitted values") 
plt.ylabel("Residuals")

Alakhator

sns.pairplot(df)

Alakhator

from sklearn.preprocessing import PolynomialFeatures
poly = PolynomialFeatures(degree = 2) 
X_poly = poly.fit_transform(X)  
poly.fit(X_poly, Y) 
X_poly = sm.add_constant(X_poly) 
results = sm.OLS(Y,X_poly).fit() 
print(results.summary())

Alakhator

def calculate_vif(data):     
  vif_df = pd.DataFrame(columns = ['Var', 'Vif'])     
  x_var_names = data.columns    
  for i in range(0, x_var_names.shape[0]):    
    y = data[x_var_names[i]]    
    x = data[x_var_names.drop([x_var_names[i]])]    
    r_squared = sm.OLS(y,x).fit().rsquared    
    vif = round(1/(1-r_squared),2)   
    vif_df.loc[i] = [x_var_names[i], vif]   
  return vif_df.sort_values(by = 'Vif', axis = 0, ascending=False, inplace=False) 

Alakhator

plt.subplots(figsize=(8,4)) 
plt.subplot(1,2,1) 
plt.title("Before") 
sns.distplot(Y-ypred1 , fit=norm); 
plt.xlabel('Residuals') 
plt.subplot(1,2,2) 
plt.title("After") 
sns.distplot(Y-ypred2 , fit=norm); 
plt.xlabel('Residuals')

Alakhator

plt.subplots(figsize=(10,5)) 
plt.subplot(1,2,1) 
plt.title("Before") 
plt.plot(Y,Y, color="red") 
plt.scatter(ypred1, Y) 
plt.xlabel("Fitted values") 
plt.ylabel("Actuals")

Alakhator

plt.subplot(1,2,2) 
plt.title("After") 
plt.plot(Y,Y, color="red") 
plt.scatter(ypred3, Y) 
plt.xlabel("Fitted values") 
plt.ylabel("Actuals")

Alakhator

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

Alakhator

dataset = pd.read_csv('Position_Salaries.csv')
X = dataset.iloc[:, 1:2].values
y = dataset.iloc[:, 2].values