Assignment2EM

import pandas as pd #to read and manipulate data
import matplotlib.pyplot as plt #to draw graphs
import numpy as np #to do scientific computing if any
from statsmodels.formula.api import ols #for linear regression
from statsmodels.api import qqplot
from statsmodels.stats.diagnostic import het_breuschpagan #for Breusch-Pagan test test
import seaborn as sns #for heatmap
from scipy import stats
from statsmodels.stats.diagnostic import linear_rainbow #linearity test
from scipy.stats import shapiro #for checking normality
from statsmodels.stats.outliers_influence import variance_inflation_factor #for checking Multicolinearity


data=pd.read_excel("CLV.xlsx")


model=ols(formula="Final_Grade~failures+romantic", data=data)

results=model.fit()

results.summary()

residuals=results.resid

het_breuschpagan(residuals,model.exog)

linear_rainbow(results)

stat,p = shapiro(residuals)
print(stat,p)

my_list=['romantic','failures']

vif = [variance_inflation_factor(db[my_list].values, i) for i in range(0,5)]
print(vif)