xxxxxxxxxx
#Imports
import pandas as pd
import numpy as np
from patsy import dmatrices
import statsmodels.api as sm
from statsmodels.stats.outliers_influence import variance_inflation_factor
df = pd.read_csv('loan.csv')
df.dropna()
df = df._get_numeric_data() #drop non-numeric cols
df.head()
xxxxxxxxxx
# For each X, calculate VIF and save in dataframe
vif = pd.DataFrame()
vif["VIF Factor"] = [variance_inflation_factor(X.values, i) for i in range(X.shape[1])]
vif["features"] = X.columns