g4_logistic_regression.py

#preparing column names for the model
all_columns = []
for column in df_data.columns:
    column = column.replace(" ", "_").replace("(", "_").replace(")", "_").replace("-", "_")
    all_columns.append(column)

df_data.columns = all_columns

glm_columns = 'gender'

for column in df_data.columns:
    if column not in ['Churn','customerID','gender']:
        glm_columns = glm_columns + ' + ' + column
        
#import libraries
import statsmodels.api as sm
import statsmodels.formula.api as smf
 
#fit the model
glm_model = smf.glm(formula='Churn ~ {}'.format(glm_columns), data=df_data, family=sm.families.Binomial()) 
res = glm_model.fit()

#print the summary
print(res.summary())