df_column_name.index = np.arange(1, len(df_column_name) + 1) df_column_name import statsmodels.api as sm import statsmodels.formula.api as smf #logit_model=smf.Logit(y_train, X_train) #results=logit_model.fit() #print(results.summary2()) model= smf.logit(formula="Attrition~ Age + DailyRate + DistanceFromHome + EnvironmentSatisfaction + JobInvolvement + JobSatisfaction + NumCompaniesWorked + RelationshipSatisfaction + TotalWorkingYears + TrainingTimesLastYear + WorkLifeBalance + YearsAtCompany + MaritalStatus_Divorced + MaritalStatus_Married + MaritalStatus_Single + OverTime_No + OverTime_Yes", data= df_full_data).fit() model.summary() # GETTING THE ODDS RATIOS, Z-VALUE, AND 95% CI model_odds = pd.DataFrame(np.exp(model.params), columns= ['OR']) model_odds['z-value']= model.pvalues model_odds[['2.5%', '97.5%']] = np.exp(model.conf_int()) model_odds """# Model 6: Neural Network""" # Random seeds np.random.seed(123) rn.seed(123) tf.set_random_seed(123) # Convert Attrition to one-hot encoding for NN to be able to read y_train = to_categorical(y_train) y_test = to_categorical(y_test) # Neural Network Architecture
