def main():
segmentation = Segmentation()
segmentation.check_data()
print("\n\n Start Segmenting Users Based on RFM Methods ... ")
segmentation.get_rfm_metric()
segmentation.get_rfm_index()
segmentation.transaction.apply(segmentation.define_rfm_segment, axis=1)
segmentation.save_rfm_segment_pie_chart()
segmentation.save_rfm_segment_scatter_plot()
#label the segment generated by RFM methods
segmentation.transaction['high_growth'] = segmentation.transaction.apply(segmentation.Label_Segments, axis=1)
user_label = segmentation.transaction[['user', 'high_growth']]
segmentation.save_user_group_bar_chart()
print("\n\n Finished Segmenting Users Based on RFM Methods ... ")
#---- Now start creating features for prediction -----
print("\n\n Start Feature Generation for Classification ... ")
final_dataset = segmentation.create_features()
final_dataset = final_dataset.merge(user_label)
print("\n\n Finished Feature Generation ... ")
classification = Classification()
X = final_dataset.drop(columns=['user', 'high_growth'])
y = final_dataset['high_growth']
#initial prediction of high growth merchant. in full feature set
print("\n\nLogistic Regression before feature selection")
classification.run_logistic_regression(X, y)
#Feature selection using correlation heatmap
classification.correlation_heatmap(final_dataset)
selected_feature = final_dataset.drop(
columns=['monetary', 'fall_count', 'spring_count', 'summer_count', 'winter_count', 'spring_amt', 'summer_amt',
'winter_amt', 'fall_amt'])
classification.correlation_heatmap(selected_feature)
# New prediction on selected features
X = selected_feature.drop(columns=['user', 'high_growth'])
y = selected_feature['high_growth']
print("\n\nLogistic Regression after feature selection")
classification.run_logistic_regression(X, y)
#Now run logistic regression on using cross val with k=10
print("\n\nLogistic Regression using Cross Validation")
classification.run_logistic_cross_val(X, y)
print("\n\nLogistic Regression with SMOTE Resampling")
classification.run_logistic_regression_with_resampling(X,y)
print("\n\nRun Decision Tree")
classification.run_decision_tree(X, y)
print("\n\nRun Random Forest")
y_pred_rf = classification.run_random_forest(X, y)
print("\n\nRun Support Vector Machine")
classification.run_svm(X, y)
#finally print list of High Growth Merchant
final_dataset['predicted'] = y_pred_rf
high_growth_merchant = final_dataset[['user', 'monetary']].loc[final_dataset['predicted'] == True]
high_growth_merchant[['user', 'monetary']].sort_values('monetary', ascending=False).to_csv(
'high_growth_merchant.csv', index=False)
print(
"HIGH GROWTH MERCHANT as Given by RANDOM FOREST: \n", high_growth_merchant[['user', 'monetary']].sort_values('monetary', ascending=False))