main.py

#main.py
from regularization_methods import regularized_rfr_CV_features_removed
from datetime import datetime
from ensemble_learning_techniques import residual_ensemble_rfr
from csv_loading import load_data, data_inspection
from visualization import visualization
from shapley import shapley

#entry point for program to run
def main():
    #start time
    start_time = datetime.now()
    print("Program started at:", start_time)

    filepath = "data\Data-Table_1.csv"
    print("***** Welcome to the Urban Air Quality and Health Risk Prediction Program *****")
    #popup()
    print("###Loading Data###")
    df = load_data(filepath)
    #check out and fix data
    print("###Data Inspection###")
    dataframe = data_inspection(df)
    print()
    #print("***###*** Restarting program, using new datafame with less features ***###***")
    print("### Removing Low Importance Features ###")
    new_filepath, new_dataframe = regularized_rfr_CV_features_removed(dataframe)
    # df = load_data(new_filepath)
    # new_dataframe = data_inspection(df)
    print("***** Starting ensemble methods *****")
    print("###Residual Ensemble Random Forest###")
    residual_ensemble_rfr(new_dataframe)
    #print("***###*** Running RFR models again after removing lower importance features ***###***")
    print("")
    print("Starting visualization attempts")
    visualization(new_dataframe)
    #print("***** Welcome to the Urban Air Quality and Health Risk Prediction Program *****")
    #new_dataframe = whole_main(new_filepath, stuff)
    print()
    print("Mahalo Nui Loa for using the Urban Air Quality and Health Risk Prediction Program")
    print()
    print("Program Pau :)")

    #combining csv data so it’s easier to compare R2 and MAE
    #folder_path = "data"
    #combined_df = combine_csvs_to_dataframe(folder_path)
    #print(combined_df.head())
    #print(combined_df.tail())
    #combined_df.to_csv(f"_ALL_csv_data_combined.csv", index=False)

    best_model = residual_ensemble_rfr(new_dataframe)
    shapley(best_model, new_dataframe)
    print("Done with shapley")
    print()

    #end time
    end_time = datetime.now()
    print()
    print()
    print("Program finished at:", end_time)

    #print elapsed time
    elapsed = end_time - start_time
    print("Elapsed time:", elapsed)


if __name__ == "__main__":
    main()