Step_Data_Project_India/main.py

import json
import os

import numpy as np
import pandas as pd
import sklearn

from pipeline import (
    load_dataset,
    filter_data,
    filter_test_data,
    prepare_user_data,
    train_models,
    evaluate_models,
    display_warning_about_2020_data,
    display_warnings_for_scenarios, prepare_data_for_model
)

year_str = 'Year'
month_str = 'Month'
user_str = 'user'
split_str = 'split type'
threshold_str = 'threshold used'
timespan_str = 'time used'
sequence_length_str = 'sequence length'
precision_str = 'precision'
recall_str = 'recall'
f1_string = 'f1 score'
weak_column_names = ['DayOfWeek_'+day for day in
                     ['Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday' ]]

# === Configurable Parameters ===
dataset_path = './Datasets/'
DATA_PATH = dataset_path +'ALLUSERS32_15MIN_WITHOUTTHREHOLD.xlsx'
OUTPUT_EXCEL_PATH = './working/evaluation_results.xlsx'
result_filename = './working/evaluation_results.json'
SEQUENCE_LENGTHS = [20, 15, 10, 5, 1]  # You can add more: [20, 25, 30]

TRAINING_SCENARIO = [(2018, list(range(1, 13))), (2019, list(range(1, 10)))]
VALIDATION_SCENARIO = [(2019, [10, 11, 12])]
TEST_SCENARIO = [(2020, [1, 2])]  # Jan–Feb 2020 only

# === Optional display only ===
predefined_training_scenarios = {
    "Scenario 1": {"years_months": [(2018, list(range(1, 13))), (2019, list(range(1, 10)))]},
    "Scenario 2": {"years_months": [(2017, list(range(1, 13))), (2018, list(range(1, 13))), (2019, list(range(1, 10)))]}
}
predefined_validation_scenarios = {
    "Scenario A": {"years_months": [(2019, [10, 11, 12])]}
}

def remove_covid_data(df):
    df = df[~((df[year_str]==2020) & (df[month_str]>2))]
    return df

def split_data_by_month_percentage(df, percentages):
    train_p, valid_p, test_p = percentages
    ids = df[[year_str, month_str]].drop_duplicates().sort_values([year_str, month_str])
    tr, va, te = np.split(ids, [int((train_p/100) * len(ids)), int(((train_p + valid_p)/100) * len(ids))])
    return df.merge(tr, on=[year_str, month_str], how='inner'), df.merge(va, on=[year_str, month_str], how='inner'), df.merge(te, on=[year_str, month_str], how='inner')

def split_data_by_userdata_percentage(df, percentages):
    train_p, valid_p, test_p = percentages
    tr, va, te = pd.DataFrame(), pd.DataFrame(), pd.DataFrame()
    for user_id in df[user_str].unique():
        user_data = df[df[user_str]==user_id].sort_values([year_str, month_str])
        u_tr, u_va, u_te = np.split(user_data, [int((train_p/100)*len(user_data)), int(((train_p+valid_p)/100)*len(user_data))])
        tr = pd.concat([tr, u_tr], ignore_index=True)
        va = pd.concat([va, u_va], ignore_index=True)
        te = pd.concat([te, u_te], ignore_index=True)
    return tr, va, te


def main():
    # print("=== Training Scenario Setup ===")
    # display_warning_about_2020_data()
    # display_warnings_for_scenarios("training", predefined_training_scenarios, predefined_validation_scenarios)

    # print("\n=== Validation Scenario Setup ===")
    # display_warning_about_2020_data()
    # display_warnings_for_scenarios("validation", predefined_training_scenarios, predefined_validation_scenarios)

    # === Load and preprocess ===
    df = load_dataset(DATA_PATH)

    ALLUSERS32_15MIN_WITHOUTTHREHOLD = False
    if('ALLUSERS32_15MIN_WITHOUTTHREHOLD.xlsx' in DATA_PATH):
        ALLUSERS32_15MIN_WITHOUTTHREHOLD = True

    training_data = filter_data(df, TRAINING_SCENARIO, ALLUSERS32_15MIN_WITHOUTTHREHOLD)
    validation_data = filter_data(df, VALIDATION_SCENARIO, ALLUSERS32_15MIN_WITHOUTTHREHOLD)

    user_data_train = prepare_user_data(training_data)
    user_data_val = prepare_user_data(validation_data)

    # === Train models ===
    best_models = train_models(user_data_train, user_data_val, sequence_lengths=SEQUENCE_LENGTHS)

    # === Load and evaluate test ===
    test_df = filter_test_data(df, TEST_SCENARIO)
    evaluate_models(best_models, test_df, SEQUENCE_LENGTHS, OUTPUT_EXCEL_PATH, ALLUSERS32_15MIN_WITHOUTTHREHOLD)

    print(f"\n✅ All evaluations completed. Results saved to: {OUTPUT_EXCEL_PATH}")


def reduce_columns(df, filename):
    if '15MIN' in filename:
        return df.drop(columns=['Month', 'Year', 'date']+weak_column_names)
    else:
        return df.drop(columns=['Month', 'Year', 'date'])

def main_two():
    results = pd.DataFrame()
    if os.path.exists(result_filename):
        results = pd.DataFrame(json.load(open(result_filename)))
    for sequence_length in SEQUENCE_LENGTHS:
        for data_filename in os.listdir(dataset_path):
            for split_id, split_method in [('data percentages', split_data_by_userdata_percentage),('month percentages', split_data_by_month_percentage)]:
                timespan_id = '1HR'
                threshold_id = 'WITH'
                if '15MIN' in data_filename:
                    timespan_id = '15MIN'
                if 'WITHOUT' in data_filename:
                    threshold_id = 'WITHOUT'
                if len(results) > 0:
                    if len(results[(results[split_str]==split_id) &
                                   (results[timespan_str]==timespan_id) &
                                   (results[threshold_str]==threshold_id) &
                                   (results[sequence_length_str]==sequence_length)]) > 0:
                        continue

                file_path = os.path.join(dataset_path, data_filename)
                df = load_dataset(file_path)
                df = remove_covid_data(df)
                tr,val,te = split_method(df, percentages=(80,10,10))
                tr = reduce_columns(tr, data_filename)
                val = reduce_columns(val, data_filename)
                te = reduce_columns(te, data_filename)

                user_data_train = prepare_user_data(tr)
                user_data_val = prepare_user_data(val)

                best_models = train_models(user_data_train, user_data_val, sequence_lengths=[sequence_length])

                results = pd.concat([results,
                                     evaluate_model_on_test_data(model=best_models[sequence_length]['model'], test_df=te, split_id=split_id,
                                     sequence_length=sequence_length, time_span_id=timespan_id, threshold_id=threshold_id)], ignore_index=True)
                results.to_json(result_filename)


# === Evaluation ===
def evaluate_model_on_test_data(model, test_df,sequence_length, split_id, threshold_id, time_span_id):
    user_data = prepare_user_data(test_df)
    x, y = prepare_data_for_model(user_data=user_data, sequence_length=sequence_length)

    y_pred = model.predict(x, verbose=0)
    y_pred_classes = np.argmax(y_pred, axis=1)

    recall = sklearn.metrics.recall_score(y, y_pred_classes, average='weighted')
    precision = sklearn.metrics.precision_score(y, y_pred_classes, average='weighted')
    f1_score = sklearn.metrics.f1_score(y, y_pred_classes, average='weighted')
    return pd.DataFrame({split_str:[split_id], threshold_str:[threshold_id], timespan_str:[time_span_id],
                         sequence_length_str:[sequence_length], recall_str:[recall],
                         precision_str:[precision], f1_string:[f1_score]})


if __name__ == "__main__":
    main_two()
    print('Done')