src/utils/helper_functions.py

import pickle
import os
import numpy as np
from datetime import datetime
import pandas as pd

def save_models(models, model_type, directory):

    print('Saving models...')

    for i, model in enumerate(models):

        with open(f'{directory}/{model_type}_FOLD_{i+1}.pkl', 'wb') as file:  
            pickle.dump(model, file)


def load_models(directory):
        
    print('Loading models...')

    models = []
    # List all files in the directory
    files = os.listdir(directory)

    pkl_files = [file for file in files if file.endswith('.pkl')]

    for file in pkl_files:
        with open(os.path.join(directory, file), 'rb') as file:  
            model = pickle.load(file)
        models.append(model)
    
    return models

def get_predictions(models, X_test):

    print('Forecasting test data...')

    preds = []
    for model in models:
        preds.append(post_process(model.predict(X_test)))

    return np.mean(preds, axis=0)

def post_process(predictions):
    
    predictions = predictions.clip(0)
    
    return predictions

def save_results(dataframe, file_name):

    print('Saving results...')

    today_date = datetime.now().strftime("%Y-%m-%d")

    dataframe.to_excel(f'demand_predictions/{file_name}_{today_date}.xlsx', index=False)

def save_parquet(dataframe, path):
    dataframe.to_parquet(path, index=False)

def load_parquet(path):
    return pd.read_parquet(path)