pipeline.py

from src.data.load_data import get_data, generate_test_data
from src.features.build_features import prepare_data
from src.data.preprocess import get_Xy
from src.utils.helper_functions import load_models, get_predictions, load_parquet
from config import Config
import numpy as np


import pandas as pd

config = vars(Config)

def run(forecast_start_date, forecast_end_date):

    print('Script Executing...')


    generated_test = generate_test_data(forecast_start_date, 
                                        forecast_end_date, 
                                        product_ids=load_parquet(f'{config["fold_input_directory"]}/unique_products.parquet').values)
    
    generated_test['date'] = pd.to_datetime(generated_test['date'])

    # merge the fixed columns
    generated_test = pd.merge(load_parquet(f'{config["fold_input_directory"]}/fixed_columns.parquet'), 
                              generated_test, on=['product_id'], how='right')
    
    dataframe = prepare_data(
        dataframe=pd.concat([generated_test], axis=0),
        data=None,
        split_local_test=config['split_local_test'],
        add_datetime_features=True,
        add_lag_features=True
    )

    dataframe[config['target']] = np.nan

    X, X_test, y = get_Xy(
        dataframe=dataframe,
        not_include=config['not_include_features'],
        cat_features=config['cat_features'],
        cat_encoding='category'
    )

    models = load_models(config['fold_models_directory'])

    y_test_preds = get_predictions(models, X_test)

    generated_test[config['target']] = y_test_preds

    print('Script Done!')

    return generated_test

# if __name__ == '__main__':
    # run()