src/preprocess/transform.py

import pandas as pd
import src.preprocess.extract as ex


def get_product_list(start_date=None):
    """
    Get unique product list from demand data
    
    Args:
        start_date: start date to filter data. Required.
    """
    demand = ex.read_orders_data(start_date=start_date)
    print(demand["Material Number"].unique())
    return demand["Material Number"].unique()


def get_employee_list():
    employee = ex.read_employee_data()
    employee = employee["Description"]

    return employee["Employee_Type"].unique()


def get_released_product_list(start_date=None):
    """
    get released product list from COOIS_Released_Prod_Orders.csv
    
    Args:
        start_date: start date to filter data. Required.
    """
    released_orders = ex.read_orders_data(
        start_date=start_date, 
    )
    product_list = released_orders["Material Number"].unique().tolist()
    print(f"Released products for date range {start_date}: {len(product_list)} products")
    return product_list


def get_available_dates():
    """
    get available all dates from COOIS_Released_Prod_Orders.csv
    
    Returns:
        tuple: (start_dates, end_dates) - unique start dates and end dates list
    """
    released_orders = ex.read_orders_data()
    
    released_orders["Basic start date"] = pd.to_datetime(released_orders["Basic start date"])
    released_orders["Basic finish date"] = pd.to_datetime(released_orders["Basic finish date"])
    
    start_dates = sorted(released_orders["Basic start date"].dt.date.unique())
    end_dates = sorted(released_orders["Basic finish date"].dt.date.unique())
    
    all_dates = sorted(set(start_dates + end_dates))
    
    return all_dates, start_dates, end_dates


def get_date_ranges():
    """
    get available (start_date, end_date) combinations
    Returns:
        list : available (start_date, end_date) combinations
    """
    released_orders = ex.read_orders_data()
    
    released_orders["Basic start date"] = pd.to_datetime(released_orders["Basic start date"])
    released_orders["Basic finish date"] = pd.to_datetime(released_orders["Basic finish date"])
    
    date_ranges = released_orders[["Basic start date", "Basic finish date"]].drop_duplicates()
    date_ranges["start_date"] = date_ranges["Basic start date"].dt.date
    date_ranges["end_date"] = date_ranges["Basic finish date"].dt.date
    
    ranges = [(row["start_date"], row["end_date"]) for _, row in date_ranges.iterrows()]
    ranges = sorted(set(ranges))
    
    return ranges