Change fixed values into variables from the UI or the database

src/config/optimization_config.py

@@ -1,15 +1,57 @@
 import pandas as pd
-import etl.transform as transformed_data
+import src.etl.transform as transformed_data
+import streamlit_page.page1 as dashboard
+import datetime
+from datetime import timedelta
+import src.etl.extract as extract
 
 
-DATE_SPAN = list(range(1, 8))  # Default 7 days - other than this - user input
-PRODUCT_LIST = ["a", "b", "c"]  # COOIS_Planned_and_Released.csv
-PRODUCT_LIST = transformed_data.get_product_list()
-EMPLOYEE_TYPE_LIST = ["Fixed", "Humanizer"]  # WH_Workforce_Hourly_payment_scale.csv -> This is default setting. User should be able to manipulate
-EMPLOYEE_TYPE_LIST = transformed_data.get_employee_type_list()
+def get_date_span():
+    try: 
+        start_date = dashboard.start_date
+        end_date = dashboard.end_date
+        date_span = list(range(1, (end_date - start_date).days + 1))
+        print(f"date from user input")
+        return date_span, start_date, end_date
+    except Exception as e:
+        print(f"using default value for date span")
+        return list(range(1, 5)), datetime(2025, 3, 24), datetime(2025, 3, 28)  # Default 7 days
+
+
+#fetch date from streamlit or default value. The streamlit and default references the demand data (COOIS_Planned_and_Released.csv)
+DATE_SPAN, start_date, end_date = get_date_span() 
+
+# COOIS_Released_Prod_Orders.csv
+PRODUCT_LIST = transformed_data.get_released_product_list(start_date, end_date)
+print(PRODUCT_LIST)
+
+
+def get_employee_type_list():
+    try:
+        streamlit_employee_type_list = dashboard.employee_type_list
+        return streamlit_employee_type_list
+    except Exception as e:
+        print(f"using default value for employee type list")
+        employee_type_list = extract.read_employee_data()
+        emp_type_list = employee_type_list["employment_type"].unique()
+        return emp_type_list
+
+EMPLOYEE_TYPE_LIST = get_employee_type_list()
+print(EMPLOYEE_TYPE_LIST)
+
+def get_shift_list():
+    try:
+        streamlit_shift_list = dashboard.shift_list
+        return streamlit_shift_list
+    except Exception as e:
+        print(f"using default value for shift list")
+        shift_list = extract.read_shift_data()
+        shift_list = shift_list["shift"].unique()
+        return shift_list
+SHIFT_LIST = get_shift_list()
+print(SHIFT_LIST)
+
 
-# WH_Workforce_Hourly_payment_scale.csv -> This is default setting. User should be able to manipulate
-SHIFT_LIST = [1, 2, 3]  # WH_Workforce_Hourly_Pay_Scale.csv -> This is default setting. User should be able to manipulate
 LINE_LIST = ["long", "short"]  # WH_Workforce_Hourly_Pay_Scale.csv -> This is default setting. User should be able to manipulate
 
 LINE_LIST_PER_TYPE = {

src/etl/extract.py

@@ -24,7 +24,7 @@ def read_demand_data(
 
 
 def read_employee_data(
-    path="data/real_data_excel/converted_csv/WH_Workforce_Hourly_Pay_Scale.csv",
+    path="data/real_data_excel/converted_csv/WH_Workforce_Hourly_Pay_Scale_processed.csv",
 ) -> pd.DataFrame:
     return pd.read_csv(path)
 
@@ -53,6 +53,39 @@ def read_material_master(
     return pd.read_csv(path)
 
 
+def read_released_orders_data(
+    path="data/real_data_excel/converted_csv/COOIS_Released_Prod_Orders.csv",
+    start_date=None,
+    end_date=None,
+) -> pd.DataFrame:
+    """
+    COOIS_Released_Prod_Orders.csv 
+    
+    Args:
+        path: path to the csv file
+        start_date: start date (pd.Timestamp or datetime)
+        end_date: end date (pd.Timestamp or datetime)
+
+    Returns:
+        pd.DataFrame: filtered dataframe by date
+    """
+    df = pd.read_csv(path)
+    assert len(df) > 0, "No data found in the file"
+    # convert date column to datetime
+    df["Basic start date"] = pd.to_datetime(df["Basic start date"])
+    df["Basic finish date"] = pd.to_datetime(df["Basic finish date"])
+    
+    
+    # filter by date
+    if start_date is not None and end_date is not None:
+        # filter by date
+        df = df[
+            (df["Basic start date"] == pd.to_datetime(start_date)) & (df["Basic finish date"] == pd.to_datetime(end_date))
+        ]
+    
+    return df
+
+
 if __name__ == "__main__":
     demand_data = read_demand_data()
     print(demand_data.head())

src/etl/transform.py

@@ -1,5 +1,5 @@
 import pandas as pd
-import extract as ex
+import src.etl.extract as ex
 
 
 def get_product_list():
@@ -15,6 +15,65 @@ def get_employee_list():
     return employee["Employee_Type"].unique()
 
 
-if __name__ == "__main__":
-    get_product_list()
-    # get_employee_list()
+def get_released_product_list(start_date=None, end_date=None):
+    
+    released_orders = ex.read_released_orders_data(
+        start_date=start_date, 
+        end_date=end_date
+    )
+    
+    
+    product_list = released_orders["Material Number"].unique().tolist()
+    print(f"Released products for date range {start_date} to {end_date}: {len(product_list)} products")
+    return product_list
+
+
+def get_available_dates():
+    """
+    COOIS_Released_Prod_Orders.csv에서 사용 가능한 모든 날짜를 가져옵니다.
+    
+    Returns:
+        tuple: (start_dates, end_dates) - 고유한 시작 날짜와 종료 날짜 리스트
+    """
+    # 모든 데이터를 가져옴 (날짜 필터링 없이)
+    released_orders = ex.read_released_orders_data()
+    
+    # 날짜 컬럼을 datetime으로 변환 (이미 extract.py에서 변환되지만 확실히 하기 위해)
+    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"])
+    
+    # 고유한 시작 날짜와 종료 날짜 추출
+    start_dates = sorted(released_orders["Basic start date"].dt.date.unique())
+    end_dates = sorted(released_orders["Basic finish date"].dt.date.unique())
+    
+    # 모든 고유한 날짜들 (시작날짜 + 종료날짜)
+    all_dates = sorted(set(start_dates + end_dates))
+    
+    return all_dates, start_dates, end_dates
+
+
+def get_date_ranges():
+    """
+    COOIS_Released_Prod_Orders.csv에서 날짜 범위 조합을 가져옵니다.
+    
+    Returns:
+        list: 사용 가능한 (start_date, end_date) 조합 리스트
+    """
+    released_orders = ex.read_released_orders_data()
+    
+    # 날짜 컬럼을 datetime으로 변환
+    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"])
+    
+    # 고유한 날짜 범위 조합 추출
+    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
+    
+    # (start_date, end_date) 튜플 리스트로 반환
+    ranges = [(row["start_date"], row["end_date"]) for _, row in date_ranges.iterrows()]
+    ranges = sorted(set(ranges))  # 중복 제거 및 정렬
+    
+    return ranges
+
+