finalize etl / optimization configuration

src/config/optimization_config.py

@@ -23,13 +23,14 @@ 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)
+print("product list",PRODUCT_LIST)
 
 
 def get_employee_type_list():
     try:
-        streamlit_employee_type_list = dashboard.employee_type_list
-        return streamlit_employee_type_list
+        pass
+        # 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()
@@ -37,7 +38,7 @@ def get_employee_type_list():
         return emp_type_list
 
 EMPLOYEE_TYPE_LIST = get_employee_type_list()
-print(EMPLOYEE_TYPE_LIST)
+print("employee type list",EMPLOYEE_TYPE_LIST)
 
 def get_shift_list():
     try:
@@ -86,7 +87,6 @@ def get_demand_dictionary():
     except Exception as e:
         print(f"using default value for demand dictionary")
         demand_df = extract.read_demand_data()
-        print(demand_df)
         demand_dictionary = demand_df.groupby('Material Number')["Order quantity (GMEIN)"].sum().to_dict()
         return demand_dictionary
 
@@ -114,38 +114,67 @@ print(COST_LIST_PER_EMP_SHIFT)
 #     "Humanizer": {1: 10, 2: 10, 3: 10},
 # }
 
-def get_productivity_list_per_emp_product():
+
+
+def get_productivity(PRODUCT_LIST):
     try:
-        streamlit_productivity_list_per_emp_product = dashboard.productivity_list_per_emp_product
-        return streamlit_productivity_list_per_emp_product
+        streamlit_productivity = dashboard.productivity
+        return streamlit_productivity
     except Exception as e:
-        print(f"using default value for productivity list per emp product")
-        emp_product_df = extract.read_employee_productivity_data()
-        print(emp_product_df)
-        productivity_list_per_emp_product = emp_product_df.groupby("employment_type_id")["productivity"].sum().to_dict()
+        productivity_df = extract.read_productivity_data()
+        
+        productivity_df = productivity_df[["Kit","Humanizer hours","UNICEF hours"]]
+        
+        productivity_dict = {
+            "UNICEF Fixed term": {},
+            "Humanizer": {}
+        }
+        
+        # shift별 딕셔너리 초기화
+        for shift in [1, 2, 3]:
+            productivity_dict["UNICEF Fixed term"][shift] = {}
+            productivity_dict["Humanizer"][shift] = {}
+        
+        # 제품별 데이터 처리
+        for product in PRODUCT_LIST:
+            print(product)
+            productivity_df_product = productivity_df[productivity_df['Kit'] == product]
+            
+            if not productivity_df_product.empty:
+                # 올바른 컬럼명 사용
+                humanizer_productivity = productivity_df_product["Humanizer hours"].iloc[0]
+                unicef_productivity = productivity_df_product["UNICEF hours"].iloc[0]
+                
+                for shift in [1, 2, 3]:
+                    productivity_dict["UNICEF Fixed term"][shift][product] = float(unicef_productivity) if unicef_productivity else 0
+                    productivity_dict["Humanizer"][shift][product] = float(humanizer_productivity) if humanizer_productivity else 0
+        
+        return productivity_dict
+
+
         print(productivity_list_per_emp_product)
-        return 
-    
+        return productivity_list_per_emp_product
 
-PRODUCTIVITY_LIST_PER_EMP_PRODUCT = get_productivity_list_per_emp_product()
+PRODUCTIVITY_LIST_PER_EMP_PRODUCT = get_productivity(PRODUCT_LIST)
 print(PRODUCTIVITY_LIST_PER_EMP_PRODUCT)
 
-PRODUCTIVITY_LIST_PER_EMP_PRODUCT = {  # Kits_Calculation
-    "Fixed": {
-        1: {"a": 1000, "b": 1000, "c": 1000},
-        2: {"a": 1000, "b": 1000, "c": 1000},
-        3: {"a": 1000, "b": 1000, "c": 1000},
-    },
-    "Humanizer": {
-        1: {"a": 10, "b": 6, "c": 5},
-        2: {"a": 1000, "b": 1000, "c": 1000},
-        3: {"a": 1000, "b": 1000, "c": 1000},
-    },
-}  # Kits_Calculation.csv
+
+# PRODUCTIVITY_LIST_PER_EMP_PRODUCT = {  # Kits_Calculation
+#     "UNICEF Fixed term": {
+#         1: {"product name": 1000, "b": 1000, "c": 1000},
+#         2: {"a": 1000, "b": 1000, "c": 1000},
+#         3: {"a": 1000, "b": 1000, "c": 1000},
+#     },
+#     "Humanizer": {
+#         1: {"a": 10, "b": 6, "c": 5},
+#         2: {"a": 1000, "b": 1000, "c": 1000},
+#         3: {"a": 1000, "b": 1000, "c": 1000},
+#     },
+# }  # Kits_Calculation.csv
 
 
 MAX_EMPLOYEE_PER_TYPE_ON_DAY = {  # Not available information
-    "Fixed": {
+    "UNICEF Fixed term": {
         t: 8 for t in DATE_SPAN
     },  # EDIT: e.g., {'x': {1:5,2:5,...}, 'y':{1:6,...}}
     "Humanizer": {t: 6 for t in DATE_SPAN},
@@ -153,12 +182,12 @@ MAX_EMPLOYEE_PER_TYPE_ON_DAY = {  # Not available information
 # available employee but for fixed in shift 1, it is mandatory employment
 
 MAX_HOUR_PER_PERSON_PER_DAY = 14  # legal standard
-MAX_HOUR_PER_SHIFT_PER_PERSON = {1: 3, 2: 4, 3: 6}  # work_shifts_timing.csv
+MAX_HOUR_PER_SHIFT_PER_PERSON = {1: 7, 2: 7, 3: 3}  # work_shifts_timing.csv #Need to be fixed
 CAP_PER_LINE_PER_HOUR = {
     "long": 2200,
     "short": 1600,
 }
 # number of products that can be produced per hour per line
-
+#This information is critical and it should not rely on the productivity information
 
 DAILY_WEEKLY_SCHEDULE = "daily"  # daily or weekly ,this needs to be implementedin  in         if F_x1_day is not None... F_x1_week is not None... also need to change x1 to Fixedstaff_first_shift

src/etl/extract.py

@@ -35,7 +35,7 @@ def read_shift_cost_data(
     return pd.read_csv(path)
 
 
-def read_kit_data(
+def read_productivity_data(
     path="data/real_data_excel/converted_csv/Kits__Calculation.csv",
 ) -> pd.DataFrame:
     return pd.read_csv(path)