Updated filters

app.py

@@ -44,8 +44,8 @@ def mongo_unavs_call(user_input_start_date, user_input_end_date, user_input_past
         {
             "$match": {
                 "results.generation_unavailabilities.production_type": "NUCLEAR",
-                "results.generation_unavailabilities.start_date": {"$lte": end_date},
-                "results.generation_unavailabilities.end_date": {"$gte": start_date},
+                # "results.generation_unavailabilities.start_date": {"$lte": end_date},
+                # "results.generation_unavailabilities.end_date": {"$gte": start_date},
                 "results.generation_unavailabilities.updated_date": {"$lte": end_date}
             }
         },
@@ -162,7 +162,9 @@ def nuc_monitor(usr_start_date, usr_end_date, past_date, mongo_db_data):
     past_date_str = str(past_date)
     current_datetime_str = current_datetime.strftime("%Y-%m-%d")
 
-    nuclear_unav = mongo_unavs.copy()[(mongo_unavs.copy()["production_type"] == "NUCLEAR") & (mongo_unavs.copy()["updated_date"] <= past_date_str)]
+    # nuclear_unav = mongo_unavs.copy()[(mongo_unavs.copy()["production_type"] == "NUCLEAR") & (mongo_unavs.copy()["updated_date"] <= past_date_str)]
+    nuclear_unav = mongo_unavs.copy()[(mongo_unavs.copy()["production_type"] == "NUCLEAR") & (mongo_unavs.copy()["updated_date"] <= past_date_str)
+                                      & (mongo_unavs.copy()["status"] != "DISMISSED")]
 
     # if photo_date == True:
     #     nuclear_unav = merged_df.copy()[(merged_df.copy()["production_type"] == "NUCLEAR") & (merged_df.copy()["updated_date"] <= past_date_str)]
@@ -182,19 +184,37 @@ def nuc_monitor(usr_start_date, usr_end_date, past_date, mongo_db_data):
 
     # Filter to get identifiers
     filtered_id_df = sorted_df.copy()
+# --------------------------- !!!!!!!!!!!!!!!!!!!!!!! HERE IS POTENTIAL ERROR!!!!!!!!!!!!!!!!!!!!!!! --------------------------- #
+# I commented this out
     filtered_id_df.drop_duplicates(subset='identifier', keep='last', inplace=True)
+# --------------------------- !!!!!!!!!!!!!!!!!!!!!!! HERE IS POTENTIAL ERROR!!!!!!!!!!!!!!!!!!!!!!! --------------------------- #
+
     filtered_id_df = filtered_id_df.copy().reset_index(drop=True)
 
     # This filter should take all the dates with unavs that include days with unavs in the range of the start and end date
 
-    filtered_df = filtered_id_df.copy()[(filtered_id_df.copy()['start_date'] <= end_date_str) & (filtered_id_df.copy()['end_date'] >= start_date_str)]
-    # Create a boolean mask to identify rows where status is "Dismissed"
-    mask = filtered_df["status"] == "DISMISSED"
-    print(filtered_df["status"])
-    print(filtered_df[mask])
+# --------------------------- !!!!!!!!!!!!!!!!!!!!!!! HERE IS POTENTIAL ERROR!!!!!!!!!!!!!!!!!!!!!!! --------------------------- #
+
+    # This filter might take out the most recent identifiers (Message ID) that change the dates of unavailability of a plant. 
+    # This means that the actual unavailability is something else
+    # filtered_df = filtered_id_df.copy()[(filtered_id_df.copy()['start_date'] <= end_date_str) & (filtered_id_df.copy()['end_date'] >= start_date_str)]
+    filtered_df = filtered_id_df.copy()
+    # 2022-11 a 2023-03
+    print("filtered_df\n", filtered_df)
+    filtered_df_chooz = filtered_df[filtered_df["name"] == "CHOOZ 2"]
+
+    print(filtered_df_chooz[["name", "message_id", "creation_date", "updated_date", "status", "available_capacity"]])
+
+# --------------------------- !!!!!!!!!!!!!!!!!!!!!!! HERE IS POTENTIAL ERROR!!!!!!!!!!!!!!!!!!!!!!! --------------------------- #
+
+#     # Create a boolean mask to identify rows where status is "Dismissed"
+    # mask_dismissed = filtered_df["status"] == "DISMISSED"
+
+    # print(filtered_df["status"])
+    # print(filtered_df[mask])
 
     # Update available_capacity where the condition is True
-    filtered_df.loc[mask, "available_capacity"] = filtered_df.loc[mask, "installed_capacity"]
+    # filtered_df.loc[mask_dismissed, "available_capacity"] = filtered_df.loc[mask_dismissed, "installed_capacity"]
 
     # Standardize datetime in dataframe
     filtered_df2 = filtered_df.copy() # This code will just standardize datetime stuff
@@ -280,16 +300,19 @@ def nuc_monitor(usr_start_date, usr_end_date, past_date, mongo_db_data):
     while date_plus_one < end_date:
         date_plus_one = date_plus_one + datetime.timedelta(days=1)
         dates_of_interest.append(date_plus_one) 
-        
+    
     # This is to standardize the datetimes. Without this, the datetime calculations for each power plant will not work
+    # This is just getting the plant metadata and giving it updated_date????? With an amount of items based on the length of the
+    # date range????
     results_plants = {plant_name: {date: {"available_capacity": power, "updated_date": pd.to_datetime("1970-01-01", utc=True)} for date in dates_of_interest}
                     for plant_name, power in plants_metadata.items()}
 
 
     for plant, unavailabilities in results_sorted.items():
-
+        # Get the full power of a given plant according to the sorted results
         original_power = plants_metadata[plant]
         # Get all the unavailabilities scheduled for the plant.
+        # This is actually apparently just getting the metadata though???
         results_current_plant = results_plants[plant] 
         
         for unavailability in unavailabilities: