change none value in data to be np.null

Dictionary_guesser/name_nation_guesser.py

@@ -114,7 +114,7 @@ class NameNationGuesser:
         dtype = self.names_data_dtype
         jsonApi = os.getenv('jsonApi')
         bucket_name = os.getenv('name')
-        file_name = os.getenv('f_name=')
+        file_name = os.getenv('f_name')
 
         service_account_info = json.loads(jsonApi)
         client = storage.Client.from_service_account_info(service_account_info)

get_region.py

@@ -11,8 +11,8 @@ from utils import data_utils
 
 
 class RegionPredictor:
-    def __init__(self, models_directory,names_filename="Dictionary_guesser/names.csv",places_filename='Dictionary_guesser/places.tab'):
-        self.guesser =NameNationGuesser(names_filename=names_filename,places_filename=places_filename, guess_first_second_min_mag=None,place_column_name="sub-region")
+    def __init__(self, models_directory,places_filename='Dictionary_guesser/places.tab'):
+        self.guesser =NameNationGuesser(places_filename=places_filename, guess_first_second_min_mag=None,place_column_name="sub-region")
         self.models_directory = models_directory
      
     @classmethod    
@@ -61,7 +61,6 @@ class RegionPredictor:
     def guess_zone(self,name, epoch, offset):
         dt = datetime.datetime.fromtimestamp(epoch)
         country_pop_map = self.guesser.country_pop_from_datetime(dt, offset)
-        # print(country_pop_map)
         return self.guesser.guess_zone(name, country_pop_map=country_pop_map)
     
     def get_Dictionary_Based_Region(self,df):
@@ -84,17 +83,19 @@ class RegionPredictor:
             name = data_utils.text_to_romanize(name)
             name = data_utils.remove_spaces_from_ends(name)
             return name
-        # Apply the transformation function to the entire DataFrame
+
         dataset['Author'] = dataset['Author'].apply(transform_string)
-        # dataset.to_csv("check.csv")
         dataset["Author_Timezone"]= dataset["Author_Timezone"] /60
+        
         dataset=self.get_Dictionary_Based_Region(dataset)
         model,label_encoder,optF1,optROC=self.load_model(self.models_directory+"/region/files/")
         y_pred_F1,y_pred_ROC=self.model_prediction(dataset,model,label_encoder,optF1,optROC)
         dataset["region-prediction_F1"]=y_pred_F1
         dataset["region-prediction_ROC"]=y_pred_ROC
         
-        data["region-prediction"] = data.apply(lambda row: row["region_Dictionary"] if row["region_Dictionary"]  else row["region-prediction_F1"] , axis=1)
+        
+        dataset['region_Dictionary'] = dataset['region_Dictionary'].apply(lambda x: x if pd.notna(x) else None)
+        dataset["region-prediction"] = dataset.apply(lambda row: row["region_Dictionary"] if row["region_Dictionary"]  else row["region-prediction_F1"] , axis=1)
 
         
         Europe=dataset[dataset["region-prediction"]=="Europe"]
@@ -126,10 +127,12 @@ class RegionPredictor:
             Oceania["sub-region-prediction_ROC"]="Australia and New Zealand"
         if not Africa.empty:
             Africa["sub-region-prediction_F1"]=Africa["region-prediction"]
-            Africa["sub-region-prediction_ROC"]=Africa["region-prediction"]    
+            Africa["sub-region-prediction_ROC"]=Africa["region-prediction"]
+          
         data=pd.concat([Europe,Asia,Oceania,Americas,Africa])
+        data["sub-region_Dictionary"] = data["sub-region_Dictionary"].apply(lambda x: x if pd.notna(x) else None)
         data["sub-region-prediction"] = data.apply(lambda row: row["sub-region_Dictionary"] if row["sub-region_Dictionary"]  else row["sub-region-prediction_F1"] , axis=1)
-
+        
         return data