ss

pages/3_Training the Model.py

@@ -54,12 +54,15 @@ def create_model_inputs(data, lag, mean_period, target_variable):
     X = df_processed[
         ["Location", "MinTemp", "MaxTemp", "Rainfall", "WindGustDir", "WindGustSpeed", "WindDir9am", "WindDir3pm",
          "WindSpeed9am", "WindSpeed3pm", "Humidity9am", "Humidity3pm", "Pressure9am", "Pressure3pm", "Temp9am",
-         "Temp3pm", "RainToday", target_variable + "_mean"]]
+         "Temp3pm", "RainToday", target_variable + "_mean"]].dropNa()
     from sklearn.preprocessing import LabelEncoder
     label_encoder = LabelEncoder()
     X['RainToday'] = label_encoder.fit_transform(X['RainToday'])
-
-    X = pd.get_dummies(X, columns=['Location', 'WindGustDir', 'WindDir9am', 'WindDir3pm'])
+    X['Location'] = label_encoder.fit_transform(X['Location'])
+    X['WindGustDir'] = label_encoder.fit_transform(X['WindGustDir'])
+    X['WindDir9am'] = label_encoder.fit_transform(X['WindDir9am'])
+    X['WindDir3pm'] = label_encoder.fit_transform(X['WindDir3pm'])
+    # X = pd.get_dummies(X, columns=['Location', 'WindGustDir', 'WindDir9am', 'WindDir3pm'])
     y = df_processed[target_variable + "Tomorrow"].loc[X.index]
 
     return X, y, target_variable + "Tomorrow"