Add scaler to transform

app.py

@@ -6,7 +6,7 @@
 app = Flask(__name__)
 CORS(app)
 
-single_prediction = SinglePrediction("deploy/model_scripted.pt", "data/preprocessing/raw_features_2024.csv")
+single_prediction = SinglePrediction("deploy/model_scripted.pt", "deploy/scaler.pkl", "data/preprocessing/raw_features_2024.csv")
 
 
 @app.route('/')

data/preprocessing/preprocess_features.py

@@ -13,6 +13,9 @@ def get_features_for_model(self):
         self.append_time_features()
         # self.get_lagged_features()
 
+        pd.set_option('display.max_columns', None)
+        print(self.df.head())
+
         return self.df[feature_columns], len(feature_columns)
 
     def append_time_features(self):

data/preprocessing/single_prediction_features.py

@@ -76,8 +76,6 @@ def build_dataframe(self, input_date):
 
         # parking_df = self.get_parking_data_df()
 
-        print(df.head())
-
         return PreprocessFeatures(df).get_features_for_model()
 
 

deploy/single_prediction.py

@@ -1,13 +1,16 @@
 import torch
+import pandas as pd
 from torch.utils.data import TensorDataset, DataLoader
+from model.scaler import Scaler
 from data.preprocessing.single_prediction_features import SinglePredictionFeatures
 from data.metadata.metadata import parking_data_labels
 
 batch_size = 1  # Required for model input
 
 
 class SinglePrediction:
-    def __init__(self, model_path, raw_features_path):
+    def __init__(self, model_path, scaler_path, raw_features_path):
+        self.scaler = Scaler.load(scaler_path)
         self.single_prediction_features = SinglePredictionFeatures(raw_features_path)
         self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
         self.model = torch.jit.load(model_path, map_location=self.device)
@@ -23,17 +26,21 @@ def build_dataset(self, df):
     def predict_with_model(self, dataloader, features_length):
         data = next(iter(dataloader))[0]
         data = data.view([batch_size, -1, features_length]).to(self.device)
-        return self.model(data).cpu()
+        return self.model(data).detach().cpu().numpy()
 
     def predict_for_date(self, date):
         features_df, features_length = self.single_prediction_features.build_dataframe(date)
         dataloader = self.build_dataset(features_df)
 
         output = self.predict_with_model(dataloader, features_length)
 
-        return [dict(zip(parking_data_labels, row)) for row in output.tolist()]
+        output_scaled_back = self.scaler.inverse_transform(pd.DataFrame(output, columns=parking_data_labels))
+
+        return [dict(zip(parking_data_labels, row)) for row in output_scaled_back.tolist()]
 
 
 if __name__ == "__main__":
-    predict = SinglePrediction("model_scripted.pt", "../data/preprocessing/raw_features_2024.csv")
-    print(predict.predict_for_date("2023-10-09 00:00"))
+    predict = SinglePrediction("model_scripted.pt", "scaler.pkl", "../data/preprocessing/raw_features_2024.csv")
+    print(predict.predict_for_date("2023-12-08 08:00"))
+    print(predict.predict_for_date("2023-12-10 18:00"))
+    print(predict.predict_for_date("2023-12-12 12:00"))