Autoregressive test score calculated on 96 values

src/data/dataset.py

@@ -31,7 +31,7 @@ class NrvDataset(Dataset):
         return skip_indices
 
     def __len__(self):
-        return len(self.nrv) - self.sequence_length - self.predict_sequence_length - len(self.samples_to_skip)
+        return len(self.valid_indices)
     
     def __getitem__(self, idx):
         actual_idx = self.valid_indices[idx]
@@ -63,7 +63,6 @@ class NrvDataset(Dataset):
             print(f"Found nan values in the features of sample {idx}.")
             print(f"Actual index: {actual_idx}")
             raise ValueError("There are nan values in the features.")
-        
 
         return all_features, nrv_target
 

src/data/preprocessing.py

@@ -66,15 +66,6 @@ class DataProcessor:
         df = df[['datetime', 'load_forecast', 'total_load']]
         
         df['datetime'] = pd.to_datetime(df['datetime'], utc=True)
-
-        # check if there are nan values
-        if df.isnull().values.any():
-            # print the rows with nan values
-            # print(df[df.isnull().any(axis=1)])
-            # export to temp csv
-            df[df.isnull().any(axis=1)].to_csv("temp.csv")
-            # raise ValueError("There are nan values in the load forecast data.")
-
         df.sort_values(by="datetime", inplace=True)
         return df