Minimal Code clean up

main.py

@@ -408,8 +408,8 @@ def upsampling(df):
 
 
 def manual_tuning_v3(model_type):
-    # TODO: hrs/min + different sequence lengths
-    sequence_length = 7
+    # TODO: hrs/min
+    sequence_length = 1
 
     tr, val, te = get_prepared_data_v3(dataset_hrs_path)
 
@@ -417,7 +417,7 @@ def manual_tuning_v3(model_type):
     # config
     repeats = 3
     n_batch = 1024
-    n_epochs = 200
+    n_epochs = 10
     n_neurons = 256
     n_neurons2 = 512
     n_neurons3 = 512
@@ -483,9 +483,9 @@ def get_prepared_data_v3(filename, sample=100):
     df = pd.read_json(filename)
     df = remove_covid_data(df)
 
-    # remove users with too little data
+    # remove users with too little data (optional)
     value_counts = df[user_str].value_counts()
-    df = df[df[user_str].isin(value_counts[value_counts>1000].index)]
+    # df = df[df[user_str].isin(value_counts[value_counts>1000].index)]
 
     adjusted_df = pd.DataFrame()
     # adjust labels
@@ -532,12 +532,12 @@ def scale_dataset(scaler, df):
 
 def calculate_baselines_v3():
     file_combinations = [(hour_timespan_str, dataset_hrs_path),
-                         (min_timespan_str, dataset_min_path),
+                        # (min_timespan_str, dataset_min_path), # TODO: dataset bining not ready for minutes
                          ]
     baseline_res = pd.DataFrame()
     for timespan_id, filename in file_combinations:
         _, _, te = get_prepared_data_v3(filename)
-        for sequence_length in range(5,30, 5):
+        for sequence_length in range(1,30,5):
             x, y = prepare_data_for_model(user_data=te, sequence_length=sequence_length)
 
             for strategy in ['most_frequent', 'stratified', 'uniform']:
@@ -554,13 +554,19 @@ def calculate_baselines_v3():
     print('Done')
 
 if __name__ == "__main__":
+    # Ordner erstellen, die benötigt werden
+    create_dir('results/')
+    create_dir(figure_path)
+
     # main_two_v1()
     # visualise_results_v1()
     #test(model_type=model_type_gru)
-   # main_two_v2(model_type=model_type_gru)
+    # main_two_v2(model_type=model_type_gru)
     #visualise_results_v2()
     #manual_tuning(model_type=model_type_lstm)
     #calculate_baselines()
+
+    #### Ab hier aktuell (21.01.2026)
     #calculate_baselines_v3()
     manual_tuning_v3(model_type=model_type_lstm)
-    print('Done') # TODO: unterschiedlich große Datenmengen als ein Problem (auch in der Evaluation)
+    print('Done')