Merge branch 'main' of https://gitlab.informatik.uni-halle.de/apumu/data-mining

src/models/desi/call_poly.py

@@ -8,7 +8,7 @@ from src.run_model_wrapper import main
 #optimal hyperparameters from autors: 'POLY': {'periodicity': 1, 'power': 4}
 params = {
         'periodicity': [1, 2, 3],
-        'power': [1, 2, 3, 4,5,7]
+        'power': [1, 2, 3, 4,5]
 }
 
 def run_POLY(data, periodicity=1, power=3, n_jobs=1):
@@ -22,4 +22,7 @@ model = 'POLY'
 output_path = '../../../docs/evaluation/'
 
 #writes results in .csv
-main(run_POLY,params,model,data_folders = '../../../data/', model_type='unsupervised',output_dir = output_path)
\ No newline at end of file
+main(run_POLY,params,model,data_folders = '../../../data/', model_type='unsupervised',output_dir = output_path)
+
+#pip3 install -r requirements.txt
+# python src/models/desi/call_poly.py
\ No newline at end of file

src/run_model_wrapper.py

@@ -261,11 +261,11 @@ def main(run_model, hyperparams, model_name, data_folders = '../../../data/', mo
 
     #go through all files in train data and store additionally informations about group and anomaly types
     grid_List = []
-    print(f"Start Processing files")
+    # print(f"Start Processing files")
     #reutrns [{file_name:str,train_data:list,data:list, label:list, sliding_window:int}]
     file_data_dict_list = preprocess_data(path_data_all)    
 
-    print('Start Hyperparameter Tuning')
+    # print('Start Hyperparameter Tuning')
     # Creates combinations of all hyperparameters
     param_combinations = list(itertools.product(*hyperparams.values()))
     #find hyperparametrs for each file:
@@ -278,21 +278,21 @@ def main(run_model, hyperparams, model_name, data_folders = '../../../data/', mo
 
         # Hyperparameter-Optimierung
         best_params = hyperparameter_optimization(run_model, data,label,train_data, hyperparams,sliding_window,param_combinations,model_type)
-        print(f"File: {filename}, best hyperparameter: {best_params}")
+        # print(f"File: {filename}, best hyperparameter: {best_params}")
         #grid_list looks like this: [{ params: {key:value}, file_name:str,train_data:list,data:list, label:list, sliding_window:int}]
         grid_List.append({'file_name':filename,'params':best_params,'train_data':train_data,'data':data,'label':label,'sliding_window':sliding_window})
 
-    print('Start Training and evaluation')
+    # print('Start Training and evaluation')
     results_list = train_test_model(run_model,grid_List,path_to_folder, model_type)
     #convert list of dicts to a dict with lists
     results = create_dict_from_array(results_list)
 
     #check duration time
     duration = sum(results['duration'])
-    print(f'Job done. Duration: {duration:.3f} seconds')
+    # print(f'Job done. Duration: {duration:.3f} seconds')
 
     #store results for each model by folder 
     results_df = pd.DataFrame(results)
     output_csv = os.path.join(output_dir,model_name + '.csv')
     results_df.to_csv(output_csv, index=False)
-    print(f"Ergebnisse gespeichert in: {output_csv}")
+    # print(f"Ergebnisse gespeichert in: {output_csv}")