Cross-Validation implementiert mit einer Excel Dokumentation der Ergebnisse

main.py

@@ -9,25 +9,55 @@ from src.enum.optimierungsverfahren import Optimierungsverfahren
 from src.knn.configKNN import ConfigKNN
 from src.knn.createKNN import evaluate_model, fit_model
 from src.knn.defineKNN import define_model
-from src.result.createExcelFile import create_excel_result
+from src.result.createExcelFile import create_excel_result, get_excel_workbook, get_excel_worksheet, save_excel, \
+    average_evaluate_cross_validation
 from src.result.customCallback import CustomCallback
 from src.result.plotResult import plot_values
 
 
-# run the test harness for evaluating a model
-def run_model():
+def run_cross_validation():
     print("Lese Configurationsdatei")
     # Lesen der Configurationdatei
     with open("ressources/config/config.yaml", "r") as file:
         config = yaml.load(file, Loader=yaml.FullLoader)
+
     # Initialisieren der KNN-Modellbau Eigenschaften
+    for optimization_method in Optimierungsverfahren:
+        for activation_function_1 in Aktivierungsfunktion:
+            for activation_function_128 in Aktivierungsfunktion:
+                model_evaluate_metrics = []
+                training_duration_models = []
+                workbook = get_excel_workbook()
+                worksheet = get_excel_worksheet(workbook)
+                r = 1
                 config_knn = ConfigKNN(
-        excluded_folder=Markt.Markt_C,
-        activation_function_1_units=Aktivierungsfunktion.sigmoid,
-        activation_function_128_units=Aktivierungsfunktion.ReLU,
-        optimization_method=Optimierungsverfahren.SGD
+                    excluded_folder=Markt.Kein_Markt,
+                    activation_function_1_units=activation_function_1,
+                    activation_function_128_units=activation_function_128,
+                    optimization_method=optimization_method
                 )
+                for excluded_folder in Markt:
+                    if excluded_folder == Markt.Kein_Markt:
+                        continue
+                    config_knn.excluded_folder = excluded_folder
+                    worksheet, r, evaluate_metrics, training_duration_model = run_model(config, config_knn, worksheet, r)
+                    model_evaluate_metrics.append(evaluate_metrics)
+                    training_duration_models.append(training_duration_model)
+                print("Berechne den Durchschnitt der Cross-Validation beim Modellbau")
+                average_evaluate_cross_validation(worksheet, r, model_evaluate_metrics, training_duration_models)
+                print("Speichere die Excel Tabelle")
+                save_excel(workbook, config, config_knn)
+
+    # config_knn = ConfigKNN(
+    #    excluded_folder=Markt.Markt_C,
+    #    activation_function_1_units=Aktivierungsfunktion.sigmoid,
+    #    activation_function_128_units=Aktivierungsfunktion.ReLU,
+    #    optimization_method=Optimierungsverfahren.SGD
+    # )
+
 
+# run a model definition
+def run_model(config, config_knn, worksheet, r):
     print("Initialisiere Callback")
     # Erstellen Sie eine Instanz des benutzerdefinierten Callbacks
     callback = CustomCallback()
@@ -60,14 +90,17 @@ def run_model():
     # print duration
     print("Stoppe die Zeit")
     end_time = datetime.now()
-    training_duration_model = format(end_time - start_time)
-    print('Die Dauer für das Erstellen des Modells beträgt: ' + training_duration_model)
+    training_duration_model = end_time - start_time
+    training_duration_model_str = format(training_duration_model)
+    print('Die Dauer für das Erstellen des Modells beträgt: ' + training_duration_model_str)
     # learning curves
     print("Erstelle den Plot Graphen")
     plot_values(history, config)
-    print("Erstelle die Excel-Tabelle")
-    create_excel_result(callback, config, config_knn, evaluate_metrics, training_duration_model)
+    print("Inhalte in die Excel-Tabelle schreiben")
+    worksheet, r = create_excel_result(worksheet, r, callback, config, config_knn, evaluate_metrics,
+                                       training_duration_model)
+    return worksheet, r, evaluate_metrics, training_duration_model
 
 
-# entry point, run the test harness
-run_model()
+# entry point
+run_cross_validation()

src/enum/marktEnum.py

@@ -4,8 +4,8 @@ from enum import Enum
 class Markt(Enum):
     Markt_A = 0,
     Markt_B = 1,
-    Markt_C = 2,
-    Markt_D = 3,
-    Markt_E = 4,
-    Markt_F = 5
+    #Markt_C = 2,
+    #Markt_D = 3,
+    #Markt_E = 4,
+    #Markt_F = 5
     Kein_Markt = -1

src/result/createExcelFile.py

-import openpyxl
+import time
 from datetime import datetime
 
+import openpyxl
 
-def create_excel_result(callback, config, config_knn, evaluate_metrics, training_duration_model):
-    # Öffnen Sie eine neue Excel-Arbeitsmappe
-    workbook = openpyxl.Workbook()
-
-    # Fügen Sie ein neues Arbeitsblatt hinzu
-    worksheet = workbook.active
-    r = 1
 
+def create_excel_result(worksheet, r, callback, config, config_knn, evaluate_metrics, training_duration_model):
     # Spaltenbreite setzen
     worksheet.column_dimensions["A"].width = 10
     worksheet.column_dimensions["B"].width = 20
@@ -27,12 +22,12 @@ def create_excel_result(callback, config, config_knn, evaluate_metrics, training
     worksheet.cell(row=r, column=3).value = 'Aktivierungsfunktion 128'
     worksheet.cell(row=r, column=4).value = 'Aktivierungsfunktion 2'
     worksheet.cell(row=r, column=5).value = 'Evaluationsmarkt'
-    r = r+1
+    r = r + 1
     worksheet.cell(row=r, column=2).value = config_knn.optimization_method.name
     worksheet.cell(row=r, column=3).value = config_knn.activation_function_128_units.name
     worksheet.cell(row=r, column=4).value = config_knn.activation_function_1_units.name
     worksheet.cell(row=r, column=5).value = config_knn.excluded_folder.name
-    r = r+2
+    r = r + 2
 
     # Schreiben Sie die Überschriften in die erste Zeile
     # TODO: Ergänzung Recall 1, Recall 2
@@ -46,7 +41,7 @@ def create_excel_result(callback, config, config_knn, evaluate_metrics, training
     worksheet.cell(row=r, column=8).value = 'test_recall_oos'
     worksheet.cell(row=r, column=9).value = 'test_recall_not_oos'
     worksheet.cell(row=r, column=10).value = 'duration'
-    r = r+1
+    r = r + 1
 
     # Schreiben Sie die Ergebnisse der Epochen in die Arbeitsmappe
     for i, (loss, accuracy, recall_oos, recall_not_oos,
@@ -55,40 +50,105 @@ def create_excel_result(callback, config, config_knn, evaluate_metrics, training
             callback.epoch_training_recall_oos, callback.epoch_training_recall_not_oos,
             callback.epoch_test_losses, callback.epoch_test_accuracies, callback.epoch_test_recall_oos,
             callback.epoch_test_recall_not_oos, callback.epoch_durations)):
-        worksheet.cell(row=r+i, column=1).value = i + 1
-        worksheet.cell(row=r+i, column=2).value = loss
-        worksheet.cell(row=r+i, column=3).value = accuracy
-        worksheet.cell(row=r+i, column=4).value = recall_oos
-        worksheet.cell(row=r+i, column=5).value = recall_not_oos
-        worksheet.cell(row=r+i, column=6).value = val_loss
-        worksheet.cell(row=r+i, column=7).value = val_accuracy
-        worksheet.cell(row=r+i, column=8).value = val_recall_oos
-        worksheet.cell(row=r+i, column=9).value = val_recall_not_oos
-        worksheet.cell(row=r+i, column=10).value = duration
-    r = r+config["knn"]["epochs"]+1
+        worksheet.cell(row=r + i, column=1).value = i + 1
+        worksheet.cell(row=r + i, column=2).value = loss
+        worksheet.cell(row=r + i, column=3).value = accuracy
+        worksheet.cell(row=r + i, column=4).value = recall_oos
+        worksheet.cell(row=r + i, column=5).value = recall_not_oos
+        worksheet.cell(row=r + i, column=6).value = val_loss
+        worksheet.cell(row=r + i, column=7).value = val_accuracy
+        worksheet.cell(row=r + i, column=8).value = val_recall_oos
+        worksheet.cell(row=r + i, column=9).value = val_recall_not_oos
+        worksheet.cell(row=r + i, column=10).value = duration
+    r = r + config["knn"]["epochs"] + 1
     worksheet.cell(row=r, column=2).value = 'Trainingsdauer'
     worksheet.cell(row=r, column=3).value = training_duration_model
-    r = r+3
+    r = r + 3
     worksheet.cell(row=r, column=1).value = 'Evaluation'
     worksheet.cell(row=r, column=2).value = 'loss'
     worksheet.cell(row=r, column=3).value = 'accuracy'
     worksheet.cell(row=r, column=4).value = 'recall_oos'
     worksheet.cell(row=r, column=5).value = 'recall_not_oos'
-    r = r+1
+    r = r + 1
     worksheet.cell(row=r, column=1).value = config_knn.excluded_folder.name
     worksheet.cell(row=r, column=2).value = evaluate_metrics[0]
     worksheet.cell(row=r, column=3).value = evaluate_metrics[1]
     worksheet.cell(row=r, column=4).value = evaluate_metrics[2]
     worksheet.cell(row=r, column=5).value = evaluate_metrics[3]
+    r = r + 4
+    return worksheet, r
+
+
+# TODO: Abschluss Statistik nach Cross-Validation von einer Konfiguration: Durchschnitt Accuracy, Recall 1, Recall 2, Loss, Duration für Evaluation
+
+
+def average_evaluate_cross_validation(worksheet, r, model_evaluate_metrics, training_duration_models):
+    total_information = sum_values_into_one_array(model_evaluate_metrics, training_duration_models)
+    worksheet.cell(row=r, column=2).value = 'AVERAGE'
+    worksheet.cell(row=r, column=3).value = 'EVALUATE'
+    worksheet.cell(row=r, column=4).value = 'METRICS'
+    r = r + 1
+    worksheet.cell(row=r, column=1).value = 'Models'
+    worksheet.cell(row=r, column=2).value = 'loss'
+    worksheet.cell(row=r, column=3).value = 'accuracy'
+    worksheet.cell(row=r, column=4).value = 'recall_oos'
+    worksheet.cell(row=r, column=5).value = 'recall_not_oos'
+    worksheet.cell(row=r, column=6).value = 'duration'
+    r = r + 1
+    worksheet.cell(row=r, column=1).value = len(total_information)
+    worksheet.cell(row=r, column=2).value = total_information[0]
+    worksheet.cell(row=r, column=3).value = total_information[1]
+    worksheet.cell(row=r, column=4).value = total_information[2]
+    worksheet.cell(row=r, column=5).value = total_information[3]
+    # Durchschnittswert wieder in Datetime-Objekt umwandeln
+    average_datetime = format(total_information[4])
+    worksheet.cell(row=r, column=6).value = average_datetime
+
 
+def sum_values_into_one_array(model_evaluate_metrics, training_duration_models):
+    # Initialisiere Summen-Array mit Nullen
+    sum_array = [0, 0, 0, 0, 0]
+    num_arrays = len(model_evaluate_metrics)
+
+    # Iteriere durch das äußere Array
+    for evaluate_metric in model_evaluate_metrics:
+        # Füge die Werte des inneren Arrays zum Summen-Array hinzu
+        for i in range(len(evaluate_metric)):
+            sum_array[i] += evaluate_metric[i]
+
+    # Berechne den Durchschnitt, indem das Summen-Array durch die Anzahl der inneren Arrays geteilt wird
+    avg_array = [value / num_arrays for value in sum_array]
+
+    # Jetzt durchschnittsdauer des Modelltrainings berechnen
+    current_time = datetime.now()
+    add_times = current_time
+    for training_time in training_duration_models:
+        add_times = add_times + training_time
+    add_times = add_times - current_time
+    # Durchschnitt berechnen
+    average_duration = add_times / len(training_duration_models)
+    # Ergebnis dem avg_array hinzufügen
+    avg_array[4] = average_duration
+    return avg_array
+
+
+def get_excel_workbook():
+    # Öffnen Sie eine neue Excel-Arbeitsmappe
+    workbook = openpyxl.Workbook()
+    return workbook
+
+
+def get_excel_worksheet(workbook):
+    # Fügen Sie ein neues Arbeitsblatt hinzu
+    worksheet = workbook.active
+    return worksheet
+
+
+def save_excel(workbook, config, config_knn):
     now = datetime.now()
     date_time = now.strftime("%d_%m_%y__%H_%M")
-    file_name = config_knn.optimization_method.name + "_" + config_knn.activation_function_1_units.name + "_" + \
+    file_name = config_knn.optimization_method.name + "_" + \
+                config_knn.activation_function_1_units.name + "_" + \
                 config_knn.activation_function_128_units.name + "_" + date_time + ".xlsx"
     # Speichern Sie die Arbeitsmappe
     workbook.save(config["result"]["excel_path"] + file_name)
-
-    # Abschlussbericht definieren
-    # TODO: Implementierung Evaluation mit Excluded Folder, Accuracy, Recall 1, Recall 2
-
-# TODO: Abschluss Statistik nach Cross-Validation von einer Konfiguration: Durchschnitt Accuracy, Recall 1, Recall 2, Loss, Duration für Evaluation