Excel Dokumentationsausgabe implementiert

.gitignore

@@ -55,3 +55,5 @@ assets/Bilder/*
 assets/Bilder/AktuelleTrainingsUndTestdaten/*
 assets/Bilder/Datengrundlage/*
 assets/Bilder/Datengrundlage/
+/ressources/results/
+/ressources/results/*

main.py

@@ -22,7 +22,7 @@ def run_model():
         config = yaml.load(file, Loader=yaml.FullLoader)
     # Initialisieren der KNN-Modellbau Eigenschaften
     config_knn = ConfigKNN(
-        excluded_folder=Markt.Kein_Markt,
+        excluded_folder=Markt.Markt_C,
         activation_function_1_units=Aktivierungsfunktion.sigmoid,
         activation_function_128_units=Aktivierungsfunktion.ReLU,
         optimization_method=Optimierungsverfahren.SGD
@@ -56,16 +56,17 @@ def run_model():
     history = fit_model(config, model, train_it, test_it, callback)
     # evaluate model
     print("Evaluiere das Modell")
-    evaluate_model(model, test_it)
+    evaluate_metrics = evaluate_model(model, test_it, datagen, config, config_knn)
     # print duration
     print("Stoppe die Zeit")
     end_time = datetime.now()
-    print('Die Dauer für das Erstellen des Modells beträgt: {}'.format(end_time - start_time))
+    training_duration_model = format(end_time - start_time)
+    print('Die Dauer für das Erstellen des Modells beträgt: ' + training_duration_model)
     # learning curves
     print("Erstelle den Plot Graphen")
     plot_values(history, config)
     print("Erstelle die Excel-Tabelle")
-    create_excel_result(callback, config)
+    create_excel_result(callback, config, config_knn, evaluate_metrics, training_duration_model)
 
 
 # entry point, run the test harness

ressources/config/config.yaml

 bilder:
-  original_path: "/Users/dwillers/Programmierung/Master/Evaluation_OOS-Erkennung/assets/Bilder/Datengrundlage-Reduziert-Test/"
-  # original_path: "/Users/dwillers/Programmierung/Master/Evaluation_OOS-Erkennung/assets/Bilder/Datengrundlage/"
-  knn_path: "/Users/dwillers/Programmierung/Master/Evaluation_OOS-Erkennung/assets/Bilder/AktuelleTrainingsUndTestdaten/"
+  original_path: "assets/Bilder/Datengrundlage-Reduziert-Test/"
+  # original_path: "assets/Bilder/Datengrundlage/"
+  knn_path: "assets/Bilder/AktuelleTrainingsUndTestdaten/"
 knn:
-  epochs: 6
+  epochs: 2
 result:
-  plot_path: "/Users/dwillers/Programmierung/Master/Evaluation_OOS-Erkennung/ressources/results/plot/"
-  excel_path: "/Users/dwillers/Programmierung/Master/Evaluation_OOS-Erkennung/ressources/results/excel/"
+  plot_path: "ressources/results/plot/"
+  excel_path: "ressources/results/excel/"

src/data/copyData.py

@@ -2,15 +2,14 @@ import os
 import shutil
 import random
 
-# Pfad des Quellordners
-src_dir = '/assets/Bilder/Datengrundlage'
 
-# Pfad des Zielordners
-dst_dir = '/assets/Bilder/Datengrundlage-Reduziert-Test'
-dst_dir_trainingsdaten = '/assets/Bilder/AktuelleTrainingsUndTestdaten'
+def create_reduzierte_testdaten():
+    # Pfad des Quellordners
+    src_dir = '/assets/Bilder/Datengrundlage'
 
+    # Pfad des Zielordners
+    dst_dir = '/assets/Bilder/Datengrundlage-Reduziert-Test'
 
-def create_reduzierte_testdaten():
     # Prozentualer Anteil der Bilder, die kopiert werden sollen
     sample_rate = 0.05
 

src/data/modelData.py

@@ -33,4 +33,13 @@ def get_test_data(datagen, directory):
         batch_size=64,
         target_size=(224, 224),
         subset='validation')
-    return test_it
\ No newline at end of file
+    return test_it
+
+
+def get_markt_data(datagen, directory):
+    test_it = datagen.flow_from_directory(
+        directory=directory,
+        class_mode='categorical',
+        batch_size=64,
+        target_size=(224, 224))
+    return test_it

src/knn/createKNN.py

+from src.data.modelData import get_markt_data
+from src.enum.marktEnum import Markt
+
+
 def fit_model(config, model, train_it, test_it, callback):
     trained_model = model.fit(
         train_it,
@@ -11,12 +15,11 @@ def fit_model(config, model, train_it, test_it, callback):
     return trained_model
 
 
-def evaluate_model(model, test_it):
+def evaluate_model(model, test_it, datagen, config, config_knn):
+    if config_knn.excluded_folder != Markt.Kein_Markt:
+        test_it = get_markt_data(datagen, config["bilder"]["original_path"] + config_knn.excluded_folder.name)
     all_metrics = model.evaluate(test_it, steps=len(test_it), verbose=1)
-    _, metrics, recall_0, recall_1 = all_metrics
-    print(all_metrics)
-    print(_)
-    print(metrics)
-    print(recall_0)
-    print(recall_1)
-    print('> %.3f' % (metrics * 100.0))
+    loss, accuracy, recall_0, recall_1 = all_metrics
+    print('loss: %.3f' % loss + ' - accuracy: %.3f' % accuracy +
+          ' - recall_0: %.3f' % recall_0 + ' - recall_1: %.3f' % recall_1)
+    return all_metrics

src/knn/defineKNN.py

@@ -23,12 +23,11 @@ def define_model(config_knn):
     opt = get_optimization_method(config_knn.optimization_method)
     # Die Klassifizierungsmetriken und die Loss-Funktion werden definiert
     loss_fn = tf.keras.losses.BinaryCrossentropy()
-    binary_accuracy = tf.keras.metrics.BinaryAccuracy()
     recall_0 = tf.keras.metrics.Recall(name='recall_0', class_id=0)
     recall_1 = tf.keras.metrics.Recall(name='recall_1', class_id=1)
 
     # Füge die Metriken dem Modell hinzu
-    model.compile(optimizer=opt, loss=loss_fn, metrics=[binary_accuracy, recall_0, recall_1])
+    model.compile(optimizer=opt, loss=loss_fn, metrics=['accuracy', recall_0, recall_1])
     return model
 
 

src/result/createExcelFile.py

@@ -2,67 +2,93 @@ import openpyxl
 from datetime import datetime
 
 
-def create_excel_result(callback, config):
+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
 
-    # Setzen Sie die Spaltenbreite auf 19 Pixel
-    worksheet.column_dimensions["A"].width = 6
-    worksheet.column_dimensions["B"].width = 19
-    worksheet.column_dimensions["C"].width = 19
-    worksheet.column_dimensions["D"].width = 19
-    worksheet.column_dimensions["E"].width = 19
-    worksheet.column_dimensions["F"].width = 19
-    worksheet.column_dimensions["G"].width = 19
-    worksheet.column_dimensions["H"].width = 19
-    worksheet.column_dimensions["I"].width = 19
+    # Spaltenbreite setzen
+    worksheet.column_dimensions["A"].width = 10
+    worksheet.column_dimensions["B"].width = 20
+    worksheet.column_dimensions["C"].width = 20
+    worksheet.column_dimensions["D"].width = 20
+    worksheet.column_dimensions["E"].width = 20
+    worksheet.column_dimensions["F"].width = 20
+    worksheet.column_dimensions["G"].width = 20
+    worksheet.column_dimensions["H"].width = 20
+    worksheet.column_dimensions["I"].width = 20
     worksheet.column_dimensions["J"].width = 12
 
-    # Basis Configurationen hier beschreiben
-    # TODO: Implementieren der Excluded Folder, Aktivierungsfunktion (128 Einheiten, 1 Einheit), Optimierungsverfahren
+    # Basis Configurationen beschreiben
+    worksheet.cell(row=r, column=2).value = 'Optimierungsverfahren'
+    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
+    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
 
     # Schreiben Sie die Überschriften in die erste Zeile
     # TODO: Ergänzung Recall 1, Recall 2
-    worksheet.cell(row=1, column=1).value = 'epoch'
-    worksheet.cell(row=1, column=2).value = 'training_loss'
-    worksheet.cell(row=1, column=3).value = 'training_accuracy'
-    worksheet.cell(row=1, column=4).value = 'training_recall_not_oos'
-    worksheet.cell(row=1, column=5).value = 'training_recall_oos'
-    worksheet.cell(row=1, column=6).value = 'test_loss'
-    worksheet.cell(row=1, column=7).value = 'test_accuracy'
-    worksheet.cell(row=1, column=8).value = 'test_recall_not_oos'
-    worksheet.cell(row=1, column=9).value = 'test_recall_oos'
-    worksheet.cell(row=1, column=10).value = 'duration'
+    worksheet.cell(row=r, column=1).value = 'epoch'
+    worksheet.cell(row=r, column=2).value = 'training_loss'
+    worksheet.cell(row=r, column=3).value = 'training_accuracy'
+    worksheet.cell(row=r, column=4).value = 'training_recall_oos'
+    worksheet.cell(row=r, column=5).value = 'training_recall_not_oos'
+    worksheet.cell(row=r, column=6).value = 'test_loss'
+    worksheet.cell(row=r, column=7).value = 'test_accuracy'
+    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
 
     # Schreiben Sie die Ergebnisse der Epochen in die Arbeitsmappe
-    for i, (loss, accuracy, recall_not_oos, recall_oos,
-            val_loss, val_accuracy, val_recall_not_oos, val_recall_oos, duration) in enumerate(
-            zip(callback.epoch_training_losses, callback.epoch_training_accuracies,
-                callback.epoch_training_recall_not_oos, callback.epoch_training_recall_oos,
-                callback.epoch_test_losses, callback.epoch_test_accuracies, callback.epoch_test_recall_not_oos,
-                callback.epoch_test_recall_oos, callback.epoch_durations)):
-        worksheet.cell(row=i + 2, column=1).value = i + 1
-        worksheet.cell(row=i + 2, column=2).value = loss
-        worksheet.cell(row=i + 2, column=3).value = accuracy
-        worksheet.cell(row=i + 2, column=4).value = recall_not_oos
-        worksheet.cell(row=i + 2, column=5).value = recall_oos
-        worksheet.cell(row=i + 2, column=6).value = val_loss
-        worksheet.cell(row=i + 2, column=7).value = val_accuracy
-        worksheet.cell(row=i + 2, column=8).value = val_recall_not_oos
-        worksheet.cell(row=i + 2, column=9).value = val_recall_oos
-        worksheet.cell(row=i + 2, column=10).value = duration
+    for i, (loss, accuracy, recall_oos, recall_not_oos,
+            val_loss, val_accuracy, val_recall_oos, val_recall_not_oos, duration) in enumerate(
+        zip(callback.epoch_training_losses, callback.epoch_training_accuracies,
+            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, column=2).value = 'Trainingsdauer'
+    worksheet.cell(row=r, column=3).value = training_duration_model
+    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
+    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]
 
     now = datetime.now()
     date_time = now.strftime("%d_%m_%y__%H_%M")
-    file_name = "epoch_results_" + date_time + ".xlsx"
+    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

src/result/customCallback.py

@@ -34,11 +34,11 @@ class CustomCallback(tf.keras.callbacks.Callback):
         if logs is None:
             logs = {}
         self.epoch_training_losses.append(logs.get('loss'))
-        self.epoch_training_accuracies.append(logs.get('binary_accuracy'))
+        self.epoch_training_accuracies.append(logs.get('accuracy'))
         self.epoch_training_recall_oos.append(logs.get('recall_0'))
         self.epoch_training_recall_not_oos.append(logs.get('recall_1'))
         self.epoch_test_losses.append(logs.get('val_loss'))
-        self.epoch_test_accuracies.append(logs.get('val_binary_accuracy'))
+        self.epoch_test_accuracies.append(logs.get('val_accuracy'))
         self.epoch_test_recall_oos.append(logs.get('val_recall_0'))
         self.epoch_test_recall_not_oos.append(logs.get('val_recall_1'))
         self.epoch_durations.append(time.time() - self.epoch_start_time)

src/result/plotResult.py

@@ -14,10 +14,10 @@ def plot_values(history, config):
     # plot accuracy
     pyplot.subplot(212)
     pyplot.title('Classification Accuracy')
-    pyplot.plot(history.history['binary_accuracy'], color='blue', label='Accuracy')
+    pyplot.plot(history.history['accuracy'], color='blue', label='Accuracy')
     pyplot.plot(history.history['recall_0'], color='blue', label='Recall OOS')
     pyplot.plot(history.history['recall_1'], color='yellow', label='Recall !OOS')
-    pyplot.plot(history.history['val_binary_accuracy'], color='orange', label='Test Accuracy')
+    pyplot.plot(history.history['val_accuracy'], color='orange', label='Test Accuracy')
     pyplot.plot(history.history['val_recall_0'], color='red', label='Test Recall OOS')
     pyplot.plot(history.history['val_recall_1'], color='green', label='Test Recall !OOS')
     # save plot to file