Training code

pre-preparation/condenser.py

@@ -39,25 +39,33 @@ def condenser(spreadsheets, with_images):
     # Remove rows with all NaN values
     merged_data.dropna(how='all', axis=1, inplace=True)
 
-    if with_images:
+    if not with_images:
+        # If images are not requested, include rows with image paths containing 'images/wee/' and 'images/no-image2/'
+        df_without_images = pd.concat([merged_data[merged_data['image-id'].str.contains('images/wee/Fig')],
+                                       merged_data[merged_data['image-id'].str.contains('images/no-image2/')],
+                                       merged_data[merged_data['image-id'].str.contains('to')],
+                                       merged_data[merged_data['image-id'].str.contains('and')]],
+                                      ignore_index=True)
+
+        # Return the DataFrame without images
+        return df_without_images
+
+    else:
         # If images are requested, filter rows with image paths containing 'images/wee/'
-        df_with_images = merged_data[merged_data['image-id'].str.contains('images/wee/')]
+        df_with_images = merged_data[
+            merged_data['image-id'].str.contains('images/wee/') & ~merged_data['image-id'].str.contains(
+                'images/wee/Fig')]
 
-        # Extract a cleaned-up ID from the 'image-id' column
-        df_with_images['cleaned_id'] = df_with_images['image-id'].str.extract(r'images/wee/(\d+_\d+)\.jpg')
-
-        # Drop the original 'image-id' column
-        df_with_images.drop(columns=['image-id'], inplace=True)
+        # Extract the cleaned ID and extension from the 'image-id' column
+        df_with_images[['cleaned_id', 'extension']] = df_with_images['image-id'].str.extract(
+            r'images/wee/(\d+_\d+)_?\d*\.(jpg|tif|jpeg)')
 
+        # Drop the original 'image-id' column and the 'extension' column
+        df_with_images.drop(columns=['image-id', 'extension'], inplace=True)
+        df_with_images = df_with_images[df_with_images['cleaned_id'] != '']
         # Return the DataFrame with images
         return df_with_images
 
-    # If images are not requested, filter rows with image paths containing 'images/no-image2'
-    df_without_images = merged_data[merged_data['image-id'].str.contains('images/no-image2')]
-
-    # Return the DataFrame without images
-    return df_without_images
-
 
 if __name__ == "__main__":
     # Set up command-line argument parser

pre-preparation/reformatter.py

@@ -44,6 +44,7 @@ def data_reformatter(df, training_data):
         formatted_df[tag] = filtered_df.apply(lambda row: 1 if tag in row.values else 0, axis=1)
 
     formatted_df = duplicate_cleanser(formatted_df)
+    formatted_df = formatted_df[formatted_df['image_id'] != 'nan.png']
 
     return formatted_df
 

requirements.txt

@@ -1,3 +1,6 @@
 pandas~=2.2.1
 openpyxl~=3.1.2
-pillow~=10.2.0
+pillow~=10.2.0
+numpy~=1.26.4
+tensorflow~=2.16.1
+scikit-learn~=1.4.1.post1

training.py

@@ -0,0 +1,97 @@
+import sys
+import os
+import numpy as np
+import matplotlib.pyplot as plt
+from tensorflow.keras.preprocessing.image import img_to_array, load_img
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout
+from tensorflow.keras.optimizers import Adam
+from sklearn.model_selection import train_test_split
+
+sys.path.append('pre-preparation')
+import reformatter
+import condenser
+
+# Load your dataset
+data = condenser.condenser('pre-preparation/dataset/unformatted/spreadsheets/*.xlsx', with_images=True)
+data = reformatter.data_reformatter(data, True)
+
+# Define image processing parameters
+image_size = (128, 128)
+
+
+# Function to load and preprocess an image
+def preprocess_image(image_path, target_size):
+    image = load_img(image_path, target_size=target_size)
+    image = img_to_array(image) / 255.0  # Normalize to [0, 1]
+    return image
+
+
+# Set the base path to the image folder
+base_image_path = 'pre-preparation/dataset/formatted/images/'
+
+# Initialize lists for images and labels
+images = []
+valid_labels = []
+
+# Preprocess all images and collect valid labels
+for index, row in data.iterrows():
+    image_id = row['image_id']
+    img_path = os.path.join(base_image_path, image_id)
+    if os.path.exists(img_path):
+        img = preprocess_image(img_path, image_size)
+        images.append(img)
+
+        # Ensure labels are binary (0 or 1)
+        labels = row.drop('image_id').values
+        labels = np.array(labels > 0.5, dtype=int)  # Convert to 0 or 1 if binary
+        valid_labels.append(labels)
+        print(f"Image {image_id} processed")
+    else:
+        print(f"Image {image_id} not found, skipping...")
+
+# Convert lists of images and labels to numpy arrays
+images = np.array(images, dtype='float32')
+valid_labels = np.array(valid_labels, dtype='int32')
+
+# Visualize some samples
+for i in range(5):
+    plt.imshow(images[i])
+    plt.title(f"Label: {valid_labels[i]}")
+    plt.show()
+
+# Split the data
+X_train, X_val, y_train, y_val = train_test_split(images, valid_labels, test_size=0.2, random_state=42)
+
+# Build a simpler model
+model = Sequential([
+    Conv2D(32, (3, 3), activation='relu', input_shape=(128, 128, 3)),
+    MaxPooling2D((2, 2)),
+    Dropout(0.3),
+
+    Conv2D(64, (3, 3), activation='relu'),
+    MaxPooling2D((2, 2)),
+    Dropout(0.3),
+
+    Flatten(),
+    Dense(128, activation='relu'),
+    Dropout(0.5),
+    Dense(valid_labels.shape[1], activation='sigmoid')
+])
+
+# Compile the model with a lower learning rate
+model.compile(optimizer=Adam(learning_rate=1e-5),
+              loss='binary_crossentropy',
+              metrics=['accuracy'])
+
+print(model.summary())
+
+# Train the simpler model
+history = model.fit(X_train, y_train, epochs=30, validation_data=(X_val, y_val), batch_size=32)
+
+# Calculate final accuracy
+train_accuracy_percentage = history.history['accuracy'][-1] * 100
+validation_accuracy_percentage = history.history['val_accuracy'][-1] * 100
+
+print("Train Accuracy:", train_accuracy_percentage, "%")
+print("Validation Accuracy:", validation_accuracy_percentage, "%")