import os
import pandas as pd
from sklearn.model_selection import train_test_split

# Предполагая, что набор данных загружен и сохранен в каталоге
data_dir = 'food_images/'
labels = []
images = []

for label in os.listdir(data_dir):
    for file in os.listdir(os.path.join(data_dir, label)):
        if file.endswith('.jpg') or file.endswith('.png'):
            images.append(os.path.join(data_dir, label, file))
            labels.append(label)

# CreateDataFrame
df = pd.DataFrame({
    'image': images,
    'label': labels
})

# Разделите обучающий набор и тестовый набор
train_df, test_df = train_test_split(df, test_size=0.2, random_state=42)

import tensorflow as tf
from tensorflow.keras.preprocessing.image import ImageDataGenerator

# увеличение данных
train_datagen = ImageDataGenerator(
    rescale=1./255,
    shear_range=0.2,
    zoom_range=0.2,
    horizontal_flip=True
)

test_datagen = ImageDataGenerator(rescale=1./255)

train_generator = train_datagen.flow_from_dataframe(
    train_df,
    x_col='image',
    y_col='label',
    target_size=(150, 150),
    batch_size=32,
    class_mode='binary'
)

test_generator = test_datagen.flow_from_dataframe(
    test_df,
    x_col='image',
    y_col='label',
    target_size=(150, 150),
    batch_size=32,
    class_mode='binary'
)

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout

# Построить модель CNN
model = Sequential([
    Conv2D(32, (3, 3), activation='relu', input_shape=(150, 150, 3)),
    MaxPooling2D((2, 2)),
    Conv2D(64, (3, 3), activation='relu'),
    MaxPooling2D((2, 2)),
    Conv2D(128, (3, 3), activation='relu'),
    MaxPooling2D((2, 2)),
    Flatten(),
    Dense(512, activation='relu'),
    Dropout(0.5),
    Dense(1, activation='sigmoid')
])

model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

history = model.fit(
    train_generator,
    steps_per_epoch=train_generator.samples // train_generator.batch_size,
    epochs=10,
    validation_data=test_generator,
    validation_steps=test_generator.samples // test_generator.batch_size
)

# Оценка модели
loss, accuracy = model.evaluate(test_generator)
print(f'Потеря проверки: {loss:.4f}, Точность: {accuracy:.4f}')

# Нарисуйте кривую обучения
import matplotlib.pyplot as plt

plt.plot(history.history['accuracy'], label='Точность обучения')
plt.plot(history.history['val_accuracy'], label='Точность проверки')
plt.xlabel('Epochs')
plt.ylabel('Accuracy')
plt.legend()
plt.show()

from tensorflow.keras.preprocessing import image
import numpy as np

def predict_image(img_path):
    img = image.load_img(img_path, target_size=(150, 150))
    img_array = image.img_to_array(img) / 255.0
    img_array = np.expand_dims(img_array, axis=0)
    prediction = model.predict(img_array)
    return 'нормальный' if prediction[0][0] > 0.5 else 'аномальный'

# Пример: Обнаружение изображения еды
print(predict_image('path/to/food_image.jpg'))