import os
import cv2
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D, Flatten, Dense
from keras.utils import to_categorical

# Function to load images and labels from folders
def load_data(folder):
    images = []
    labels = []
    for filename in os.listdir(folder):
        if filename.endswith(".png"):
            image = cv2.imread(os.path.join(folder, filename))
            image = cv2.resize(image, (100, 100))  # Resize images to a fixed size
            images.append(image)
            labels.append(folder)
    return images, labels

# Load images and labels for each class
lumos_images, lumos_labels = load_data("lumos")
nox_images, nox_labels = load_data("nox")
none_images, none_labels = load_data("none")

# Combine all images and labels
images = lumos_images + nox_images + none_images
labels = lumos_labels + nox_labels + none_labels

# Convert images and labels to numpy arrays
images = np.array(images)
labels = np.array(labels)

# Encode labels
label_encoder = LabelEncoder()
labels_encoded = label_encoder.fit_transform(labels)

# Split data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(images, labels_encoded, test_size=0.2, random_state=42)

# Normalize pixel values to be between 0 and 1
X_train = X_train / 255.0
X_test = X_test / 255.0

# Convert labels to one-hot encoding
y_train = to_categorical(y_train)
y_test = to_categorical(y_test)

# Build CNN model
model = Sequential()
model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(100, 100, 3)))
model.add(MaxPooling2D((2, 2)))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D((2, 2)))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(Flatten())
model.add(Dense(64, activation='relu'))
model.add(Dense(3, activation='softmax'))

# Compile model
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])

# Train model
model.fit(X_train, y_train, epochs=10, batch_size=32, validation_data=(X_test, y_test))

# Evaluate model
loss, accuracy = model.evaluate(X_test, y_test)
print("Test Accuracy:", accuracy)

# Save the model in native Keras format
model.save("image_classifier_model.keras")