import gradio as gr
import matplotlib.pyplot as plt
import numpy as np
import os
import PIL
import tensorflow as tf

from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras.models import Sequential

from PIL import Image
import gdown
import zipfile
import pathlib

# Define the Google Drive shareable link
gdrive_url = 'https://drive.google.com/file/d/1HjHYlQyRz5oWt8kehkt1TiOGRRlKFsv8/view?usp=drive_link'

# Extract the file ID from the URL
file_id = gdrive_url.split('/d/')[1].split('/view')[0]
direct_download_url = f'https://drive.google.com/uc?id={file_id}'

# Define the local filename to save the ZIP file
local_zip_file = 'file.zip'

# Download the ZIP file
gdown.download(direct_download_url, local_zip_file, quiet=False)

# Directory to extract files
extracted_path = 'extracted_files'

# Verify if the downloaded file is a ZIP file and extract it
try:
    with zipfile.ZipFile(local_zip_file, 'r') as zip_ref:
        zip_ref.extractall(extracted_path)
    print("Extraction successful!")
except zipfile.BadZipFile:
    print("Error: The downloaded file is not a valid ZIP file.")

# Optionally, you can delete the ZIP file after extraction
os.remove(local_zip_file)

# Convert the extracted directory path to a pathlib.Path object
data_dir = pathlib.Path(extracted_path)

# Print the directory structure to debug
for root, dirs, files in os.walk(extracted_path):
    level = root.replace(extracted_path, '').count(os.sep)
    indent = ' ' * 4 * (level)
    print(f"{indent}{os.path.basename(root)}/")
    subindent = ' ' * 4 * (level + 1)
    for f in files:
        print(f"{subindent}{f}")

# Path to the dataset directory
data_dir = pathlib.Path('extracted_files/Pest_Dataset')
data_dir = pathlib.Path(data_dir)

# Verify if the path exists
assert data_dir.exists(), f"Path {data_dir} does not exist."

# Load the dataset
img_height, img_width = 180, 180
batch_size = 32

train_ds = tf.keras.preprocessing.image_dataset_from_directory(
  data_dir,
  validation_split=0.2,
  subset="training",
  seed=123,
  image_size=(img_height, img_width),
  batch_size=batch_size
)

val_ds = tf.keras.preprocessing.image_dataset_from_directory(
  data_dir,
  validation_split=0.2,
  subset="validation",
  seed=123,
  image_size=(img_height, img_width),
  batch_size=batch_size
)

class_names = train_ds.class_names
print(class_names)

# Plot some images from the training dataset
plt.figure(figsize=(10, 10))
for images, labels in train_ds.take(1):
  for i in range(9):
    ax = plt.subplot(3, 3, i + 1)
    plt.imshow(images[i].numpy().astype("uint8"))
    plt.title(class_names[labels[i]])
    plt.axis("off")

# Define data augmentation
data_augmentation = keras.Sequential(
  [
    layers.RandomFlip("horizontal", input_shape=(img_height, img_width, 3)),
    layers.RandomRotation(0.1),
    layers.RandomZoom(0.1),
  ]
)

# Plot augmented images
plt.figure(figsize=(10, 10))
for images, _ in train_ds.take(1):
  for i in range(9):
    augmented_images = data_augmentation(images)
    ax = plt.subplot(3, 3, i + 1)
    plt.imshow(augmented_images[0].numpy().astype("uint8"))
    plt.axis("off")

# Define the model
num_classes = len(class_names)
model = Sequential([
  data_augmentation,
  layers.Rescaling(1./255),
  layers.Conv2D(16, 3, padding='same', activation='relu'),
  layers.MaxPooling2D(),
  layers.Conv2D(32, 3, padding='same', activation='relu'),
  layers.MaxPooling2D(),
  layers.Conv2D(64, 3, padding='same', activation='relu'),
  layers.MaxPooling2D(),
  layers.Dropout(0.2),
  layers.Flatten(),
  layers.Dense(128, activation='relu'),
  layers.Dense(num_classes, activation='softmax')
])

model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
              metrics=['accuracy'])

model.summary()

# Train the model
epochs = 15
history = model.fit(
  train_ds,
  validation_data=val_ds,
  epochs=epochs
)

# Define the Gradio interface
def predict_image(img):
    img = np.array(img)
    img_resized = tf.image.resize(img, (img_height, img_width))
    img_4d = tf.expand_dims(img_resized, axis=0)
    prediction = model.predict(img_4d)[0]
    return {class_names[i]: float(prediction[i]) for i in range(len(class_names))}

image = gr.Image()
label = gr.Label(num_top_classes=1)

# Define custom CSS for background image
custom_css = """
body {
    background-image: url('extracted_files/Pest_Dataset/bees/bees (444).jpg');
    background-size: cover;
    background-repeat: no-repeat;
    background-attachment: fixed;
    color: white;
}
"""

gr.Interface(
    fn=predict_image,
    inputs=image,
    outputs=label,
    title="Welcome to Agricultural Pest Image Classification",
    description="The image data set used was obtained from Kaggle and has a collection of 12 different types of agricultural pests: Ants, Bees, Beetles, Caterpillars, Earthworms, Earwigs, Grasshoppers, Moths, Slugs, Snails, Wasps, and Weevils",
    css=custom_css
).launch(debug=True)