download_plantvillage.py

import os
import requests
import zipfile
from tqdm import tqdm
import shutil

def download_plantvillage_dataset():
    """
    Downloads a small subset of the PlantVillage dataset for demonstration purposes.
    """
    print("Downloading PlantVillage dataset sample...")
    
    # Create directory for dataset
    os.makedirs('dataset_download', exist_ok=True)
    
    # URL for a small subset of PlantVillage dataset
    # Note: This is a placeholder URL. In a real scenario, you would use the actual dataset URL.
    dataset_url = "https://github.com/spMohanty/PlantVillage-Dataset/archive/master.zip"
    
    try:
        # Check if we can access the URL
        response = requests.head(dataset_url)
        if response.status_code != 200:
            print(f"Cannot access dataset URL (status code: {response.status_code})")
            print("Creating a synthetic dataset instead...")
            return False
        
        # Download the dataset
        zip_path = os.path.join('dataset_download', 'plantvillage.zip')
        print(f"Downloading dataset to {zip_path}...")
        
        response = requests.get(dataset_url, stream=True)
        total_size = int(response.headers.get('content-length', 0))
        
        with open(zip_path, 'wb') as f:
            for data in tqdm(response.iter_content(chunk_size=1024), total=total_size//1024, unit='KB'):
                f.write(data)
        
        # Extract the dataset
        print("Extracting dataset...")
        with zipfile.ZipFile(zip_path, 'r') as zip_ref:
            zip_ref.extractall('dataset_download')
        
        # Find the extracted directory
        extracted_dir = None
        for item in os.listdir('dataset_download'):
            if os.path.isdir(os.path.join('dataset_download', item)) and 'PlantVillage' in item:
                extracted_dir = os.path.join('dataset_download', item)
                break
        
        if not extracted_dir:
            print("Could not find extracted dataset directory")
            return False
        
        # Move the dataset to the PlantVillage directory
        print("Organizing dataset...")
        if os.path.exists('PlantVillage'):
            shutil.rmtree('PlantVillage')
        
        # Find the color images directory
        color_dir = None
        for root, dirs, files in os.walk(extracted_dir):
            if 'color' in dirs:
                color_dir = os.path.join(root, 'color')
                break
        
        if not color_dir:
            print("Could not find color images directory")
            return False
        
        # Copy the color images to PlantVillage directory
        shutil.copytree(color_dir, 'PlantVillage')
        
        # Clean up
        shutil.rmtree('dataset_download')
        
        print("Dataset downloaded and organized successfully")
        return True
        
    except Exception as e:
        print(f"Error downloading dataset: {e}")
        print("Creating a synthetic dataset instead...")
        return False

if __name__ == "__main__":
    download_plantvillage_dataset()