nltk_setup.py

import nltk
import os

# Make sure NLTK data directory exists
nltk_data_dir = os.path.expanduser('~/nltk_data')
os.makedirs(nltk_data_dir, exist_ok=True)

# Check if punkt tokenizer already exists
punkt_dir = os.path.join(nltk_data_dir, 'tokenizers', 'punkt')
if not os.path.exists(punkt_dir):
    print("Downloading NLTK punkt tokenizer...")
    nltk.download('punkt', quiet=False)
else:
    print("NLTK punkt tokenizer already exists")

print("NLTK setup complete")