download_data.py

import nltk
import os

# Create a folder for NLTK data inside your repo
NLTK_DATA_DIR = "/tmp/nltk_data"
os.makedirs(NLTK_DATA_DIR, exist_ok=True)

# Download datasets to that folder
nltk.download("twitter_samples", download_dir=NLTK_DATA_DIR)
nltk.download("stopwords", download_dir=NLTK_DATA_DIR)

# Append the path so NLTK can find the datasets
nltk.data.path.append(NLTK_DATA_DIR)