train.py

import tarfile
import os

archive_path = "data/raw/emotion/IMDB.tar.gz"
extract_path = "data/raw/emotion/aclImdb"

os.makedirs(extract_path, exist_ok=True)

print(f"[INFO] Extracting {archive_path} ...")
with tarfile.open(archive_path, "r:gz") as tar:
    tar.extractall(path=extract_path)
print(f"[INFO] Extraction complete: {extract_path}")