new quality save layer
This commit is contained in:
28
scripts/setup_nltk.py
Normal file
28
scripts/setup_nltk.py
Normal file
@@ -0,0 +1,28 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Setup script for NLTK data."""
|
||||
import nltk
|
||||
from loguru import logger
|
||||
|
||||
def setup_nltk():
|
||||
"""Download required NLTK data."""
|
||||
logger.info("Setting up NLTK data...")
|
||||
|
||||
required_packages = [
|
||||
'punkt', # Tokenizer
|
||||
'averaged_perceptron_tagger', # POS tagger (optional)
|
||||
'stopwords', # Stopwords (optional)
|
||||
]
|
||||
|
||||
for package in required_packages:
|
||||
try:
|
||||
nltk.data.find(f'tokenizers/{package}')
|
||||
logger.info(f"✅ {package} already installed")
|
||||
except LookupError:
|
||||
logger.info(f"📥 Downloading {package}...")
|
||||
nltk.download(package, quiet=False)
|
||||
logger.info(f"✅ {package} installed")
|
||||
|
||||
logger.info("🎉 NLTK setup complete!")
|
||||
|
||||
if __name__ == "__main__":
|
||||
setup_nltk()
|
||||
Reference in New Issue
Block a user