Update src/streamlit_app.py

src/streamlit_app.py

@@ -7,7 +7,15 @@ import nltk
 from nltk.corpus import stopwords as stp
 from nltk import pos_tag, word_tokenize as w, sent_tokenize as s
 from nltk.stem import WordNetLemmatizer as wl
+import os
+NLTK_DATA_PATH = "/app/nltk_data"
+os.makedirs(NLTK_DATA_PATH, exist_ok=True)
+os.environ["NLTK_DATA"] = NLTK_DATA_PATH
 
+nltk.download('punkt', download_dir=NLTK_DATA_PATH, quiet=True)
+nltk.download('averaged_perceptron_tagger', download_dir=NLTK_DATA_PATH, quiet=True)
+nltk.download('wordnet', download_dir=NLTK_DATA_PATH, quiet=True)
+nltk.download('stopwords', download_dir=NLTK_DATA_PATH, quiet=True)
 # Download necessary NLTK data
 nltk.download('punkt', quiet=True)
 nltk.download('averaged_perceptron_tagger', quiet=True)