try:

nltk.data.find('tokenizers/punkt')
except LookupError:
nltk.download('punkt')

try:
nltk.data.find('corpora/stopwords')
except LookupError:
nltk.download('stopwords')

# --- Preprocess text function (moved outside session state) ---
def preprocess_text(text):
# Convert to lowercase
text = text.lower()

cleaned_text = re.sub(r'[^a-zA-Z0-9\s\,]', ' ', text)
# Tokenize text
tokens = word_tokenize(cleaned_text)

# Remove stop words
stop_words = set(stopwords.words('english'))
tokens = [word for word in tokens if word not in stop_words]

# Rejoin tokens into a single string
cleaned_text = ' '.join(tokens)

return cleaned_text

frontend/app.py

@@ -28,6 +28,11 @@ try:
 except LookupError:
     nltk.download('punkt')
 
+try:
+    nltk.data.find('corpora/stopwords')
+except LookupError:
+    nltk.download('stopwords')
+
 # --- Preprocess text function (moved outside session state) ---
 def preprocess_text(text):
     # Convert to lowercase