Update app.py

app.py

@@ -8,16 +8,37 @@ from nltk.tokenize import word_tokenize
 from nltk.corpus import stopwords
 from nltk.stem import WordNetLemmatizer
 import nltk
+import os
 
-# Download NLTK resources
-nltk.download('punkt', download_dir='/root/nltk_data')
-nltk.download('stopwords', download_dir='/root/nltk_data')
-nltk.download('wordnet', download_dir='/root/nltk_data')
+# Specify the directory for nltk_data
+nltk_data_dir = '/root/nltk_data'
+
+# Ensure the directory exists
+if not os.path.exists(nltk_data_dir):
+    os.makedirs(nltk_data_dir)
+
+# Set the NLTK data path explicitly
+nltk.data.path.append(nltk_data_dir)
+
+# Try downloading required NLTK resources
+try:
+    nltk.download('punkt', download_dir=nltk_data_dir)
+    nltk.download('stopwords', download_dir=nltk_data_dir)
+    nltk.download('wordnet', download_dir=nltk_data_dir)
+except Exception as e:
+    print(f"Error while downloading NLTK resources: {e}")
+
+# Proceed with your application code
+from nltk.tokenize import word_tokenize
+from nltk.corpus import stopwords
+from nltk.stem import WordNetLemmatizer
 
 # Initialize lemmatizer and stopwords
 lemmatizer = WordNetLemmatizer()
 stop_words = set(stopwords.words('english'))
 
+
+
 # Load fine-tuned model and tokenizer (adjust the model name)
 model_name = "TAgroup5/news-classification-model"  # Replace with the correct model name
 model = AutoModelForSequenceClassification.from_pretrained(model_name)