Update app.py

app.py

@@ -12,8 +12,18 @@ from nltk.stem import WordNetLemmatizer
 from nltk.tokenize import word_tokenize, sent_tokenize
 from sklearn.feature_extraction.text import CountVectorizer
 
-if not os.path.exists('/root/nltk_data'):
-    os.system("python download_nltk_data.py")
+nltk_data_path = '/home/user/nltk_data'
+if not os.path.exists(nltk_data_path):
+    os.makedirs(nltk_data_path)
+    nltk.download('punkt', download_dir=nltk_data_path)
+    nltk.download('stopwords', download_dir=nltk_data_path)
+else:
+    if not os.path.exists(os.path.join(nltk_data_path, "tokenizers/punkt")):
+        nltk.download('punkt', download_dir=nltk_data_path)
+    if not os.path.exists(os.path.join(nltk_data_path, "corpora/stopwords")):
+        nltk.download('stopwords', download_dir=nltk_data_path)
+
+nltk.data.path.append(nltk_data_path)
     
 model = load_model('model_improved.keras')
 vectorizer = joblib.load('vectorizer.joblib')
@@ -52,9 +62,9 @@ def make_prediction(input_text):
     return predicted_label
 
 st.title("Text Classification with NLP")
-st.write("Enter text to classify into predefined categories")
+st.write("Please type the customer's complaint into this text area")
 
-user_input = st.text_area("Input Text", "")
+user_input = st.text_area("Write here!", "")
 if st.button("Classify"):
     if user_input:
         result = make_prediction(user_input)