Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,3 +1,36 @@
+# import streamlit as st
+# import numpy as np
+# from tensorflow.keras.models import load_model
+# import joblib
+
+# st.title('Sentiment Analysis Prediction')
+
+# # Load the model and preprocessor
+# try:
+#     model = load_model('src/cnn_model.keras')
+#     preproc = joblib.load('src/preproc.joblib')
+# except Exception as e:
+#     st.error(f"Error loading model or preprocessor: {e}")
+
+# # Input field for text
+# text_input = st.text_area('Enter text for sentiment analysis:', '')
+
+# if st.button('Predict Sentiment'):
+#     if not text_input.strip():
+#         st.warning('Please enter some text.')
+#     else:
+#         try:
+#             # Preprocess input text
+#             X = preproc.transform([text_input])
+#             # Predict sentiment
+#             prediction = model.predict(X)
+#             # Assuming binary classification: 0=Negative, 1=Positive
+#             sentiment = 'Positive' if prediction[0][0] > 0.5 else 'Negative'
+#             st.success(f'Prediction: {sentiment} (score: {prediction[0][0]:.2f})')
+#         except Exception as e:
+#             st.error(f"Error making prediction: {e
+
+
 import streamlit as st
 import numpy as np
 from tensorflow.keras.models import load_model
@@ -7,24 +40,48 @@ st.title('Sentiment Analysis Prediction')
 
 # Load the model and preprocessor
 try:
-    model = load_model('src/cnn_model.keras')
-    preproc = joblib.load('src/preproc.joblib')
+    model = load_model('Sentiment Analyis/cnn/cnn_model.keras')
+    preproc = joblib.load('Sentiment Analyis/cnn/preproc.joblib')
 except Exception as e:
     st.error(f"Error loading model or preprocessor: {e}")
 
-# Input field for text
 text_input = st.text_area('Enter text for sentiment analysis:', '')
 
+def preprocess_text(text, preproc):
+    # If preproc is a dict, try common keys
+    if isinstance(preproc, dict):
+        if 'tokenizer' in preproc:
+            # Keras Tokenizer
+            tokenizer = preproc['tokenizer']
+            seq = tokenizer.texts_to_sequences([text])
+            # Pad sequences if needed
+            if 'padder' in preproc:
+                padder = preproc['padder']
+                seq = padder(seq)
+            return np.array(seq)
+        elif 'vectorizer' in preproc:
+            # scikit-learn TfidfVectorizer or similar
+            vectorizer = preproc['vectorizer']
+            return vectorizer.transform([text])
+        else:
+            raise ValueError("Unknown preprocessor dict keys.")
+    else:
+        # If preproc is a single object
+        if hasattr(preproc, 'transform'):
+            return preproc.transform([text])
+        elif hasattr(preproc, 'texts_to_sequences'):
+            seq = preproc.texts_to_sequences([text])
+            return np.array(seq)
+        else:
+            raise ValueError("Unknown preprocessor type.")
+
 if st.button('Predict Sentiment'):
     if not text_input.strip():
         st.warning('Please enter some text.')
     else:
         try:
-            # Preprocess input text
-            X = preproc.transform([text_input])
-            # Predict sentiment
+            X = preprocess_text(text_input, preproc)
             prediction = model.predict(X)
-            # Assuming binary classification: 0=Negative, 1=Positive
             sentiment = 'Positive' if prediction[0][0] > 0.5 else 'Negative'
             st.success(f'Prediction: {sentiment} (score: {prediction[0][0]:.2f})')
         except Exception as e: