Update app.py

app.py

@@ -8,7 +8,7 @@ st.title("Sentiment Analysis with LASER Embeddings")
 
 label_encoder = LabelEncoder()
 # Load the saved model
-model = load_model("sentiment_model_2.h5")
+model = load_model("sentiment_model.h5")
 
 languages = [
     "english",
@@ -28,7 +28,8 @@ user_text = st.text_input('Enter the text:')
 
 encoder = LaserEncoderPipeline(lang=selected_language)
 
-target_classes = [0, 1]
+# Update target_classes and fit the label encoder
+target_classes = ['negative', 'positive']
 label_encoder.fit(target_classes)
 
 user_text_embedding = encoder.encode_sentences([user_text])[0]
@@ -40,11 +41,10 @@ predicted_logits = model.predict(user_text_embedding)[0]
 # Use softmax to get probability scores
 predicted_probabilities = np.exp(predicted_logits) / np.sum(np.exp(predicted_logits))
 
-predicted_sentiment_no = np.argmax(predicted_probabilities)
-predicted_sentiment_label = label_encoder.inverse_transform([predicted_sentiment_no])[0]
+predicted_sentiment_label = label_encoder.inverse_transform([np.argmax(predicted_probabilities)])[0]
 
 # Display predicted sentiment and probability scores
 st.write("Predicted Sentiment:", predicted_sentiment_label)
 st.write("Probability Scores:")
 for label, probability in zip(target_classes, predicted_probabilities):
-    st.write(f"{label_encoder.inverse_transform([label])[0]}: {probability:.4f}")
+    st.write(f"{label}: {probability:.4f}")