new changes

app.py

@@ -5,15 +5,15 @@ model_name = "mrm8488/distilroberta-finetuned-financial-news-sentiment-analysis"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForSequenceClassification.from_pretrained(model_name)
 
-# Set the page title
-st.title("Financial Sentiment Analysis App")
+# Seting the page title
+st.title("Financial Sentiment Analysis")
 
-# Add a text input for the user to input financial news
+# Adding a text input for the user to input financial news
 text_input = st.text_area("Enter Financial News:", "Tesla stock is soaring after record-breaking earnings.")
 
 # Function to perform sentiment analysis
 def predict_sentiment(text):
-    inputs = tokenizer(text, return_tensors="pt")
+    inputs = tokenizer(text, return_tensors="pt", max_length=1022, truncation=True)
     outputs = model(**inputs)
     sentiment_class = outputs.logits.argmax(dim=1).item()
     sentiment_mapping = {0: 'Negative', 1: 'Neutral', 2: 'Positive'}
@@ -23,28 +23,43 @@ def predict_sentiment(text):
 # Button to trigger sentiment analysis
 if st.button("Analyze Sentiment"):
     # Check if the input text is not empty
-    if text_input:
-        # Show loading spinner while processing
+    if text_input and text_input.strip():  # Check if input is not empty or contains only whitespaces
+        # Showing loading spinner while processing
         with st.spinner("Analyzing sentiment..."):
             sentiment = predict_sentiment(text_input)
-            # Change the view based on the predicted sentiment
-            st.success(f"Sentiment: {sentiment}")
-            if sentiment == 'Positive':
-                st.balloons()  # Celebratory animation for positive sentiment
-            # Add additional views for other sentiments as needed
+
+            # Extracting confidence scores
+            inputs = tokenizer(text_input, return_tensors="pt")
+            outputs = model(**inputs)
+            confidence_scores = outputs.logits.softmax(dim=1)[0].tolist()
+
+            # Considering a threshold for sentiment prediction
+            threshold = 0.5
+
+            # Change the success message background color based on sentiment and threshold
+            if sentiment == 'Positive' and confidence_scores[2] > threshold:
+                st.success(f"Sentiment: {sentiment} (Confidence: {confidence_scores[2]:.3f})")
+            elif sentiment == 'Negative' and confidence_scores[0] > threshold:
+                st.error(f"Sentiment: {sentiment} (Confidence: {confidence_scores[0]:.3f})")
+            elif sentiment == 'Neutral' and confidence_scores[1] > threshold:
+                st.info(f"Sentiment: {sentiment} (Confidence: {confidence_scores[1]:.3f})")
+            else:
+                st.warning("Low confidence, or sentiment not above threshold. Please try again.")
+
     else:
-        st.warning("Please enter some text for sentiment analysis.")
+        st.warning("Please enter some valid text for sentiment analysis.")
 
-# Optional: Display the raw sentiment scores
+# Optional: Displaying the raw sentiment scores
 if st.checkbox("Show Raw Sentiment Scores"):
-    if text_input:
+    if text_input and text_input.strip():
         inputs = tokenizer(text_input, return_tensors="pt")
         outputs = model(**inputs)
         raw_scores = outputs.logits[0].tolist()
         st.info(f"Raw Sentiment Scores: {raw_scores}")
 
-# Optional: Display additional information or analysis
-# Add more components as needed for your specific use case
-
-# Add a footer
-st.text("Built with Streamlit and Transformers")
+# footer
+st.markdown(
+    """
+    **Built with [Streamlit](https://streamlit.io/) and [Transformers](https://huggingface.co/models).**
+    """
+)