Update app.py

app.py

@@ -2,8 +2,8 @@ import streamlit as st
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
 import shap
 import torch
-import matplotlib.pyplot as plt
 import numpy as np
+import os
 
 # Load model and tokenizer with caching
 @st.cache_resource
@@ -65,7 +65,7 @@ if st.button("Analyze Sentiment"):
             
             with cols[1]:
                 st.markdown("**Confidence Scores**")
-                for i, (label, score) in enumerate(zip(output_names, probabilities)):
+                for label, score in zip(output_names, probabilities):
                     st.progress(float(score), text=f"{label}: {score:.1%}")
             
             # Generate SHAP explanations
@@ -75,18 +75,27 @@ if st.button("Analyze Sentiment"):
             Red → Increases score | Blue → Decreases score  
             Intensity shows magnitude of impact
             """)
-            
+
             shap_values = explainer([text_input])
-            
+
             # Create tabs for each sentiment class
             tabs = st.tabs(output_names)
             for i, tab in enumerate(tabs):
                 with tab:
-                    # Create a new matplotlib figure
-                    plt.figure()
-                    shap.plots.text(shap_values[:, :, i],)  # Generate SHAP plot
-                    st.pyplot(plt.gcf())  # Pass the current figure to st.pyplot
-                    plt.close()  # Close the figure to free memory
+                    # Save SHAP text explanation as an HTML file
+                    html_path = f"shap_explanation_{i}.html"
+                    with open(html_path, "w", encoding="utf-8") as file:
+                        file.write(shap.plots.text(shap_values[:, :, i], display=False))
+                    
+                    # Read and display the saved HTML file in Streamlit
+                    with open(html_path, "r", encoding="utf-8") as file:
+                        shap_html = file.read()
+                    
+                    st.components.v1.html(shap_html, height=400, scrolling=True)
+
+                    # Clean up temporary HTML files (optional)
+                    os.remove(html_path)
+
     else:
         st.warning("Please enter some text to analyze")
 
@@ -106,4 +115,4 @@ for col, text in zip(examples, example_texts):
             st.session_state.last_input = text
 
 if 'last_input' in st.session_state:
-    text_input = st.text_area("", value=st.session_state.last_input, height=100)
+    text_input = st.text_area("", value=st.session_state.last_input, height=100)