Update app.py

app.py

@@ -31,13 +31,33 @@ def process_company(company_name):
         # Call the analysis function directly from utils
         data = analyze_company_data(company_name)
         
-        # Generate Hindi audio if needed
-        if 'summary' in data:
-            tts_converter = TextToSpeechConverter()
-            audio_path = tts_converter.generate_audio(data['summary'], f'{company_name}_summary')
-            data['audio_path'] = audio_path
+        # Generate Hindi audio from final analysis
+        if data.get("final_sentiment_analysis"):
+            # Get the translator
+            translator = get_translator()
+            if translator:
+                try:
+                    # Translate final analysis to Hindi
+                    translated_analysis = translator.translate(
+                        data["final_sentiment_analysis"],
+                        dest='hi'
+                    ).text
+                    
+                    # Generate Hindi audio
+                    tts_converter = TextToSpeechConverter()
+                    audio_path = tts_converter.generate_audio(
+                        translated_analysis,
+                        f'{company_name}_summary'
+                    )
+                    data['audio_path'] = audio_path
+                except Exception as e:
+                    print(f"Error generating Hindi audio: {str(e)}")
+                    data['audio_path'] = None
+            else:
+                print("Translator not available")
+                data['audio_path'] = None
             
-            return data
+        return data
     except Exception as e:
         st.error(f"Error processing company: {str(e)}")
         return {"articles": [], "comparative_sentiment_score": {}, "final_sentiment_analysis": "", "audio_path": None}
@@ -62,7 +82,7 @@ def main():
             with st.spinner("Analyzing news articles..."):
                 try:
                     # Process company data
-                    data = analyze_company_data(company)
+                    data = process_company(company)
                     
                     if not data["articles"]:
                         st.error("No articles found for analysis.")
@@ -309,48 +329,77 @@ def main():
                         except Exception as e:
                             st.error(f"Error creating indices visualization: {str(e)}")
                     
-                    # Display Final Analysis and Audio
-                    st.header("🎯 Final Analysis")
-                    if "final_sentiment_analysis" in data:
+                    # Display Final Analysis
+                    st.header("📊 Final Analysis")
+                    
+                    # Display overall sentiment analysis
+                    if data.get("final_sentiment_analysis"):
                         st.write(data["final_sentiment_analysis"])
+                    
+                    # Display ensemble model details
+                    if data.get("ensemble_info"):
+                        st.subheader("Ensemble Model Details")
+                        ensemble_info = data["ensemble_info"]
                         
-                        # Display sentiment indices in the sidebar
-                        if "sentiment_indices" in analysis and analysis["sentiment_indices"]:
-                            indices = analysis["sentiment_indices"]
-                            if indices and any(isinstance(v, (int, float)) for v in indices.values()):
-                                st.sidebar.markdown("### Sentiment Indices")
-                                for idx_name, idx_value in indices.items():
-                                    if isinstance(idx_value, (int, float)):
-                                        formatted_name = " ".join(word.capitalize() for word in idx_name.replace("_", " ").split())
-                                        st.sidebar.metric(formatted_name, f"{idx_value:.2f}")
+                        # Create columns for model details
+                        model_cols = st.columns(3)
                         
-                        # Display ensemble model information if available
-                        if "ensemble_info" in data:
-                            with st.expander("Ensemble Model Details"):
-                                ensemble = data["ensemble_info"]
-                                
-                                if "agreement" in ensemble:
-                                    st.metric("Model Agreement", f"{ensemble['agreement']*100:.1f}%")
-                                
-                                if "models" in ensemble:
-                                    st.subheader("Individual Model Results")
-                                    models_data = []
-                                    for model_name, model_info in ensemble["models"].items():
-                                        models_data.append({
-                                            "Model": model_name,
-                                            "Sentiment": model_info.get("sentiment", "N/A"),
-                                            "Confidence": f"{model_info.get('confidence', 0)*100:.1f}%"
-                                        })
-                                    
-                                    if models_data:
-                                        st.table(pd.DataFrame(models_data))
+                        with model_cols[0]:
+                            st.markdown("**Primary Model:**")
+                            if "models" in ensemble_info and "transformer" in ensemble_info["models"]:
+                                model = ensemble_info["models"]["transformer"]
+                                st.write(f"Sentiment: {model['sentiment']}")
+                                st.write(f"Score: {model['score']:.3f}")
+                        
+                        with model_cols[1]:
+                            st.markdown("**TextBlob Analysis:**")
+                            if "models" in ensemble_info and "textblob" in ensemble_info["models"]:
+                                model = ensemble_info["models"]["textblob"]
+                                st.write(f"Sentiment: {model['sentiment']}")
+                                st.write(f"Score: {model['score']:.3f}")
+                        
+                        with model_cols[2]:
+                            st.markdown("**VADER Analysis:**")
+                            if "models" in ensemble_info and "vader" in ensemble_info["models"]:
+                                model = ensemble_info["models"]["vader"]
+                                st.write(f"Sentiment: {model['sentiment']}")
+                                st.write(f"Score: {model['score']:.3f}")
                         
-                        # Audio Playback Section
-                        st.subheader("🔊 Listen to Analysis (Hindi)")
-                        if data.get("audio_path") and os.path.exists(data["audio_path"]):
-                            st.audio(data["audio_path"])
-                        else:
-                            st.warning("Hindi audio summary not available")
+                        # Display ensemble agreement if available
+                        if "model_agreement" in ensemble_info:
+                            st.markdown(f"**Model Agreement:** {ensemble_info['model_agreement']:.3f}")
+                    
+                    # Display Hindi audio player
+                    st.subheader("🔊 Listen to Analysis (Hindi)")
+                    if data.get("audio_path") and os.path.exists(data["audio_path"]):
+                        st.audio(data["audio_path"])
+                    else:
+                        st.info("Generating Hindi audio summary...")
+                        with st.spinner("Please wait while we generate the Hindi audio summary..."):
+                            # Try to generate audio again
+                            translator = get_translator()
+                            if translator and data.get("final_sentiment_analysis"):
+                                try:
+                                    # Translate final analysis to Hindi
+                                    translated_analysis = translator.translate(
+                                        data["final_sentiment_analysis"],
+                                        dest='hi'
+                                    ).text
+                                    
+                                    # Generate Hindi audio
+                                    tts_converter = TextToSpeechConverter()
+                                    audio_path = tts_converter.generate_audio(
+                                        translated_analysis,
+                                        f'{company}_summary'
+                                    )
+                                    if audio_path and os.path.exists(audio_path):
+                                        st.audio(audio_path)
+                                    else:
+                                        st.error("Hindi audio summary not available")
+                                except Exception as e:
+                                    st.error(f"Error generating Hindi audio: {str(e)}")
+                            else:
+                                st.error("Hindi audio summary not available")
                     
                     # Total Articles
                     if "total_articles" in analysis: