Update app.py

app.py

@@ -17,66 +17,6 @@ def calculate_star_rating(positive_percent):
     else:
         return 1
 
-@st.cache_resource
-def analyze_sentiment(comments, progress_bar=None, status_text=None):
-    """Perform sentiment analysis on a list of comments"""
-    # Load model inside the function
-    classifier = pipeline(
-        "text-classification",
-        model="KeonBlackwell/movie_sentiment_model",
-        tokenizer="distilbert-base-uncased"
-    )
-    
-    results = []
-    total = len(comments)
-    
-    for i, comment in enumerate(comments):
-        if progress_bar and status_text:
-            progress = (i+1)/total
-            progress_bar.progress(progress)
-            status_text.text(f"Analyzing sentiment for {i+1}/{total} reviews...")
-        
-        prediction = classifier(comment)[0]
-        results.append({
-            'comment': comment,
-            'sentiment': 1 if prediction['label'] == 'LABEL_1' else 0,
-            'confidence': prediction['score']
-        })
-    
-    return results
-
-@st.cache_resource
-def extract_keyphrases(text, top_n=5):
-    """Extract top keyphrases from text"""
-    # Load model inside the function
-    keyphrase_extractor = pipeline(
-        "token-classification",
-        model="ml6team/keyphrase-extraction-distilbert-inspec",
-        aggregation_strategy="simple"
-    )
-    
-    keyphrases = keyphrase_extractor(text)
-    # Sort by confidence and take the top N
-    top_keyphrases = sorted(keyphrases, key=lambda x: x['score'], reverse=True)[:top_n]
-    return top_keyphrases
-
-@st.cache_resource
-def generate_summary(text, max_length=130, min_length=30):
-    """Generate summary from text"""
-    # Load model inside the function
-    summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
-    
-    # Limit text length to avoid model limitations
-    max_input_length = 1024  # Maximum input length for the model
-    if len(text) > max_input_length:
-        text = text[:max_input_length]
-    
-    summary = summarizer(text, 
-                        max_length=max_length, 
-                        min_length=min_length, 
-                        do_sample=False)
-    return summary[0]['summary_text']
-
 def main():
     st.set_page_config(page_title="Movie Review Analysis System", page_icon="🎬")
 
@@ -92,6 +32,31 @@ def main():
     </style>
     """, unsafe_allow_html=True)
 
+    # Model loading
+    with st.spinner("Loading all models, this may take a few minutes..."):
+        try:
+            # Sentiment analysis model
+            classifier = pipeline(
+                "text-classification",
+                model="KeonBlackwell/movie_sentiment_model",
+                tokenizer="distilbert-base-uncased"
+            )
+
+            # Keyphrase extraction model
+            keyphrase_extractor = pipeline(
+                "token-classification",
+                model="ml6team/keyphrase-extraction-distilbert-inspec",
+                aggregation_strategy="simple"
+            )
+
+            # Summarization model
+            summarizer = pipeline("summarization",
+                                model="facebook/bart-large-cnn")
+
+        except Exception as e:
+            st.error(f"Model loading failed: {str(e)}")
+            return
+
     # Page layout
     st.title("🎬 Movie Review Batch Analysis System")
     st.markdown("""
@@ -126,11 +91,24 @@ def main():
             progress_bar = st.progress(0)
             status_text = st.empty()
 
-            # Sentiment analysis
+            results = []
+            total = len(comments)
+
+            # Batch prediction
             try:
-                with st.spinner("Loading sentiment analysis model..."):
-                    results = analyze_sentiment(comments, progress_bar, status_text)
-                
+                # Sentiment analysis
+                for i, comment in enumerate(comments):
+                    progress = (i+1)/total
+                    progress_bar.progress(progress)
+                    status_text.text(f"Analyzing sentiment for {i+1}/{total} reviews...")
+
+                    prediction = classifier(comment)[0]
+                    results.append({
+                        'comment': comment,
+                        'sentiment': 1 if prediction['label'] == 'LABEL_1' else 0,
+                        'confidence': prediction['score']
+                    })
+
                 # Convert to DataFrame
                 result_df = pd.DataFrame(results)
 
@@ -163,11 +141,13 @@ def main():
                 st.subheader("📌 Keyphrase Extraction and Summary of Reviews")
 
                 # Combine all comments into a single text
-                combined_text = " ".join(comments)
+                combined_text = " ".join(comment)
 
                 # Keyphrase extraction
-                with st.spinner("Loading keyphrase extraction model..."):
-                    top_keyphrases = extract_keyphrases(combined_text)
+                with st.spinner("Extracting keyphrases..."):
+                    keyphrases = keyphrase_extractor(combined_text)
+                    # Sort by confidence and take the top 5
+                    top_keyphrases = sorted(keyphrases, key=lambda x: x['score'], reverse=True)[:5]
 
                 # Show keyphrases
                 st.markdown("**🔍 Extracted Keyphrases:**")
@@ -188,12 +168,20 @@ def main():
                     """, unsafe_allow_html=True)
 
                 # Generate summary
-                with st.spinner("Loading summarization model..."):
-                    summary = generate_summary(combined_text)
+                with st.spinner("Generating review summary..."):
+                    # Limit text length to avoid model limitations
+                    max_length = 1024  # Maximum input length for the model
+                    if len(combined_text) > max_length:
+                        combined_text = combined_text[:max_length]
+
+                    summary = summarizer(combined_text, 
+                                        max_length=130, 
+                                        min_length=30, 
+                                        do_sample=False)
 
                 # Show summary
                 st.markdown("**📝 Review Summary:**")
-                st.info(summary)
+                st.info(summary[0]['summary_text'])
 
                 # Generate downloadable file
                 with tempfile.NamedTemporaryFile(delete=False, suffix=".csv") as tmp: