Create app.py

app.py

@@ -0,0 +1,226 @@
+import gradio as gr
+import cloudpickle
+import codecs
+import string
+from bnltk.tokenize import Tokenizers
+
+# Global variables to store loaded models and components
+model = None
+tfidf_vectorizer = None
+tokenizer = None
+bangla_stopwords = None
+punctuation_marks = None
+
+def load_models_and_components():
+    """Load the saved model, vectorizer, and preprocessing components"""
+    global model, tfidf_vectorizer, tokenizer, bangla_stopwords, punctuation_marks
+    
+    try:
+        # Load the SVM Optimized model
+        with open('model.pkl', 'rb') as f:
+            model = cloudpickle.load(f)
+        
+        # Load the TF-IDF Vectorizer
+        with open('tfidf_VECt.pkl', 'rb') as f:
+            tfidf_vectorizer = cloudpickle.load(f)
+        
+        # Initialize tokenizer
+        tokenizer = Tokenizers()
+        
+        # Load stopwords
+        stopwords_list = "stopwords.txt"
+        bangla_stopwords = codecs.open(stopwords_list, 'r', encoding='utf-8').read().split()
+        
+        # Define punctuation marks
+        punctuation_marks = set(string.punctuation)
+        
+        return "Models and components loaded successfully!"
+        
+    except Exception as e:
+        return f"Error loading models: {str(e)}"
+
+def preprocess_text(text):
+    """Preprocess the input text similar to training data preprocessing"""
+    # Tokenize the sentence
+    words = tokenizer.bn_word_tokenizer(text)
+    
+    # Exclude punctuation marks
+    words_no_punct = [word for word in words if word not in punctuation_marks]
+    
+    # Exclude stopwords
+    words_clean = [word for word in words_no_punct if word not in bangla_stopwords]
+    
+    # Join words back into a string
+    return ' '.join(words_clean)
+
+def predict_sentiment(input_text):
+    """Predict sentiment for the input text"""
+    if not input_text.strip():
+        return "Please enter some text to analyze.", ""
+    
+    if model is None or tfidf_vectorizer is None:
+        return "Models not loaded. Please load models first.", ""
+    
+    try:
+        # Preprocess the input text
+        processed_text = preprocess_text(input_text)
+        
+        if not processed_text.strip():
+            return "After preprocessing, no valid words found. Please try different text.", ""
+        
+        # Transform using the loaded TF-IDF vectorizer
+        transformed_input = tfidf_vectorizer.transform([processed_text])
+        
+        # Predict using the loaded model
+        prediction = model.predict(transformed_input)[0]
+        
+        # Get prediction probability for confidence score
+        prediction_proba = model.predict_proba(transformed_input)[0]
+        confidence = max(prediction_proba) * 100
+        
+        # Determine sentiment
+        sentiment = "Positive 😊" if prediction == 1 else "Negative 😞"
+        
+        # Create detailed result
+        result = f"**Sentiment:** {sentiment}\n**Confidence:** {confidence:.2f}%"
+        
+        # Additional info
+        details = f"**Processed Text:** {processed_text}\n**Raw Prediction:** {prediction}\n**Probabilities:** Negative: {prediction_proba[0]:.3f}, Positive: {prediction_proba[1]:.3f}"
+        
+        return result, details
+        
+    except Exception as e:
+        return f"Error during prediction: {str(e)}", ""
+
+def create_gradio_interface():
+    """Create and configure the Gradio interface"""
+    
+    # Custom CSS for better styling
+    css = """
+    .gradio-container {
+        font-family: 'Arial', sans-serif;
+    }
+    .main-header {
+        text-align: center;
+        color: #2d3748;
+        margin-bottom: 20px;
+    }
+    .prediction-box {
+        background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
+        color: white;
+        padding: 15px;
+        border-radius: 10px;
+        margin: 10px 0;
+    }
+    """
+    
+    with gr.Blocks(css=css, title="Bengali Sentiment Analysis") as demo:
+        gr.HTML("""
+        <div class="main-header">
+            <h1>🇧🇩 Bengali Sentiment Analysis</h1>
+            <p>Analyze the sentiment of Bengali text using machine learning</p>
+        </div>
+        """)
+        
+        with gr.Row():
+            with gr.Column(scale=2):
+                # Input section
+                gr.Markdown("### 📝 Enter Bengali Text")
+                input_text = gr.Textbox(
+                    label="Bengali Text",
+                    placeholder="এখানে বাংলা টেক্সট লিখুন... (Enter Bengali text here...)",
+                    lines=4,
+                    max_lines=8
+                )
+                
+                with gr.Row():
+                    predict_btn = gr.Button("🔍 Analyze Sentiment", variant="primary", size="lg")
+                    clear_btn = gr.Button("🗑️ Clear", variant="secondary")
+                
+                # Load models button
+                gr.Markdown("### ⚙️ Model Management")
+                load_btn = gr.Button("📥 Load Models", variant="secondary")
+                load_status = gr.Textbox(label="Load Status", interactive=False)
+            
+            with gr.Column(scale=2):
+                # Output section
+                gr.Markdown("### 📊 Results")
+                output_sentiment = gr.Markdown(label="Sentiment Analysis Result")
+                output_details = gr.Textbox(
+                    label="Analysis Details",
+                    lines=6,
+                    interactive=False
+                )
+        
+        # Examples section
+        gr.Markdown("### 💡 Example Texts to Try")
+        gr.Examples(
+            examples=[
+                ["এই পণ্যটি অসাধারণ! আমি খুবই সন্তুষ্ট।"],
+                ["এই পণ্যটি কাজ করছে না। খুবই খারাপ।"],
+                ["দারুণ সার্ভিস! দ্রুত ডেলিভারি পেয়েছি।"],
+                ["প্রোডাক্ট কোয়ালিটি ভালো না। টাকার অপচয়।"],
+                ["চমৎকার অভিজ্ঞতা! আবার কিনব।"]
+            ],
+            inputs=[input_text],
+            label="Click on any example to try it"
+        )
+        
+        # Event handlers
+        predict_btn.click(
+            fn=predict_sentiment,
+            inputs=[input_text],
+            outputs=[output_sentiment, output_details]
+        )
+        
+        clear_btn.click(
+            fn=lambda: ("", "", ""),
+            outputs=[input_text, output_sentiment, output_details]
+        )
+        
+        load_btn.click(
+            fn=load_models_and_components,
+            outputs=[load_status]
+        )
+        
+        # Footer
+        gr.HTML("""
+        <div style="text-align: center; margin-top: 30px; padding: 20px; background-color: #f8f9fa; border-radius: 10px;">
+            <p><strong>Bengali Sentiment Analysis App</strong></p>
+            <p>Powered by SVM with TF-IDF features | Built with Gradio</p>
+            <p><em>Load the models first, then enter Bengali text to analyze sentiment</em></p>
+        </div>
+        """)
+    
+    return demo
+
+def main():
+    """Main function to run the Gradio app"""
+    print("Starting Bengali Sentiment Analysis App...")
+    print("Make sure you have the following files in the specified paths:")
+    print("- model.pkl")
+    print("- tfidf_VECt.pkl") 
+    print("- stopwords.txt")
+    
+    # Create and launch the interface
+    demo = create_gradio_interface()
+    
+    # Launch the app
+    demo.launch(
+        share=True,  # Creates a public link
+        inbrowser=True,  # Opens in browser automatically
+        server_name="0.0.0.0",  # Makes it accessible from any IP
+        server_port=7860,  # Port number
+        show_error=True  # Shows detailed error messages
+    )
+
+if __name__ == "__main__":
+    # Install required packages if not already installed
+    try:
+        import gradio
+    except ImportError:
+        print("Installing Gradio...")
+        import subprocess
+        subprocess.check_call(["pip", "install", "gradio"])
+    
+    main()