Update app.py

app.py

@@ -7,6 +7,11 @@ import torch
 import numpy as np
 from transformers import AutoModelForSequenceClassification, AutoTokenizer
 import time
+import os
+
+print("🚀 Starting Shakespeare Authenticator...")
+print(f"📦 PyTorch version: {torch.__version__}")
+print(f"🔧 CUDA available: {torch.cuda.is_available()}")
 
 # Configuration
 MODEL_NAME = "lanretto/shakespeare-authenticator"  # Your model on HF Hub
@@ -17,14 +22,27 @@ This model analyzes linguistic patterns, vocabulary, and stylistic elements
 to determine if text was written by William Shakespeare or is a modern creation.
 """
 
-# Cache model loading to avoid reloading on every prediction
+# Global variables for model caching
+model = None
+tokenizer = None
+device = None
+
 def load_model():
-    """Load model and tokenizer with caching"""
+    """Load model and tokenizer with caching and error handling"""
+    global model, tokenizer, device
+    
+    if model is not None:
+        return model, tokenizer, device
+        
     print("🔄 Loading model from Hugging Face Hub...")
     start_time = time.time()
     
     try:
-        model = AutoModelForSequenceClassification.from_pretrained(MODEL_NAME)
+        # Load model with explicit trust for remote code
+        model = AutoModelForSequenceClassification.from_pretrained(
+            MODEL_NAME,
+            trust_remote_code=True
+        )
         tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
         
         # Set to evaluation mode
@@ -35,15 +53,31 @@ def load_model():
         load_time = time.time() - start_time
         print(f"✅ Model loaded successfully in {load_time:.2f}s")
         print(f"📊 Model device: {device}")
+        print(f"🏷️ Model labels: {model.config.id2label}")
         
         return model, tokenizer, device
         
     except Exception as e:
         print(f"❌ Error loading model: {e}")
-        raise e
+        # Fallback to CPU if CUDA fails
+        try:
+            model = AutoModelForSequenceClassification.from_pretrained(MODEL_NAME)
+            tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+            model.eval()
+            device = torch.device('cpu')
+            model = model.to(device)
+            print(f"✅ Model loaded on CPU as fallback")
+            return model, tokenizer, device
+        except Exception as e2:
+            print(f"❌ Complete failure loading model: {e2}")
+            raise e2
 
-# Load model once at startup
-model, tokenizer, device = load_model()
+# Pre-load model at startup
+try:
+    model, tokenizer, device = load_model()
+    print("🎉 Model pre-loaded and ready for inference!")
+except Exception as e:
+    print(f"⚠️ Model loading failed: {e}")
 
 def classify_shakespeare(text):
     """
@@ -57,6 +91,18 @@ def classify_shakespeare(text):
             "detailed_breakdown": None
         }
     
+    # Ensure model is loaded
+    if model is None:
+        try:
+            load_model()
+        except:
+            return {
+                "error": "Model failed to load. Please refresh the page.",
+                "prediction": None,
+                "confidence": None,
+                "detailed_breakdown": None
+            }
+    
     try:
         # Tokenize the input text
         inputs = tokenizer(
@@ -112,16 +158,21 @@ def classify_shakespeare(text):
 def create_visual_output(result):
     """Create beautiful visual output for the prediction"""
     if result["error"]:
-        return f"## ❌ Error\n{result['error']}"
+        return f"""
+        <div style="text-align: center; padding: 20px; color: #d63031;">
+            <h3>❌ Error</h3>
+            <p>{result['error']}</p>
+        </div>
+        """
     
     # Determine emoji and color based on prediction
     if "Authentic" in result["prediction"]:
         emoji = "✅"
-        color = "green"
+        color = "#00b894"
         explanation = "This text exhibits characteristics of authentic Shakespearean writing."
     else:
         emoji = "🔄" 
-        color = "orange"
+        color = "#e17055"
         explanation = "This text appears to be a modern creation or imitation."
     
     # Create confidence bar visualization
@@ -131,36 +182,44 @@ def create_visual_output(result):
     confidence_bars = f"""
     <div style="margin: 20px 0;">
         <div style="display: flex; justify-content: space-between; margin-bottom: 5px;">
-            <span>Modern Creation</span>
-            <span>{modern_score:.1f}%</span>
+            <span style="font-weight: 500;">Modern Creation</span>
+            <span style="font-weight: 600;">{modern_score:.1f}%</span>
         </div>
-        <div style="background: #e0e0e0; border-radius: 10px; height: 20px;">
-            <div style="background: #ff6b6b; width: {modern_score}%; height: 100%; border-radius: 10px;"></div>
+        <div style="background: #e0e0e0; border-radius: 10px; height: 20px; overflow: hidden;">
+            <div style="background: #ff6b6b; width: {modern_score}%; height: 100%; border-radius: 10px; transition: width 0.5s ease;"></div>
         </div>
         
         <div style="display: flex; justify-content: space-between; margin: 15px 0 5px 0;">
-            <span>Authentic Shakespeare</span>
-            <span>{shakespeare_score:.1f}%</span>
+            <span style="font-weight: 500;">Authentic Shakespeare</span>
+            <span style="font-weight: 600;">{shakespeare_score:.1f}%</span>
         </div>
-        <div style="background: #e0e0e0; border-radius: 10px; height: 20px;">
-            <div style="background: #4ecdc4; width: {shakespeare_score}%; height: 100%; border-radius: 10px;"></div>
+        <div style="background: #e0e0e0; border-radius: 10px; height: 20px; overflow: hidden;">
+            <div style="background: #4ecdc4; width: {shakespeare_score}%; height: 100%; border-radius: 10px; transition: width 0.5s ease;"></div>
         </div>
     </div>
     """
     
     output = f"""
-    ## {emoji} Analysis Results
-    
-    **Prediction:** <span style="color: {color}; font-weight: bold;">{result['prediction']}</span>
-    **Overall Confidence:** **{result['confidence']}**
-    
-    {explanation}
-    
-    ### Confidence Breakdown:
-    {confidence_bars}
+    <div style="padding: 20px; border-radius: 10px; background: linear-gradient(135deg, #667eea 0%, #764ba2 100%); color: white;">
+        <h2 style="margin: 0; text-align: center;">{emoji} Analysis Results</h2>
+    </div>
     
-    ---
-    *Powered by fine-tuned BERT • [View Model on Hugging Face](https://huggingface.co/{MODEL_NAME})*
+    <div style="padding: 20px;">
+        <div style="text-align: center; margin-bottom: 20px;">
+            <h3 style="color: {color}; margin: 0;">{result['prediction']}</h3>
+            <p style="font-size: 1.2em; font-weight: bold; margin: 10px 0;">Overall Confidence: {result['confidence']}</p>
+        </div>
+        
+        <p style="text-align: center; color: #666; font-style: italic;">{explanation}</p>
+        
+        <h4>Confidence Breakdown:</h4>
+        {confidence_bars}
+        
+        <div style="margin-top: 20px; padding-top: 20px; border-top: 1px solid #e0e0e0; text-align: center; color: #888; font-size: 0.9em;">
+            Powered by fine-tuned BERT • 
+            <a href="https://huggingface.co/{MODEL_NAME}" target="_blank" style="color: #667eea;">View Model on Hugging Face</a>
+        </div>
+    </div>
     """
     
     return output
@@ -169,7 +228,12 @@ def predict_shakespeare(text):
     """
     Main prediction function for Gradio interface
     """
+    start_time = time.time()
     result = classify_shakespeare(text)
+    processing_time = time.time() - start_time
+    
+    print(f"🔍 Processed text ({len(text)} chars) in {processing_time:.2f}s")
+    
     return create_visual_output(result)
 
 # Example texts
@@ -191,11 +255,15 @@ with gr.Blocks(
     css="""
     .gradio-container {
         max-width: 800px !important;
+        margin: 0 auto !important;
     }
     .example-text {
         font-style: italic;
         color: #666;
     }
+    footer {
+        display: none !important;
+    }
     """
 ) as demo:
     
@@ -233,7 +301,10 @@ with gr.Blocks(
             # Output section
             output = gr.HTML(
                 label="📊 Analysis Results",
-                value="<div style='text-align: center; color: #666; padding: 40px;'>Enter text above to see analysis results</div>"
+                value="""<div style='text-align: center; color: #666; padding: 40px; border: 2px dashed #ddd; border-radius: 10px;'>
+                    <h3>👆 Enter text to analyze</h3>
+                    <p>Paste any text above and click "Analyze Text" to see if it's authentic Shakespeare!</p>
+                </div>"""
             )
     
     # Model information
@@ -254,11 +325,6 @@ with gr.Blocks(
         - Works best with complete sentences or passages
         - More accurate with longer text samples
         - Designed for Early Modern English vs Contemporary English distinction
-        
-        **Limitations**
-        - May struggle with very short text fragments
-        - Performance varies with writing style and genre
-        - Not designed for other languages or time periods
         """)
     
     # Event handlers
@@ -275,15 +341,14 @@ with gr.Blocks(
     )
     
     clear_btn.click(
-        fn=lambda: ("", "<div style='text-align: center; color: #666; padding: 40px;'>Enter text above to see analysis results</div>"),
+        fn=lambda: ("", """<div style='text-align: center; color: #666; padding: 40px; border: 2px dashed #ddd; border-radius: 10px;'>
+                    <h3>👆 Enter text to analyze</h3>
+                    <p>Paste any text above and click "Analyze Text" to see if it's authentic Shakespeare!</p>
+                </div>"""),
         inputs=[],
         outputs=[text_input, output]
     )
 
-# For Hugging Face Spaces deployment
+# Launch the application - SIMPLIFIED FOR SPACES
 if __name__ == "__main__":
-    demo.launch(
-        server_name="0.0.0.0" if gr.is_space else None,
-        share=False,  # Set to True if you want public link during development
-        show_error=True
-    )
+    demo.launch()