Update app.py

app.py

@@ -9,22 +9,19 @@ device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 print(f"Using device: {device}")
 
 # Load model and tokenizer from Hugging Face Model Hub
-tokenizer = BertTokenizer.from_pretrained("entropy25/sentimentanalysis")  # Replace with your model path
-model = BertForSequenceClassification.from_pretrained("entropy25/sentimentanalysis")  # Replace with your model path
+tokenizer = BertTokenizer.from_pretrained("entropy25/sentimentanalysis") # Replace with your model path
+model = BertForSequenceClassification.from_pretrained("entropy25/sentimentanalysis") # Replace with your model path
 model.to(device)
 
 # Define sentiment analysis function
 def analyze_sentiment(text):
     inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True, max_length=512).to(device)
-
     with torch.no_grad():
         outputs = model(**inputs)
         logits = outputs.logits
         prediction = torch.argmax(logits, dim=-1).item()
-        confidence = torch.nn.functional.softmax(logits, dim=-1).max().item()  # Get maximum confidence score
-
-    sentiment = "Positive" if prediction == 1 else "Negative"
-    
+        confidence = torch.nn.functional.softmax(logits, dim=-1).max().item() # Get maximum confidence score
+        sentiment = "Positive" if prediction == 1 else "Negative"
     # Return sentiment and confidence score
     return f"Sentiment: {sentiment} (Confidence: {confidence:.2f})"
 
@@ -33,16 +30,18 @@ def plot_sentiment_distribution():
     sentiments = ["Positive", "Negative"]
     # Randomly generate some distribution data for demonstration
     scores = np.random.rand(2)
+    plt.figure(figsize=(8, 6))
     plt.bar(sentiments, scores, color=['green', 'red'])
     plt.title("Sentiment Distribution")
     plt.ylabel("Confidence")
-    plt.show()
+    plt.tight_layout()
+    return plt
 
 # Gradio interface setup
 with gr.Blocks() as demo:
     gr.Markdown("# 🎬 AI Movie Sentiment Analyzer")
     gr.Markdown("This tool uses a BERT model to analyze movie reviews. Enter a review to analyze its sentiment!")
-
+    
     with gr.Row():
         with gr.Column(scale=3):
             input_text = gr.Textbox(
@@ -51,14 +50,16 @@ with gr.Blocks() as demo:
                 lines=4
             )
             submit_button = gr.Button("Analyze Sentiment")
+        
         with gr.Column(scale=2):
             sentiment_output = gr.Textbox(label="Prediction")
-            sentiment_plot = gr.Button("Visualize Sentiment Distribution")
-
+            sentiment_plot_btn = gr.Button("Visualize Sentiment Distribution")
+            plot_output = gr.Plot()
+    
     # Trigger sentiment analysis when button is clicked
     submit_button.click(fn=analyze_sentiment, inputs=input_text, outputs=sentiment_output)
-    sentiment_plot.click(fn=plot_sentiment_distribution)
-
+    sentiment_plot_btn.click(fn=plot_sentiment_distribution, outputs=plot_output)
+    
     # Add some more complex example inputs for user convenience
     examples = [
         ["The cinematography was absolutely stunning, but the pacing felt slow at times."],
@@ -72,10 +73,18 @@ with gr.Blocks() as demo:
         ["A great film for fans of the genre, but it may not appeal to everyone. It's definitely a niche film."],
         ["The ending left me speechless, and the entire movie had a fantastic build-up."]
     ]
-
-    # Launch the interface with examples passed as argument here
-    demo.launch(share=True, examples=examples)
-
+    
+    # 正确的方式：使用 gr.Examples 组件
+    gr.Examples(
+        examples=examples,
+        inputs=input_text,
+        outputs=sentiment_output,
+        fn=analyze_sentiment,
+        cache_examples=True
+    )
+
+# Launch the interface - 移除 examples 参数
+demo.launch(share=True)