Update app.py

app.py

@@ -1,8 +1,6 @@
 import gradio as gr
-import spaces
 import torch
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
-import math
 
 # Initialize device
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
@@ -22,156 +20,101 @@ SENTIMENT_MAP = {
     4: "Very Positive"
 }
 
-def split_text(text, max_length=512):
-    """
-    Splits the input text into chunks where each chunk has tokens <= max_length.
-    Splitting is done at sentence boundaries to maintain context.
-    """
-    # Simple sentence splitting based on periods. For more accurate splitting, consider using nltk or spacy.
-    sentences = text.split('. ')
-    chunks = []
-    current_chunk = ""
-
-    for sentence in sentences:
-        # Add the period back if it was removed during splitting
-        if not sentence.endswith('.'):
-            sentence += '.'
-
-        # Check if adding the sentence exceeds the max_length
-        encoded = tokenizer.encode(current_chunk + " " + sentence, truncation=False)
-        if len(encoded) > max_length:
-            if current_chunk:
-                chunks.append(current_chunk.strip())
-                current_chunk = sentence
-            else:
-                # Single sentence longer than max_length, force split
-                for i in range(0, len(encoded), max_length):
-                    chunk_tokens = encoded[i:i + max_length]
-                    chunk_text = tokenizer.decode(chunk_tokens, skip_special_tokens=True)
-                    chunks.append(chunk_text.strip())
-                current_chunk = ""
-        else:
-            current_chunk += " " + sentence
-
-    if current_chunk:
-        chunks.append(current_chunk.strip())
-
-    return chunks
-
-def aggregate_sentiments(all_probabilities, threshold=0.7):
-    """
-    Aggregates the sentiment probabilities from all chunks.
-    Prioritizes extreme sentiments if any chunk has a high confidence in them.
-    Otherwise, uses weighted voting based on confidence scores.
-    """
-    aggregated_probs = torch.tensor(all_probabilities).mean(dim=0).numpy()
-    aggregated_confidence = torch.tensor(all_probabilities).mean(dim=0).max().item()
-    predicted_class = aggregated_probs.argmax()
-    final_sentiment = SENTIMENT_MAP[predicted_class]
-    final_confidence = aggregated_probs[predicted_class]
-
-    # Check for extreme sentiments with high confidence
-    for idx, prob in enumerate(aggregated_probs):
-        if (idx == 0 or idx == 4) and prob > threshold:
-            final_sentiment = SENTIMENT_MAP[idx]
-            final_confidence = prob
-            break
-
-    return final_sentiment, final_confidence, aggregated_probs
-
-@spaces.GPU
 def analyze_sentiment(text, show_probabilities=False):
     """
-    Analyzes the sentiment of the input text. If the text exceeds the token limit,
-    it splits the text into chunks and aggregates the results intelligently.
+    Analyzes the sentiment of the input text with preprocessing.
     """
     try:
-        chunks = split_text(text)
-        all_probabilities = []
-        detailed_results = ""
-
-        for idx, chunk in enumerate(chunks, 1):
-            inputs = tokenizer(chunk, return_tensors="pt", truncation=True, padding=True, max_length=512).to(device)
-
-            with torch.no_grad():
-                outputs = model(**inputs)
-
-            probabilities = torch.nn.functional.softmax(outputs.logits, dim=-1).cpu().numpy()[0]
-            predicted_class = probabilities.argmax()
-            predicted_sentiment = SENTIMENT_MAP[predicted_class]
-            confidence = probabilities[predicted_class]
-
-            all_probabilities.append(probabilities)
-
-            if show_probabilities:
-                detailed_results += f"**Chunk {idx}: {predicted_sentiment} ({confidence:.2%})**\n"
-                for cls, prob in zip(SENTIMENT_MAP.values(), probabilities):
-                    detailed_results += f"{cls}: {prob:.2%}\n"
-                detailed_results += "\n"
-            else:
-                detailed_results += f"**Chunk {idx}: {predicted_sentiment} ({confidence:.2%})**\n"
-
-        # Aggregate results
-        final_sentiment, final_confidence, aggregated_probs = aggregate_sentiments(all_probabilities)
-
-        result = f"**Overall Sentiment: {final_sentiment}**\nConfidence: {final_confidence:.2%}\n\n"
+        # Preprocess text - convert to lowercase
+        text = text.lower()
+        
+        # Tokenize and prepare input
+        inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=512).to(device)
+
+        with torch.no_grad():
+            outputs = model(**inputs)
+
+        probabilities = torch.nn.functional.softmax(outputs.logits, dim=-1).cpu().numpy()[0]
+        predicted_class = probabilities.argmax()
+        predicted_sentiment = SENTIMENT_MAP[predicted_class]
+        confidence = probabilities[predicted_class]
+
+        # Prepare the result with emoji indicators
+        sentiment_emojis = {
+            "Very Negative": "😡",
+            "Negative": "😔",
+            "Neutral": "😐",
+            "Positive": "😊",
+            "Very Positive": "🤩"
+        }
+
+        result = f"## {sentiment_emojis[predicted_sentiment]} Overall Sentiment: {predicted_sentiment}\n"
+        result += f"### Confidence: {confidence:.2%}\n\n"
 
         if show_probabilities:
-            result += "### Detailed Analysis:\n" + detailed_results
-            result += "### Aggregated Probabilities:\n"
-            for cls, prob in zip(SENTIMENT_MAP.values(), aggregated_probs):
-                result += f"{cls}: {prob:.2%}\n"
-        else:
-            result += "### Detailed Analysis:\n" + detailed_results
+            result += "### Detailed Analysis:\n"
+            for cls, prob in zip(SENTIMENT_MAP.values(), probabilities):
+                emoji = sentiment_emojis[cls]
+                result += f"{emoji} {cls}: {prob:.2%}\n"
 
         return result
     except Exception as e:
         return f"An error occurred during sentiment analysis: {str(e)}"
 
+# Custom theme
+custom_theme = gr.themes.Soft().set(
+    body_background_fill="*radial-gradient(circle at top left, #f3e7e9, #e3eeff)",
+    block_background_fill="rgba(255, 255, 255, 0.95)",
+    block_border_width="0px",
+    block_shadow="*0 4px 6px -1px rgb(0 0 0 / 0.1), 0 2px 4px -2px rgb(0 0 0 / 0.1)",
+    button_primary_background_fill="*linear-gradient(90deg, #4F46E5, #7C3AED)",
+    button_primary_background_fill_hover="*linear-gradient(90deg, #4338CA, #6D28D9)",
+    button_primary_text_color="white",
+    input_background_fill="white",
+)
+
 # Create Gradio interface using Blocks for better layout control
-with gr.Blocks(theme=gr.themes.Soft()) as demo:
-    gr.Markdown("# 🎭 Sentiment Analysis Wizard")
+with gr.Blocks(theme=custom_theme) as demo:
     gr.Markdown(
         """
-        Discover the emotional tone behind any text with our advanced AI model! This app uses a state-of-the-art language model to analyze the sentiment of your text, classifying it into one of five categories: **Very Negative**, **Negative**, **Neutral**, **Positive**, or **Very Positive**.
+        # 🎭 Sentiment Analysis Wizard
+        
+        <div style='text-align: center; padding: 1rem; background: rgba(255, 255, 255, 0.5); border-radius: 1rem; margin: 1rem 0;'>
+            Discover the emotional tone behind any text with our advanced AI model! Let our wizard analyze your text and reveal its true sentiment.
+        </div>
         """
     )
 
     with gr.Row():
-        with gr.Column():
+        with gr.Column(scale=2):
             input_text = gr.Textbox(
                 lines=10,
-                placeholder="Enter text for sentiment analysis...",
-                label="Input Text"
-            )
-            show_probs = gr.Checkbox(
-                label="Show probabilities for each class",
-                value=False
+                placeholder="Enter your text here to uncover its emotional essence...",
+                label="✍️ Input Text",
+                show_label=True
             )
-            analyze_button = gr.Button("Analyze Sentiment")
-        with gr.Column():
+            with gr.Row():
+                show_probs = gr.Checkbox(
+                    label="🎯 Show detailed probabilities",
+                    value=False
+                )
+                analyze_button = gr.Button("✨ Analyze Sentiment", variant="primary")
+        
+        with gr.Column(scale=1):
             output = gr.Markdown(label="Result")
 
-    with gr.Accordion("Examples", open=False):
+    with gr.Accordion("📚 Example Texts", open=False):
         examples = [
             ["I absolutely loved this movie! The acting was superb and the plot was engaging.", True],
             ["The service at this restaurant was terrible. I'll never go back.", False],
             ["The product works as expected. Nothing special, but it gets the job done.", True],
             ["I'm somewhat disappointed with my purchase. It's not as good as I hoped.", False],
-            ["This book changed my life! I couldn't put it down and learned so much.", True],
-            [
-                """Discover the emotional tone behind any text with our advanced AI model! This app uses a state-of-the-art language model to analyze the sentiment of your text, classifying it into one of five categories: Very Negative, Negative, Neutral, Positive, or Very Positive.
-
-                Discover the emotional tone behind any text with our advanced AI model! This app uses a state-of-the-art language model to analyze the sentiment of your text, classifying it into one of five categories: Very Negative, Negative, Neutral, Positive, or Very Positive.
-
-                FUCK YOU BITCH""",
-                True
-            ]
+            ["This book changed my life! I couldn't put it down and learned so much.", True]
         ]
         gr.Examples(
             examples=examples,
             inputs=[input_text, show_probs],
-            label="Predefined Examples"
+            label="Try these examples"
         )
 
     analyze_button.click(
@@ -180,12 +123,6 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
         outputs=output
     )
 
-    gr.Markdown(
-        """
-        ---
-        **Developed with ❤️ using Gradio and Transformers by Hugging Face**
-        """
-    )
 
 # Launch the interface
-demo.launch()
+demo.launch()