Update app.py

app.py

@@ -1,42 +1,41 @@
 import gradio as gr
-from transformers import pipeline
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+import torch.nn.functional as F
 
-# Load sentiment analysis model
-sentiment_pipeline = pipeline("sentiment-analysis", model="cardiffnlp/twitter-roberta-base-sentiment")
+# Load model and tokenizer
+model_name = "cardiffnlp/twitter-roberta-base-sentiment"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
 
-# Custom label mapping for multi-level output
-label_map = {
-    "LABEL_0": "Very Negative",
-    "LABEL_1": "Negative",
-    "LABEL_2": "Neutral",
-    "LABEL_3": "Positive",
-    "LABEL_4": "Very Positive"
-}
+# Label map for 3-level sentiment
+labels = ['Negative', 'Neutral', 'Positive']
 
 def advanced_sentiment_analysis(text):
-    # Predict sentiment
-    result = sentiment_pipeline(text, top_k=None)[0]
+    # Tokenize input
+    inputs = tokenizer(text, return_tensors="pt", truncation=True)
     
-    # Sum total scores for normalization (if needed)
-    total_score = sum([entry['score'] for entry in result])
+    # Get model logits
+    with torch.no_grad():
+        logits = model(**inputs).logits
     
-    # Build formatted output
-    formatted_output = ""
-    for entry in result:
-        label = label_map.get(entry['label'], entry['label'])
-        percentage = (entry['score'] / total_score) * 100
-        formatted_output += f"{label}: {percentage:.2f}%\n"
+    # Convert logits to probabilities
+    probs = F.softmax(logits, dim=1)[0]
     
-    return formatted_output.strip()
+    # Format result
+    results = ""
+    for i, prob in enumerate(probs):
+        results += f"{labels[i]}: {prob.item() * 100:.2f}%\n"
+    
+    return results.strip()
 
 # Gradio UI
 with gr.Blocks() as demo:
-    gr.Markdown("### Welcome, please enter a sample of what you may respond or tell a customer,let's tell you how cool it is")
-    with gr.Row():
-        text_input = gr.Textbox(lines=4, placeholder="Type your message here...", label="Customer Message")
+    gr.Markdown("### Welcome, please enter a sample of what you may respond or tell a customer, let's tell you how cool it is")
+    text_input = gr.Textbox(lines=4, placeholder="Type your message here...", label="Customer Message")
     output = gr.Textbox(label="Sentiment Analysis Result")
     analyze_button = gr.Button("Analyze Sentiment")
-    
+
     analyze_button.click(fn=advanced_sentiment_analysis, inputs=text_input, outputs=output)
 
 demo.launch()