Update app.py

app.py

@@ -1,20 +1,43 @@
 from transformers import pipeline
 import gradio as gr
+import lime
+import lime.lime_text
+import numpy as np
+from sklearn.pipeline import make_pipeline
 
-# Load sentiment analysis model
-sentiment_model = pipeline("sentiment-analysis")
+# Load multi-class sentiment analysis model
+sentiment_model = pipeline("text-classification", model="cardiffnlp/twitter-roberta-base-sentiment", top_k=None)
 
+# Define possible sentiment classes
+labels = ["very negative", "negative", "slightly negative", "neutral", "slightly positive", "positive", "very positive", "anger", "joy", "sadness"]
+
+# Function to get sentiment prediction
 def analyze_sentiment(text):
-    result = sentiment_model(text)[0]
-    return f"Sentiment: {result['label']} (Confidence: {result['score']:.2f})"
+    results = sentiment_model(text)
+    scores = {res['label']: res['score'] for res in results[0]}
+    sorted_scores = sorted(scores.items(), key=lambda x: x[1], reverse=True)
+    top_label, top_confidence = sorted_scores[0]
+    return f"Sentiment: {top_label} (Confidence: {top_confidence:.2f})"
+
+# Explainability function using LIME
+def explain_prediction(text):
+    explainer = lime.lime_text.LimeTextExplainer(class_names=labels)
+    
+    def predictor(texts):
+        predictions = [sentiment_model(text)[0] for text in texts]
+        return np.array([[pred[label] if label in pred else 0 for label in labels] for pred in predictions])
+    
+    exp = explainer.explain_instance(text, predictor, num_features=6)
+    return exp.as_list()
 
 # Create Gradio interface
 iface = gr.Interface(
     fn=analyze_sentiment, 
     inputs="text", 
     outputs="text",
-    title="Sentiment Analysis App",
-    description="Enter a sentence to analyze its sentiment (Positive/Negative)."
+    title="Multi-Class Sentiment Analysis App",
+    description="Enter a sentence to analyze its sentiment across multiple categories.",
+    live=True
 )
 
-iface.launch()
+iface.launch()