Update app.py

app.py

@@ -1,3 +1,4 @@
+
 from transformers import pipeline
 import gradio as gr
 import lime
@@ -8,28 +9,27 @@ from sklearn.pipeline import make_pipeline
 # Load multi-class sentiment analysis model
 sentiment_model = pipeline("text-classification", model="cardiffnlp/twitter-roberta-base-sentiment", top_k=None)
 
-# Define possible sentiment classes
+# Define possible sentiment classes based on the actual model output
 label_mapping = {
     "LABEL_0": "very negative",
     "LABEL_1": "negative",
-    "LABEL_2": "slightly negative",
-    "LABEL_3": "neutral",
-    "LABEL_4": "slightly positive",
-    "LABEL_5": "positive",
-    "LABEL_6": "very positive",
-    "LABEL_7": "anger",
-    "LABEL_8": "joy",
-    "LABEL_9": "sadness"
+    "LABEL_2": "neutral",
+    "LABEL_3": "positive",
+    "LABEL_4": "very positive"
 }
 
 # Function to get sentiment prediction
 def analyze_sentiment(text):
-    results = sentiment_model(text)
-    scores = {label_mapping.get(res['label'], 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]
+    results = sentiment_model(text)[0]  # Get predictions
+    sorted_results = sorted(results, key=lambda x: x['score'], reverse=True)
+    top_label, top_confidence = label_mapping[sorted_results[0]['label']], sorted_results[0]['score']
+    
     return f"Sentiment: {top_label} (Confidence: {top_confidence:.2f})"
 
+# Suggest test cases to ensure correct labeling
+def get_suggestions():
+    return "Try these examples:\n- 'I love this! Best experience ever!' (very positive)\n- 'I am so happy today!' (positive)\n- 'It was okay, nothing special.' (neutral)\n- 'I am disappointed with this product.' (negative)\n- 'This is the worst day of my life.' (very negative)"
+
 # Explainability function using LIME
 def explain_prediction(text):
     explainer = lime.lime_text.LimeTextExplainer(class_names=list(label_mapping.values()))
@@ -48,7 +48,14 @@ iface = gr.Interface(
     outputs="text",
     title="Multi-Class Sentiment Analysis App",
     description="Enter a sentence to analyze its sentiment across multiple categories.",
-    live=True
+    live=True,
+    examples=[
+        ["I love this! Best experience ever!"],
+        ["I am so happy today!"],
+        ["It was okay, nothing special."],
+        ["I am disappointed with this product."],
+        ["This is the worst day of my life."]
+    ]
 )
 
-iface.launch()
+iface.launch()