Update app.py

app.py

@@ -1,50 +1,56 @@
 import gradio as gr
 from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification
-import shap
-import numpy as np
 
-# Load model and tokenizer
+# Load sentiment model
 def load_model():
     model_name = "cardiffnlp/twitter-roberta-base-sentiment"
     tokenizer = AutoTokenizer.from_pretrained(model_name)
     model = AutoModelForSequenceClassification.from_pretrained(model_name)
     sentiment_pipeline = pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)
-    return sentiment_pipeline, tokenizer, model
+    return sentiment_pipeline
 
-sentiment_pipeline, tokenizer, model = load_model()
-
-# Label mapping
+sentiment_pipeline = load_model()
 label_map = {"LABEL_0": "negative", "LABEL_1": "neutral", "LABEL_2": "positive"}
 
-# Gradio inference function
+# Simple explanation generator
+def explain_sentiment(text, sentiment):
+    text_lower = text.lower()
+    if sentiment == "positive":
+        if any(word in text_lower for word in ["love", "great", "happy", "excellent", "good", "amazing"]):
+            return "Detected positive language such as 'great', 'happy', or 'love'."
+        else:
+            return "Overall positive tone based on context."
+    elif sentiment == "negative":
+        if any(word in text_lower for word in ["hate", "bad", "terrible", "awful", "worst", "sad"]):
+            return "Detected negative words like 'hate', 'bad', or 'worst'."
+        else:
+            return "Overall negative tone based on context."
+    else:
+        return "Text appears to be neutral with no strong emotional cues."
+
+# Gradio function
 def analyze_sentiment(text):
     if not text.strip():
-        return "Please enter text.", "", None
-
-    # Get prediction
+        return "Please enter some text.", ""
+    
     result = sentiment_pipeline(text)[0]
     sentiment = label_map[result["label"]]
     confidence = result["score"]
-
-    # Explain with SHAP
-    explainer = shap.Explainer(sentiment_pipeline)
-    shap_values = explainer([text])
-    explanation_html = shap.plots.text(shap_values[0], display=False)
-
+    explanation = explain_sentiment(text, sentiment)
+    
     sentiment_result = f"**Sentiment**: {sentiment.capitalize()}  \n**Confidence**: {confidence:.2f}"
-    return sentiment_result, shap_values.data[0], explanation_html
+    return sentiment_result, explanation
 
-# Gradio Interface
+# Gradio interface
 iface = gr.Interface(
     fn=analyze_sentiment,
-    inputs=gr.Textbox(label="Enter text", lines=4, placeholder="Type something here..."),
+    inputs=gr.Textbox(lines=4, placeholder="Type something here..."),
     outputs=[
         gr.Markdown(label="Sentiment Result"),
-        gr.Textbox(label="Tokenized Input"),
-        gr.HTML(label="SHAP Explanation"),
+        gr.Textbox(label="Explanation")
     ],
-    title="Sentiment Analyzer with Explanation",
-    description="Enter a sentence or paragraph. This app will classify its sentiment as Positive, Negative, or Neutral and explain why using SHAP values.",
+    title="Fast Sentiment Analyzer",
+    description="Enter some text. This app will classify the sentiment (Positive, Negative, or Neutral) and offer a basic explanation.",
 )
 
 if __name__ == "__main__":