Update app.py

app.py

@@ -2,13 +2,14 @@ import gradio as gr
 import pandas as pd
 import numpy as np
 import faiss
-import os
 from sentence_transformers import SentenceTransformer
 import joblib
+import os
+import traceback
 
-# ------------------------
+# ===============================
 # Load assets
-# ------------------------
+# ===============================
 print("🔄 Loading data and models...")
 df = pd.read_csv("clean_feedback.csv")
 print("✅ CSV loaded with columns:", df.columns.tolist())
@@ -25,82 +26,73 @@ print("✅ Sentiment model loaded")
 model = SentenceTransformer("paraphrase-multilingual-MiniLM-L12-v2", device="cpu")
 print("✅ SentenceTransformer ready")
 
-# ------------------------
-# Setup shared CSV for user submissions
-# ------------------------
-USER_LOG_FILE = "user_feedback.csv"
+# File to store user submissions
+USER_FEEDBACK_FILE = "user_feedback.csv"
+if not os.path.exists(USER_FEEDBACK_FILE):
+    pd.DataFrame(columns=["Sentence", "Predicted_Sentiment", "Confidence"]).to_csv(USER_FEEDBACK_FILE, index=False)
 
-# Create file if missing
-if not os.path.exists(USER_LOG_FILE):
-    pd.DataFrame(columns=["Sentence", "Predicted_Sentiment"]).to_csv(USER_LOG_FILE, index=False)
-    print("✅ Created user_feedback.csv")
-
-# ------------------------
-# Define classification + logging function
-# ------------------------
+# ===============================
+# Core classification function
+# ===============================
 def classify_feedback(text, top_k=5):
-    print(f"\n🧠 New query: {text}")
-
-    if not text.strip():
-        return "⚠️ Please enter a feedback text."
-
-    # Embed the input
-    query_emb = model.encode([text])
-    print("Embedding shape:", query_emb.shape)
-
-    # Retrieve top similar examples
-    distances, indices = index.search(query_emb, top_k)
-    retrieved = df.iloc[indices[0]]
-
-    # Predict sentiment and probability
     try:
-        sentiment = clf.predict(query_emb)[0]
-        if hasattr(clf, "predict_proba"):
-            confidence = clf.predict_proba(query_emb).max() * 100
-            confidence = round(confidence, 2)
-        else:
-            confidence = "N/A"
-    except Exception as e:
-        return f"❌ Model prediction error: {str(e)}"
-
-    examples = "\n".join([f"{i+1}. {s}" for i, s in enumerate(retrieved['Sentence'].tolist())])
-    print("✅ Prediction done")
-
-    return (
-        f"**Predicted Sentiment:** {sentiment}\n"
-        f"**Confidence:** {confidence}%\n\n"
-        f"**Similar Feedbacks:**\n{examples}"
-    )
-
+        if not text.strip():
+            return "⚠️ Please enter a feedback text.", pd.read_csv(USER_FEEDBACK_FILE)
+
+        # Embed query
+        query_emb = model.encode([text])
+
+        # Retrieve similar sentences
+        distances, indices = index.search(query_emb, top_k)
+        retrieved = df.iloc[indices[0]]
+
+        # Predict sentiment & probability
+        probs_all = clf.predict_proba(query_emb)[0]
+        sentiment = clf.classes_[np.argmax(probs_all)]
+        confidence = np.max(probs_all)
+
+        examples = "\n".join(
+            [f"{i+1}. {s}" for i, s in enumerate(retrieved['Sentence'].tolist())]
+        )
+
+        # Save user submission to shared file
+        new_row = pd.DataFrame(
+            [{"Sentence": text, "Predicted_Sentiment": sentiment, "Confidence": round(confidence, 2)}]
+        )
+        existing = pd.read_csv(USER_FEEDBACK_FILE)
+        updated = pd.concat([existing, new_row], ignore_index=True)
+        updated.to_csv(USER_FEEDBACK_FILE, index=False)
+
+        print(f"✅ Prediction: {sentiment} ({confidence:.2f})")
+
+        # Return both text output + table
+        explanation = (
+            f"**Predicted Sentiment:** {sentiment}\n"
+            f"**Confidence:** {confidence:.2f}\n\n"
+            f"**Similar Feedbacks:**\n{examples}"
+        )
+        return explanation, updated
 
-    # ------------------------
-    # Save user input to log
-    # ------------------------
-    log_entry = pd.DataFrame([[text, sentiment]], columns=["Sentence", "Predicted_Sentiment"])
-    log_entry.to_csv(USER_LOG_FILE, mode="a", header=False, index=False)
-    print("📝 Saved to user_feedback.csv")
-
-    # Read updated log to show
-    user_log = pd.read_csv(USER_LOG_FILE)
-
-    output_text = f"**Predicted Sentiment:** {sentiment}\n\n**Similar Feedbacks:**\n{examples}"
-    return output_text, user_log
+    except Exception as e:
+        tb = traceback.format_exc()
+        print("❌ Error:", tb)
+        return f"❌ Error occurred:\n```\n{tb}\n```", pd.read_csv(USER_FEEDBACK_FILE)
 
-# ------------------------
-# Gradio UI
-# ------------------------
+# ===============================
+# Gradio Interface
+# ===============================
 demo = gr.Interface(
     fn=classify_feedback,
     inputs=[gr.Textbox(label="Enter Student Feedback")],
     outputs=[
         gr.Markdown(label="Prediction & Explanation"),
-        gr.Dataframe(label="🧾 All User Feedback", headers=["Sentence", "Predicted_Sentiment"])
+        gr.Dataframe(headers=["Sentence", "Predicted_Sentiment", "Confidence"], label="🗂️ All User Feedback")
     ],
     title="🎓 Student Feedback RAG System",
     description=(
-        "Classifies Roman Urdu/English student feedback with context and reasoning.\n\n"
+        "Classifies Roman Urdu/English student feedback with context and reasoning.<br>"
         "All submissions are saved and visible to everyone below 👇"
     ),
 )
 
-demo.launch(server_name="0.0.0.0", server_port=7860)
+demo.launch()