Update app.py

app.py

@@ -47,8 +47,8 @@ def main():
             st.subheader("Uploaded Data")
             st.write(df.head())
 
-            # Ensure the required columns exist
-            required_columns = ["S.No.", "Name", "Class", "Maths", "Urdu", "English"]  # Excluding Science, History, Islamiat, Geography
+            # Ensure the required columns exist (excluding "S.No.", "Science", "History", "Islamiat", "Geography")
+            required_columns = ["Name", "Class", "Maths", "Urdu", "English"]
             missing_columns = [col for col in required_columns if col not in df.columns]
             
             if missing_columns:
@@ -56,7 +56,7 @@ def main():
                 return
 
             # Convert marks columns to numeric (if not already numeric)
-            marks_columns = ["Maths", "Urdu", "English"]  # Excluding Science, History, Islamiat, Geography
+            marks_columns = ["Maths", "Urdu", "English"]
             for col in marks_columns:
                 df[col] = pd.to_numeric(df[col], errors='coerce')
             
@@ -66,3 +66,27 @@ def main():
             # Show the top 10 students based on Total Marks
             top_performers = df.sort_values(by="Total Marks", ascending=False).head(10)
             st.subheader("Top 10 Students Based on Total Marks")
+            st.write(top_performers[["Name", "Class", "Total Marks"]])
+
+            # Add embedding column (for searching students by name or details)
+            df['Embedding'] = df.apply(lambda row: model.encode(f"{row['Name']} {row['Class']} {row['Maths']} {row['Urdu']} {row['English']}"), axis=1)
+
+            # Search functionality
+            st.subheader("Search for a Student")
+            search_query = st.text_input("Enter the student's name:")
+            
+            if search_query:
+                # Find the most similar student based on embeddings
+                search_embedding = model.encode(search_query)
+                df['Similarity'] = df['Embedding'].apply(lambda emb: (emb @ search_embedding) / (emb.dot(emb) ** 0.5))
+                # Get the student with the highest similarity score
+                result = df.sort_values(by="Similarity", ascending=False).iloc[0]
+                st.write("Search Result:")
+                st.write(result[["Name", "Class", "Maths", "Urdu", "English", "Total Marks"]])
+            
+            # Show the updated data with Total Marks column
+            st.subheader("Updated Data with Total Marks")
+            st.write(df)
+
+if __name__ == "__main__":
+    main()