Update app.py

app.py

@@ -16,7 +16,10 @@ def process_file(uploaded_file):
             from PyPDF2 import PdfReader
             reader = PdfReader(uploaded_file)
             text = "".join(page.extract_text() for page in reader.pages)
+            # Assuming a format with Name, Grade, Marks per line
             df = pd.DataFrame([row.split() for row in text.splitlines()], columns=["Name", "Grade", "Marks"])
+            # Convert marks column to numeric
+            df["Marks"] = pd.to_numeric(df["Marks"], errors='coerce')
         else:
             st.error("Unsupported file format. Please upload Excel, CSV, or PDF.")
             return None
@@ -30,7 +33,7 @@ def main():
     st.title("School Performance Analysis App")
     st.write("Upload a document containing student grades and marks to analyze their performance.")
     
-    uploaded_file = st.file_uploader("Upload Word, Excel, or PDF file", type=["xlsx", "xls", "csv", "pdf"])
+    uploaded_file = st.file_uploader("Upload Excel, CSV, or PDF file", type=["xlsx", "xls", "csv", "pdf"])
     
     if uploaded_file:
         df = process_file(uploaded_file)
@@ -38,23 +41,37 @@ def main():
             st.subheader("Uploaded Data")
             st.write(df.head())
             
-            # Add embedding column
-            df['Embedding'] = df.apply(lambda row: model.encode(f"{row['Name']} {row['Grade']} {row['Marks']}"), axis=1)
+            # Convert Marks to numeric (if not already numeric)
+            df['Marks'] = pd.to_numeric(df['Marks'], errors='coerce')
+            
+            # Add a Total Marks column (sum of all marks if there are multiple subjects)
+            # Assuming "Marks" column represents the total of all subjects for simplicity.
+            df['Total Marks'] = df['Marks'].sum(axis=1)
             
-            # Top 10 students
-            top_students = df.sort_values(by="Marks", ascending=False).head(10)
-            st.subheader("Top 10 Students")
-            st.write(top_students[["Name", "Grade", "Marks"]])
+            # 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", "Grade", "Total Marks"]])
             
+            # Add embedding column (for searching students by name or details)
+            df['Embedding'] = df.apply(lambda row: model.encode(f"{row['Name']} {row['Grade']} {row['Marks']}"), axis=1)
+
             # Search functionality
             st.subheader("Search for a Student")
             search_query = st.text_input("Enter the student's name or details:")
+            
             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", "Grade", "Marks"]])
+                st.write(result[["Name", "Grade", "Marks", "Total Marks"]])
+            
+            # Show the updated data
+            st.subheader("Updated Data with Total Marks")
+            st.write(df)
 
 if __name__ == "__main__":
     main()