Create app.py

app.py

@@ -0,0 +1,60 @@
+import streamlit as st
+import pandas as pd
+from sentence_transformers import SentenceTransformer
+
+# Load pre-trained model for embedding
+model = SentenceTransformer('all-MiniLM-L6-v2')
+
+# Function to process uploaded files
+def process_file(uploaded_file):
+    try:
+        if uploaded_file.name.endswith('.xlsx') or uploaded_file.name.endswith('.xls'):
+            df = pd.read_excel(uploaded_file)
+        elif uploaded_file.name.endswith('.csv'):
+            df = pd.read_csv(uploaded_file)
+        elif uploaded_file.name.endswith('.pdf'):
+            from PyPDF2 import PdfReader
+            reader = PdfReader(uploaded_file)
+            text = "".join(page.extract_text() for page in reader.pages)
+            df = pd.DataFrame([row.split() for row in text.splitlines()], columns=["Name", "Grade", "Marks"])
+        else:
+            st.error("Unsupported file format. Please upload Excel, CSV, or PDF.")
+            return None
+        return df
+    except Exception as e:
+        st.error(f"Error processing file: {e}")
+        return None
+
+# Main app
+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"])
+    
+    if uploaded_file:
+        df = process_file(uploaded_file)
+        if df is not None:
+            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)
+            
+            # 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"]])
+            
+            # Search functionality
+            st.subheader("Search for a Student")
+            search_query = st.text_input("Enter the student's name or details:")
+            if search_query:
+                search_embedding = model.encode(search_query)
+                df['Similarity'] = df['Embedding'].apply(lambda emb: (emb @ search_embedding) / (emb.dot(emb) ** 0.5))
+                result = df.sort_values(by="Similarity", ascending=False).iloc[0]
+                st.write("Search Result:")
+                st.write(result[["Name", "Grade", "Marks"]])
+
+if __name__ == "__main__":
+    main()