Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,81 +1,133 @@
+from pyngrok import ngrok
+import threading
+import time
+import os
+
+# ----------------- Streamlit Dashboard Code ------------------
+dashboard_code = """
 import streamlit as st
 import pandas as pd
-import re
 import io
 
-st.set_page_config(page_title="Excel to Cleaned CSV", layout="centered")
+# Helper to normalize college name
+def normalize_name(name):
+    if pd.isna(name):
+        return ""
+    return name.replace("(B)", "B").strip().lower()
+
+# Transformation Logic
+def transform_file(main_df, attendance_df):
+    # Normalize college names in both DataFrames
+    main_df['normalized_name'] = main_df.iloc[:, 2].apply(normalize_name)
+    attendance_df['normalized_name'] = attendance_df.iloc[:, 2].apply(lambda x: str(x).strip().lower())
+
+    # Create attendance lookup dictionary
+    attendance_lookup = attendance_df.set_index('normalized_name')
+
+    school_attendance_list = []
+    inter_attendance_list = []
+
+    for name in main_df['normalized_name']:
+        if name in attendance_lookup.index:
+            row = attendance_lookup.loc[name]
+            school_attendance_list.append(row.iloc[6])  # 7th column
+            inter_attendance_list.append(row.iloc[10]) # 11th column
+        else:
+            school_attendance_list.append(None)
+            inter_attendance_list.append(None)
+
+    # Construct final dataframe
+    new_df = pd.DataFrame({
+        'serial_no': main_df.iloc[:, 0],
+        'district': main_df.iloc[:, 1],
+        'college_name': main_df.iloc[:, 2],
+        'class': 'School',
+        'school_minority_sanction': main_df.iloc[:, 3],
+        'school_minority_admitted': main_df.iloc[:, 4],
+        'school_minority_vacancies': main_df.iloc[:, 3] - main_df.iloc[:, 4],
+        'school_non_minority_sanction': main_df.iloc[:, 5],
+        'school_non_minority_admitted': main_df.iloc[:, 6],
+        'school_non_minority_vacancies': main_df.iloc[:, 5] - main_df.iloc[:, 6],
+        'school_attendance': school_attendance_list,
+        'school_attendance_percentage': '',  # Placeholder
+        'class_grade': 'Intermediate',
+        'inter_minority_sanction': main_df.iloc[:, 8],
+        'inter_minority_admitted': main_df.iloc[:, 9],
+        'inter_minority_vacancies': main_df.iloc[:, 8] - main_df.iloc[:, 9],
+        'inter_non_minority_sanction': main_df.iloc[:, 10],
+        'inter_non_minority_admitted': main_df.iloc[:, 11],
+        'inter_non_minority_vacancies': main_df.iloc[:, 10] - main_df.iloc[:, 11],
+        'inter_attendance': inter_attendance_list,
+        'inter_attendance_percentage': ''  # Placeholder
+    })
 
-st.title("📊 Clean Admission Excel Data")
-st.write("Upload the Excel file and download the cleaned CSV file.")
+    return new_df
 
-uploaded_file = st.file_uploader("Upload your Excel file", type=["xlsx"])
+# Streamlit App
+st.set_page_config(layout="wide", page_title="📝 File Format Converter")
+st.title("📤 Upload Two Files to Convert Format")
 
-if uploaded_file is not None:
+uploaded_main = st.file_uploader("Upload Main File (Sanctions, Admissions)", type=["csv", "xlsx"], key="main")
+uploaded_attendance = st.file_uploader("Upload Attendance File", type=["csv", "xlsx"], key="att")
+
+if uploaded_main and uploaded_attendance:
     try:
-        # Read and clean data
-        df_raw = pd.read_excel(uploaded_file, skiprows=4)
-
-        df_raw.columns = [
-            'S.No', 'District', 'Institution Name',
-            'V Minorities Sanctioned', 'V Minorities Admitted',
-            'V NonMinorities Sanctioned', 'V NonMinorities Admitted',
-            'Course',
-            'Inter Minorities Sanctioned', 'Inter Minorities Admitted',
-            'Inter NonMinorities Sanctioned', 'Inter NonMinorities Admitted'
-        ]
-
-        # Remove last row
-        df_raw = df_raw.iloc[:-1]
-
-        # Clean Institution Name
-        df_raw['Institution Name'] = df_raw['Institution Name'].astype(str).apply(
-            lambda x: re.sub(r'\([^)]*\)', '', x).replace('Boys', 'B').replace('Girls', 'G').strip()
-        )
-
-        # Convert numeric cols
-        numeric_cols = [
-            'V Minorities Sanctioned', 'V Minorities Admitted',
-            'V NonMinorities Sanctioned', 'V NonMinorities Admitted',
-            'Inter Minorities Sanctioned', 'Inter Minorities Admitted',
-            'Inter NonMinorities Sanctioned', 'Inter NonMinorities Admitted'
-        ]
-        for col in numeric_cols:
-            df_raw[col] = pd.to_numeric(df_raw[col], errors='coerce').fillna(0).astype(int)
-
-        # Process Class V
-        df_v = df_raw[['S.No', 'District', 'Institution Name',
-                       'V Minorities Sanctioned', 'V Minorities Admitted',
-                       'V NonMinorities Sanctioned', 'V NonMinorities Admitted']].copy()
-        df_v['Class'] = 'V'
-        df_v['Sanctioned'] = df_v['V Minorities Sanctioned'] + df_v['V NonMinorities Sanctioned']
-        df_v['Admitted'] = df_v['V Minorities Admitted'] + df_v['V NonMinorities Admitted']
-
-        # Process Inter
-        df_inter = df_raw[['S.No', 'District', 'Institution Name',
-                           'Inter Minorities Sanctioned', 'Inter Minorities Admitted',
-                           'Inter NonMinorities Sanctioned', 'Inter NonMinorities Admitted']].copy()
-        df_inter['Class'] = 'Inter 1st Year'
-        df_inter['Sanctioned'] = df_inter['Inter Minorities Sanctioned'] + df_inter['Inter NonMinorities Sanctioned']
-        df_inter['Admitted'] = df_inter['Inter Minorities Admitted'] + df_inter['Inter NonMinorities Admitted']
-
-        # Combine and calculate
-        df_final = pd.concat([df_v, df_inter], ignore_index=True)
-        df_final['Vacancies'] = df_final['Sanctioned'] - df_final['Admitted']
-        df_final = df_final[['S.No', 'District', 'Institution Name', 'Class', 'Sanctioned', 'Admitted', 'Vacancies']]
-
-        # Download CSV
-        csv_buffer = io.StringIO()
-        df_final.to_csv(csv_buffer, index=False)
-        csv_data = csv_buffer.getvalue()
-
-        st.success("✅ File processed successfully!")
-
-        st.download_button(
-            label="📥 Download Cleaned CSV",
-            data=csv_data,
-            file_name="cleaned_admission_data.csv",
-            mime="text/csv"
-        )
+        # Determine extension and read both files
+        ext1 = uploaded_main.name.split('.')[-1].lower()
+        ext2 = uploaded_attendance.name.split('.')[-1].lower()
+
+        if ext1 == 'csv':
+            main_df = pd.read_csv(uploaded_main, skiprows=4)
+        else:
+            main_df = pd.read_excel(uploaded_main, skiprows=4)
+
+        if ext2 == 'csv':
+            attendance_df = pd.read_csv(uploaded_attendance)
+        else:
+            attendance_df = pd.read_excel(uploaded_attendance)
+
+        st.success("✅ Both files uploaded and read successfully!")
+
+        new_df = transform_file(main_df, attendance_df)
+        st.dataframe(new_df.head())
+
+        output = io.BytesIO()
+        with pd.ExcelWriter(output, engine='xlsxwriter') as writer:
+            new_df.to_excel(writer, index=False, sheet_name='Sheet1')
+            worksheet = writer.sheets['Sheet1']
+
+            # Set wider column widths (20 characters)
+            for i, col in enumerate(new_df.columns):
+                worksheet.set_column(i, i, 20)
+
+        st.download_button("📥 Download Converted Excel File", output.getvalue(), file_name="converted_output.xlsx")
 
     except Exception as e:
-        st.error(f"❌ Error processing file: {e}")
+        st.error(f"❌ Error while processing files: {e}")
+"""
+
+# ----------------- Save Streamlit Code -----------------------
+with open("app_file_filter.py", "w") as f:
+    f.write(dashboard_code)
+
+# ----------------- Ngrok Setup & Streamlit Launch ------------------
+ngrok.set_auth_token("30VAe4T9qTjFG7urJrdYiwizPYO_3BVhHNvCaLGXkWDVAtnmu")
+
+# Function to run Streamlit
+def run():
+    os.system("streamlit run app_file_filter.py")
+
+# Start Streamlit in background thread
+thread = threading.Thread(target=run)
+thread.start()
+
+# Give Streamlit time to boot
+time.sleep(5)
+
+# Close existing tunnels if any
+for tunnel in ngrok.get_tunnels():
+    ngrok.disconnect(tunnel.public_url)
+
+# Open a new ngrok tunnel
+public_url = ngrok.connect(addr=8501)
+print("🔗 Public URL:", public_url)