Upload 6 files

processAttendance/__init__.py

@@ -0,0 +1,2 @@
+from processAttendance.findMisMatchedStudents import *
+from processAttendance.convertXlsxToCsv import *

processAttendance/convertXlsxToCsv.py

@@ -0,0 +1,35 @@
+import pandas as pd
+
+def extract_route_emails_and_timestamps(xlsx_file, output_csv_file):
+    # Load the Excel file
+    sheets = pd.read_excel(xlsx_file, sheet_name=None)
+    
+    # Prepare a list to hold the data
+    data = []
+
+    # Iterate over each sheet
+    for sheet_name, sheet_data in sheets.items():
+        # Extract the route number from the sheet name
+        route_no = sheet_name
+        
+        # Remove spaces from column names
+        sheet_data.columns = sheet_data.columns.str.replace(' ', '')
+        
+        # Check if required columns exist in the sheet
+        if 'EmailAddress' in sheet_data.columns and 'Timestamp' in sheet_data.columns:
+            # Append the route number, email IDs, and timestamps to the data list
+            for _, row in sheet_data.iterrows():
+                data.append({'routeNo': route_no, 'Email Address': row['EmailAddress'], 'Timestamp': row['Timestamp']})
+
+    # Convert the list of data to a DataFrame
+    result_df = pd.DataFrame(data)
+    
+    # Save the DataFrame to a CSV file
+    result_df.to_csv(output_csv_file, index=False)
+
+    print(f"CSV file '{output_csv_file}' created successfully.")
+
+if __name__ == "_main_":
+    xlsx_file = "/Users/sarathrajan/Documents/Projects/haversineRestAPI/utilities/datasetCreate/syntheticAlteredAttendance.xlsx"
+    output_csv_file = "attendance.csv"
+    extract_route_emails_and_timestamps(xlsx_file, output_csv_file)

processAttendance/findMisMatchedStudents.py

@@ -0,0 +1,40 @@
+import pandas as pd
+
+def find_mismatched_students(assigned_csv, boarded_csv, output_csv):
+    # Load the CSV files
+    assigned_df = pd.read_csv(assigned_csv)
+    boarded_df = pd.read_csv(boarded_csv)
+    
+    # Clean up the 'Email Address' column (remove whitespaces and convert to lowercase)
+    assigned_df['Email Address'] = assigned_df['Email Address'].str.replace(r'\s+', '', regex=True).str.lower()
+    boarded_df['Email Address'] = boarded_df['Email Address'].str.replace(r'\s+', '', regex=True).str.lower()
+    
+    # Merge the dataframes on 'Email Address' to compare assigned and boarded buses
+    merged_df = pd.merge(boarded_df, assigned_df, on='Email Address', how='left', suffixes=('_boarded', '_assigned'))
+
+    # Convert route numbers to strings and clean up the data
+    merged_df['routeNo_boarded'] = merged_df['routeNo_boarded'].astype(str).str.replace(r'\s+', '', regex=True).str.lower()
+    merged_df['routeNo_assigned'] = merged_df['routeNo_assigned'].astype(str).str.replace(r'\s+', '', regex=True).str.lower()
+
+    # Identify mismatched students (where boarded routeNo is not equal to assigned routeNo or assigned is NaN)
+    mismatched_students_df = merged_df[
+        (merged_df['routeNo_boarded'] != merged_df['routeNo_assigned']) | 
+        merged_df['routeNo_assigned'].isna()
+    ]
+    
+    # Select relevant columns to include in the output
+    mismatched_students_df = mismatched_students_df[['registerNo', 'name', 'Email Address', 'routeNo_assigned', 'routeNo_boarded']]
+
+    # Save the results to a new CSV file
+    mismatched_students_df.to_csv(output_csv, index=False)
+
+    print(f"Mismatched students have been saved to '{output_csv}'.")
+
+
+if __name__ == "__main__":
+    # Example usage:
+    assigned_csv = 'busAssignedList.csv'  # Replace with the path to your assigned CSV file
+    boarded_csv = 'attendance.csv'    # Replace with the path to your boarded CSV file
+    output_csv = 'mismatched_students.csv'  # Replace with your desired output file name
+
+    find_mismatched_students(assigned_csv, boarded_csv, output_csv)

processAttendance/mismatchedStudents.csv

@@ -0,0 +1,16 @@
+registerNo,name,Email Address,routeNo_assigned,routeNo_boarded
+,,[email protected],nan,1
+23BCE1030,Alan Price,[email protected],1,3
+21BMV1032,Alan Ramirez,[email protected],1,3
+23BEE1001,Alan Rivera,[email protected],1,3
+24PHD1037,Albert Smith,[email protected],1a,20a
+22BBH1027,Albert Taylor,[email protected],1a,20a
+24BCE1009,Albert Turner,[email protected],1a,20a
+24BLA1046,Albert Wright,[email protected],1a,20a
+24BLB1001,Alexander Alvarez,[email protected],1a,20a
+21PHD1031,Alexander Brooks,[email protected],1a,20a
+21MIS1028,Deborah Reyes,[email protected],27a,34
+24BEC1026,Deborah Scott,[email protected],27a,34
+23BME1003,Deborah Thomas,[email protected],27a,34
+23BMV1028,Deborah Watson,[email protected],27a,34
+24BMV1023,Deborah Williams,[email protected],27a,34