import pandas as pd

# Load the CSV files into dataframes
df1 = pd.read_csv('file1.csv')
df2 = pd.read_csv('file2.csv')

# Extract the ID columns
ids1 = set(df1['ID'])
ids2 = set(df2['ID'])

# Find IDs in file1 but not in file2
missing_in_file2 = ids1 - ids2

# Find IDs in file2 but not in file1
missing_in_file1 = ids2 - ids1

# Optionally, convert the sets to dataframes for easy export or analysis
missing_in_file2_df = pd.DataFrame(list(missing_in_file2), columns=['Missing_IDs'])
missing_in_file1_df = pd.DataFrame(list(missing_in_file1), columns=['Missing_IDs'])

# Save the missing IDs to new CSV files if needed
missing_in_file2_df.to_csv('missing_in_file2.csv', index=False)
missing_in_file1_df.to_csv('missing_in_file1.csv', index=False)

# Print the results
print("IDs in file1 but not in file2:", missing_in_file2)
print("IDs in file2 but not in file1:", missing_in_file1)