csv_diff_compare_two_files_by_primary_key.py

1from csv_diff import load_csv, compare
2
3# Load the data from two CSV files, specifying the primary key column
4previous_data = load_csv(open("previous.csv"), key="id")
5current_data = load_csv(open("current.csv"), key="id")
6
7# Compare the two datasets
8diff = compare(previous_data, current_data)
9
10# The result is a dictionary containing added, removed, and changed items
11print(diff)
12
13# Example output structure:
14# {
15#     'added': [],
16#     'removed': [],
17#     'changed': [
18#         {
19#             'key': '1',
20#             'changes': {'name': ['Old Name', 'New Name']}
21#         }
22#     ],
23#     'columns_added': [],
24#     'columns_removed': []
25# }