LeetCode/Python/2882.py

# 2882. Drop Duplicate Rows

import sys

import pandas as pd

def dropDuplicateEmails(customers: pd.DataFrame) -> pd.DataFrame:
    return customers.drop_duplicates(subset=['email'], keep='first')


def main() -> int:

    def r(customers: pd.DataFrame, exp: pd.DataFrame) -> None:
        res: pd.DataFrame = dropDuplicateEmails(customers)
        print(f"dropDuplicateEmails({customers}) = {res} | exp: {exp}")
        pass

    r(
        pd.DataFrame.from_dict(
            {
                "customer_id": [1, 2, 3, 4, 5, 6],
                "name": ["Ella", "David", "Zachary", "Alice", "Finn", "Violet"],
                "email": [
                    "emily@example.com",
                    "michael@example.com",
                    "sarah@example.com",
                    "john@example.com",
                    "john@example.com",
                    "alice@example.com",
                ],
            }
        ),
        pd.DataFrame.from_dict(
            {
                "customer_id": [1, 2, 3, 4, 6],
                "name": ["Ella", "David", "Zachary", "Alice", "Violet"],
                "email": [
                    "emily@example.com",
                    "michael@example.com",
                    "sarah@example.com",
                    "john@example.com",
                    "alice@example.com",
                ],
            }
        ),
    )

    return 0


if __name__ == "__main__":
    sys.exit(main())