pandas groupby로 월별 요약표를 만들고 원본 합계와 확인하기

order_id,order_date,team,units,amount
O001,2026-01-05,North,2,40
O002,2026-01-20,South,3,60
O003,2026-02-02,North,1,25
O004,2026-02-18,South,4,100
O005,2026-02-28,North,2,50
O006,2026-03-03,South,5,125
O007,2026-03-15,North,1,30

from pathlib import Path
import pandas as pd

SOURCE = Path("monthly_orders.csv")
OUTPUT_DIR = Path("outputs") / "monthly_summary_result"
OUTPUT = OUTPUT_DIR / "monthly_summary.csv"
REQUIRED = ["order_id", "order_date", "units", "amount"]


def main() -> None:
    if not SOURCE.is_file():
        raise FileNotFoundError(f"Source CSV not found: {SOURCE}")
    if OUTPUT_DIR.exists():
        raise FileExistsError(f"Output folder already exists: {OUTPUT_DIR}")

    data = pd.read_csv(SOURCE, dtype={"order_id": "string"})

    missing = [name for name in REQUIRED if name not in data.columns]
    if missing:
        raise ValueError(f"Missing required columns: {missing}")
    if data.empty:
        raise ValueError("Source CSV contains no data rows.")
    if data[REQUIRED].isna().any().any():
        raise ValueError("A required field contains a missing value.")
    if data["order_id"].str.strip().eq("").any():
        raise ValueError("order_id contains a blank value.")
    if data["order_id"].duplicated().any():
        raise ValueError("Duplicate order_id found.")

    data["order_date"] = pd.to_datetime(
        data["order_date"], format="%Y-%m-%d", errors="raise"
    )
    data["units"] = pd.to_numeric(data["units"], errors="raise")
    data["amount"] = pd.to_numeric(data["amount"], errors="raise")
    data["month"] = data["order_date"].dt.to_period("M").astype(str)

    summary = (
        data.groupby("month", as_index=False, sort=True)
        .agg(
            orders=("order_id", "count"),
            units=("units", "sum"),
            amount=("amount", "sum"),
        )
    )

    source_totals = (len(data), data["units"].sum(), data["amount"].sum())
    summary_totals = (
        summary["orders"].sum(),
        summary["units"].sum(),
        summary["amount"].sum(),
    )
    if summary_totals != source_totals:
        raise RuntimeError("Monthly totals do not reconcile with the source.")

    OUTPUT_DIR.parent.mkdir(parents=True, exist_ok=True)
    OUTPUT_DIR.mkdir()
    summary.to_csv(OUTPUT, index=False)

    check = pd.read_csv(OUTPUT)
    if check.to_dict("records") != summary.to_dict("records"):
        raise RuntimeError("Saved CSV does not match the calculated summary.")

    print(f"Source rows: {len(data)}.")
    print(f"Months: {len(summary)}.")
    print(f"Verified totals: units={source_totals[1]}, amount={source_totals[2]}.")
    print(f"Output: {OUTPUT.as_posix()}")


if __name__ == "__main__":
    main()

python monthly_summary_pandas.py

month,orders,units,amount
2026-01,2,5,100
2026-02,3,7,175
2026-03,2,6,155

Source rows: 7.
Months: 3.
Verified totals: units=18, amount=430.
Output: outputs/monthly_summary_result/monthly_summary.csv