import pandas as pd

orders = pd.DataFrame(
    {
        "region": [
            "East",
            "East",
            "East",
            "West",
            "West",
            "West",
            "North",
            "North",
        ],
        "channel": [
            "online",
            "store",
            "online",
            "online",
            "store",
            "store",
            "online",
            "partner",
        ],
        "order_id": [1001, 1002, 1003, 1004, 1005, 1006, 1007, 1008],
        "sales_usd": [1200, 750, 980, 1430, 1020, 650, 500, 780],
        "units": [12, 8, 10, 14, 9, 5, 4, 7],
    }
)

group_columns = ["region", "channel"]

summary = (
    orders.groupby(group_columns, as_index=False, sort=False)
    .agg(
        order_count=("order_id", "count"),
        total_sales_usd=("sales_usd", "sum"),
        avg_order_usd=("sales_usd", "mean"),
        total_units=("units", "sum"),
    )
)

summary["avg_order_usd"] = summary["avg_order_usd"].round(2)

source_total = orders["sales_usd"].sum()
summary_total = summary["total_sales_usd"].sum()
expected_groups = len(orders.loc[:, group_columns].drop_duplicates())

assert len(summary) == expected_groups
assert source_total == summary_total

print(f"pandas {pd.__version__}")
print()
print("GROUPED_SALES")
print(summary.to_string(index=False))
print()
print("VERIFY_TOTALS")
print(f"source rows: {len(orders)}")
print(f"group rows: {len(summary)}")
print(f"source sales: {source_total}")
print(f"summary sales: {summary_total}")
print("verification: grouped totals match source rows")