load_data.py

import sqlite3
from pathlib import Path

import pandas as pd

CSV_PATH = Path(__file__).parent / "SampleSuperstore.csv"
DB_PATH = Path(__file__).parent / "superstore.db"
TABLE_NAME = "sales"


def main():
    df = pd.read_csv(CSV_PATH)

    conn = sqlite3.connect(DB_PATH)
    df.to_sql(TABLE_NAME, conn, if_exists="replace", index=False)

    print("=== Nama Kolom ===")
    print(list(df.columns))

    print("\n=== 5 Baris Pertama ===")
    print(df.head())

    print("\n=== Total Sales per Region ===")
    query = f"""
        SELECT Region, SUM(Sales) AS Total_Sales
        FROM {TABLE_NAME}
        GROUP BY Region
        ORDER BY Total_Sales DESC
    """
    result = pd.read_sql_query(query, conn)
    print(result.to_string(index=False))

    conn.close()
    print(f"\nData berhasil disimpan ke {DB_PATH} (tabel: {TABLE_NAME})")


if __name__ == "__main__":
    main()