analyze.py

import sys
import pandas as pd


def analyze(path: str) -> None:
    df = pd.read_csv(path)

    print(f"=== {path} ===")
    print(f"행: {len(df):,}  열: {len(df.columns)}")
    print(f"컬럼: {list(df.columns)}\n")

    numeric = df.select_dtypes(include="number")
    if not numeric.empty:
        print("[ 수치형 통계 ]")
        stats = numeric.describe().T[["count", "mean", "std", "min", "50%", "max"]]
        stats.columns = ["count", "평균", "표준편차", "최솟값", "중앙값", "최댓값"]
        print(stats.to_string())
        print()

    categorical = df.select_dtypes(exclude="number")
    if not categorical.empty:
        print("[ 범주형 통계 ]")
        for col in categorical.columns:
            top = df[col].value_counts().head(5)
            print(f"  {col} (고유값 {df[col].nunique()}개):")
            for val, cnt in top.items():
                print(f"    {val}: {cnt}건")
        print()

    missing = df.isnull().sum()
    missing = missing[missing > 0]
    if not missing.empty:
        print("[ 결측치 ]")
        for col, cnt in missing.items():
            print(f"  {col}: {cnt}건 ({cnt / len(df):.1%})")
    else:
        print("[ 결측치 ] 없음")


if __name__ == "__main__":
    path = sys.argv[1] if len(sys.argv) > 1 else "data.csv"
    analyze(path)