데이터 타입 다운캐스팅(Downcasting) & 카테고리 최적화

import pandas as pd
import numpy as np

def reduce_mem_usage(df: pd.DataFrame) -> pd.DataFrame:
    start_mem = df.memory_usage(deep=True).sum() / (1024**2)
    print(f"시작 메모리: {start_mem:.2f} MB")
    
    for col in df.columns:
        col_type = df[col].dtype
        if str(col_type).startswith('int'):
            c_min, c_max = df[col].min(), df[col].max()
            if c_min >= np.iinfo(np.int8).min and c_max <= np.iinfo(np.int8).max:
                df[col] = df[col].astype(np.int8)
            elif c_min >= np.iinfo(np.int16).min and c_max <= np.iinfo(np.int16).max:
                df[col] = df[col].astype(np.int16)
            elif c_min >= np.iinfo(np.int32).min and c_max <= np.iinfo(np.int32).max:
                df[col] = df[col].astype(np.int32)
        elif str(col_type).startswith('float'):
            df[col] = df[col].astype(np.float32)
        elif col_type == object:
            if df[col].nunique() / len(df[col]) < 0.5:
                df[col] = df[col].astype('category')
                
    end_mem = df.memory_usage(deep=True).sum() / (1024**2)
    print(f"최적화 후 메모리: {end_mem:.2f} MB (절감률: {(1 - end_mem/start_mem)*100:.1f}%)")
    return df