数据内存压缩

主要的思想是改变int和float字段的占位，使用尽量小的占位存储字段

## reduce memory

def reduce_mem(df, verbose=True):
    start_mem = df.memory_usage().sum() / 1024**2
    numerics = ['int16', 'int32', 'int64', 'float16', 'float32', 'float64']
    
    for col in df.columns:
        col_type = df[col].dtypes
        if col_type in numerics:
            c_min = df[col].min()
            c_max = df[col].max()
            if str(col_type)[:3] == 'int':
                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 c_min > np.iinfo(np.int64).min and c_max < np.iinfo(np.int64).max:
                    df[col] = df[col].astype(np.int64)
            elif str(col_type)[:5] == 'float':
                if c_min > np.finfo(np.float16).min and c_max < np.finfo(np.float16).max:
                    df[col] = df[col].astype(np.float16)
                elif c_min > np.finfo(np.float32).min and c_max < np.finfo(np.float32).max:
                    df[col] = df[col].astype(np.float32)
                else:
                    df[col] = df[col].astype(np.float64)
            else:
                continue
                
    end_mem = df.memory_usage().sum() / 1024**2
    print('Memroy usage after optimization is {:.2f} MB'.format(end_mem))
    print('Decrease by {:.1f}%'.format(100 * (start_mem - end_mem) / start_mem))
    return df