python减少pandas数据的内存占用_python pandas 关闭表格释放内存-优快云博客

本文链接：https://blog.youkuaiyun.com/Cameback_Tang/article/details/124389493

这两个函数`reduce_mem_usage`和`reduce_mem2`专注于减少DataFrame的内存使用。它们通过检查数据类型并将其转换为更节省内存的格式（如int8、int16、float16等）来实现这一目标。对于非数值类型，它们会将其转换为category类型。这些方法有助于在处理大规模数据集时优化内存效率。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

def reduce_mem_usage(df):
    start_mem = df.memory_usage().sum()
    print('Memory usage of dataframe is {:.2f} MB'.format(start_mem))
    for col in df.columns:
        col_type = df[col].dtype
        if col_type != object:
            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)
            else:
                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:
            df[col] = df[col].astype('category')
    end_mem = df.memory_usage().sum()
    print('Memory usage after optimization is: {:.2f} MB'.format(end_mem))
    print('Decreased by {:.1f}%'.format(100 * (start_mem - end_mem) / start_mem))
    return df

def reduce_mem2(df):
    start_mem = df.memory_usage().sum()
    print('Memory usage of dataframe is {:.2f} MB'.format(start_mem))
    
    # 把计数型变量由float改int
    nx_fea = ['n0', 'n1', 'n2', 'n4', 'n5', 'n6', 'n7', 'n8', 'n9', 'n10', 'n11', 'n12', 'n13', 'n14']
    for col in nx_fea:
        df[col] = df[col].astype(np.int8)
   
    end_mem = df.memory_usage().sum()
    print('Memory usage after optimization is: {:.2f} MB'.format(end_mem))
    print('Decreased by {:.1f}%'.format(100 * (start_mem - end_mem) / start_mem))
    return df