压缩pandas中dataframe内存

标签：start   nan   support   init   reduce   压缩   asi   apach   ace   

从这里找的一个宝贝源码，可以大大缓解内存问题。https://www.kaggle.com/arjanso/reducing-dataframe-memory-size-by-65/code

# @from: https://www.kaggle.com/arjanso/reducing-dataframe-memory-size-by-65/code
# @liscense: Apache 2.0
# @author: weijian
def reduce_mem_usage(props):
    # 计算当前内存
    start_mem_usg = props.memory_usage().sum() / 1024 ** 2
    print("Memory usage of the dataframe is :", start_mem_usg, "MB")
    
    # 哪些列包含空值，空值用-999填充。why：因为np.nan当做float处理
    NAlist = []
    for col in props.columns:
        # 这里只过滤了objectd格式，如果你的代码中还包含其他类型，请一并过滤
        if (props[col].dtypes != object):
            
            print("**************************")
            print("columns: ", col)
            print("dtype before", props[col].dtype)
            
            # 判断是否是int类型
            isInt = False
            mmax = props[col].max()
            mmin = props[col].min()
            
            # Integer does not support NA, therefore Na needs to be filled
            if not np.isfinite(props[col]).all():
                NAlist.append(col)
                props[col].fillna(-999, inplace=True) # 用-999填充
                
            # test if column can be converted to an integer
            asint = props[col].fillna(0).astype(np.int64)
            result = np.fabs(props[col] - asint)
            result = result.sum()
            if result < 0.01: # 绝对误差和小于0.01认为可以转换的，要根据task修改
                isInt = True
            
            # make interger / unsigned Integer datatypes
            if isInt:
                if mmin >= 0: # 最小值大于0，转换成无符号整型
                    if mmax <= 255:
                        props[col] = props[col].astype(np.uint8)
                    elif mmax <= 65535:
                        props[col] = props[col].astype(np.uint16)
                    elif mmax <= 4294967295:
                        props[col] = props[col].astype(np.uint32)
                    else:
                        props[col] = props[col].astype(np.uint64)
                else: # 转换成有符号整型
                    if mmin > np.iinfo(np.int8).min and mmax < np.iinfo(np.int8).max:
                        props[col] = props[col].astype(np.int8)
                    elif mmin > np.iinfo(np.int16).min and mmax < np.iinfo(np.int16).max:
                        props[col] = props[col].astype(np.int16)
                    elif mmin > np.iinfo(np.int32).min and mmax < np.iinfo(np.int32).max:
                        props[col] = props[col].astype(np.int32)
                    elif mmin > np.iinfo(np.int64).min and mmax < np.iinfo(np.int64).max:
                        props[col] = props[col].astype(np.int64)  
            else: # 注意：这里对于float都转换成float16，需要根据你的情况自己更改
                props[col] = props[col].astype(np.float16)
            
            print("dtype after", props[col].dtype)
            print("********************************")
    print("___MEMORY USAGE AFTER COMPLETION:___")
    mem_usg = props.memory_usage().sum() / 1024**2 
    print("Memory usage is: ",mem_usg," MB")
    print("This is ",100*mem_usg/start_mem_usg,"% of the initial size")
    return props, NAlist

压缩pandas中dataframe内存

标签：start   nan   support   init   reduce   压缩   asi   apach   ace   

原文地址：https://www.cnblogs.com/duoba/p/12431544.html