?

?

代碼如下:

def memory_usage_mb(df, *args, **kwargs):"""Dataframe memory usage in MB. """return df.memory_usage(*args, **kwargs).sum() / 1024**2def reduce_memory_usage(df, deep=True, verbose=True, categories=True):# All types that we want to change for "lighter" ones.# int8 and float16 are not include because we cannot reduce# those data types.# float32 is not include because float16 has too low precision.numeric2reduce = ["int16", "int32", "int64", "float64"]start_mem = 0if verbose:start_mem = memory_usage_mb(df, deep=deep)for col, col_type in df.dtypes.iteritems():best_type = Noneif col_type == "object":df[col] = df[col].astype("category")best_type = "category"elif col_type in numeric2reduce:downcast = "integer" if "int" in str(col_type) else "float"df[col] = pd.to_numeric(df[col], downcast=downcast)best_type = df[col].dtype.name# Log the conversion performed.if verbose and best_type is not None and best_type != str(col_type):print(f"Column '{col}' converted from {col_type} to {best_type}")if verbose:end_mem = memory_usage_mb(df, deep=deep)diff_mem = start_mem - end_mempercent_mem = 100 * diff_mem / start_memprint(f"Memory usage decreased from"f" {start_mem:.2f}MB to {end_mem:.2f}MB"f" ({diff_mem:.2f}MB, {percent_mem:.2f}% reduction)")return df

?

%%time import multiprocessinglists=[train,test] with multiprocessing.Pool() as pool:train,test = pool.map(reduce_memory_usage, lists)#這里的map就是傳入參數的意思

?

創作挑戰賽新人創作獎勵來咯，堅持創作打卡瓜分現金大獎

總結

以上是生活随笔為你收集整理的多进程减少多个文件的内存占用的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。