7

我有以下功能

from multiprocessing import Pool
def do_comparison(tupl):
    x, y = tupl # unpack arguments
    return compare_clusters(x, y)

def distance_matrix(clusters, condensed=False):
    pool = Pool()
    values = pool.map_async(do_comparison, itertools.combinations(clusters, 2)).get()
    do stuff

是否可以打印进度pool.map_async(do_comparison, itertools.combinations(clusters, 2)).get()？我通过像这样向 do_comparison 添加计数来尝试它

count = 0
def do_comparison(tupl):
    global count
    count += 1
    if count % 1000 == 0:
        print count
    x, y = tupl # unpack arguments
    return compare_clusters(x, y)

但除了看起来不是一个好的解决方案之外，这些数字直到脚本结束才会打印出来。有没有好的方法来做到这一点？

4

2 回答 2

4

I track progress as follows:

import multiprocessing
import time

class PoolProgress:
  def __init__(self,pool,update_interval=3):
    self.pool            = pool
    self.update_interval = update_interval
  def track(self, job):
    task = self.pool._cache[job._job]
    while task._number_left>0:
      print("Tasks remaining = {0}".format(task._number_left*task._chunksize))
      time.sleep(self.update_interval)


def hi(x): #This must be defined before `p` if we are to use in the interpreter
  time.sleep(x//2)
  return x

a = list(range(50))

p   = multiprocessing.Pool()
pp  = PoolProgress(p)

res = p.map_async(hi,a)

pp.track(res)
于 2016-12-12T01:33:57.247 回答
4

Richard 的解决方案适用于少量工作，但由于某种原因，它似乎在大量工作时冻结，我发现最好使用：

import multiprocessing
import time

def track_job(job, update_interval=3):
    while job._number_left > 0:
        print("Tasks remaining = {0}".format(
        job._number_left * job._chunksize))
        time.sleep(update_interval)



def hi(x): #This must be defined before `p` if we are to use in the interpreter
  time.sleep(x//2)
  return x

a = [x for x in range(50)]

p   = multiprocessing.Pool()

res = p.map_async(hi,a)

track_job(res)
于 2017-08-28T18:04:53.867 回答