Question

#Version1 
main_df = pd.read_csv('Million_rows.csv')
def myfunction(args*,start,end):
   for i in range(start,end):
    if condition1:
        for item in mainTreeSearch:
            ...
                lock.acquire()
                ###write to main_df
                lock.release()
                noLuck = False
                break
        if noLuck and Acondition:
            lock.acquire()
            ###write to main_df
            lock.release()
    elif
    ... various asymmetric decision trees...

t1 = Thread(target=myfuct, args=(args*),0,250))
t2 = Thread(target=myfuct, args=(args*),250,500))
t3 = Thread(target=myfuct, args=(args*),500,750))
t4 = Thread(target=myfuct, args=(args*),750,1000))

我的问题是我不知道如何为剩下的行提供线程，我尝试Queue，但没有成功。

#Version2 
def myfuntion(args*,q)
  while True:
    q.get()
    ....same search as above...without locking
    q.task_done() 

q = Queue(maxsize=0)
num_threads = 5
threads =[]
for i in range(num_threads):
   worker = Thread(target=myfunction, args=(args*))
   worker.setDaemon(True)
   threads.append(worker)
   worker.start()

for x in range(1000):
  #time.sleep(.005) 
  q.put(x)

q.join()

在没有sleep的版本2中，1个线程占用所有数据或随机崩溃。

在版本1中，我应该使用threading.nodify()机制，如果是这样，它是如何实现的？

Answer 1

我将其重新格式化为此并且按预期工作

from Queue import Queue
import threading

q = Queue()


def myfuntion(q):
    while True:
        val = q.get()
        print('\n' + str(threading.currentThread()))
        print('\n' + str(val))
        q.task_done()


num_threads = 5
threads = []
for i in range(num_threads):
    worker = threading.Thread(target=myfuntion, args=(q,))
    worker.setDaemon(True)
    threads.append(worker)
    worker.start()

for x in range(1000):
    q.put(x)

q.join()

检查出来。我认为你传递参数的方式是错误的。

如何在线程之间进行通信以请求下一个块？

1 个答案: