Nameerror traceback (последний звонок в последний раз) ⇐ Python

[Anonymous]

Я пытался запустить эту программу ниже без какого -либо успеха из -за ошибки Traceback, которую я не понимаю, поскольку функция четко определена. Любые предложения очень ценится. Я работаю на Windows10, Jupyter Notebook, Python3. Я надеюсь, что информации достаточно, чтобы предоставить некоторые указатели. < /P>
"""
Multi processing in Python, threading
"""

import pandas as pd
import timeit, sys
import numpy as np
import multiprocess as mp

df = pd.read_csv("C:/files/data.csv", encoding="UTF-8")

df['start-digits'] = None

startTime = timeit.default_timer()

def strip_digits(x):
return str(x)[:4]

def zip_handler(x):
x['start-digits'] = x['Zip Codes'].apply(strip_digits)
return x

def parallelize(dataframe, func):
dataframe_split = np.array_split(dataframe, partitions)
pool = mp.Pool(cores)
dataframe_return = pd.concat(pool.map(func, dataframe_split), ignore_index=True)
pool.close()

return dataframe_return

if __name__ == '__main__':
#mp.set_start_method('spawn')

cores = mp.cpu_count()
partitions = cores

df = parallelize(df, zip_handler)

group_dataframe = df.groupby(['Zip Codes'])
size_of_group = group_dataframe.size()

print(size_of_group)
print(group_dataframe.get_group(2443))

stopTime = timeit.default_timer() - startTime
round_time = round(stopTime, 6)

print('')
print(round_time/60, 'min handle time')
print('cpu threads', cores)
print('split size', partitions)
< /code>

RemoteTraceback Traceback (most recent call last)
RemoteTraceback:
"""
Traceback (most recent call last):
File "C:\Users\trevo\anaconda3\lib\site-packages\multiprocess\pool.py", line 125, in worker
result = (True, func(*args, **kwds))
File "C:\Users\trevo\anaconda3\lib\site-packages\multiprocess\pool.py", line 48, in mapstar
return list(map(*args))
File "", line 20, in zip_handler
NameError: name 'strip_digits' is not defined
"""

The above exception was the direct cause of the following exception:

NameError Traceback (most recent call last)
in
35 partitions = cores
36
---> 37 df = parallelize(df, zip_handler)
38
39 group_dataframe = df.groupby(['Zip Codes'])

in parallelize(dataframe, func)
24 dataframe_split = np.array_split(dataframe, partitions)
25 pool = mp.Pool(cores)
---> 26 dataframe_return = pd.concat(pool.map(func, dataframe_split), ignore_index=True)
27 pool.close()
28

~\anaconda3\lib\site-packages\multiprocess\pool.py in map(self, func, iterable, chunksize)
362 in a list that is returned.
363 '''
--> 364 return self._map_async(func, iterable, mapstar, chunksize).get()
365
366 def starmap(self, func, iterable, chunksize=None):

~\anaconda3\lib\site-packages\multiprocess\pool.py in get(self, timeout)
769 return self._value
770 else:
--> 771 raise self._value
772
773 def _set(self, i, obj):

NameError: name 'strip_digits' is not defined


Подробнее здесь: https://stackoverflow.com/questions/667 ... -call-last