Tentei reescrever alguns códigos de leitura csv para poder executá-los em vários núcleos no Python 3.2.2. Tentei usar o Pool
objeto de multiprocessamento, que adaptei de exemplos de trabalho (e já trabalhei para mim em outra parte do meu projeto). Encontrei uma mensagem de erro que achei difícil de decifrar e solucionar.
O erro:
Traceback (most recent call last):
File "parser5_nodots_parallel.py", line 256, in <module>
MG,ppl = csv2graph(r)
File "parser5_nodots_parallel.py", line 245, in csv2graph
node_chunks)
File "/Library/Frameworks/Python.framework/Versions/3.2/lib/python3.2/multiprocessing/pool.py", line 251, in map
return self.map_async(func, iterable, chunksize).get()
File "/Library/Frameworks/Python.framework/Versions/3.2/lib/python3.2/multiprocessing/pool.py", line 552, in get
raise self._value
AttributeError: __exit__
O código relevante:
import csv
import time
import datetime
import re
from operator import itemgetter
from multiprocessing import Pool
import itertools
def chunks(l,n):
"""Divide a list of nodes `l` in `n` chunks"""
l_c = iter(l)
while 1:
x = tuple(itertools.islice(l_c,n))
if not x:
return
yield x
def csv2nodes(r):
strptime = time.strptime
mktime = time.mktime
l = []
ppl = set()
pattern = re.compile(r"""[A-Za-z0-9"/]+?(?=[,\n])""")
for row in r:
with pattern.findall(row) as f:
cell = int(f[3])
id = int(f[2])
st = mktime(strptime(f[0],'%d/%m/%Y'))
ed = mktime(strptime(f[1],'%d/%m/%Y'))
# collect list
l.append([(id,cell,{1:st,2: ed})])
# collect separate sets
ppl.add(id)
return (l,ppl)
def csv2graph(source):
MG=nx.MultiGraph()
# Remember that I use integers for edge attributes, to save space! Dic above.
# start: 1
# end: 2
p = Pool()
node_divisor = len(p._pool)
node_chunks = list(chunks(source,int(len(source)/int(node_divisor))))
num_chunks = len(node_chunks)
pedgelists = p.map(csv2nodes,
node_chunks)
ll = []
ppl = set()
for l in pedgelists:
ll.append(l[0])
ppl.update(l[1])
MG.add_edges_from(ll)
return (MG,ppl)
with open('/Users/laszlosandor/Dropbox/peers_prisons/python/codetenus_test.txt','r') as source:
r = source.readlines()
MG,ppl = csv2graph(r)
Qual é uma boa maneira de solucionar isso?
None
devido a problemas de escopo.