Python中的数据Pickle错误

Question

我需要在数据Pickle中保存我的训练数据集。这是密码。执行此代码时出错。如何修复此错误。我需要在两个pickle中保存featureCounts和labelCounts变量。你知道吗

from __future__ import division
import collections
import math
import pickle

class TrainClassifier:
    def __init__(self, arffFile):
        self.trainingFile = arffFile
        self.features = {}
        self.featureNameList = []
        self.featureCounts = collections.defaultdict(lambda: 1)
        self.featureVectors = []
        self.labelCounts = collections.defaultdict(lambda: 0)

    def DataTraning(self):
        for fv in self.featureVectors:
            self.labelCounts[fv[len(fv)-1]] += 1 #udpate count of the label
            for counter in range(0, len(fv)-1):
                self.featureCounts[(fv[len(fv)-1], self.featureNameList[counter], fv[counter])] += 1

        for label in self.labelCounts:
            for feature in self.featureNameList[:len(self.featureNameList)-1]:
                self.labelCounts[label] += len(self.features[feature])

    def GetValues(self):
        file = open(self.trainingFile, 'r')

        for line in file:
            if line[0] != '@':  #start of actual data
                self.featureVectors.append(line.strip().lower().split(','))
            else:   #feature definitions
                if line.strip().lower().find('@data') == -1 and (not line.lower().startswith('@relation')):
                    self.featureNameList.append(line.strip().split()[1])
                    self.features[self.featureNameList[len(self.featureNameList) - 1]] = line[line.find('{')+1: line.find('}')].strip().split(',')

        file.close()

    def SaveOnPickle(self):
        f = open('dict.pickle', 'wb')
        pickle.dump(self.labelCounts, f)
        f.close()

if __name__ == "__main__":
    Predic = TrainClassifier("Military.arff")
    Predic.GetValues()
    Predic.DataTraning()
    Predic.SaveOnPickle()

这是错误

Traceback (most recent call last):
  File "C:\wamp64\www\M360\M360py\src\TrainClassifier.py", line 69, in <module>
    Predic.SaveOnPickle()
  File "C:\wamp64\www\M360\M360py\src\TrainClassifier.py", line 43, in SaveOnPickle
    pickle.dump(self.labelCounts, f)
  File "C:\Users\Udara\AppData\Roaming\NetBeans\8.1\jython-2.7.0\Lib\pickle.py", line 1370, in dump
    Pickler(file, protocol).dump(obj)
  File "C:\Users\Udara\AppData\Roaming\NetBeans\8.1\jython-2.7.0\Lib\pickle.py", line 224, in dump
    self.save(obj)
  File "C:\Users\Udara\AppData\Roaming\NetBeans\8.1\jython-2.7.0\Lib\pickle.py", line 331, in save
    self.save_reduce(obj=obj, *rv)
  File "C:\Users\Udara\AppData\Roaming\NetBeans\8.1\jython-2.7.0\Lib\pickle.py", line 401, in save_reduce
    save(args)
  File "C:\Users\Udara\AppData\Roaming\NetBeans\8.1\jython-2.7.0\Lib\pickle.py", line 286, in save
    f(self, obj) # Call unbound method with explicit self
  File "C:\Users\Udara\AppData\Roaming\NetBeans\8.1\jython-2.7.0\Lib\pickle.py", line 562, in save_tuple
    save(element)
  File "C:\Users\Udara\AppData\Roaming\NetBeans\8.1\jython-2.7.0\Lib\pickle.py", line 286, in save
    f(self, obj) # Call unbound method with explicit self
  File "C:\Users\Udara\AppData\Roaming\NetBeans\8.1\jython-2.7.0\Lib\pickle.py", line 746, in save_global
    raise PicklingError(
pickle.PicklingError: Can't pickle <function <lambda> at 0x5>: it's not found as __main__.<lambda>

Answer 1

您不能序列化self.labelCounts，因为它是一个带有lambda的defaultdict（这没问题）：这里有一个问题：Pickle不能序列化函数。你知道吗

你写道：

self.labelCounts = collections.defaultdict(lambda: 0)

但您很幸运：这里不需要lambda（对于列表之类的可变对象需要lambda，但0没有问题），只需执行以下操作：

self.labelCounts = collections.defaultdict(0)

（当然，对于你的另一个dict featureCounts来说，这是同样的问题和解决方案）。这样做：

self.featureCounts = collections.defaultdict(1)