>>> train = [
... (dict(a=1,b=1,c=1), 'y'),
... (dict(a=1,b=1,c=1), 'x'),
... (dict(a=1,b=1,c=0), 'y'),
... (dict(a=0,b=1,c=1), 'x'),
... (dict(a=0,b=1,c=1), 'y'),
... (dict(a=0,b=0,c=1), 'y'),
... (dict(a=0,b=1,c=0), 'x'),
... (dict(a=0,b=0,c=0), 'x'),
... (dict(a=0,b=1,c=1), 'y'),
... ]
>>>
>>>
>>> test = [
... (dict(a=1,b=0,c=1)), # unseen
... (dict(a=1,b=0,c=0)), # unseen
... (dict(a=0,b=1,c=1)), # seen 3 times, labels=y,y,x
... (dict(a=0,b=1,c=0)), # seen 1 time, label=x
... ]
>>>
>>>
>>> import nltk
>>> classifier = nltk.classify.DecisionTreeClassifier.train(train, entropy_cutoff=0, support_cutoff=0)
>>> sorted(classifier.labels())
['x', 'y']
>>> print(classifier)
c=0? .................................................. x
a=0? ................................................ x
a=1? ................................................ y
c=1? .................................................. y
>>> classifier.batch_classify(test)
['y', 'y', 'y', 'x']
>>> for pdist in classifier.batch_prob_classify(test):
... print('%.4f %.4f' % (pdist.prob('x'), pdist.prob('y')))
...
Traceback (most recent call last):
File "", line 1, in
File "//anaconda/lib/python2.7/site-packages/nltk/classify/api.py", line 87, in batch_prob_classify
return [self.prob_classify(fs) for fs in featuresets]
File "//anaconda/lib/python2.7/site-packages/nltk/classify/api.py", line 67, in prob_classify
raise NotImplementedError()
NotImplementedError
>>>
问题出在batch_prob_classify函数上。有谁能建议如何解决这个问题,以及如何得到概率分布值。在