我是编程新手，但是一遍又一遍地查看我的代码，看不到任何错误。我不知道如何继续进行，因为无论我尝试什么，都会弹出此错误。我将在此处发布完整代码。
任何帮助将不胜感激，谢谢！
import nltk
import random
from nltk.corpus import movie_reviews
import pickle
from nltk.classify.scikitlearn import SklearnClassifier
from sklearn.naive_bayes import MultinomialNB,BernoulliNB
from sklearn.linear_model import LogisticRegression, SGDClassifier
from sklearn.svm import SVC, LinearSVC, NuSVC
from nltk.classify import ClassifierI
from statistics import mode
class VoteClassifier(ClassifierI):
def __init__(self, *classifiers):
self._classifiers = classifiers
def classify(self, features):
votes = []
for c in self._classifiers:
v = c.classify(features)
votes.append(v)
return mode(votes)
def confidence(self, features):
votes = []
for c in self._classifiers:
v = c.classify(features)
votes.append(v)
choice_votes = votes.count(mode(votes))
conf = choice_votes / len(votes)
return conf
documents = [(list(movie_reviews.words(fileid)), category)
for category in movie_reviews.categories()
for fileid in movie_reviews.fileids(category)]
random.shuffle(documents)
all_words = []
for w in movie_reviews.words():
all_words.append(w.lower())
all_words = nltk.FreqDist(all_words)
word_features = list(all_words.keys())[:3000]
def find_features(document):
words = set(document)
features = {}
for w in word_features:
features[w] = (w in words)
return features
featuresets = [(find_features(rev), category) for (rev, category) in documents]
training_set = featuresets[:1900]
testing_set = featuresets[1900:]
# classifier = nltk.NaiveBayesClassifier.train(training_set)
classifier_f = open("naivebayes.pickle", "rb")
classifier = pickle.load(classifier_f)
classifier_f.close()
print("Original NaiveBayes accuracy percent:",(nltk.classify.accuracy(classifier, testing_set))*100)
classifier.show_most_informative_features(10)
MNB_classifier = SklearnClassifier(MultinomialNB())
MNB_classifier.train(training_set)
print("MNB_classifier accuracy percent:", (nltk.classify.accuracy(MNB_classifier, testing_set))*100)
BernoulliNB_classifier = SklearnClassifier(BernoulliNB())
BernoulliNB_classifier.train(training_set)
print("BernoulliNB_classifier accuracy percent:", (nltk.classify.accuracy(BernoulliNB_classifier, testing_set))*100)
LogisticRegression_classifier = SklearnClassifier(LogisticRegression())
LogisticRegression_classifier.train(training_set)
print("LogisticRegression_classifier accuracy percent:", (nltk.classify.accuracy(LogisticRegression_classifier, testing_set))*100)
SGDClassifier_classifier = SklearnClassifier(SGDClassifier())
SGDClassifier_classifier.train(training_set)
print("SGDClassifier_classifier accuracy percent:", (nltk.classify.accuracy(SGDClassifier_classifier, testing_set))*100)
##SVC_classifier = SklearnClassifier(SVC())
##SVC_classifier.train(training_set)
##print("SVC_classifier accuracy percent:", (nltk.classify.accuracy(SVC_classifier, testing_set))*100)
LinearSVC_classifier = SklearnClassifier(LinearSVC())
LinearSVC_classifier.train(training_set)
print("LinearSVC_classifier accuracy percent:", (nltk.classify.accuracy(LinearSVC_classifier, testing_set))*100)
NuSVC_classifier = SklearnClassifier(NuSVC())
NuSVC_classifier.train(training_set)
print("NuSVC_classifier accuracy percent:", (nltk.classify.accuracy(NuSVC_classifier, testing_set))*100)
voted_classifier = VoteClassifier(classifier,
NuSVC_classifier,
LinearSVC_classifier,
SGDClassifier_classifier,
MNB_classifier,
BernoulliNB_classifier,
LogisticRegression_classifier)
print("voted_classifier accuracy percent:", (nltk.classify.accuracy(voted_classifier, testing_set))*100)
我还尝试在顶部的类上引发NotImplementedError异常，但它并未更改Python中的输出。
这是错误：
Traceback (most recent call last):
File "code/test.py", line 109, in <module>
print("voted_classifier accuracy percent:", (nltk.classify.accuracy(voted_classifier, testing_set))*100)
File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/nltk/classify/util.py", line 87, in accuracy
results = classifier.classify_many([fs for (fs, l) in gold])
File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/nltk/classify/api.py", line 77, in classify_many
return [self.classify(fs) for fs in featuresets]
File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/nltk/classify/api.py", line 56, in classify
raise NotImplementedError()
NotImplementedError
最佳答案
如评论中所述，ClassiferI api中有一些不好的意大利面条，如代码，在重写时classify调用classify_many。考虑到ClassifierI与NaiveBayesClassifier对象紧密关联，这可能不是一件坏事。
但是对于OP中的特定用途，不欢迎使用意大利面条式代码。
TL; DR
看看https://www.kaggle.com/alvations/sklearn-nltk-voteclassifier
在长
从追溯开始，错误是从nltk.classify.util.accuracy()调用ClassifierI.classify()开始的。ClassifierI.classify()通常用于对一个文档进行分类，输入内容是具有其二进制值的功能集字典。ClassifierI.classify_many()应该分类多个文档，而输入是具有其二进制值的功能集字典的列表。
因此，快速的技巧是改写accuracy()函数的方式，以使VotedClassifier不会依赖于ClassifierI与classify()的classify_many()定义。这也意味着我们不继承ClassifierI。恕我直言，如果您不需要classify()以外的其他功能，则无需继承ClassifierI可能附带的行李：
def my_accuracy(classifier, gold):
documents, labels = zip(*gold)
predictions = classifier.classify_documents(documents)
correct = [y == y_hat for y, y_hat in zip(labels, predictions)]
if correct:
return sum(correct) / len(correct)
else:
return 0
class VotraClassifier:
def __init__(self, *classifiers):
self._classifiers = classifiers
def classify_documents(self, documents):
return [self.classify_many(doc) for doc in documents]
def classify_many(self, features):
votes = []
for c in self._classifiers:
v = c.classify(features)
votes.append(v)
return mode(votes)
def confidence(self, features):
votes = []
for c in self._classifiers:
v = c.classify(features)
votes.append(v)
choice_votes = votes.count(mode(votes))
conf = choice_votes / len(votes)
return conf
现在，如果我们用新的
my_accuracy()对象调用新的VotedClassifier：voted_classifier = VotraClassifier(nltk_nb,
NuSVC_classifier,
LinearSVC_classifier,
SGDClassifier_classifier,
MNB_classifier,
BernoulliNB_classifier,
LogisticRegression_classifier)
my_accuracy(voted_classifier, testing_set)
[出]：
0.86
注意：在随机整理文档然后提供一组用于测试分类器准确性时，存在一定的随机性。
我的建议是执行以下操作，而不是简单的
random.shuffle(documents)用各种随机种子重复实验。
对于每个随机种子，进行10倍交叉验证。