我收到此错误 DataFrame的真值不明确。使用a.empty,a.bool(),a.item(),a.any()或a.all()。
import nltk
def buildVocabulary(preprocessedTrainingSet):
all_words = []
for text in preprocessedTrainingSet:
all_words.extend(text)
wordlist = nltk.FreqDist(all_words)
word_features = wordlist.keys()
return word_features
def extract_features(text):
text_words = set(text)
features = {}
for word in word_features:
features['contains(%s)' % word] = (word in text_words)
return features
word_features = buildVocabulary(preprocessedTrainingSet)
trainingFeatures = nltk.classify.apply_features(extract_features,preprocessedTrainingSet)
NBayesClassifier = nltk.NaiveBayesClassifier.train(trainingFeatures)
DataFrame的真值不明确。使用a.empty,a.bool(),a.item(),a.any()或a.all()。