以下是我使用nltk和Python编写的代码。
import nltk
import random
from nltk.corpus import movie_reviews
#from sklearn.naive_bayes import GaussianNB
documents = [(list(movie_reviews.words(fileid)), category)
for category in movie_reviews.categories()
for fileid in movie_reviews.fileids(category)]
random.shuffle(documents)
#print(documents[1:3])
all_words= []
for w in movie_reviews.words():
all_words.append(w.lower())
all_words = nltk.FreqDist(all_words)
#print(all_words.most_common(15))
#print(all_words["great"])
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
#print((find_features(movie_reviews.words('neg/cv000_29416.txt'))))
featuresets = [(find_features(rev), category) for (rev, category) in documents]
training_set = featuresets[:1900]
testing_set = featuresets[1900:]
classifier = nltk.NaiveBayesClassifier.train(training_set)
print("Naive Bayes Algo Accuracy percent:", (nltk.classify.accuracy(classifier, testing_set))*100)
classifier.show_most_informative_features(15)
# clf = GaussianNB()
# clf.fit(training_set)
我收到此错误
追踪(最近一次调用最后一次): 文件" naive_bayes_application.py",第37行,in classifier = nltk.NaiveBayesClassifier.train(training_set) 文件" C:\ Users \ jshub \ Anaconda3 \ lib \ site-packages \ nltk \ classify \ naivebayes.py", 198号线,在火车上 feature_freqdist [label,fname] [fval] + = 1 TypeError:不可用类型:'设置'
请帮忙。
答案 0 :(得分:1)
在构造特征字典时,在def find_features中传递普通括号中的值。
示例:
HR
Banks 1 1
Banks 2 3
Banks 3 1