次のコードでは、naivebayesクラシファイアがtrainset1で正しく動作しているが、なぜtrainset2で動作していないのかが分かります。私はTextBlobからのものとnltkから直接のものの2つの分類器でそれを試しました。nltk naivebayesテキスト分類用の分類器
from textblob.classifiers import NaiveBayesClassifier
from textblob import TextBlob
from nltk.tokenize import word_tokenize
import nltk
trainset1 = [('I love this sandwich.', 'pos'),
('This is an amazing place!', 'pos'),
('I feel very good about these beers.', 'pos'),
('This is my best work.', 'pos'),
("What an awesome view", 'pos'),
('I do not like this restaurant', 'neg'),
('I am tired of this stuff.', 'neg'),
("I can't deal with this", 'neg'),
('He is my sworn enemy!', 'neg'),
('My boss is horrible.', 'neg')]
trainset2 = [('hide all brazil and everything plan limps to anniversary inflation plan initiallyis limping its first anniversary amid soaring prices', 'class1'),
('hello i was there and no one came', 'class2'),
('all negative terms like sad angry etc', 'class2')]
def nltk_naivebayes(trainset, test_sentence):
all_words = set(word.lower() for passage in trainset for word in word_tokenize(passage[0]))
t = [({word: (word in word_tokenize(x[0])) for word in all_words}, x[1]) for x in trainset]
classifier = nltk.NaiveBayesClassifier.train(t)
test_sent_features = {word.lower(): (word in word_tokenize(test_sentence.lower())) for word in all_words}
return classifier.classify(test_sent_features)
def textblob_naivebayes(trainset, test_sentence):
cl = NaiveBayesClassifier(trainset)
blob = TextBlob(test_sentence,classifier=cl)
return blob.classify()
test_sentence1 = "he is my horrible enemy"
test_sentence2 = "inflation soaring limps to anniversary"
print nltk_naivebayes(trainset1, test_sentence1)
print nltk_naivebayes(trainset2, test_sentence2)
print textblob_naivebayes(trainset1, test_sentence1)
print textblob_naivebayes(trainset2, test_sentence2)
出力:
neg
class2
neg
class2
test_sentence2がはっきりCLASS1に属しますが。