nltk NaiveBayesClassifier情绪分析培训

Question

我正在NaiveBayesClassifier使用句子在Python中进行训练，这给了我下面的错误。我不知道错误可能是什么，任何帮助都将是很好的。我尝试了许多其他输入格式，但错误仍然存在。下面给出的代码：from text.classifiers import NaiveBayesClassifierfrom text.blob import TextBlobtrain = [('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') ]test = [('The beer was good.', 'pos'),        ('I do not enjoy my job', 'neg'),        ("I ain't feeling dandy today.", 'neg'),        ("I feel amazing!", 'pos'),        ('Gary is a friend of mine.', 'pos'),        ("I can't believe I'm doing this.", 'neg') ]classifier = nltk.NaiveBayesClassifier.train(train)我包括下面的追溯。Traceback (most recent call last):  File "C:\Users\5460\Desktop\train01.py", line 15, in <module>    all_words = set(word.lower() for passage in train for word in word_tokenize(passage[0]))  File "C:\Users\5460\Desktop\train01.py", line 15, in <genexpr>    all_words = set(word.lower() for passage in train for word in word_tokenize(passage[0]))  File "C:\Python27\lib\site-packages\nltk\tokenize\__init__.py", line 87, in word_tokenize    return _word_tokenize(text)  File "C:\Python27\lib\site-packages\nltk\tokenize\treebank.py", line 67, in tokenize    text = re.sub(r'^\"', r'``', text)  File "C:\Python27\lib\re.py", line 151, in sub    return _compile(pattern, flags).sub(repl, string, count)TypeError: expected string or buffer

Answer 1

有关NLTK贝叶斯分类器的数据结构的教程很棒。从更高的角度来看，我们可以将其视为

我们有带有情感标签的输入句子：

training_data = [('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')]

让我们将特征集视为单个单词，因此我们从训练数据中提取所有可能单词的列表（我们称之为词汇），如下所示：

from nltk.tokenize import word_tokenize

from itertools import chain

vocabulary = set(chain(*[word_tokenize(i[0].lower()) for i in training_data]))

本质上，vocabulary这里是@ 275365的相同all_word

>>> all_words = set(word.lower() for passage in training_data for word in word_tokenize(passage[0]))

>>> vocabulary = set(chain(*[word_tokenize(i[0].lower()) for i in training_data]))

>>> print vocabulary == all_words

True

从每个数据点（即每个句子和pos / neg标签），我们要说一个特征（即词汇中的单词）是否存在。

>>> sentence = word_tokenize('I love this sandwich.'.lower())

>>> print {i:True for i in vocabulary if i in sentence}

{'this': True, 'i': True, 'sandwich': True, 'love': True, '.': True}

但是我们还想告诉分类器，句子中不存在哪个单词，而是词汇中的单词，因此对于每个数据点，我们列出词汇中所有可能的单词，并说出一个单词是否存在：

>>> sentence = word_tokenize('I love this sandwich.'.lower())

>>> x =  {i:True for i in vocabulary if i in sentence}

>>> y =  {i:False for i in vocabulary if i not in sentence}

>>> x.update(y)

>>> print x

{'love': True, 'deal': False, 'tired': False, 'feel': False, 'is': False, 'am': False, 'an': False, 'good': False, 'best': False, '!': False, 'these': False, 'what': False, '.': True, 'amazing': False, 'horrible': False, 'sworn': False, 'ca': False, 'do': False, 'sandwich': True, 'very': False, 'boss': False, 'beers': False, 'not': False, 'with': False, 'he': False, 'enemy': False, 'about': False, 'like': False, 'restaurant': False, 'this': True, 'of': False, 'work': False, "n't": False, 'i': True, 'stuff': False, 'place': False, 'my': False, 'awesome': False, 'view': False}

但是，由于这两次遍历词汇表，因此这样做更有效：

>>> sentence = word_tokenize('I love this sandwich.'.lower())

>>> x = {i:(i in sentence) for i in vocabulary}

{'love': True, 'deal': False, 'tired': False, 'feel': False, 'is': False, 'am': False, 'an': False, 'good': False, 'best': False, '!': False, 'these': False, 'what': False, '.': True, 'amazing': False, 'horrible': False, 'sworn': False, 'ca': False, 'do': False, 'sandwich': True, 'very': False, 'boss': False, 'beers': False, 'not': False, 'with': False, 'he': False, 'enemy': False, 'about': False, 'like': False, 'restaurant': False, 'this': True, 'of': False, 'work': False, "n't": False, 'i': True, 'stuff': False, 'place': False, 'my': False, 'awesome': False, 'view': False}

因此，对于每个句子，我们想告诉每个句子的分类器哪个词存在，哪个词不存在，并为其赋予pos / neg标记。我们可以称其为feature_set，它是一个由x（如上所示）及其标签组成的元组。

>>> feature_set = [({i:(i in word_tokenize(sentence.lower())) for i in vocabulary},tag) for sentence, tag in training_data]

[({'this': True, 'love': True, 'deal': False, 'tired': False, 'feel': False, 'is': False, 'am': False, 'an': False, 'sandwich': True, 'ca': False, 'best': False, '!': False, 'what': False, '.': True, 'amazing': False, 'horrible': False, 'sworn': False, 'awesome': False, 'do': False, 'good': False, 'very': False, 'boss': False, 'beers': False, 'not': False, 'with': False, 'he': False, 'enemy': False, 'about': False, 'like': False, 'restaurant': False, 'these': False, 'of': False, 'work': False, "n't": False, 'i': False, 'stuff': False, 'place': False, 'my': False, 'view': False}, 'pos'), ...]

然后，我们将feature_set中的这些功能和标签提供给分类器以对其进行训练：

from nltk import NaiveBayesClassifier as nbc

classifier = nbc.train(feature_set)

现在，您拥有训练有素的分类器，并且当您要标记新句子时，您必须“特征化”新句子以查看新句子中哪个词在分类器接受过训练的词汇表中：

>>> test_sentence = "This is the best band I've ever heard! foobar"

>>> featurized_test_sentence = {i:(i in word_tokenize(test_sentence.lower())) for i in vocabulary}

注意：从上面的步骤中可以看到，朴素的贝叶斯分类器无法处理超出词汇量的单词，因为foobar标记化为特征后会消失。

然后，您将特征化的测试句子输入分类器，并要求其进行分类：

>>> classifier.classify(featurized_test_sentence)

'pos'

希望这可以更清晰地说明如何将数据输入到NLTK的朴素贝叶斯分类器中进行情感分析。这是完整的代码，没有注释和演练：

from nltk import NaiveBayesClassifier as nbc

from nltk.tokenize import word_tokenize

from itertools import chain

training_data = [('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')]

vocabulary = set(chain(*[word_tokenize(i[0].lower()) for i in training_data]))

feature_set = [({i:(i in word_tokenize(sentence.lower())) for i in vocabulary},tag) for sentence, tag in training_data]

classifier = nbc.train(feature_set)

test_sentence = "This is the best band I've ever heard!"

featurized_test_sentence =  {i:(i in word_tokenize(test_sentence.lower())) for i in vocabulary}

print "test_sent:",test_sentence

print "tag:",classifier.classify(featurized_test_sentence)