当前位置: 首页>>代码示例>>Python>>正文


Python nltk.classify方法代码示例

本文整理汇总了Python中nltk.classify方法的典型用法代码示例。如果您正苦于以下问题:Python nltk.classify方法的具体用法?Python nltk.classify怎么用?Python nltk.classify使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在nltk的用法示例。


在下文中一共展示了nltk.classify方法的8个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。

示例1: demo_sent_subjectivity

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import classify [as 别名]
def demo_sent_subjectivity(text):
    """
    Classify a single sentence as subjective or objective using a stored
    SentimentAnalyzer.

    :param text: a sentence whose subjectivity has to be classified.
    """
    from nltk.classify import NaiveBayesClassifier
    from nltk.tokenize import regexp
    word_tokenizer = regexp.WhitespaceTokenizer()
    try:
        sentim_analyzer = load('sa_subjectivity.pickle')
    except LookupError:
        print('Cannot find the sentiment analyzer you want to load.')
        print('Training a new one using NaiveBayesClassifier.')
        sentim_analyzer = demo_subjectivity(NaiveBayesClassifier.train, True)

    # Tokenize and convert to lower case
    tokenized_text = [word.lower() for word in word_tokenizer.tokenize(text)]
    print(sentim_analyzer.classify(tokenized_text)) 
开发者ID:rafasashi,项目名称:razzy-spinner,代码行数:22,代码来源:util.py

示例2: demo_sent_subjectivity

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import classify [as 别名]
def demo_sent_subjectivity(text):
    """
    Classify a single sentence as subjective or objective using a stored
    SentimentAnalyzer.

    :param text: a sentence whose subjectivity has to be classified.
    """
    from nltk.classify import NaiveBayesClassifier
    from nltk.tokenize import regexp

    word_tokenizer = regexp.WhitespaceTokenizer()
    try:
        sentim_analyzer = load('sa_subjectivity.pickle')
    except LookupError:
        print('Cannot find the sentiment analyzer you want to load.')
        print('Training a new one using NaiveBayesClassifier.')
        sentim_analyzer = demo_subjectivity(NaiveBayesClassifier.train, True)

    # Tokenize and convert to lower case
    tokenized_text = [word.lower() for word in word_tokenizer.tokenize(text)]
    print(sentim_analyzer.classify(tokenized_text)) 
开发者ID:V1EngineeringInc,项目名称:V1EngineeringInc-Docs,代码行数:23,代码来源:util.py

示例3: train

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import classify [as 别名]
def train(self, *args, **kwargs):
        """Train the classifier with a labeled feature set and return
        the classifier. Takes the same arguments as the wrapped NLTK class.
        This method is implicitly called when calling ``classify`` or
        ``accuracy`` methods and is included only to allow passing in arguments
        to the ``train`` method of the wrapped NLTK class.

        .. versionadded:: 0.6.2

        :rtype: A classifier
        """
        try:
            self.classifier = self.nltk_class.train(self.train_features,
                                                    *args, **kwargs)
            return self.classifier
        except AttributeError:
            raise ValueError("NLTKClassifier must have a nltk_class"
                            " variable that is not None.") 
开发者ID:alvarobartt,项目名称:twitter-stock-recommendation,代码行数:20,代码来源:classifiers.py

示例4: demo

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import classify [as 别名]
def demo(train_size=100, test_size=100, java_home=None, mallet_home=None):
    from nltk.corpus import brown
    import textwrap

    # Define a very simple feature detector
    def fd(sentence, index):
        word = sentence[index]
        return dict(word=word, suffix=word[-2:], len=len(word))

    # Let nltk know where java & mallet are.
    nltk.internals.config_java(java_home)
    nltk.classify.mallet.config_mallet(mallet_home)

    # Get the training & test corpus.  We simplify the tagset a little:
    # just the first 2 chars.
    def strip(corpus): return [[(w, t[:2]) for (w,t) in sent]
                               for sent in corpus]
    brown_train = strip(brown.tagged_sents(categories='news')[:train_size])
    brown_test = strip(brown.tagged_sents(categories='editorial')[:test_size])

    crf = MalletCRF.train(fd, brown_train, #'/tmp/crf-model',
                          transduction_type='VITERBI')
    sample_output = crf.tag([w for (w,t) in brown_test[5]])
    acc = nltk.tag.accuracy(crf, brown_test)
    print '\nAccuracy: %.1f%%' % (acc*100)
    print 'Sample output:'
    print textwrap.fill(' '.join('%s/%s' % w for w in sample_output),
                        initial_indent='  ', subsequent_indent='  ')+'\n'

    # Clean up
    print 'Clean-up: deleting', crf.filename
    os.remove(crf.filename)

    return crf 
开发者ID:blackye,项目名称:luscan-devel,代码行数:36,代码来源:crf.py

示例5: classify

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import classify [as 别名]
def classify(self, features):
        votes = []
        for c in self._classifiers:
            v = c.classify(features)
            votes.append(v)
        return mode(votes) 
开发者ID:singnet,项目名称:nlp-services,代码行数:8,代码来源:train_mod.py

示例6: confidence

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import classify [as 别名]
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


# Fetching trained dataset 
开发者ID:singnet,项目名称:nlp-services,代码行数:14,代码来源:train_mod.py

示例7: classify

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import classify [as 别名]
def classify(self, text):
        """Classifies a string of text."""
        raise NotImplementedError('Must implement a "classify" method.') 
开发者ID:alvarobartt,项目名称:twitter-stock-recommendation,代码行数:5,代码来源:classifiers.py

示例8: accuracy

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import classify [as 别名]
def accuracy(self, test_set, format=None):
        """Compute the accuracy on a test set.

        :param test_set: A list of tuples of the form ``(text, label)``, or a
            file pointer.
        :param format: If ``test_set`` is a filename, the file format, e.g.
            ``"csv"`` or ``"json"``. If ``None``, will attempt to detect the
            file format.
        """
        if is_filelike(test_set):
            test_data = self._read_data(test_set, format)
        else:  # test_set is a list of tuples
            test_data = test_set
        test_features = [(self.extract_features(d), c) for d, c in test_data]
        return nltk.classify.accuracy(self.classifier, test_features) 
开发者ID:alvarobartt,项目名称:twitter-stock-recommendation,代码行数:17,代码来源:classifiers.py


注:本文中的nltk.classify方法示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。