Python nltk.classify() Examples

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.") 

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)) 

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)) 

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 

def classify(self, features):
        votes = []
        for c in self._classifiers:
            v = c.classify(features)
            votes.append(v)
        return mode(votes) 

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 

def classify(self, text):
        """Classifies a string of text."""
        raise NotImplementedError('Must implement a "classify" method.') 

def classify(self, text):
        """Classifies the text.

        :param str text: A string of text.
        """
        text_features = self.extract_features(text)
        return self.classifier.classify(text_features) 

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) 

def train(self, *args, **kwargs):
        """Train the classifier with a labeled and unlabeled feature sets 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.

        :rtype: A classifier
        """
        self.classifier = self.nltk_class.train(self.positive_features,
                                                self.unlabeled_features,
                                                self.positive_prob_prior)
        return self.classifier