>>> import kex
>>> model = kex.SingleRank()  # any algorithm listed above
>>> sample = '''
We propose a novel unsupervised keyphrase extraction approach that filters candidate keywords using outlier detection.
It starts by training word embeddings on the target document to capture semantic regularities among the words. It then
uses the minimum covariance determinant estimator to model the distribution of non-keyphrase word vectors, under the
assumption that these vectors come from the same distribution, indicative of their irrelevance to the semantics
expressed by the dimensions of the learned vector representation. Candidate keyphrases only consist of words that are
detected as outliers of this dominant distribution. Empirical results show that our approach outperforms state
of-the-art and recent unsupervised keyphrase extraction methods.
'''
>>> model.get_keywords(sample, n_keywords=2)
[{'stemmed': 'non-keyphras word vector',
  'pos': 'ADJ NOUN NOUN',
  'raw': ['non-keyphrase word vectors'],
  'offset': [[47, 49]],
  'count': 1,
  'score': 0.06874471825637762,
  'n_source_tokens': 112},
 {'stemmed': 'semant regular word',
  'pos': 'ADJ NOUN NOUN',
  'raw': ['semantic regularities words'],
  'offset': [[28, 32]],
  'count': 1,
  'score': 0.06001468574146248,
  'n_source_tokens': 112}]

>>> import kex
>>> model = kex.SingleTPR()
>>> test_sentences = ['documentA', 'documentB', 'documentC']
>>> model.train(test_sentences, export_directory='./tmp')

>>> import kex
>>> model = kex.SingleTPR()
>>> model.load('./tmp')

>>> import kex
>>> json_line, language = kex.get_benchmark_dataset('Inspec')
>>> json_line[0]
{
    'keywords': ['kind infer', 'type check', 'overload', 'nonstrict pure function program languag', ...],
    'source': 'A static semantics for Haskell\nThis paper gives a static semantics for Haskell 98, a non-strict ...',
    'id': '1053.txt'
}

import kex

class CustomExtractor:
    """ Custom keyword extractor example: First N keywords extractor """

    def __init__(self, maximum_word_number: int = 3):
        """ First N keywords extractor """
        self.phrase_constructor = kex.PhraseConstructor(maximum_word_number=maximum_word_number)

    def get_keywords(self, document: str, n_keywords: int = 10):
        """ Get keywords

         Parameter
        ------------------
        document: str
        n_keywords: int

         Return
        ------------------
        a list of dictionary consisting of 'stemmed', 'pos', 'raw', 'offset', 'count'.
        eg) {'stemmed': 'grid comput', 'pos': 'ADJ NOUN', 'raw': ['grid computing'], 'offset': [[11, 12]], 'count': 1}
        """
        phrase_instance, stemmed_tokens = self.phrase_constructor.tokenize_and_stem_and_phrase(document)
        sorted_phrases = sorted(phrase_instance.values(), key=lambda x: x['offset'][0][0])
        return sorted_phrases[:min(len(sorted_phrases), n_keywords)]