esa_jobtitle_normalizer.py 文件源码

def __init__(self, onet_source=OnetSourceDownloader):
        self.onet_downloader = onet_source()
        self.onet_titles = self.retrieve_onet_titles()
        logging.info('Retrieved onet titles')
        # ... Following the ESA description:
        # https://en.wikipedia.org/wiki/Explicit_semantic_analysis
        self.tfidf_vectorizer = TfidfVectorizer(stop_words='english')
        # optimization note: convert from CSR to CSC
        self.tf = self.tfidf_vectorizer.fit_transform(self.onet_titles['Description'].values)
        self.concept_row = self.onet_titles.index.values
        try:
            wn.synset
        except LookupError:
            nltk.download('wordnet')