esa_jobtitle_normalizer.py 文件源码

def retrieve_onet_titles(self):
        onet_titles = pd.concat(
            (pd.read_csv(self.onet_downloader.download(
                version,
                'Occupation Data.txt',
                'occupation_data.txt'
            ), sep='\t') for version in ONET_VERSIONS),
            ignore_index=True
        )
        # Assumes pandas 0.19, keeps newest duplicate Title
        onet_titles.drop_duplicates('Title', inplace=True, keep='last')
        onet_titles['Major'] = onet_titles.iloc[:, 0].apply(lambda x: x[:2])

        LOWER = True
        if LOWER:
            # all RDD strings are unicode
            onet_titles['Title'] = onet_titles['Title'].str.lower()
            onet_titles['Description'] = onet_titles['Description'].str.lower()

        # now we can do a title -> Major, Minor lookup
        onet_titles.set_index('Title', inplace=True)
        # access with onet_titles.loc[u'Sales Agents, Financial Services']
        return onet_titles