algorithms

algorithms

• aggregators - Methods for dataset aggregation.

• corpus_creators - Methods for different corpus creation.

• elasticsearch_indexers - Elasticsearch indexers for different corpora.

• geocoders - Methods for geocoding locations from job postings

• job_geography_queriers - Method for querying the Core-Based Statistical Area for a job.

• job_labelers - Method to label each job posting with an occupation category.

• job_normalizers - Methods for normalizing arbitrary job titles into job titles defined in ONET data.

• job_vectorizers - Methods for converting job listing data into dense low-dimensional vectors of real number.

• jobtitle_cleaner - Methods for cleaning job titles into a more reasonable form.

• occupation_classifiers - Methods for classifying the occupation of a job posting

• representativeness_calculators - Methods for calculating geographic representativeness of SOC Codes.

• sampling - Methods for sampling from a corpus

• skill_extractors - Methods for extracting skills from structured or unstructured data sources

• skill_importance_extractors - Methods for creating a skills importance CSV based on ONET data.

• skill_taggers - Methods for tagging skills in job listing data.

• title_extractors - Methods for creating a job titles CSV based on ONET data.