search

homander / ids2020

0 stars 1 forks source link

Define multi-gram skills to be extracted #5

Closed homander closed 3 years ago

homander commented 3 years ago

Created a feature count extractor with sklearn CountVectorizer.

Features (education, experiece, skills) are defined with dictionaries that are given as vocabularies for the CountVectorizer. Terms can be n-grams of multiple words.