regex - How to extraxt the experience from resume using python? -

i have extracted mail id, phone number- using regular expressions have extracted name using core nlp server had extracted skills giving in set , comparing words. didn't have idea how extract years of experience using python - can please give idea regarding it? examples:

2 years of experience

two years of experience

2010-2014

like there many possibilities

you can take couple of approaches. if there lots of possibilities, say, can treat machine learning problem , use approach 1. otherwise 1, if possibilities limited (say, around 5), can use second approach.

approach 1:

consider machine learning problem. classify each sentence in text 0 or 1 depending on if contains year of experience. can done training data manually. against each training example, assign label. example:

job experience: 3 years (label 1)

studying 2 years (label 0)

working hard years (label 0)

two years of experience (label 1)

experience: 2010-2014 (label 1)

once have lot of examples, can use skicit-learn or similar package train model.

approach 2:

1- search years. either, exact word (year or years), or 4 digit number (e.g, 2014).

2- if 1 passes, search word experience (or that) in close proximity.

if both 1 , 2 pass, have years of experience. then, depending on want, can further extract.