def test_exactmatch_skill_extractor():
competency_framework = CompetencyFramework(
name='test_competencies',
description='Test competencies',
competencies=[
Competency(identifier='2.a.1.a', name='Reading Comprehension'),
Competency(identifier='2.a.1.b', name='Active Listening'),
])
extractor = ExactMatchSkillExtractor(competency_framework)
assert competency_framework.name in extractor.name
assert competency_framework.description in extractor.description
result = [
extractor.document_skill_counts({'description': doc}) for doc in [
'this is a job that needs active listening',
'this is a reading comprehension job',
'this is an active and reading listening job',
'this is a reading comprehension and active listening job',
]
]
assert result == [
Counter({'active listening': 1}),
Counter({'reading comprehension': 1}),
Counter(),
Counter({
'active listening': 1,
'reading comprehension': 1
})
]
def test_exactmatch_skill_extractor():
content = [[
'', 'O*NET-SOC Code', 'Element ID', 'ONET KSA', 'Description',
'skill_uuid', 'nlp_a'
],
[
'1', '11-1011.00', '2.a.1.a', 'reading comprehension',
'...', '2c77c703bd66e104c78b1392c3203362',
'reading comprehension'
],
[
'2', '11-1011.00', '2.a.1.b', 'active listening', '...',
'a636cb69257dcec699bce4f023a05126', 'active listening'
]]
with utils.makeNamedTemporaryCSV(content, '\t') as skills_filename:
extractor = ExactMatchSkillExtractor(skill_lookup_path=skills_filename)
result = [
extractor.document_skill_counts(doc) for doc in [
'this is a job that needs active listening',
'this is a reading comprehension job',
'this is an active and reading listening job',
'this is a reading comprehension and active listening job',
]
]
assert result == [
Counter({'active listening': 1}),
Counter({'reading comprehension': 1}),
Counter(),
Counter({
'active listening': 1,
'reading comprehension': 1
})
]
def test_exactmatch_skill_extractor_candidate_skills():
extractor = ExactMatchSkillExtractor(sample_framework())
candidate_skills = sorted(extractor.candidate_skills(sample_job_posting()),
key=lambda cs: cs.skill_name)
assert candidate_skills[0].skill_name == 'cooking'
assert candidate_skills[
0].context == 'One-two years cooking experience in a professional kitchen'
assert candidate_skills[0].confidence == 100
assert candidate_skills[1].skill_name == 'organization'
assert candidate_skills[
1].context == 'Organization, Cleanliness, Trainability, team player, good communication skillz, Motivation, a Sense of Responsibility and Pride in your Performance'
assert candidate_skills[1].confidence == 100
def _compute_func_on_one(self):
corpus_creator = SimpleCorpusCreator()
skill_extractor = ExactMatchSkillExtractor(
skill_lookup_path=self.skill_lookup_path)
def func(job_posting):
count_dict = skill_extractor.document_skill_counts(
document=corpus_creator._transform(job_posting))
count_lists = [[k] * v for k, v in count_dict.items()]
flattened = [
count for countlist in count_lists for count in countlist
]
return {self.property_name: flattened}
return func
def setUp(self):
s3_conn = boto.connect_s3()
client = boto3.resource('s3')
bucket = client.create_bucket(Bucket='test-bucket')
storage = S3Store('s3://test-bucket/computed_properties')
skill_extractor = ExactMatchSkillExtractor(utils.sample_framework())
self.computed_property = SkillCounts(
skill_extractor=skill_extractor,
storage=storage,
)
self.job_postings = [
utils.job_posting_factory(datePosted=self.datestring,
description='reading comprehension')
]
self.computed_property.compute_on_collection(self.job_postings)
from skills_ml.ontologies.onet import Onet
from skills_ml.evaluation.skill_extractors import candidate_skills_from_sample, metrics_for_candidate_skills
from skills_ml.evaluation.skill_extraction_metrics import TotalOccurrences, TotalVocabularySize, OntologyCompetencyRecall
from skills_ml.job_postings.common_schema import JobPostingCollectionSample
from tests.utils import sample_factory
sample = sample_factory(JobPostingCollectionSample())
print('Building ONET, may take a while to download')
full_onet = Onet()
skill_extractors = [
SectionExtractSkillExtractor(),
SkillEndingPatternExtractor(only_bulleted_lines=False),
AbilityEndingPatternExtractor(only_bulleted_lines=False),
FuzzyMatchSkillExtractor(full_onet.competency_framework),
ExactMatchSkillExtractor(full_onet.competency_framework),
SocScopedExactMatchSkillExtractor(full_onet)
]
print('Done building ONET! Now subsetting ONET into K,S,A')
metric_ontologies = [
full_onet,
full_onet.filter_by(lambda edge: 'Knowledge' in edge.competency.categories,
competency_name='onet_knowledge',
competency_description='ONET Knowledge'),
full_onet.filter_by(lambda edge: 'Abilities' in edge.competency.categories,
competency_name='onet_ability',
competency_description='ONET Ability'),
full_onet.filter_by(lambda edge: 'Skills' in edge.competency.categories,
competency_name='onet_skill',
competency_description='ONET Skill')
]