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 sample_framework():
return CompetencyFramework(
name='sample_framework',
description='A few basic competencies',
competencies=[
Competency(identifier='a', name='Reading Comprehension'),
Competency(identifier='b', name='Active Listening'),
]
)
def sample_framework():
return CompetencyFramework(name='Sample Framework',
description='A few basic competencies',
competencies=[
Competency(identifier='a',
name='Organization'),
Competency(identifier='b',
name='Communication Skills'),
Competency(identifier='c', name='Cooking')
])
def ontology_from_candidate_skills(candidate_skills: CandidateSkillYielder, skill_extractor_name: str='unknown') -> CompetencyOntology:
"""Create an ontology from a list of candidate skills
Simply associate each candidate skill with its ONET occupation.
Args:
candidate_skills (iterable of algorithms.skill_extractors.base.CandidateSkill objects)
Returns: (skills_ml.ontologies.base.CompetencyOntology)
"""
ontology = CompetencyOntology(
name=f'candidate_skill_{skill_extractor_name}',
competency_name=f'candidate_skill_{skill_extractor_name}',
competency_description=f'Constructed from CandidateSkill objects produced by the {skill_extractor_name} skill extractor'
)
competencies_by_document_id = defaultdict(set)
for candidate_skill in candidate_skills:
competency = Competency(
identifier=candidate_skill.skill_name.lower(),
name=candidate_skill.skill_name
)
if competency not in competencies_by_document_id[candidate_skill.document_id]:
competencies_by_document_id[candidate_skill.document_id].add(competency)
if competency not in ontology.competencies:
ontology.add_competency(competency)
occupation_code = get_onet_occupation(candidate_skill.source_object)
occupation = Occupation(identifier=occupation_code)
if occupation not in ontology.occupations:
ontology.add_occupation(occupation)
ontology.add_edge(occupation=occupation, competency=competency)
return ontology
def sample_ontology():
return CompetencyOntology(
competency_name='Sample Framework',
competency_description='A few basic competencies',
edges=[
CompetencyOccupationEdge(
competency=Competency(identifier='a', name='Organization'),
occupation=Occupation(identifier='11-1011.00')),
CompetencyOccupationEdge(
competency=Competency(identifier='a', name='Organization'),
occupation=Occupation(identifier='11-1012.00')),
CompetencyOccupationEdge(
competency=Competency(identifier='b',
name='Communication Skills'),
occupation=Occupation(identifier='11-1011.00')),
CompetencyOccupationEdge(
competency=Competency(identifier='c', name='Cooking'),
occupation=Occupation(identifier='11-1011.00')),
])
def test_occupation_scoped_freetext_skill_extractor():
ontology = CompetencyOntology(
competency_name='Sample Framework',
competency_description='A few basic competencies',
edges=[
CompetencyOccupationEdge(
competency=Competency(identifier='2.a.1.a',
name='Reading Comprehension'),
occupation=Occupation(identifier='11-1011.00')),
CompetencyOccupationEdge(
competency=Competency(identifier='2.a.1.b',
name='Active Listening'),
occupation=Occupation(identifier='11-1011.00')),
])
extractor = SocScopedExactMatchSkillExtractor(ontology)
documents = [
{
'id': '1234',
'@type': 'JobPosting',
'onet_soc_code': '11-1011.00',
'description': 'this is a job that needs active listening',
'expected_value': Counter({'active listening': 1})
},
{
'id': '2234',
'@type': 'JobPosting',
'onet_soc_code': '11-1011.00',
'description': 'this is a reading comprehension job',
'expected_value': Counter({'reading comprehension': 1})
},
{
'id': '3234',
'@type': 'JobPosting',
'onet_soc_code': '11-1011.00',
'description': 'this is an active and reading listening job',
'expected_value': Counter(),
},
{
'id':
'4234',
'@type':
'JobPosting',
'onet_soc_code':
'11-1011.00',
'description':
'this is a reading comprehension and active listening job',
'expected_value':
Counter({
'active listening': 1,
'reading comprehension': 1
})
},
{
'id': '5234',
'@type': 'JobPosting',
'onet_soc_code': '11-1021.00',
'description': 'this is a job that needs active listening',
'expected_value': Counter()
},
{
'id': '6234',
'@type': 'JobPosting',
'onet_soc_code': '11-1021.00',
'description': 'this is a reading comprehension job',
'expected_value': Counter()
},
{
'id': '7234',
'@type': 'JobPosting',
'onet_soc_code': '11-1021.00',
'description': 'this is an active and reading listening job',
'expected_value': Counter(),
},
{
'id': '8234',
'@type': 'JobPosting',
'onet_soc_code': '11-1021.00',
'description':
'this is a reading comprehension and active listening job',
'expected_value': Counter()
},
{
'id': '9234',
'@type': 'JobPosting',
'onet_soc_code': None,
'description': 'this is a job that needs active listening',
'expected_value': Counter()
},
{
'id': '1334',
'@type': 'JobPosting',
'onet_soc_code': None,
'description': 'this is a reading comprehension job',
'expected_value': Counter()
},
{
'id': '1434',
'@type': 'JobPosting',
'onet_soc_code': None,
'description': 'this is an active and reading listening job',
'expected_value': Counter(),
},
{
'id': '1534',
'@type': 'JobPosting',
'onet_soc_code': None,
'description':
'this is a reading comprehension and active listening job',
'expected_value': Counter()
},
]
for document in documents:
assert extractor.document_skill_counts(
document) == document['expected_value']