def transform(observations, nlp):
# TODO Docstring
logging.info('Begin transform')
# Extract candidate name
observations['candidate_name'] = observations['text'].apply(
lambda x: field_extraction.candidate_name_extractor(x, nlp))
if observations['candidate_name'] == "NOT FOUND":
match = re.search(field_extraction.NAME_REGEX, observations['text'],
re.IGNORECASE)
observations['candidate_name'] = match[0]
# Extract contact fields
observations['email'] = observations['text'].apply(
lambda x: lib.term_match(x, field_extraction.EMAIL_REGEX))
observations['phone'] = observations['text'].apply(
lambda x: lib.term_match(x, field_extraction.PHONE_REGEX))
# Extract skills
observations = field_extraction.extract_fields(observations)
# Archive schema and return
lib.archive_dataset_schemas('transform', locals(), globals())
logging.info('End transform')
return observations, nlp
def transform(observations, nlp):
# TODO Docstring
logging.info('Begin transform')
# Extract candidate name
observations['candidate_name'] = observations['text'].apply(
lambda x: field_extraction.candidate_name_extractor(x, nlp))
# Extract contact fields
observations['email'] = observations['text'].apply(
lambda x: lib.term_match(x, field_extraction.EMAIL_REGEX))
observations['phone'] = observations['text'].apply(
lambda x: lib.term_match(x, field_extraction.PHONE_REGEX))
# Extract education data
count = 0
observations['university'] = observations['text'].apply(
lambda x: field_extraction.university_extractor(x, nlp))
observations['Major'] = observations['text'].apply(
lambda x: field_extraction.major_extractor(x, nlp))
# Extract skills
observations = field_extraction.extract_fields(observations)
# Archive schema and return
lib.archive_dataset_schemas('transform', locals(), globals())
logging.info('End transform')
return observations, nlp