def transform(observations, nlp):
logging.info('Begin transform')
print("Extracting name, email, phone, GPA, and dates of work experience")
observations = observations.fillna('')
observations['candidate_name'] = observations['text'].apply(lambda x: field_extraction.candidate_name_extractor(x, nlp))
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))
observations['GPA'] = observations['text'].apply(lambda x: field_extraction.gpa_extractor(x))
observations['years_experience'] = observations['Work'].apply(lambda x: field_extraction.years_of_experience(x))
observations['mos_experience'] = field_extraction.months_of_experience(observations['years_experience'])
# observations['work_dates'] = observations['Work'].apply(
# lambda x: field_extraction.spacy_extractor_by_type(str(x).replace('\n', '. '), nlp, 'DATE', 2))
# observations['uni'] = observations['Edu'].apply(
# lambda x: field_extraction.spacy_extractor_by_type(str(x), nlp, 'ORG', 2))
observations = field_extraction.extract_fields(observations) # search for terms in whole resume
# Archive schema and return
lib.archive_dataset_schemas('transform', locals(), globals())
logging.info('End transform')
return observations
def transform(observations, nlp):
# TODO Docstring
logging.info('Begin transform')
# 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 candidate name
observations['candidate_name'] = observations['text'].apply(
lambda x: field_extraction.candidate_name_extractor(
x, nlp, observations['email']))
# 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, root_file_path, nlp):
logging.info("Extracting email, phone, GPA, and dates of work experience")
observations = observations.fillna('')
observations['candidate_name'] = observations['text'].apply(
lambda x: field_extraction.candidate_name_extractor(x, nlp))
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))
observations['GPA'] = observations['text'].apply(
lambda x: field_extraction.gpa_extractor(x))
observations['years_experience'] = observations['Work'].apply(
lambda x: field_extraction.years_of_experience(x))
observations['mos_experience'] = field_extraction.months_of_experience(
observations['years_experience'])
# convert GPA to a single number
GPA_REGEX = r"[01234]{1}\.[0-9]{1,3}"
observations.GPA.fillna('[]', inplace=True)
observations['GPAnum'] = observations.GPA.apply(
lambda x: re.findall(re.compile(GPA_REGEX), str(x)))
def getmax(x):
try:
y = max(x)
except:
y = 0
return y
observations['GPAmax'] = observations['GPAnum'].apply(lambda x: getmax(x))
observations['GPAmax'] = observations['GPAmax'].apply(lambda x: np.nan
if x == 0 else x)
observations.filter(like='GPA')
np.mean(observations['GPAmax'].astype('float'))
observations.drop('GPAnum', axis=1, inplace=True)
observations = field_extraction.extract_fields(
observations, root_file_path) # search for terms in whole resume
return observations