def extract():
logging.info('Begin extract')
# Reference variables
candidate_file_agg = list()
# Create list of candidate files
for root, subdirs, files in os.walk(lib.get_conf('resume_directory')):
folder_files = map(lambda x: os.path.join(root, x), files)
candidate_file_agg.extend(folder_files)
# Convert list to a pandas DataFrame
observations = pandas.DataFrame(data=candidate_file_agg,
columns=['file_path'])
logging.info('Found {} candidate files'.format(len(observations.index)))
# Subset candidate files to supported extensions
observations['extension'] = observations['file_path'].apply(
lambda x: os.path.splitext(x)[1])
observations = observations[observations['extension'].isin(
lib.AVAILABLE_EXTENSIONS)]
logging.info(
'Subset candidate files to extensions w/ available parsers. {} files remain'
.format(len(observations.index)))
# Attempt to extract text from files
observations['text'] = observations['file_path'].apply(lib.convert_pdf)
# Archive schema and return
lib.archive_dataset_schemas('extract', locals(), globals())
logging.info('End extract')
return observations
def load(observations, nlp):
logging.info('Begin load')
output_path = os.path.join(lib.get_conf('summary_output_directory'),
'resume_summary.csv')
logging.info('Results being output to {}'.format(output_path))
print('Results output to {}'.format(output_path))
observations.to_csv(path_or_buf=output_path, index_label='index')
logging.info('End transform')
pass
def save(observations):
logging.info('Begin load')
output_path = os.path.join(lib.get_conf('summary_output_directory'), 'resume_summary.csv')
tmp = observations.copy()
del tmp['text']
tmp.to_csv(path_or_buf=output_path, index_label='index')
logging.info('End transform')
pass
def extract_fields(df):
for extractor, items_of_interest in lib.get_conf('extractors').items():
df[extractor] = df['text'].apply(lambda x: extract_skills(x, extractor, items_of_interest))
return df
