def output_results(df, columns):
"""
:param df: pandas.DataFrame
:param columns: columns with paper_id and results
:return: None
"""
logger = logging.getLogger(__name__)
results_path = Config.get_next_results_file_path()
upload_path = Config.get_results_upload_path()
logger.info('Storing results in a CSV %s', results_path)
CsvDatastore().store_results(df, results_path, columns)
logger.info('Copying results to the upload file %s', upload_path)
shutil.copyfile(results_path, upload_path)
return
def output_results(df, columns):
"""
:param df: pandas.DataFrame
:param columns: columns with paper_id and results
:return: None
"""
logger = logging.getLogger(__name__)
results_path = Config.get_next_results_file_path()
upload_path = Config.get_results_upload_path()
logger.info('Storing results in a CSV %s', results_path)
CsvDatastore().store_results(df, results_path, columns)
logger.info('Copying results to the upload file %s', upload_path)
shutil.copyfile(results_path, upload_path)
return
def store_authors(self):
"""
:return: None
"""
authors_file = 'Authors.txt'
authors_path = Config.get_path_to_data_file(authors_file)
self.logger.info('Reading authors from %s', authors_file)
rows = Hdf5Datastore().store_table('authors_table', AuthorsHdf5,
authors_path, AuthorsCsv)
self.logger.info('Rows exported: %s', rows)
def store_papers(self):
"""
:return: None
"""
papers_file = 'Papers.txt'
papers_path = Config.get_path_to_data_file(papers_file)
self.logger.info('Reading papers from %s', papers_path)
rows = Hdf5Datastore().store_table('papers_table', PapersHdf5,
papers_path, PapersCsv)
self.logger.info('Rows exported: %s', rows)
def store_papers(self):
"""
:return: None
"""
papers_file = 'Papers.txt'
papers_path = Config.get_path_to_data_file(papers_file)
self.logger.info('Reading papers from %s', papers_path)
rows = Hdf5Datastore().store_table('papers_table', PapersHdf5,
papers_path, PapersCsv)
self.logger.info('Rows exported: %s', rows)
def load_paper_journal_matrix(self, papers, journals):
"""
:param papers: dictionary of {id: index}
:param journals: dictionary of {id: index}
:return:
"""
fpath = Config.get_path_to_data_file('Papers.txt')
return CsvDatastore().csv_to_relation_matrix(
fpath, PapersCsv.paper_id.value, papers,
PapersCsv.journal_id.value, journals)
def store_authors(self):
"""
:return: None
"""
authors_file = 'Authors.txt'
authors_path = Config.get_path_to_data_file(authors_file)
self.logger.info('Reading authors from %s', authors_file)
rows = Hdf5Datastore().store_table('authors_table', AuthorsHdf5,
authors_path, AuthorsCsv)
self.logger.info('Rows exported: %s', rows)
def load_paper_field_of_study_matrix(self, papers, fos):
"""
:param papers: dictionary of {id: index}
:param fos: fields of study, dictionary of {id: index}
:return:
"""
fpath = Config.get_path_to_data_file('PaperKeywords.txt')
return CsvDatastore().csv_to_relation_matrix(
fpath, PaperKeywordsCsv.paper_id.value, papers,
PaperKeywordsCsv.field_id.value, fos)
def load_paper_conf_series_matrix(self, papers, conf_series):
"""
:param papers: dictionary of {id: index}
:param conf_series: dictionary of {id: index}
:return:
"""
fpath = Config.get_path_to_data_file('Papers.txt')
return CsvDatastore().csv_to_relation_matrix(
fpath, PapersCsv.paper_id.value, papers,
PapersCsv.conference_series_id.value, conf_series)
def store_journals(self):
"""
:return: None
"""
journals_file = 'Journals.txt'
journals_path = Config.get_path_to_data_file(journals_file)
self.logger.info('Reading journals from %s', journals_path)
rows = Hdf5Datastore().store_table('journals_table', JournalsHdf5,
journals_path, JournalsCsv)
self.logger.info('Rows exported: %s', rows)
def load_author_sequence_matrix(self, papers, authors):
"""
:param papers: dictionary of {id: index}
:param authors: dictionary of {id: index}
:return:
"""
fpath = Config.get_path_to_data_file('PaperAuthorAffiliations.txt')
return CsvDatastore().csv_to_relation_matrix(
fpath, PapAuthAff.paper_id.value, papers,
PapAuthAff.author_id.value, authors,
PapAuthAff.author_seq_number.value)
def store_affiliations(self):
"""
:return: None
"""
affiliations_file = 'Affiliations.txt'
affiliations_path = Config.get_path_to_data_file(affiliations_file)
self.logger.info('Reading affiliations from %s', affiliations_path)
rows = Hdf5Datastore().store_table('affiliations_table',
AffiliationsHdf5, affiliations_path,
AffiliationsCsv)
self.logger.info('Rows exported: %s', rows)
def store_journals(self):
"""
:return: None
"""
journals_file = 'Journals.txt'
journals_path = Config.get_path_to_data_file(journals_file)
self.logger.info('Reading journals from %s', journals_path)
rows = Hdf5Datastore().store_table('journals_table',
JournalsHdf5,
journals_path, JournalsCsv)
self.logger.info('Rows exported: %s', rows)
def store_affiliations(self):
"""
:return: None
"""
affiliations_file = 'Affiliations.txt'
affiliations_path = Config.get_path_to_data_file(affiliations_file)
self.logger.info('Reading affiliations from %s', affiliations_path)
rows = Hdf5Datastore().store_table('affiliations_table',
AffiliationsHdf5,
affiliations_path, AffiliationsCsv)
self.logger.info('Rows exported: %s', rows)
def store_conference_series(self):
"""
:return: None
"""
conf_series_file = 'Conferences.txt'
conf_series_path = Config.get_path_to_data_file(conf_series_file)
self.logger.info('Reading conference series from %s', conf_series_path)
rows = Hdf5Datastore().store_table('conference_series_table',
ConferenceSeriesHdf5,
conf_series_path,
ConferenceSeriesCsv)
self.logger.info('Rows exported: %s', rows)
def load_citation_matrix(self, papers):
"""
Build adjacency matrix from list of edges in PaperReferences.txt file
:param papers: dictionary of {id: index}
:return: scipy.sparse.csr_matrix
"""
fpath = Config.get_path_to_data_file('PaperReferences.txt')
return CsvDatastore().csv_to_relation_matrix(fpath,
PapRef.paper_id.value,
papers,
PapRef.reference_id.value,
papers)
def load_paper_affiliation_matrix(self, papers, affiliations):
"""
Build matrix of papers and affiliations from list of
paper-affiliation relations in PaperAuthorAffiliations.txt file
:param papers: dictionary of {id: index}
:param affiliations: dictionary of {id: index}
:return: scipy.sparse.csr_matrix
"""
fpath = Config.get_path_to_data_file('PaperAuthorAffiliations.txt')
return CsvDatastore().csv_to_relation_matrix(
fpath, PapAuthAff.paper_id.value, papers,
PapAuthAff.affiliation_id.value, affiliations)
def store_fields_of_study(self):
"""
:return: None
"""
fos_file = 'FieldsOfStudy.txt'
fos_path = Config.get_path_to_data_file(fos_file)
self.logger.info('Reading fields of study from %s', fos_path)
rows = Hdf5Datastore().store_table('fields_of_study_table',
FieldsOfStudyHdf5, fos_path,
FieldsOfStudyCsv)
self.logger.info('Rows exported: %s', rows)
return
def store_conference_series(self):
"""
:return: None
"""
conf_series_file = 'Conferences.txt'
conf_series_path = Config.get_path_to_data_file(conf_series_file)
self.logger.info('Reading conference series from %s', conf_series_path)
rows = Hdf5Datastore().store_table('conference_series_table',
ConferenceSeriesHdf5,
conf_series_path,
ConferenceSeriesCsv)
self.logger.info('Rows exported: %s', rows)
def store_fields_of_study(self):
"""
:return: None
"""
fos_file = 'FieldsOfStudy.txt'
fos_path = Config.get_path_to_data_file(fos_file)
self.logger.info('Reading fields of study from %s', fos_path)
rows = Hdf5Datastore().store_table('fields_of_study_table',
FieldsOfStudyHdf5,
fos_path,
FieldsOfStudyCsv)
self.logger.info('Rows exported: %s', rows)
return
def setup_logging(default_path='logging.json', default_level=logging.DEBUG):
"""
Setup logging configuration
:param default_path:
:param default_level:
:return: None
"""
path = default_path
if os.path.exists(path):
with open(path, 'rt') as f:
config = json.load(f)
config['handlers']['file']['filename'] = \
Config.get_path_to_log_file('debug.log')
logging.config.dictConfig(config)
else:
logging.basicConfig(level=default_level)
return
def __init__(self, datastore_fname=Config.DATASTORE_FNAME):
self.datastore_path = Config.get_path_to_hdf5_file(datastore_fname)
self.logger = logging.getLogger(__name__)
def __init__(self, datastore_fname = Config.DATASTORE_FNAME):
self.datastore_path = Config.get_path_to_hdf5_file(datastore_fname)
self.logger = logging.getLogger(__name__)
