def init_name_proposals(self):
"""Gets name proposals for new measurements
Returns:
NameIndex
"""
name_proposals = NameIndex()
for db in [
'crinacle', 'oratory1990', 'rtings', 'referenceaudioanalyzer'
]:
name_index = NameIndex.read_tsv(
os.path.join(DIR_PATH, db, 'name_index.tsv'))
name_proposals.concat(name_index)
for db in ['innerfidelity', 'headphonecom']:
name_index = NameIndex.read_files(
os.path.join(DIR_PATH, db, 'data', '**', '*.csv'))
name_proposals.concat(name_index)
name_proposals.remove_duplicates()
manufacturer_pattern = rf'^({"|".join([m[0] for m in self.manufacturers.manufacturers])})'
proposal_data = {'form': [], 'manufacturer': [], 'model': []}
for item in name_proposals.items:
if not item.true_name or item.form == 'ignore':
continue
manufacturer = re.search(manufacturer_pattern,
item.true_name,
flags=re.IGNORECASE)
if not manufacturer:
continue
manufacturer = manufacturer[0]
proposal_data['form'].append(item.form)
proposal_data['manufacturer'].append(manufacturer)
proposal_data['model'].append(
item.true_name.replace(manufacturer, '').strip())
self.name_proposals = pd.DataFrame(proposal_data)
def get_existing():
suffix_regex = re.compile(r' \(.*\)$')
name_index = NameIndex.read_files(
os.path.join(DIR_PATH, 'data', '**', '*.csv'))
for i, row in name_index.df.iterrows():
row.true_name = re.sub(suffix_regex, '', row.true_name)
name_index.df.drop_duplicates()
return name_index
def get_existing():
suffix_regex = re.compile(r' \(.*\)$')
name_index = NameIndex.read_files(
os.path.join(DIR_PATH, 'data', '**', '*.csv'))
# Add models without mod suffixes which don't exist
for i, row in name_index.df.iterrows():
model = re.sub(suffix_regex, '', row.true_name)
if model != row.true_name:
name_index.df = name_index.df.append(
pd.DataFrame([[row.false_name, model, row.form]],
columns=name_index.df.columns))
name_index.df.drop_duplicates()
return name_index
def get_name_proposals(self):
"""Gets name proposals for new measurements
Returns:
NameIndex
"""
name_proposals = NameIndex()
for db in ['crinacle', 'oratory1990', 'rtings', 'referenceaudioanalyzer']:
name_index = NameIndex.read_tsv(os.path.join(DIR_PATH, db, 'name_index.tsv'))
name_proposals.concat(name_index)
for db in ['innerfidelity', 'headphonecom']:
name_index = NameIndex.read_files(os.path.join(DIR_PATH, db, 'data', '**', '*.csv'))
name_proposals.concat(name_index)
name_proposals.remove_duplicates()
return name_proposals
def get_existing():
return NameIndex.read_files(os.path.join(DIR_PATH, 'data', '**', '*.csv'))