def store_values(self):
print('Loading coordinates...')
coords = Coordinates()
print('Checking language overrides...')
overrides = LanguageOverrides().list_language_overrides()
print('Loading OED vital statistics...')
vitalstats = VitalStatisticsCache()
entries = []
iterator = FrequencyIterator(message='Listing entries')
for entry in iterator.iterate():
if (entry.has_frequency_table() and
not ' ' in entry.lemma and
not '-' in entry.lemma):
language_breadcrumb = vitalstats.find(entry.id, field='language')
year = vitalstats.find(entry.id, field='first_date') or 0
languages = []
if language_breadcrumb is not None:
languages = [l for l in language_breadcrumb.split('/')
if coords.is_listed(l)
or l == 'English']
else:
languages = ['unspecified', ]
if entry.id in overrides:
languages = [overrides[entry.id], ]
if languages:
# pick the most granular level (e.g. 'Icelandic' in
# preference to 'Germanic')
language = languages[-1]
# Find frequency for this word
freq_table = entry.frequency_table()
frequency = freq_table.frequency(period='modern')
band = freq_table.band(period='modern')
row = (entry.lemma,
entry.label,
entry.id,
year,
frequency,
band,
language)
entries.append(row)
entries = sorted(entries, key=lambda entry: entry[2])
with (open(self.out_file, 'w')) as csvfile:
writer = csv.writer(csvfile)
writer.writerows(entries)
