def get_name(vf_col, ocdid, districts, state):
full_name = ''
small = ['IN', 'NJ', 'NM', 'OK']
ocdid_split = ocdid.split('/')
suffix = ocdid_split[-1]
specific_suffix = suffix.split(':')[-1].upper()
if re.match(r'[0-9]+', specific_suffix):
specific_suffix = add_zeros(specific_suffix)
possible_names = districts[vf_col]
if which_level(vf_col) == 'high':
full_name = get_high_level(vf_col, ocdid, districts)
else:
if vf_col == 'vf_county_council':
if state in small and re.match(r'[0-9]+', specific_suffix):
specific_suffix = specific_suffix[1:]
county_ocdid = ocdid.split('/council_district')[0]
county = get_high_level('vf_county_name', county_ocdid, districts)
for p in possible_names:
if specific_suffix == p:
index = possible_names.index(specific_suffix)
full_name = '{}_{}'.format(county, possible_names[index])
elif county in p and len(county) > 2:
if ocdid.split(':')[-1] in p:
full_name = '{}_{}'.format(county, specific_suffix)
elif vf_col == 'vf_judicial_district':
# print ocdid
# print possible_names
pass
# print 'FULL NAME: {}'.format(full_name)
return full_name
def get_high_level(vf_col, ocdid, districts):
# Reads in all possible districts as ripped from the VF
possible_names = districts[vf_col]
# Pull most specific section of the ocdid & clean up
suffix = ocdid.split('/')[-1]
specific_suffix = suffix.split(':')[-1].upper().replace('_', ' ').replace('~', '')
if re.match(r'[0-9]+', specific_suffix):
specific_suffix = add_zeros(specific_suffix)
if 'state:md' in ocdid:
specific_suffix = se.md_ts_exceptions(specific_suffix, ocdid)
# Check for state exception cases
if 'state:nh' in ocdid:
if vf_col == 'vf_hd':
return se.nh_ts_exceptions(specific_suffix, possible_names)
elif 'state:ma' in ocdid:
if vf_col == 'vf_hd' or vf_col == 'vf_sd':
return se.ma_ts_exceptions(specific_suffix, possible_names)
elif 'state:vt' in ocdid:
if vf_col == 'vf_hd' or 'GRAND ISLE' in specific_suffix:
return se.vt_ts_exceptions(vf_col, specific_suffix, possible_names)
elif 'state:va' in ocdid and 'place:' in ocdid:
return se.va_ts_exceptions(specific_suffix, possible_names, vf_col)
# Match to possible districts if there are no exceptions
if specific_suffix in possible_names:
return no_spaces(possible_names[possible_names.index(specific_suffix)])
else:
for p in possible_names:
if fuzz.ratio(specific_suffix, p) >= 90:
return no_spaces(possible_names[possible_names.index(p)])
elif fuzz.partial_ratio(specific_suffix, p) >= 90:
return no_spaces(possible_names[possible_names.index(p)])
else:
return ''
