def build_names():
cnt = 0
for name,hints,nicknames in GivenNames:
if type(name) != tuple:
name = (name,)
name = tuple([names.normalize(n) for n in name])
if type(hints) != tuple:
hints = (hints,)
for n in name:
for h in hints:
if not hint.is_hint(h):
print((name,h,' is not a hint'))
else:
cnt += 1
if n in GivenNameDict:
GivenNameDict[n].append(h)
else:
GivenNameDict[n] = [h]
if type(nicknames) != tuple:
nicknames = (nicknames,)
for nick in nicknames:
nick = names.normalize(nick)
if nick in Nicknames:
Nicknames[nick].append(list(name))
else:
Nicknames[nick] = list(name)
return cnt
def build_names():
cnt = 0
for name, hints, nicknames in GivenNames:
if type(name) != tuple:
name = (name, )
name = tuple([names.normalize(n) for n in name])
if type(hints) != tuple:
hints = (hints, )
for n in name:
for h in hints:
if not hint.is_hint(h):
print((name, h, ' is not a hint'))
else:
cnt += 1
if n in GivenNameDict:
GivenNameDict[n].append(h)
else:
GivenNameDict[n] = [h]
if type(nicknames) != tuple:
nicknames = (nicknames, )
for nick in nicknames:
nick = names.normalize(nick)
if nick in Nicknames:
Nicknames[nick].append(list(name))
else:
Nicknames[nick] = list(name)
return cnt
def lookup(conn, surnames):
for name in surnames:
# handle hyphenated surnames
for subname in name.split('-'):
norm = names.normalize(subname)
e = ethnicity(conn, norm)
o = origin(conn, norm)
print(('%-15s %5.2f%% %-6s %s' % (subname,e[1],e[0],' '.join(o))))
def lookup(conn, surnames):
for name in surnames:
# handle hyphenated surnames
for subname in name.split('-'):
norm = names.normalize(subname)
e = ethnicity(conn, norm)
o = origin(conn, norm)
print(
('%-15s %5.2f%% %-6s %s' % (subname, e[1], e[0], ' '.join(o))))
def yob_generator():
files = glob.glob('./' + dir + '/yob*.txt')
for filename in files:
year = re.search('yob(\d+)\.txt', filename).group(1)
if int(year) >= 1900:
for line in open(filename, 'r'):
(name,gender,total) = line.strip().split(",")
norm = names.normalize(name)
yield (year, norm, gender, total)
def classify(name):
name = names.normalize(name)
# get list of all names to look up
name = [name] + (Nicknames[name] if name in Nicknames else [])
# get list of list of hints
hint = [GivenNameDict[n] if n in GivenNameDict else [] for n in name]
# merge lists
hint = list(itertools.chain(*hint))
# unique-ify list FIXME: no good; order matters
#hint = list(set(hint))
return hint
def classify(name):
name = names.normalize(name)
# get list of all names to look up
name = [name] + (Nicknames[name] if name in Nicknames else [])
# get list of list of hints
hint = [GivenNameDict[n] if n in GivenNameDict else [] for n in name]
# merge lists
hint = list(itertools.chain(*hint))
# unique-ify list FIXME: no good; order matters
#hint = list(set(hint))
return hint
def lookup(conn, givennames):
for name in givennames:
norm = names.normalize(name)
g = gender(conn, norm)
pct, span = 70, 20
plo, phi = birthspan_pct(conn, norm, pct)
(slo, shi), spct = birthspan(conn, norm, span)
hints = givenname_origin.classify(norm)
if g['F'] == 0. and g['M'] == 0. and spct == 0 and hints == []:
# name not found
print('%-15s %3.0f%%' % (name, max(g.values()) * 100.))
else:
print('%-15s %3.0f%%%s %3.0f%%@%.0fyr=%d-%d %.0f%%=%d-%d %s' %
(name, max(g.values()) * 100., 'F' if g['F'] >= g['M'] else
'M', spct, span, slo, shi, pct, plo, phi, hints))
def lookup(conn, givennames):
for name in givennames:
norm = names.normalize(name)
g = gender(conn, norm)
pct, span = 70, 20
plo,phi = birthspan_pct(conn, norm, pct)
(slo,shi),spct = birthspan(conn, norm, span)
hints = givenname_origin.classify(norm)
if g['F'] == 0. and g['M'] == 0. and spct == 0 and hints == []:
# name not found
print('%-15s %3.0f%%' %
(name, max(g.values())*100.))
else:
print('%-15s %3.0f%%%s %3.0f%%@%.0fyr=%d-%d %.0f%%=%d-%d %s' %
(name, max(g.values())*100.,
'F' if g['F'] >= g['M'] else 'M',
spct, span, slo, shi, pct, plo, phi, hints))
