def test_klass():
dset = Dataset()
# dset.add(dset.load_emojis())
dset.add(dset.tm_words())
kl = dset.klasses
xx = dset.klass("xxx good xxx morning xxT")
for k in xx:
assert k in kl
def test_add():
dset = Dataset()
assert len(dset.klasses) == 0
dset.add(dset.load_emojis())
cnt = len(dset.klasses)
assert cnt > 0
words = dset.tm_words()
dset.add(words)
print(len(dset.klasses), len(words), cnt)
assert len(dset.klasses) <= len(words) + cnt
def test_remove():
dset = Dataset()
dset.add(dset.load_emojis())
dset.add(dset.tm_words())
xx = dset.klass("xxx good morning xxx asdfa")
print(xx)
assert len(xx) == 2
dset.remove("~good~")
xx = dset.klass("xxx good xxx morning xxx")
print(xx)
assert len(xx) == 1
def test_process():
from microtc.emoticons import convert_emoji
dset = Dataset()
dset.add(dset.load_emojis())
dset.add(dset.tm_words())
xx = dset.process("xxx good 9 morning xxx fax x la", "~x~")
for a, b in zip(xx, ["~xxx~good~9~morning~xxx~fax~", "~la~", "~la~"]):
print(a, b)
assert a == b
txt = 'xxx good {} morning xxx fax x la'.format(convert_emoji('1F600'))
xx = dset.process(txt, convert_emoji('1F600'))
print(xx)
for a, b in zip(xx, ["~xxx~good~", "~morning~xxx~fax~x~la~"]):
assert a == b
def recall_emo(lang='zh', n_jobs=1):
def predict(fname, ds, tm, emoji):
D = []
for key, tweets in load_model(fname).items():
labels = [ds.klass(x['text']) for x in tweets]
_ = [[x['text'], label] for label, x in zip(labels, tweets)
if len(klasses.intersection(label))]
D.extend(_)
X = tm.transform([x for x, _ in D])
y = [y for _, y in D]
hy = []
for k, emo in enumerate(emoji):
output = join('models', f'{lang}_emo_{k}_mu{microtc.__version__}')
m = load_model(f'{output}.LinearSVC')
hy.append(m.predict(X))
return y, hy
def performance(emo, y, hy):
y_emo = [emo in i for i in y]
perf = recall_score(y_emo, hy > 0, pos_label=True)
return perf, sum(y_emo) / len(y)
info = load_model(join('models', f'{lang}_emo.info'))
info = [[k, v] for k, (v, _) in enumerate(info.most_common())
if _ >= 2**10]
klasses = set([v for k, v in info])
fnames = glob(join('data', lang, 'test', '*.gz'))
ds = Dataset(text_transformations=False)
ds.add(ds.load_emojis())
dd = load_model(join('models', f'{lang}_emo.info'))
emoji = [x for x, v in dd.most_common() if v >= 2**10]
tm = load_model(join('models', f'{lang}_{microtc.__version__}.microtc'))
predictions = Parallel(n_jobs=n_jobs)(
delayed(predict)(fname, ds, tm, emoji) for fname in fnames)
y = []
[y.extend(x) for x, hy in predictions]
hys = np.vstack([np.vstack(hy).T for _, hy in predictions])
output = dict()
_ = Parallel(n_jobs=n_jobs)(delayed(performance)(emo, y, hy)
for emo, hy in zip(emoji, hys.T))
output = {
emo: {
'recall': perf,
'ratio': ratio
}
for emo, (perf, ratio) in zip(emoji, _)
}
save_model(output, join('models', f'{lang}_emo.perf'))
def emo_data(lang='zh'):
fnames = glob(join('data', lang, '*.gz'))
ds = Dataset(text_transformations=False)
ds.add(ds.load_emojis())
for fname in fnames:
output = dict()
for key, tweets in load_model(fname).items():
labels = [ds.klass(x['text']) for x in tweets]
inner = []
for tweet, label in zip(tweets, labels):
if len(label) == 0:
continue
tweet['klass'] = label
inner.append(tweet)
if len(inner):
output[key] = inner
if len(output) == 0:
continue
output_fname = join(dirname(fname), 'emo')
if not isdir(output_fname):
os.mkdir(output_fname)
output_fname = join(output_fname, basename(fname))
save_model(output, output_fname)
def emo(k, lang='zh', size=2**19):
ds = Dataset(text_transformations=False)
ds.add(ds.load_emojis())
output = join('models', f'{lang}_emo_{k}_mu{microtc.__version__}')
dd = load_model(join('models', f'{lang}_emo.info'))
_ = [x for x, v in dd.most_common() if v >= 2**10]
tot = sum([v for x, v in dd.most_common() if v >= 2**10])
if k >= len(_):
return
pos = _[k]
neg = set([x for i, x in enumerate(_) if i != k])
POS, NEG, ADD = [], [], []
for fname in glob(join('data', lang, 'emo', '*.gz')):
for key, data in load_model(fname).items():
for d in data:
klass = d['klass']
if len(klass) == 1:
klass = klass.pop()
if klass == pos:
POS.append(ds.process(d['text']))
elif klass in neg:
NEG.append(ds.process(d['text']))
elif tot < size:
if pos not in klass and len(klass.intersection(neg)):
ADD.append(ds.process(d['text']))
shuffle(POS), shuffle(NEG), shuffle(ADD)
size2 = size // 2
POS = POS[:size2]
if len(NEG) < size2:
NEG.extend(ADD)
NEG = NEG[:size2]
y = [1] * len(POS)
y.extend([-1] * len(NEG))
tm = load_model(join('models', f'{lang}_{microtc.__version__}.microtc'))
X = tm.transform(POS + NEG)
m = LinearSVC().fit(X, y)
save_model(m, f'{output}.LinearSVC')
for x in emojis['fully-qualified']:
key = remove_components(x)
emojis_filter[key].append(x)
components.add('FE0F')
m_qual = {remove_components(x): x for x in emojis_filter.keys()}
for x in emojis['minimally-qualified']:
key = remove_components(x)
value = m_qual[key]
emojis_filter[value].append(x)
for x in emojis['unqualified']:
key = remove_components(x)
value = m_qual[key]
emojis_filter[value].append(x)
output = dict()
for k, v in emojis_filter.items():
ident = convert_emoji(k).strip()
for item in v:
output[convert_emoji(item).strip()] = ident
save_model(output, 'emojis.dict')
ds = Dataset()
ds.add(output)
ds.process('buenos xx 12 dias. {} todos! acción'.format(
convert_emoji('1F44B 1F3FC')))
def test_map():
dset = Dataset()
dset.add(dict(buenos="malos"))
res = dset.klass("en estos buenos dias")
print(res)
assert "malos" in res