def test_create_hash_func(self):
rma = RakutenMA()
hash_func = rma.create_hash_func(4)
assert_equals(hash_func("feat1", "foo"), ["5"])
assert_equals(hash_func("feat1", "bar"), ["2"])
assert_equals(hash_func("feat1", "baz"), ["10"])
assert_equals(hash_func("feat1", "qux"), ["3"])
def _get_tokenizer(lang):
rma = None
if lang == 'ja':
rma = RakutenMA()
rma.load('model_ja.json')
rma.hash_func = rma.create_hash_func(15)
tokenizer = _jap_tokenizer
# tokenizer = _jap_character_tokenizer
else:
tokenizer = _eng_tokenizer
return tokenizer, rma
def __init__(self, kv_filepath, model):
self.rma = RakutenMA(json.loads(open(model).read()))
self.rma.hash_func = RakutenMA.create_hash_func(self.rma, 15)
self.ja_to_en = defaultdict(list)
self.en_to_ja = defaultdict(list)
for l in open(kv_filepath):
[k, v] = l.strip().split(',')[:2]
raw = unicode(k, 'utf-8')
# lemma = self.rma.tokenize(raw)[0][0]
self.ja_to_en[raw].append(v)
self.en_to_ja[v].append(raw)
def __init__(self, model):
print model
self.rma = RakutenMA(json.loads(open(model).read()))
self.rma.hash_func = RakutenMA.create_hash_func(self.rma, 15)
return
def __init__(self):
rma = RakutenMA()
rma.load("model_ja.json")
rma.hash_func = rma.create_hash_func(15)
self.rma = rma
# Now what does the result look like?
# First trained, maybe?
print('After first trained')
print('segment')
print(rma.tokenize(result))
print('rma')
print(rma.tokenize(
"米中間選挙は6日に午後6時（日本時間7日午前8時）に一部の投票所が締め切られ、開票が始まった。米連邦議会の多数党がどちらになるかによって、ドナルド・トランプ米大統領の政策の行方が決まる。特に下院でどれだけ、民主党が共和党現職の議席を奪うかが注目されている。"))
# Initialize a RakutenMA instance with a pre-trained model
rma = RakutenMA(phi=1024, c=0.007812) # Specify hyperparameter for SCW (for demonstration purpose)
rma.load("model_ja.json")
# Set the feature hash function (15bit)
rma.hash_func = rma.create_hash_func(15)
# Tokenize one sample sentence
print('Tokenize simple sentence')
print(rma.tokenize("うらにわにはにわにわとりがいる"));
# Re-train the model feeding the right answer (pairs of [token, PoS tag])
res = rma.train_one(
[["うらにわ", "N-nc"],
["に", "P-k"],
["は", "P-rj"],
["にわ", "N-n"],
["にわとり", "N-nc"],
["が", "P-k"],
["いる", "V-c"]])
# The result of train_one contains:
def create_tokenizer():
rma = RakutenMA()
rma.load('model_ja.json')
rma.hash_func = rma.create_hash_func(15)
return rma.tokenize
