def test_bernoulli():
import numpy as np
from EvoMSA.model import Corpus, Bernoulli
from sklearn.preprocessing import LabelEncoder
c = Corpus([x['text'] for x in tweet_iterator(TWEETS)])
X = c.transform([x['text'] for x in tweet_iterator(TWEETS)])
y = [x['klass'] for x in tweet_iterator(TWEETS)]
le = LabelEncoder().fit(y)
y = le.transform(y)
b = Bernoulli()
b.fit(X, y)
pr = b.decision_function(X)
assert pr.shape[0] == 1000 and pr.shape[1] == 4
assert np.all((pr <= 1) & (pr >= -1))
def test_multinomial():
import numpy as np
from EvoMSA.model import Corpus, Multinomial
from sklearn.preprocessing import LabelEncoder
c = Corpus([x['text'] for x in tweet_iterator(TWEETS)])
X = c.tonp([c[x['text']] for x in tweet_iterator(TWEETS)])
y = [x['klass'] for x in tweet_iterator(TWEETS)]
le = LabelEncoder().fit(y)
y = le.transform(y)
b = Multinomial()
b.fit(X, y)
pr = b.decision_function(X)
print(pr.shape[0], pr, b.num_terms)
assert pr.shape[0] == 1000 and pr.shape[1] == 4
assert np.all((pr <= 1) & (pr >= -1))
def test_OutputClassifier():
from EvoMSA.model import Corpus, OutputClassifier
from sklearn.preprocessing import LabelEncoder
c = Corpus([x['text'] for x in tweet_iterator(TWEETS)])
X = c.transform([x['text'] for x in tweet_iterator(TWEETS)])
y = [x['klass'] for x in tweet_iterator(TWEETS)]
le = LabelEncoder().fit(y)
y = le.transform(y)
b = OutputClassifier(output='xx')
assert b._output == 'xx'
b.fit(X, y)
assert os.path.isfile('xx_train.csv')
pr = b.decision_function(X)
assert os.path.isfile('xx_test.csv')
assert len(open('xx_test.csv').readlines()) == pr.shape[0]
os.unlink('xx_train.csv')
os.unlink('xx_test.csv')
def test_corpus():
from EvoMSA.model import Corpus
c = Corpus([x['text'] for x in tweet_iterator(TWEETS)])
a = c['hola hola mundo']
assert len(a) == 3
assert a[0] == a[1]