def test_TextModel():
from b4msa.textmodel import TextModel
X, y = get_data()
evo = EvoMSA()
evo.model(X)
assert isinstance(evo._textModel, list)
assert isinstance(evo._textModel[0], TextModel)
assert len(evo._textModel) == 1
def test_vector_space():
X, y = get_data()
evo = EvoMSA(evodag_args=dict(popsize=10,
early_stopping_rounds=10,
n_estimators=3),
models=[['EvoMSA.model.Corpus', 'EvoMSA.model.Bernulli']])
evo.model(X)
nrows = len(X)
X = evo.vector_space(X)
assert X[0].shape[0] == nrows
def test_EvoMSA_model():
X, y = get_data()
model = EvoMSA(evodag_args=dict(popsize=10,
early_stopping_rounds=10,
n_estimators=3),
models=[['EvoMSA.model.Corpus', 'EvoMSA.model.Bernulli']],
n_jobs=2)
assert len(model.models) == 2
model.model(X)
assert len(model._textModel) == 2
print(model._textModel)
def test_EvoMSA_kfold_decision_function():
from sklearn.preprocessing import LabelEncoder
X, y = get_data()
le = LabelEncoder().fit(y)
y = le.transform(y)
evo = EvoMSA(evodag_args=dict(popsize=10,
early_stopping_rounds=10,
n_estimators=3),
models=[['EvoMSA.model.Corpus', 'EvoMSA.model.Bernulli']])
evo.model(X)
X = evo.vector_space(X)
cl = evo.models[1][1]
D = evo.kfold_decision_function(cl, X[1], y)
assert len(D[0]) == 4
assert isinstance(D[0], list)
def test_EvoMSA_fit_svm():
from sklearn.preprocessing import LabelEncoder
X, y = get_data()
from sklearn.svm import LinearSVC
from EvoMSA.model import Bernoulli
model = EvoMSA(stacked_method_args=dict(popsize=10,
early_stopping_rounds=10,
n_estimators=3),
models=[['EvoMSA.model.Corpus', 'EvoMSA.model.Bernoulli']],
n_jobs=2)
le = LabelEncoder().fit(y)
y = le.transform(y)
model.model(X)
Xvs = model.vector_space(X)
model.fit_svm(Xvs, y)
print(model._svc_models)
assert len(model._svc_models) == 2
for ins, klass in zip(model._svc_models, [LinearSVC, Bernoulli]):
assert isinstance(ins, klass)