def test_log_reg(self):
# python tests_classification.py Tests_Classification.test_log_reg
from discomll.classification import logistic_regression
train_data1, test_data1 = datasets.breastcancer_cont_orange()
train_data2, test_data2 = datasets.breastcancer_cont_discomll()
learner = Orange.classification.logreg.LogRegLearner(fitter=Orange.classification.logreg.LogRegFitter_Cholesky)
classifier = learner(train_data1)
thetas1 = classifier.beta
predictions1 = []
probabilities1 = []
for inst in test_data1:
target, probs = classifier(inst, Orange.classification.Classifier.GetBoth)
predictions1.append(target.value)
probabilities1.append(probs.values())
thetas_url = logistic_regression.fit(train_data2, alpha=1e-8, max_iterations=10)
thetas2 = [v for k, v in result_iterator(thetas_url["logreg_fitmodel"]) if k == "thetas"]
results_url = logistic_regression.predict(test_data2, thetas_url)
predictions2 = []
probabilities2 = []
for k, v in result_iterator(results_url):
predictions2.append(v[0])
probabilities2.append(v[1])
self.assertTrue(np.allclose(thetas1, thetas2))
self.assertTrue(np.allclose(probabilities1, probabilities2, atol=1e-5))
self.assertListEqual(predictions1, predictions2)
def test_log_reg(self):
# python tests_classification.py Tests_Classification.test_log_reg
from discomll.classification import logistic_regression
train_data1, test_data1 = datasets.breastcancer_cont_orange()
train_data2, test_data2 = datasets.breastcancer_cont_discomll()
learner = Orange.classification.logreg.LogRegLearner(fitter=Orange.classification.logreg.LogRegFitter_Cholesky)
classifier = learner(train_data1)
thetas1 = classifier.beta
predictions1 = []
probabilities1 = []
for inst in test_data1:
target, probs = classifier(inst, Orange.classification.Classifier.GetBoth)
predictions1.append(target.value)
probabilities1.append(probs.values())
thetas_url = logistic_regression.fit(train_data2, alpha=1e-8, max_iterations=10)
thetas2 = [v for k, v in result_iterator(thetas_url["logreg_fitmodel"]) if k == "thetas"]
results_url = logistic_regression.predict(test_data2, thetas_url)
predictions2 = []
probabilities2 = []
for k, v in result_iterator(results_url):
predictions2.append(v[0])
probabilities2.append(v[1])
self.assertTrue(np.allclose(thetas1, thetas2))
self.assertTrue(np.allclose(probabilities1, probabilities2, atol=1e-5))
self.assertListEqual(predictions1, predictions2)
def test_naivebayes_breastcancer_cont(self):
# python -m unittest tests_classification.Tests_Classification.test_naivebayes_breastcancer_cont
from sklearn.naive_bayes import GaussianNB
from discomll.classification import naivebayes
x_train, y_train, x_test, y_test = datasets.breastcancer_cont(replication=1)
train_data, test_data = datasets.breastcancer_cont_discomll(replication=1)
clf = GaussianNB()
probs_log1 = clf.fit(x_train, y_train).predict_proba(x_test)
fitmodel_url = naivebayes.fit(train_data)
prediction_url = naivebayes.predict(test_data, fitmodel_url)
probs_log2 = [v[1] for _, v in result_iterator(prediction_url)]
self.assertTrue(np.allclose(probs_log1, probs_log2, atol=1e-8))
def test_naivebayes_breastcancer_cont(self):
# python -m unittest tests_classification.Tests_Classification.test_naivebayes_breastcancer_cont
from sklearn.naive_bayes import GaussianNB
from discomll.classification import naivebayes
x_train, y_train, x_test, y_test = datasets.breastcancer_cont(replication=1)
train_data, test_data = datasets.breastcancer_cont_discomll(replication=1)
clf = GaussianNB()
probs_log1 = clf.fit(x_train, y_train).predict_proba(x_test)
fitmodel_url = naivebayes.fit(train_data)
prediction_url = naivebayes.predict(test_data, fitmodel_url)
probs_log2 = [v[1] for _, v in result_iterator(prediction_url)]
self.assertTrue(np.allclose(probs_log1, probs_log2, atol=1e-8))