def naivebayes_predict(input_dict):
from discomll.classification import naivebayes
m = 1 if input_dict["m"] == "" else input_dict["m"]
predictions_url = naivebayes.predict(input_dict["dataset"],
fitmodel_url=input_dict["fitmodel_url"],
m=input_dict["m"],
save_results=True)
return {"string": predictions_url}
def naivebayes_predict(input_dict):
from discomll.classification import naivebayes
m = 1 if input_dict["m"] == "" else input_dict["m"]
predictions_url = naivebayes.predict(
input_dict["dataset"],
fitmodel_url=input_dict["fitmodel_url"],
m=input_dict["m"],
save_results=True)
return {"string": predictions_url}
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))
def test_naivebayes_breastcancer(self):
# python -m unittest tests_classification.Tests_Classification.test_naivebayes_breastcancer
from discomll.classification import naivebayes
train_data1, test_data1 = datasets.breastcancer_disc_orange()
train_data2, test_data2 = datasets.breastcancer_disc_discomll()
for m in range(3):
learner = Orange.classification.bayes.NaiveLearner(m=m)
classifier = learner(train_data1)
predictions1 = [classifier(inst, Orange.classification.Classifier.GetBoth) for inst in test_data1]
predictions1_target = [v[0].value for v in predictions1]
predictions1_probs = [v[1].values() for v in predictions1]
fitmodel_url = naivebayes.fit(train_data2)
predictions_url = naivebayes.predict(test_data2, fitmodel_url, m=m)
predictions2_target = []
predictions2_probs = []
for k, v in result_iterator(predictions_url):
predictions2_target.append(v[0])
predictions2_probs.append(v[1])
self.assertListEqual(predictions1_target, predictions2_target)
self.assertTrue(np.allclose(predictions1_probs, predictions2_probs))
def test_naivebayes_breastcancer(self):
# python -m unittest tests_classification.Tests_Classification.test_naivebayes_breastcancer
from discomll.classification import naivebayes
train_data1, test_data1 = datasets.breastcancer_disc_orange()
train_data2, test_data2 = datasets.breastcancer_disc_discomll()
for m in range(3):
learner = Orange.classification.bayes.NaiveLearner(m=m)
classifier = learner(train_data1)
predictions1 = [classifier(inst, Orange.classification.Classifier.GetBoth) for inst in test_data1]
predictions1_target = [v[0].value for v in predictions1]
predictions1_probs = [v[1].values() for v in predictions1]
fitmodel_url = naivebayes.fit(train_data2)
predictions_url = naivebayes.predict(test_data2, fitmodel_url, m=m)
predictions2_target = []
predictions2_probs = []
for k, v in result_iterator(predictions_url):
predictions2_target.append(v[0])
predictions2_probs.append(v[1])
self.assertListEqual(predictions1_target, predictions2_target)
self.assertTrue(np.allclose(predictions1_probs, predictions2_probs))
from discomll import dataset
from discomll.classification import naivebayes
train = dataset.Data(data_tag=["http://ropot.ijs.si/data/lymphography/train/xaaaaa.gz",
"http://ropot.ijs.si/data/lymphography/train/xaaabj.gz"],
data_type="gzip",
generate_urls=True,
X_indices=range(2, 20),
id_index=0,
y_index=1,
X_meta=["d", "d", "d", "d", "d", "d", "d", "d", "c", "c", "d", "d", "d", "d", "d", "d", "d", "c"],
delimiter=",")
test = dataset.Data(data_tag=["http://ropot.ijs.si/data/lymphography/test/xaaaaa.gz",
"http://ropot.ijs.si/data/lymphography/test/xaaabj.gz"],
data_type="gzip",
generate_urls=True,
X_indices=range(2, 20),
id_index=0,
y_index=1,
X_meta=["d", "d", "d", "d", "d", "d", "d", "d", "c", "c", "d", "d", "d", "d", "d", "d", "d", "c"],
delimiter=",")
fit_model = naivebayes.fit(train)
predictions = naivebayes.predict(test, fit_model)
print predictions