def test_fit_predict(self):
metric = Metric({"name": "logloss"})
cat = CatBoostAlgorithm(self.params)
loss_prev = None
for _ in range(5):
cat.fit(self.X, self.y)
y_predicted = cat.predict(self.X)
loss = metric(self.y, y_predicted)
if loss_prev is not None:
self.assertTrue(loss + 0.001 < loss_prev)
loss_prev = loss
def test_fit_predict(self):
metric = Metric({"name": "logloss"})
loss_prev = None
for _ in range(2):
cat = CatBoostAlgorithm(self.params)
cat.fit(self.X, self.y)
y_predicted = cat.predict(self.X)
loss = metric(self.y, y_predicted)
if loss_prev is not None:
assert_almost_equal(loss, loss_prev)
loss_prev = loss
def test_reproduce_fit(self):
metric = Metric({"name": "logloss"})
prev_loss = None
for _ in range(3):
model = CatBoostAlgorithm(self.params)
model.fit(self.X, self.y)
y_predicted = model.predict(self.X)
loss = metric(self.y, y_predicted)
if prev_loss is not None:
assert_almost_equal(prev_loss, loss)
prev_loss = loss
def test_copy(self):
# train model #1
metric = Metric({"name": "logloss"})
cat = CatBoostAlgorithm(self.params)
cat.fit(self.X, self.y)
y_predicted = cat.predict(self.X)
loss = metric(self.y, y_predicted)
# create model #2
cat2 = CatBoostAlgorithm(self.params)
# model #2 is initialized in constructor
self.assertTrue(cat2.model is not None)
# do a copy and use it for predictions
cat2 = cat.copy()
self.assertEqual(type(cat), type(cat2))
y_predicted = cat2.predict(self.X)
loss2 = metric(self.y, y_predicted)
self.assertEqual(loss, loss2)
def test_get_metric_name(self):
model = CatBoostAlgorithm(self.params)
self.assertEqual(model.get_metric_name(), "logloss")
params = dict(self.params)
params["loss_function"] = "MultiClass"
model = CatBoostAlgorithm(params)
self.assertEqual(model.get_metric_name(), "logloss")
def test_copy(self):
# train model #1
metric = Metric({"name": "logloss"})
cat = CatBoostAlgorithm(self.params)
cat.fit(self.X, self.y)
y_predicted = cat.predict(self.X)
loss = metric(self.y, y_predicted)
# create model #2
cat2 = CatBoostAlgorithm(self.params)
# model #2 is initialized in constructor
self.assertTrue(cat2.model is not None)
# do a copy and use it for predictions
cat2 = cat.copy()
self.assertEqual(type(cat), type(cat2))
y_predicted = cat2.predict(self.X)
loss2 = metric(self.y, y_predicted)
self.assertEqual(loss, loss2)
# fit model #1, there should be improvement in loss
cat.fit(self.X, self.y)
y_predicted = cat.predict(self.X)
loss3 = metric(self.y, y_predicted)
self.assertTrue(loss3 < loss)
# the loss of model #2 should not change
y_predicted = cat2.predict(self.X)
loss4 = metric(self.y, y_predicted)
assert_almost_equal(loss2, loss4)
def test_save_and_load(self):
metric = Metric({"name": "logloss"})
cat = CatBoostAlgorithm(self.params)
cat.fit(self.X, self.y)
y_predicted = cat.predict(self.X)
loss = metric(self.y, y_predicted)
with tempfile.NamedTemporaryFile() as tmp:
cat.save(tmp.name)
cat2 = CatBoostAlgorithm(self.params)
self.assertTrue(cat.uid != cat2.uid)
self.assertTrue(cat2.model is not None)
cat2.load(tmp.name)
y_predicted = cat2.predict(self.X)
loss2 = metric(self.y, y_predicted)
assert_almost_equal(loss, loss2)
def test_save_and_load(self):
metric = Metric({"name": "logloss"})
cat = CatBoostAlgorithm(self.params)
cat.fit(self.X, self.y)
y_predicted = cat.predict(self.X)
loss = metric(self.y, y_predicted)
filename = os.path.join(tempfile.gettempdir(), os.urandom(12).hex())
cat.save(filename)
cat2 = CatBoostAlgorithm(self.params)
self.assertTrue(cat.uid != cat2.uid)
self.assertTrue(cat2.model is not None)
cat2.load(filename)
# Finished with the file, delete it
os.remove(filename)
y_predicted = cat2.predict(self.X)
loss2 = metric(self.y, y_predicted)
assert_almost_equal(loss, loss2)
def test_get_metric_name(self):
model = CatBoostAlgorithm(self.params)
self.assertEqual(model.get_metric_name(), "rmse")
def test_is_fitted(self):
cat = CatBoostAlgorithm(self.params)
self.assertFalse(cat.is_fitted())
cat.fit(self.X, self.y)
self.assertTrue(cat.is_fitted())
def test_save_and_load(self):
metric = Metric({"name": "logloss"})
cat = CatBoostAlgorithm(self.params)
cat.fit(self.X, self.y)
y_predicted = cat.predict(self.X)
loss = metric(self.y, y_predicted)
json_desc = cat.save()
cat2 = CatBoostAlgorithm({})
self.assertTrue(cat.uid != cat2.uid)
self.assertTrue(cat2.model is not None)
cat2.load(json_desc)
self.assertTrue(cat.uid == cat2.uid)
y_predicted = cat2.predict(self.X)
loss2 = metric(self.y, y_predicted)
assert_almost_equal(loss, loss2)
