def test_copy(self):
metric = Metric({"name": "logloss"})
rf = RandomForestAlgorithm({"ml_task": "binary_classification"})
rf.fit(self.X, self.y)
y_predicted = rf.predict(self.X)
loss = metric(self.y, y_predicted)
rf2 = RandomForestAlgorithm({"ml_task": "binary_classification"})
rf2 = rf.copy()
self.assertEqual(type(rf), type(rf2))
y_predicted = rf2.predict(self.X)
loss2 = metric(self.y, y_predicted)
assert_almost_equal(loss, loss2)
def test_save_and_load(self):
metric = Metric({"name": "logloss"})
rf = RandomForestAlgorithm({"ml_task": "binary_classification"})
rf.fit(self.X, self.y)
y_predicted = rf.predict(self.X)
loss = metric(self.y, y_predicted)
with tempfile.NamedTemporaryFile() as tmp:
rf.save(tmp.name)
rf2 = RandomForestAlgorithm({"ml_task": "binary_classification"})
rf2.load(tmp.name)
y_predicted = rf2.predict(self.X)
loss2 = metric(self.y, y_predicted)
assert_almost_equal(loss, loss2)
def test_fit_predict(self):
metric = Metric({"name": "logloss"})
params = {"ml_task": "binary_classification"}
rf = RandomForestAlgorithm(params)
rf.fit(self.X, self.y)
y_predicted = rf.predict(self.X)
self.assertTrue(metric(self.y, y_predicted) < 1.0)
def test_fit_predict(self):
metric = Metric({"name": "logloss"})
params = {"trees_in_step": 50}
rf = RandomForestAlgorithm(params)
rf.fit(self.X, self.y)
y_predicted = rf.predict(self.X)
self.assertTrue(metric(self.y, y_predicted) < 0.6)
def test_save_and_load(self):
metric = Metric({"name": "logloss"})
rf = RandomForestAlgorithm({"ml_task": "binary_classification"})
rf.fit(self.X, self.y)
y_predicted = rf.predict(self.X)
loss = metric(self.y, y_predicted)
filename = os.path.join(tempfile.gettempdir(), os.urandom(12).hex())
rf.save(filename)
rf2 = RandomForestAlgorithm({"ml_task": "binary_classification"})
rf2.load(filename)
#Finished with the file, delete it
os.remove(filename)
y_predicted = rf2.predict(self.X)
loss2 = metric(self.y, y_predicted)
assert_almost_equal(loss, loss2)
def test_reproduce_fit(self):
metric = Metric({"name": "logloss"})
params = {"trees_in_step": 1, "seed": 1, "ml_task": "binary_classification"}
prev_loss = None
for _ in range(3):
model = RandomForestAlgorithm(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