def test_predict(self):
x = np.array([[1, 0, 0], [0, 1, 1], [1, 1, 1], [0, 1, 1]])
y = {"test1": [1, 0, 2, 0], "test2": [1, 0, 2, 0]}
lr = LogisticRegression()
lr.fit(EncodedData(x, y), Label("test2"))
test_x = np.array([[0, 1, 0], [1, 0, 0]])
y = lr.predict(EncodedData(test_x), Label("test2"))
self.assertTrue(len(y["test2"]) == 2)
self.assertTrue(y["test2"][1] in [0, 1, 2])
def test_run(self):
method = LogisticRegression()
dataset = RepertoireDataset()
dataset.encoded_data = EncodedData(examples=np.array([[1, 2, 3],
[2, 3, 4],
[1, 2, 3],
[2, 3, 4],
[1, 2, 3],
[2, 3, 4]]),
labels={
"l1": [1, 0, 1, 0, 1, 0],
"l2": [0, 1, 0, 1, 0, 1]
},
feature_names=["f1", "f2", "f3"])
path = EnvironmentSettings.root_path / "test/tmp/mlmethodtrainer/"
method = MLMethodTrainer.run(
MLMethodTrainerParams(result_path=path,
dataset=dataset,
label=Label(name="l1", values=[0, 1]),
method=method,
model_selection_n_folds=2,
model_selection_cv=True,
cores_for_training=1,
train_predictions_path=path /
"predictions.csv",
ml_details_path=path / "details.yaml",
optimization_metric="balanced_accuracy"))
method.predict(EncodedData(np.array([1, 2, 3]).reshape(1, -1)),
Label("l1"))
self.assertTrue(os.path.isfile(path / "predictions.csv"))
self.assertTrue(os.path.isfile(path / "details.yaml"))
shutil.rmtree(path)