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="l1",
method=method,
model_selection_n_folds=2,
model_selection_cv=True,
cores_for_training=1,
train_predictions_path=f"{path}predictions.csv",
ml_details_path=f"{path}details.yaml",
optimization_metric="balanced_accuracy"))
method.predict(EncodedData(np.array([1, 2, 3]).reshape(1, -1)), "l1")
self.assertTrue(os.path.isfile(f"{path}predictions.csv"))
self.assertTrue(os.path.isfile(f"{path}details.yaml"))
shutil.rmtree(path)
def test_run(self):
path = EnvironmentSettings.root_path + "test/tmp/mlmethodassessment/"
PathBuilder.build(path)
dataset = RepertoireDataset(repertoires=RepertoireBuilder.build([["AA"], ["CC"], ["AA"], ["CC"], ["AA"], ["CC"], ["AA"], ["CC"], ["AA"], ["CC"], ["AA"], ["CC"]], path)[0])
dataset.encoded_data = EncodedData(
examples=np.array([[1, 1], [1, 1], [3, 3], [1, 1], [1, 1], [3, 3], [1, 1], [1, 1], [3, 3], [1, 1], [1, 1], [3, 3]]),
labels={"l1": [1, 1, 3, 1, 1, 3, 1, 1, 3, 1, 1, 3], "l2": [1, 2, 3, 1, 2, 3, 1, 2, 3, 1, 2, 3]}
)
label_config = LabelConfiguration()
label_config.add_label("l1", [1, 3])
method1 = LogisticRegression()
method1.fit(dataset.encoded_data, label_name='l1')
res = MLMethodAssessment.run(MLMethodAssessmentParams(
dataset=dataset,
method=method1,
metrics={Metric.ACCURACY, Metric.BALANCED_ACCURACY, Metric.F1_MACRO},
optimization_metric=Metric.LOG_LOSS,
predictions_path=EnvironmentSettings.root_path + "test/tmp/mlmethodassessment/predictions.csv",
label="l1",
ml_score_path=EnvironmentSettings.root_path + "test/tmp/mlmethodassessment/ml_score.csv",
split_index=1,
path=EnvironmentSettings.root_path + "test/tmp/mlmethodassessment/"
))
self.assertTrue(isinstance(res, dict))
self.assertTrue(res[Metric.LOG_LOSS.name.lower()] <= 0.1)
self.assertTrue(os.path.isfile(EnvironmentSettings.root_path + "test/tmp/mlmethodassessment/ml_score.csv"))
df = pd.read_csv(EnvironmentSettings.root_path + "test/tmp/mlmethodassessment/ml_score.csv")
self.assertTrue(df.shape[0] == 1)
df = pd.read_csv(EnvironmentSettings.root_path + "test/tmp/mlmethodassessment/predictions.csv")
self.assertEqual(12, df.shape[0])
shutil.rmtree(EnvironmentSettings.root_path + "test/tmp/mlmethodassessment/")