def test_fit_by_cross_validation(self):
x = EncodedData(
np.array([[1, 0, 0], [0, 1, 1], [1, 1, 1], [0, 1, 1], [1, 0, 0],
[0, 1, 1], [1, 1, 1], [0, 1, 1]]), {
"t1": [1, 0, 2, 0, 1, 0, 2, 0],
"t2": [1, 0, 2, 0, 1, 0, 2, 0]
})
svm = SVM()
svm.fit_by_cross_validation(x, number_of_splits=2, label_name="t1")
def test_predict(self):
x = np.array([[1, 0, 0], [0, 1, 1], [1, 1, 1], [0, 1, 1]])
y = {"test": np.array([1, 0, 2, 0])}
svm = SVM()
svm.fit(EncodedData(x, y), "test")
test_x = np.array([[0, 1, 0], [1, 0, 0]])
y = svm.predict(EncodedData(test_x), 'test')["test"]
self.assertTrue(len(y) == 2)
self.assertTrue(y[0] in [0, 1, 2])
self.assertTrue(y[1] in [0, 1, 2])
def test_store_load(self):
x = np.array([[1, 0, 0], [0, 1, 1], [1, 1, 1], [0, 1, 1]])
y = {"default": np.array(['a', "b", "c", "a"])}
svm = SVM()
svm._fit(sparse.csr_matrix(x), y["default"])
path = EnvironmentSettings.root_path / "test/tmp/store_load_sklearn/"
details_path = EnvironmentSettings.root_path / "test/tmp/store_load_sklearn/details.yaml"
svm.store(path=path, details_path=details_path)
svm2 = SVM()
svm2.load(path=path, details_path=details_path)
shutil.rmtree(path)
def test_load(self):
x = np.array([[1, 0, 0], [0, 1, 1], [1, 1, 1], [0, 1, 1]])
y = {"default": np.array([1, 0, 2, 0])}
svm = SVM()
svm.fit(EncodedData(x, y), 'default')
path = EnvironmentSettings.tmp_test_path / "my_svm2/"
PathBuilder.build(path)
with open(path / "svm.pickle", "wb") as file:
pickle.dump(svm.get_model(), file)
svm2 = SVM()
svm2.load(path)
self.assertTrue(isinstance(svm2.get_model(), SVC))
shutil.rmtree(path)
def test_store(self):
x = np.array([[1, 0, 0], [0, 1, 1], [1, 1, 1], [0, 1, 1]])
y = {"default": np.array(['a', "b", "c", "a"])}
svm = SVM()
svm.fit(EncodedData(x, y), 'default')
path = EnvironmentSettings.root_path / "my_svm/"
svm.store(path)
self.assertTrue(os.path.isfile(path / "svm.pickle"))
with open(path / "svm.pickle", "rb") as file:
svm2 = pickle.load(file)
self.assertTrue(isinstance(svm2, SVC))
shutil.rmtree(path)
def test_store(self):
x = np.array([[1, 0, 0], [0, 1, 1], [1, 1, 1], [0, 1, 1]])
y = {"default": np.array(['a', "b", "c", "a"])}
svm = SVM()
svm._fit(sparse.csr_matrix(x), y["default"])
path = EnvironmentSettings.root_path / "test/tmp/storesklearn/"
svm.store(path)
self.assertTrue(os.path.isfile(path / "svm.pickle"))
with open(path / "svm.pickle", "rb") as file:
svm2 = pickle.load(file)
self.assertTrue(isinstance(svm2, SVC))
shutil.rmtree(path)
def test_fit(self):
x = np.array([[1, 0, 0], [0, 1, 1], [1, 1, 1], [0, 1, 1]])
y = {"default": np.array([1, 0, 2, 0])}
svm = SVM()
svm.fit(EncodedData(x, y), 'default')
def test_run(self):
path = EnvironmentSettings.tmp_test_path / "hpoptimproc/"
PathBuilder.build(path)
repertoires, metadata = RepertoireBuilder.build(
sequences=[["AAA", "CCC", "DDD"], ["AAA", "CCC", "DDD"],
["AAA", "CCC", "DDD"], ["AAA", "CCC", "DDD"],
["AAA", "CCC", "DDD"], ["AAA", "CCC", "DDD"],
["AAA", "CCC", "DDD"], ["AAA", "CCC", "DDD"],
["AAA", "CCC", "DDD"], ["AAA", "CCC", "DDD"],
["AAA", "CCC", "DDD"], ["AAA", "CCC", "DDD"],
["AAA", "CCC", "DDD"], ["AAA", "CCC", "DDD"],
["AAA", "CCC", "DDD"], ["AAA", "CCC", "DDD"],
["AAA", "CCC", "DDD"], ["AAA", "CCC", "DDD"],
["AAA", "CCC", "DDD"], ["AAA", "CCC", "DDD"],
["AAA", "CCC", "DDD"], ["AAA", "CCC", "DDD"],
["AAA", "CCC", "DDD"], ["AAA", "CCC", "DDD"],
["AAA", "CCC", "DDD"], ["AAA", "CCC", "DDD"],
["AAA", "CCC", "DDD"], ["AAA", "CCC", "DDD"],
["AAA", "CCC", "DDD"], ["AAA", "CCC", "DDD"],
["AAA", "CCC", "DDD"], ["AAA", "CCC", "DDD"],
["AAA", "CCC", "DDD"], ["AAA", "CCC", "DDD"]],
path=path,
labels={
"l1": [
1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2,
1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2
],
"l2": [
0, 0, 1, 1, 0, 0, 1, 1, 0, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 1,
0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
]
})
dataset = RepertoireDataset(repertoires=repertoires,
metadata_file=metadata,
labels={
"l1": [1, 2],
"l2": [0, 1]
})
enc1 = {
"k": 3,
"model_type": ModelType.SEQUENCE.name,
"vector_size": 4
}
enc2 = {
"k": 3,
"model_type": ModelType.SEQUENCE.name,
"vector_size": 6
}
hp_settings = [
HPSetting(Word2VecEncoder.build_object(dataset, **enc1), enc1,
LogisticRegression(), {
"model_selection_cv": False,
"model_selection_n_folds": -1
}, []),
HPSetting(
Word2VecEncoder.build_object(dataset, **enc2), enc2, SVM(), {
"model_selection_cv": False,
"model_selection_n_folds": -1
},
[ClonesPerRepertoireFilter(lower_limit=-1, upper_limit=1000)])
]
report = SequenceLengthDistribution()
label_config = LabelConfiguration(
[Label("l1", [1, 2]), Label("l2", [0, 1])])
process = TrainMLModelInstruction(
dataset, GridSearch(hp_settings), hp_settings,
SplitConfig(SplitType.RANDOM,
1,
0.5,
reports=ReportConfig(data_splits={"seqlen": report})),
SplitConfig(SplitType.RANDOM,
1,
0.5,
reports=ReportConfig(data_splits={"seqlen": report})),
{Metric.BALANCED_ACCURACY}, Metric.BALANCED_ACCURACY, label_config,
path)
state = process.run(result_path=path)
self.assertTrue(isinstance(state, TrainMLModelState))
self.assertEqual(1, len(state.assessment_states))
self.assertTrue("l1" in state.assessment_states[0].label_states)
self.assertTrue("l2" in state.assessment_states[0].label_states)
shutil.rmtree(path)