def test_cleanup(self):
clf1 = RGFClassifier()
clf1.fit(self.X_train, self.y_train)
clf2 = RGFClassifier()
clf2.fit(self.X_train, self.y_train)
self.assertNotEqual(clf1.cleanup(), 0)
self.assertEqual(clf1.cleanup(), 0)
for est in clf1.estimators_:
glob_file = os.path.join(_get_temp_path(), est._file_prefix + "*")
self.assertFalse(glob.glob(glob_file))
self.assertRaises(NotFittedError, clf1.predict, self.X_test)
clf2.predict(self.X_test)
def test_string_y(self):
clf = RGFClassifier()
y_str = np.array(self.iris.target, dtype=str)
y_str[y_str == '0'] = 'Zero'
y_str[y_str == '1'] = 'One'
y_str[y_str == '2'] = 'Two'
clf.fit(self.iris.data, y_str)
y_pred = clf.predict(self.iris.data)
score = accuracy_score(y_str, y_pred)
self.assertGreater(score, 0.95, "Failed with score = {0:.5f}".format(score))
def test_pickle(self):
clf = RGFClassifier()
clf.fit(self.X_train, self.y_train)
y_pred1 = clf.predict(self.X_test)
s = pickle.dumps(clf)
# Remove model file
_cleanup()
reg2 = pickle.loads(s)
y_pred2 = reg2.predict(self.X_test)
np.testing.assert_allclose(y_pred1, y_pred2)
def test_joblib_pickle(self):
clf = RGFClassifier()
clf.fit(self.X_train, self.y_train)
y_pred1 = clf.predict(self.X_test)
joblib.dump(clf, 'test_clf.pkl')
# Remove model file
_cleanup()
clf2 = joblib.load('test_clf.pkl')
y_pred2 = clf2.predict(self.X_test)
np.testing.assert_allclose(y_pred1, y_pred2)
def train(params):
# log hyperparams for this run
for k, v in params.items():
mlflow.log_param(k, v)
# load dataset files
# NOTE: to get meta data, set allow_pickle=True for np.load, then index into dataset object with key 'meta'
dataset = np.load('preprocessed/dataset.npz')
X_arr = dataset['X_arr']
Y_arr = dataset['Y_arr']
# split for train-test
X_train, X_test, Y_train, Y_test = train_test_split(X_arr,
Y_arr,
stratify=Y_arr,
test_size=0.2)
# instantiate model with params
rgf_clf = RGFClassifier(**params)
rgf_clf.fit(X_train, Y_train)
# predict on test data
Y_pred = rgf_clf.predict(X_test)
Y_pred_proba = rgf_clf.predict_proba(X_test)
# log logistic loss value
logistic_loss = log_loss(Y_test, Y_pred_proba)
mlflow.log_metric('log_loss', logistic_loss)
# log precision, recall, f1
p, r, f, _ = precision_recall_fscore_support(y_true=Y_test,
y_pred=Y_pred,
average='binary')
mlflow.log_metric('precision', p)
mlflow.log_metric('recall', r)
mlflow.log_metric('f1', f)
# which features matter the most
print("========== FEATURE IMPORTANCES ==========")
print(rgf_clf.feature_importances_)