def test_pipeline_subclass_correctly_supports_predict_proba(self):
X, y = generate_dataset_1()
pipeline = Pipeline([LogisticRegressionBinaryClassifier()])
pipeline.fit(X, y)
orig_result = pipeline.predict_proba(X)
pipeline = CustomPipeline([LogisticRegressionBinaryClassifier()])
pipeline.fit(X, y)
new_result = pipeline.predict_proba(X)
self.assertTrue(np.array_equal(orig_result, new_result))
def test_pass_predict_proba_from_load_model(selfs):
pipeline = Pipeline([LogisticRegressionBinaryClassifier()])
pipeline.fit(X_train, y_train)
probs1 = pipeline.predict_proba(X_test)
sum1 = probs1.sum().sum()
(fd, modelfilename) = tempfile.mkstemp(suffix='.model.bin')
fl = os.fdopen(fd, 'w')
fl.close()
pipeline.save_model(modelfilename)
pipeline2 = Pipeline()
pipeline2.load_model(modelfilename)
probs2 = pipeline2.predict_proba(X_test)
sum2 = probs2.sum().sum()
assert_equal(sum1, sum2,
"model probabilities don't match after loading model")
def test_pass_predict_proba_multiclass_with_pipeline_adds_classes(self):
clf = FastLinearClassifier(number_of_threads=1)
pipeline = Pipeline([clf])
pipeline.fit(X_train_3class, y_train_3class)
expected_classes = {'Blue', 'Green', 'Red'}
assert_equal(set(clf.classes_), expected_classes)
assert_equal(set(pipeline.classes_), expected_classes)
s = pipeline.predict_proba(X_test_3class).sum()
assert_almost_equal(s,
38.0,
decimal=4,
err_msg=invalid_predict_proba_output)
assert_equal(set(clf.classes_), expected_classes)
assert_equal(set(pipeline.classes_), expected_classes)
