def test_preprocessor_normalization(self):
dataset = new_line(random_seed=0)
target_preprocessor = StandardPreprocessor(continuous=[0],
threshold=-1)
feature_preprocessor = StandardPreprocessor(continuous=[0],
threshold=-1)
num_batches = 8
for _ in range(num_batches):
X, y = dataset.input_fn()
# Inputs are all 1D
self.assertEqual(1, len(shape_of_array(X)))
self.assertEqual(1, len(shape_of_array(y)))
# Scale up to be able to put pressure on normalization
X = (X - 0.5) * 100
y = (y - 0.5) * 100
self.assertGreaterEqual(X.max() - X.min(), 1)
self.assertGreaterEqual(y.max() - y.min(), 1)
X_ = feature_preprocessor.fit(X).transform(X)
self.assertEqual(1, X_.ndim)
self.assertEqual(round(X_.mean()), 0, X_.mean())
self.assertNotAlmostEqual(X_.min(), 0)
self.assertNotAlmostEqual(X_.max(), 0)
y_ = target_preprocessor.fit(y).transform(y)
self.assertEqual(round(y_.mean()), 0, y_.mean())
self.assertNotAlmostEqual(y_.min(), 0)
self.assertNotAlmostEqual(y_.max(), 0)
def test_learner_synthetic(self):
opts = dict(random_seed=0)
test_data = [
(LinearRegressor, new_line(**opts), 0.95), # Approximate a line
(LogisticRegression, new_labels(**opts),
0.55), # Correctly guess labels
(LinearRegressor, new_poly(**opts),
0.85), # Approximate a 4th deg. poly
(LinearRegressor, new_3x3(**opts), 0.95), # 3x3 fuzzy matrix
]
for learner, dataset, target_score in test_data:
pipeline = learner(verbose=False, **opts)
history = pipeline.train(dataset.input_fn,
max_score=target_score,
progress=True)
self.assertGreaterEqual(max(history.scores), target_score,
dataset.name)
def test_learner_synthetic(self):
opts = dict(random_seed=0)
learner_kwargs = dict(kernel_size=1, padding=0, maxpool_size=1, **opts)
test_data = [
(CNNRegressor, new_line(**opts), 0.95), # Approximate a line
(CNNRegressor, new_trig(**opts), 0.60), # Approximate a sine curve
(CNNRegressor, new_poly(**opts),
0.85), # Approximate a 4th deg. poly
(CNNClassifier, new_labels(**opts),
0.80), # Correctly guess labels
(CNNRegressor, new_3x3(**opts), 0.90), # 3x3 fuzzy matrix
]
for learner, dataset, target_score in test_data:
pipeline = learner(verbose=False, **learner_kwargs)
history = pipeline.train(dataset.input_fn,
max_score=target_score,
progress=True)
self.assertGreaterEqual(max(history.scores), target_score,
dataset.name)
def test_learner_synthetic(self):
opts = dict(random_seed=0)
learners_classifiers = [
LogisticRegression, MLPClassifier, CNNClassifier
]
learners_regressors = [LinearRegressor, MLPRegressor, CNNRegressor]
test_data = [
(learners_regressors, new_line(**opts),
0.95), # Approximate a line
(learners_regressors, new_trig(**opts),
.75), # Approximate a sine curve
(learners_regressors, new_poly(**opts),
0.85), # Approximate a 4th deg. poly
(learners_classifiers, new_labels(**opts),
0.80), # Correctly guess labels
(learners_regressors, new_3x3(**opts), 0.90), # 3x3 fuzzy matrix
]
for learners, dataset, target_score in test_data:
pipeline = BruteForce(dataset, learners, n_jobs=4)
history = pipeline.train(dataset.input_fn,
max_score=target_score,
progress=True)
self.assertGreaterEqual(max(history.scores), target_score,
dataset.name)