def test_all_metrics():
"""Check all supported metrics work"""
params = {'function_set': ['add2', 'sub2', 'mul2', 'div2'],
'arities': {2: ['add2', 'sub2', 'mul2', 'div2']},
'init_depth': (2, 6),
'init_method': 'half and half',
'n_features': 10,
'const_range': (-1.0, 1.0),
'metric': 'mean absolute error',
'p_point_replace': 0.05,
'parsimony_coefficient': 0.1}
random_state = check_random_state(415)
# Test for a small program
test_gp = ['mul2', 'div2', 8, 1, 'sub2', 9, .5]
gp = _Program(random_state=random_state, program=test_gp, **params)
X = np.reshape(random_state.uniform(size=50), (5, 10))
y = random_state.uniform(size=5)
sample_weight = np.ones(5)
expected = [1.48719809776, 1.82389179833, 1.76013763179, 0.98663772258,
-0.2928200724, -0.5]
result = []
for m in ['mean absolute error', 'mse', 'rmse', 'rmsle',
'pearson', 'spearman']:
gp.metric = m
gp.raw_fitness_ = gp.raw_fitness(X, y, sample_weight)
result.append(gp.fitness())
assert_array_almost_equal(result, expected)
# And check a fake one
gp.metric = 'the larch'
assert_raises(ValueError, gp.raw_fitness, X, y, sample_weight)
def check_regressors_train(name, Regressor):
X, y = _boston_subset()
y = StandardScaler().fit_transform(y) # X is already scaled
y = multioutput_estimator_convert_y_2d(name, y)
rnd = np.random.RandomState(0)
# catch deprecation warnings
with warnings.catch_warnings(record=True):
regressor = Regressor()
set_fast_parameters(regressor)
if not hasattr(regressor, 'alphas') and hasattr(regressor, 'alpha'):
# linear regressors need to set alpha, but not generalized CV ones
regressor.alpha = 0.01
if name == 'PassiveAggressiveRegressor':
regressor.C = 0.01
# raises error on malformed input for fit
assert_raises(ValueError, regressor.fit, X, y[:-1])
# fit
if name in CROSS_DECOMPOSITION:
y_ = np.vstack([y, 2 * y + rnd.randint(2, size=len(y))])
y_ = y_.T
else:
y_ = y
set_random_state(regressor)
regressor.fit(X, y_)
regressor.fit(X.tolist(), y_.tolist())
regressor.predict(X)
# TODO: find out why PLS and CCA fail. RANSAC is random
# and furthermore assumes the presence of outliers, hence
# skipped
if name not in ('PLSCanonical', 'CCA', 'RANSACRegressor'):
print(regressor)
assert_greater(regressor.score(X, y_), 0.5)
def check_transformers_unfitted(name, Transformer):
X, y = _boston_subset()
with warnings.catch_warnings(record=True):
transformer = Transformer()
assert_raises(NotFittedError, transformer.transform, X)
def test_transformer_iterable():
"""Check that the transformer is iterable"""
random_state = check_random_state(415)
X = np.reshape(random_state.uniform(size=50), (5, 10))
y = random_state.uniform(size=5)
est = SymbolicTransformer(generations=2, random_state=0)
# Check unfitted
unfitted_len = len(est)
unfitted_iter = [gp.length_ for gp in est]
expected_iter = []
assert_true(unfitted_len == 0)
assert_true(unfitted_iter == expected_iter)
# Check fitted
est.fit(X, y)
fitted_len = len(est)
fitted_iter = [gp.length_ for gp in est]
expected_iter = [15, 19, 19, 12, 9, 10, 7, 14, 6, 21]
assert_true(fitted_len == 10)
assert_true(fitted_iter == expected_iter)
# Check IndexError
assert_raises(IndexError, est.__getitem__, 10)
def test_transformer_iterable():
"""Check that the transformer is iterable"""
random_state = check_random_state(415)
X = np.reshape(random_state.uniform(size=50), (5, 10))
y = random_state.uniform(size=5)
function_set = [
'add', 'sub', 'mul', 'div', 'sqrt', 'log', 'abs', 'neg', 'inv', 'max',
'min'
]
est = SymbolicTransformer(population_size=500,
generations=2,
function_set=function_set,
random_state=0)
# Check unfitted
unfitted_len = len(est)
unfitted_iter = [gp.length_ for gp in est]
expected_iter = []
assert_true(unfitted_len == 0)
assert_true(unfitted_iter == expected_iter)
# Check fitted
est.fit(X, y)
fitted_len = len(est)
fitted_iter = [gp.length_ for gp in est]
expected_iter = [15, 19, 19, 12, 9, 10, 7, 14, 6, 21]
assert_true(fitted_len == 10)
assert_true(fitted_iter == expected_iter)
# Check IndexError
assert_raises(IndexError, est.__getitem__, 10)
def test_validate_program():
"""Check that valid programs are accepted & invalid ones raise error"""
function_set = ['add2', 'sub2', 'mul2', 'div2',
'sqrt1', 'log1', 'abs1', 'max2', 'min2']
arities = {1: ['sqrt1', 'log1', 'abs1'],
2: ['add2', 'sub2', 'mul2', 'div2', 'max2', 'min2']}
init_depth = (2, 6)
init_method = 'half and half'
n_features = 10
const_range = (-1.0, 1.0)
metric = 'mean absolute error'
p_point_replace = 0.05
parsimony_coefficient = 0.1
random_state = check_random_state(415)
test_gp = ['sub2', 'abs1', 'sqrt1', 'log1', 'log1', 'sqrt1', 7, 'abs1',
'abs1', 'abs1', 'log1', 'sqrt1', 2]
# This one should be fine
_ = _Program(function_set, arities, init_depth, init_method, n_features,
const_range, metric, p_point_replace, parsimony_coefficient,
random_state, test_gp)
# Now try a couple that shouldn't be
assert_raises(ValueError, _Program, function_set, arities, init_depth,
init_method, n_features, const_range, metric,
p_point_replace, parsimony_coefficient, random_state,
test_gp[:-1])
assert_raises(ValueError, _Program, function_set, arities, init_depth,
init_method, n_features, const_range, metric,
p_point_replace, parsimony_coefficient, random_state,
test_gp + [1])
def test_make_rng():
# Check the check_random_state utility function behavior
assert_true(check_random_state(None) is np.random.mtrand._rand)
assert_true(check_random_state(np.random) is np.random.mtrand._rand)
rng_42 = np.random.RandomState(42)
assert_true(check_random_state(42).randint(100) == rng_42.randint(100))
rng_42 = np.random.RandomState(42)
assert_true(check_random_state(rng_42) is rng_42)
rng_42 = np.random.RandomState(42)
assert_true(check_random_state(43).randint(100) != rng_42.randint(100))
assert_raises(ValueError, check_random_state, "some invalid seed")
def test_make_rng():
# Check the check_random_state utility function behavior
assert_true(check_random_state(None) is np.random.mtrand._rand)
assert_true(check_random_state(np.random) is np.random.mtrand._rand)
rng_42 = np.random.RandomState(42)
assert_true(check_random_state(42).randint(100) == rng_42.randint(100))
rng_42 = np.random.RandomState(42)
assert_true(check_random_state(rng_42) is rng_42)
rng_42 = np.random.RandomState(42)
assert_true(check_random_state(43).randint(100) != rng_42.randint(100))
assert_raises(ValueError, check_random_state, "some invalid seed")
def check_estimators_empty_data_messages(name, Estimator):
e = Estimator()
set_fast_parameters(e)
set_random_state(e, 1)
X_zero_samples = np.empty(0).reshape(0, 3)
# The precise message can change depending on whether X or y is
# validated first. Let us test the type of exception only:
assert_raises(ValueError, e.fit, X_zero_samples, [])
X_zero_features = np.empty(0).reshape(3, 0)
# the following y should be accepted by both classifiers and regressors
# and ignored by unsupervised models
y = multioutput_estimator_convert_y_2d(name, np.array([1, 0, 1]))
msg = "0 feature(s) (shape=(3, 0)) while a minimum of 1 is required."
assert_raise_message(ValueError, msg, e.fit, X_zero_features, y)
def check_estimators_partial_fit_n_features(name, Alg):
# check if number of features changes between calls to partial_fit.
if not hasattr(Alg, 'partial_fit'):
return
X, y = make_blobs(n_samples=50, random_state=1)
X -= X.min()
with warnings.catch_warnings(record=True):
alg = Alg()
set_fast_parameters(alg)
if isinstance(alg, ClassifierMixin):
classes = np.unique(y)
alg.partial_fit(X, y, classes=classes)
else:
alg.partial_fit(X, y)
assert_raises(ValueError, alg.partial_fit, X[:, :-1], y)
def test_input_shape():
"""Check changed dimensions cause failure"""
random_state = check_random_state(415)
X = np.reshape(random_state.uniform(size=50), (5, 10))
y = random_state.uniform(size=5)
X2 = np.reshape(random_state.uniform(size=45), (5, 9))
# Check the regressor
est = SymbolicRegressor(generations=2, random_state=0)
est.fit(X, y)
assert_raises(ValueError, est.predict, X2)
# Check the transformer
est = SymbolicTransformer(generations=2, random_state=0)
est.fit(X, y)
assert_raises(ValueError, est.transform, X2)
def test_input_shape():
"""Check changed dimensions cause failure"""
random_state = check_random_state(415)
X = np.reshape(random_state.uniform(size=50), (5, 10))
y = random_state.uniform(size=5)
X2 = np.reshape(random_state.uniform(size=45), (5, 9))
# Check the regressor
est = SymbolicRegressor(generations=2, random_state=0)
est.fit(X, y)
assert_raises(ValueError, est.predict, X2)
# Check the transformer
est = SymbolicTransformer(generations=2, random_state=0)
est.fit(X, y)
assert_raises(ValueError, est.transform, X2)
def check_classifiers_pickle(name, Classifier):
X, y = make_blobs(random_state=0)
X, y = shuffle(X, y, random_state=7)
X -= X.min()
# catch deprecation warnings
with warnings.catch_warnings(record=True):
classifier = Classifier()
set_fast_parameters(classifier)
# raises error on malformed input for fit
assert_raises(ValueError, classifier.fit, X, y[:-1])
# fit
classifier.fit(X, y)
y_pred = classifier.predict(X)
pickled_classifier = pickle.dumps(classifier)
unpickled_classifier = pickle.loads(pickled_classifier)
pickled_y_pred = unpickled_classifier.predict(X)
assert_array_almost_equal(pickled_y_pred, y_pred)
def test_column_or_1d():
EXAMPLES = [
("binary", ["spam", "egg", "spam"]),
("binary", [0, 1, 0, 1]),
("continuous", np.arange(10) / 20.),
("multiclass", [1, 2, 3]),
("multiclass", [0, 1, 2, 2, 0]),
("multiclass", [[1], [2], [3]]),
("multilabel-indicator", [[0, 1, 0], [0, 0, 1]]),
("multiclass-multioutput", [[1, 2, 3]]),
("multiclass-multioutput", [[1, 1], [2, 2], [3, 1]]),
("multiclass-multioutput", [[5, 1], [4, 2], [3, 1]]),
("multiclass-multioutput", [[1, 2, 3]]),
("continuous-multioutput", np.arange(30).reshape((-1, 3))),
]
for y_type, y in EXAMPLES:
if y_type in ["binary", 'multiclass', "continuous"]:
assert_array_equal(column_or_1d(y), np.ravel(y))
else:
assert_raises(ValueError, column_or_1d, y)
def test_column_or_1d():
EXAMPLES = [
("binary", ["spam", "egg", "spam"]),
("binary", [0, 1, 0, 1]),
("continuous", np.arange(10) / 20.),
("multiclass", [1, 2, 3]),
("multiclass", [0, 1, 2, 2, 0]),
("multiclass", [[1], [2], [3]]),
("multilabel-indicator", [[0, 1, 0], [0, 0, 1]]),
("multiclass-multioutput", [[1, 2, 3]]),
("multiclass-multioutput", [[1, 1], [2, 2], [3, 1]]),
("multiclass-multioutput", [[5, 1], [4, 2], [3, 1]]),
("multiclass-multioutput", [[1, 2, 3]]),
("continuous-multioutput", np.arange(30).reshape((-1, 3))),
]
for y_type, y in EXAMPLES:
if y_type in ["binary", 'multiclass', "continuous"]:
assert_array_equal(column_or_1d(y), np.ravel(y))
else:
assert_raises(ValueError, column_or_1d, y)
def test_validate_functions():
"""Check that valid functions are accepted & invalid ones raise error"""
random_state = check_random_state(415)
X = np.reshape(random_state.uniform(size=50), (5, 10))
y = random_state.uniform(size=5)
for Symbolic in (SymbolicRegressor, SymbolicTransformer):
# These should be fine
est = Symbolic(generations=2,
random_state=0,
function_set=(add2, sub2, mul2, div2))
est.fit(boston.data, boston.target)
est = Symbolic(generations=2,
random_state=0,
function_set=('add', 'sub', 'mul', div2))
est.fit(boston.data, boston.target)
# These should fail
est = Symbolic(generations=2,
random_state=0,
function_set=('ni', 'sub', 'mul', div2))
assert_raises(ValueError, est.fit, boston.data, boston.target)
est = Symbolic(generations=2,
random_state=0,
function_set=(7, 'sub', 'mul', div2))
assert_raises(ValueError, est.fit, boston.data, boston.target)
est = Symbolic(generations=2, random_state=0, function_set=())
assert_raises(ValueError, est.fit, boston.data, boston.target)
def test_indices():
"""Check that indices are stable when generated on the fly."""
params = {
'function_set': [add2, sub2, mul2, div2],
'arities': {
2: [add2, sub2, mul2, div2]
},
'init_depth': (2, 6),
'init_method': 'half and half',
'n_features': 10,
'const_range': (-1.0, 1.0),
'metric': 'mean absolute error',
'p_point_replace': 0.05,
'parsimony_coefficient': 0.1
}
random_state = check_random_state(415)
test_gp = [mul2, div2, 8, 1, sub2, 9, .5]
gp = _Program(random_state=random_state, program=test_gp, **params)
assert_raises(ValueError, gp.get_all_indices)
assert_raises(ValueError, gp._indices)
def get_indices_property():
return gp.indices_
assert_raises(ValueError, get_indices_property)
indices, _ = gp.get_all_indices(10, 7, random_state)
assert_array_equal(indices, gp.get_all_indices()[0])
assert_array_equal(indices, gp._indices())
assert_array_equal(indices, gp.indices_)
def test_all_metrics():
"""Check all supported metrics work"""
params = {
'function_set': [add2, sub2, mul2, div2],
'arities': {
2: [add2, sub2, mul2, div2]
},
'init_depth': (2, 6),
'init_method': 'half and half',
'n_features': 10,
'const_range': (-1.0, 1.0),
'metric': 'mean absolute error',
'p_point_replace': 0.05,
'parsimony_coefficient': 0.1
}
random_state = check_random_state(415)
# Test for a small program
test_gp = [mul2, div2, 8, 1, sub2, 9, .5]
gp = _Program(random_state=random_state, program=test_gp, **params)
X = np.reshape(random_state.uniform(size=50), (5, 10))
y = random_state.uniform(size=5)
sample_weight = np.ones(5)
expected = [
1.48719809776, 1.82389179833, 1.76013763179, 0.98663772258,
-0.2928200724, -0.5
]
result = []
for m in [
'mean absolute error', 'mse', 'rmse', 'rmsle', 'pearson',
'spearman'
]:
gp.metric = m
gp.raw_fitness_ = gp.raw_fitness(X, y, sample_weight)
result.append(gp.fitness())
assert_array_almost_equal(result, expected)
# And check a fake one
gp.metric = 'the larch'
assert_raises(ValueError, gp.raw_fitness, X, y, sample_weight)
def check_estimators_unfitted(name, Estimator):
"""Check if NotFittedError is raised when calling predict and related
functions"""
# Common test for Regressors as well as Classifiers
X, y = _boston_subset()
with warnings.catch_warnings(record=True):
est = Estimator()
assert_raises(NotFittedError, est.predict, X)
if hasattr(est, 'predict'):
assert_raises(NotFittedError, est.predict, X)
if hasattr(est, 'decision_function'):
assert_raises(NotFittedError, est.decision_function, X)
if hasattr(est, 'predict_proba'):
assert_raises(NotFittedError, est.predict_proba, X)
if hasattr(est, 'predict_log_proba'):
assert_raises(NotFittedError, est.predict_log_proba, X)
def test_validate_program():
"""Check that valid programs are accepted & invalid ones raise error"""
function_set = [add2, sub2, mul2, div2, sqrt1, log1, abs1, max2, min2]
arities = {
1: [sqrt1, log1, abs1],
2: [add2, sub2, mul2, div2, max2, min2]
},
init_depth = (2, 6)
init_method = 'half and half'
n_features = 10
const_range = (-1.0, 1.0)
metric = 'mean absolute error'
p_point_replace = 0.05
parsimony_coefficient = 0.1
random_state = check_random_state(415)
test_gp = [
sub2, abs1, sqrt1, log1, log1, sqrt1, 7, abs1, abs1, abs1, log1, sqrt1,
2
]
# This one should be fine
_ = _Program(function_set, arities, init_depth, init_method, n_features,
const_range, metric, p_point_replace, parsimony_coefficient,
random_state, test_gp)
# Now try a couple that shouldn't be
assert_raises(ValueError, _Program, function_set, arities, init_depth,
init_method, n_features, const_range, metric,
p_point_replace, parsimony_coefficient, random_state,
test_gp[:-1])
assert_raises(ValueError, _Program, function_set, arities, init_depth,
init_method, n_features, const_range, metric,
p_point_replace, parsimony_coefficient, random_state,
test_gp + [1])
def test_validate_fitness():
"""Check that valid fitness measures are accepted & invalid raise error"""
# Check arg count checks
fun = make_fitness(function=_mean_square_error, greater_is_better=True)
# non-bool greater_is_better
assert_raises(ValueError, make_fitness, _mean_square_error, 'Sure')
assert_raises(ValueError, make_fitness, _mean_square_error, 1)
# Check arg count tests
def bad_fun1(x1, x2):
return 1.0
assert_raises(ValueError, make_fitness, bad_fun1, True)
# Check return type tests
def bad_fun2(x1, x2, w):
return 'ni'
assert_raises(ValueError, make_fitness, bad_fun2, True)
def test_program_input_validation():
"""Check that guarded input validation raises errors"""
for Symbolic in (SymbolicRegressor, SymbolicTransformer):
# Check too much proba
est = Symbolic(p_point_mutation=.5)
assert_raises(ValueError, est.fit, boston.data, boston.target)
# Check invalid init_method
est = Symbolic(init_method='ni')
assert_raises(ValueError, est.fit, boston.data, boston.target)
# Check invalid const_ranges
est = Symbolic(const_range=2)
assert_raises(ValueError, est.fit, boston.data, boston.target)
est = Symbolic(const_range=[2, 2])
assert_raises(ValueError, est.fit, boston.data, boston.target)
est = Symbolic(const_range=(2, 2, 2))
assert_raises(ValueError, est.fit, boston.data, boston.target)
est = Symbolic(const_range='ni')
assert_raises(ValueError, est.fit, boston.data, boston.target)
# And check acceptable, but strange, representations of init_depth
est = Symbolic(const_range=(2, 2))
est.fit(boston.data, boston.target)
est = Symbolic(const_range=(4, 2))
est.fit(boston.data, boston.target)
# Check invalid init_depth
est = Symbolic(init_depth=2)
assert_raises(ValueError, est.fit, boston.data, boston.target)
est = Symbolic(init_depth=2)
assert_raises(ValueError, est.fit, boston.data, boston.target)
est = Symbolic(init_depth=[2, 2])
assert_raises(ValueError, est.fit, boston.data, boston.target)
est = Symbolic(init_depth=(2, 2, 2))
assert_raises(ValueError, est.fit, boston.data, boston.target)
est = Symbolic(init_depth='ni')
assert_raises(ValueError, est.fit, boston.data, boston.target)
est = Symbolic(init_depth=(4, 2))
assert_raises(ValueError, est.fit, boston.data, boston.target)
# And check acceptable, but strange, representations of init_depth
est = Symbolic(init_depth=(2, 2))
est.fit(boston.data, boston.target)
# Check hall_of_fame and n_components for transformer
est = SymbolicTransformer(hall_of_fame=1000)
assert_raises(ValueError, est.fit, boston.data, boston.target)
est = SymbolicTransformer(n_components=1000)
assert_raises(ValueError, est.fit, boston.data, boston.target)
est = SymbolicTransformer(hall_of_fame=0)
assert_raises(ValueError, est.fit, boston.data, boston.target)
est = SymbolicTransformer(n_components=0)
assert_raises(ValueError, est.fit, boston.data, boston.target)
# Check regressor metrics
for m in ['mean absolute error', 'mse', 'rmse', 'rmsle']:
est = SymbolicRegressor(generations=2, metric=m)
est.fit(boston.data, boston.target)
# And check the transformer metrics as well as a fake one
for m in ['pearson', 'spearman', 'the larch']:
est = SymbolicRegressor(generations=2, metric=m)
assert_raises(ValueError, est.fit, boston.data, boston.target)
# Check transformer metrics
for m in ['pearson', 'spearman']:
est = SymbolicTransformer(generations=2, metric=m)
est.fit(boston.data, boston.target)
# And check the regressor metrics as well as a fake one
for m in ['mean absolute error', 'mse', 'rmse', 'rmsle', 'the larch']:
est = SymbolicTransformer(generations=2, metric=m)
assert_raises(ValueError, est.fit, boston.data, boston.target)
def test_resample_value_errors():
# Check that invalid arguments yield ValueError
assert_raises(ValueError, resample, [0], [0, 1])
assert_raises(ValueError, resample, [0, 1], [0, 1], n_samples=3)
assert_raises(ValueError, resample, [0, 1], [0, 1], meaning_of_life=42)
def check_classifiers_train(name, Classifier):
X_m, y_m = make_blobs(random_state=0)
X_m, y_m = shuffle(X_m, y_m, random_state=7)
X_m = StandardScaler().fit_transform(X_m)
# generate binary problem from multi-class one
y_b = y_m[y_m != 2]
X_b = X_m[y_m != 2]
for (X, y) in [(X_m, y_m), (X_b, y_b)]:
# catch deprecation warnings
classes = np.unique(y)
n_classes = len(classes)
n_samples, n_features = X.shape
with warnings.catch_warnings(record=True):
classifier = Classifier()
if name in ['BernoulliNB', 'MultinomialNB']:
X -= X.min()
set_fast_parameters(classifier)
set_random_state(classifier)
# raises error on malformed input for fit
assert_raises(ValueError, classifier.fit, X, y[:-1])
# fit
classifier.fit(X, y)
# with lists
classifier.fit(X.tolist(), y.tolist())
assert_true(hasattr(classifier, "classes_"))
y_pred = classifier.predict(X)
assert_equal(y_pred.shape, (n_samples,))
# training set performance
if name not in ['BernoulliNB', 'MultinomialNB']:
assert_greater(accuracy_score(y, y_pred), 0.83)
# raises error on malformed input for predict
assert_raises(ValueError, classifier.predict, X.T)
if hasattr(classifier, "decision_function"):
try:
# decision_function agrees with predict
decision = classifier.decision_function(X)
if n_classes is 2:
assert_equal(decision.shape, (n_samples,))
dec_pred = (decision.ravel() > 0).astype(np.int)
assert_array_equal(dec_pred, y_pred)
if n_classes is 3:
assert_equal(decision.shape, (n_samples, n_classes))
assert_array_equal(np.argmax(decision, axis=1), y_pred)
# raises error on malformed input
assert_raises(ValueError,
classifier.decision_function, X.T)
# raises error on malformed input for decision_function
assert_raises(ValueError,
classifier.decision_function, X.T)
except NotImplementedError:
pass
if hasattr(classifier, "predict_proba"):
# predict_proba agrees with predict
y_prob = classifier.predict_proba(X)
assert_equal(y_prob.shape, (n_samples, n_classes))
assert_array_equal(np.argmax(y_prob, axis=1), y_pred)
# check that probas for all classes sum to one
assert_array_almost_equal(np.sum(y_prob, axis=1),
np.ones(n_samples))
# raises error on malformed input
assert_raises(ValueError, classifier.predict_proba, X.T)
# raises error on malformed input for predict_proba
assert_raises(ValueError, classifier.predict_proba, X.T)
def test_resample_value_errors():
# Check that invalid arguments yield ValueError
assert_raises(ValueError, resample, [0], [0, 1])
assert_raises(ValueError, resample, [0, 1], [0, 1], n_samples=3)
assert_raises(ValueError, resample, [0, 1], [0, 1], meaning_of_life=42)
def _check_transformer(name, Transformer, X, y):
if name in ('CCA', 'LocallyLinearEmbedding', 'KernelPCA') and _is_32bit():
# Those transformers yield non-deterministic output when executed on
# a 32bit Python. The same transformers are stable on 64bit Python.
# FIXME: try to isolate a minimalistic reproduction case only depending
# on numpy & scipy and/or maybe generate a test dataset that does not
# cause such unstable behaviors.
msg = name + ' is non deterministic on 32bit Python'
raise SkipTest(msg)
n_samples, n_features = np.asarray(X).shape
# catch deprecation warnings
with warnings.catch_warnings(record=True):
transformer = Transformer()
set_random_state(transformer)
set_fast_parameters(transformer)
# fit
if name in CROSS_DECOMPOSITION:
y_ = np.c_[y, y]
y_[::2, 1] *= 2
else:
y_ = y
transformer.fit(X, y_)
X_pred = transformer.fit_transform(X, y=y_)
if isinstance(X_pred, tuple):
for x_pred in X_pred:
assert_equal(x_pred.shape[0], n_samples)
else:
assert_equal(X_pred.shape[0], n_samples)
if hasattr(transformer, 'transform'):
if name in CROSS_DECOMPOSITION:
X_pred2 = transformer.transform(X, y_)
X_pred3 = transformer.fit_transform(X, y=y_)
else:
X_pred2 = transformer.transform(X)
X_pred3 = transformer.fit_transform(X, y=y_)
if isinstance(X_pred, tuple) and isinstance(X_pred2, tuple):
for x_pred, x_pred2, x_pred3 in zip(X_pred, X_pred2, X_pred3):
assert_array_almost_equal(
x_pred, x_pred2, 2,
"fit_transform and transform outcomes not consistent in %s"
% Transformer)
assert_array_almost_equal(
x_pred, x_pred3, 2,
"consecutive fit_transform outcomes not consistent in %s"
% Transformer)
else:
assert_array_almost_equal(
X_pred, X_pred2, 2,
"fit_transform and transform outcomes not consistent in %s"
% Transformer)
assert_array_almost_equal(
X_pred, X_pred3, 2,
"consecutive fit_transform outcomes not consistent in %s"
% Transformer)
# raises error on malformed input for transform
if hasattr(X, 'T'):
# If it's not an array, it does not have a 'T' property
assert_raises(ValueError, transformer.transform, X.T)
def test_compute_class_weight_not_present():
# Raise error when y does not contain all class labels
classes = np.arange(4)
y = np.asarray([0, 0, 0, 1, 1, 2])
assert_raises(ValueError, compute_class_weight, "auto", classes, y)
def test_compute_sample_weight_errors():
# Test compute_sample_weight raises errors expected.
# Invalid preset string
y = np.asarray([1, 1, 1, 2, 2, 2])
y_ = np.asarray([[1, 0], [1, 0], [1, 0], [2, 1], [2, 1], [2, 1]])
assert_raises(ValueError, compute_sample_weight, "ni", y)
assert_raises(ValueError, compute_sample_weight, "ni", y, range(4))
assert_raises(ValueError, compute_sample_weight, "ni", y_)
assert_raises(ValueError, compute_sample_weight, "ni", y_, range(4))
# Not "auto" for subsample
assert_raises(ValueError,
compute_sample_weight, {1: 2, 2: 1}, y, range(4))
# Not a list or preset for multi-output
assert_raises(ValueError, compute_sample_weight, {1: 2, 2: 1}, y_)
# Incorrect length list for multi-output
assert_raises(ValueError, compute_sample_weight, [{1: 2, 2: 1}], y_)
def test_validate_function():
"""Check that valid functions are accepted & invalid ones raise error"""
# Check arity tests
fun = make_function(function=_protected_sqrt, name='sqrt', arity=1)
# non-integer arity
assert_raises(ValueError, make_function, _protected_sqrt, 'sqrt', '1')
assert_raises(ValueError, make_function, _protected_sqrt, 'sqrt', 1.0)
# non-matching arity
assert_raises(ValueError, make_function, _protected_sqrt, 'sqrt', 2)
assert_raises(ValueError, make_function, maximum, 'max', 1)
# Check name test
assert_raises(ValueError, make_function, _protected_sqrt, 2, 1)
# Check return type tests
def bad_fun1(x1, x2):
return 'ni'
assert_raises(ValueError, make_function, bad_fun1, 'ni', 2)
# Check return shape tests
def bad_fun2(x1):
return np.ones((2, 1))
assert_raises(ValueError, make_function, bad_fun2, 'ni', 1)
# Check closure for negatives test
def _unprotected_sqrt(x1):
with np.errstate(divide='ignore', invalid='ignore'):
return np.sqrt(x1)
assert_raises(ValueError, make_function, _unprotected_sqrt, 'sqrt', 1)
# Check closure for zeros test
def _unprotected_div(x1, x2):
with np.errstate(divide='ignore', invalid='ignore'):
return np.divide(x1, x2)
assert_raises(ValueError, make_function, _unprotected_div, 'div', 2)
def test_program_input_validation():
"""Check that guarded input validation raises errors"""
for Symbolic in (SymbolicRegressor, SymbolicTransformer):
# Check too much proba
est = Symbolic(p_point_mutation=.5)
assert_raises(ValueError, est.fit, boston.data, boston.target)
# Check invalid init_method
est = Symbolic(init_method='ni')
assert_raises(ValueError, est.fit, boston.data, boston.target)
# Check invalid const_ranges
est = Symbolic(const_range=2)
assert_raises(ValueError, est.fit, boston.data, boston.target)
est = Symbolic(const_range=[2, 2])
assert_raises(ValueError, est.fit, boston.data, boston.target)
est = Symbolic(const_range=(2, 2, 2))
assert_raises(ValueError, est.fit, boston.data, boston.target)
est = Symbolic(const_range='ni')
assert_raises(ValueError, est.fit, boston.data, boston.target)
# And check acceptable, but strange, representations of init_depth
est = Symbolic(const_range=(2, 2))
est.fit(boston.data, boston.target)
est = Symbolic(const_range=(4, 2))
est.fit(boston.data, boston.target)
# Check invalid init_depth
est = Symbolic(init_depth=2)
assert_raises(ValueError, est.fit, boston.data, boston.target)
est = Symbolic(init_depth=2)
assert_raises(ValueError, est.fit, boston.data, boston.target)
est = Symbolic(init_depth=[2, 2])
assert_raises(ValueError, est.fit, boston.data, boston.target)
est = Symbolic(init_depth=(2, 2, 2))
assert_raises(ValueError, est.fit, boston.data, boston.target)
est = Symbolic(init_depth='ni')
assert_raises(ValueError, est.fit, boston.data, boston.target)
est = Symbolic(init_depth=(4, 2))
assert_raises(ValueError, est.fit, boston.data, boston.target)
# And check acceptable, but strange, representations of init_depth
est = Symbolic(init_depth=(2, 2))
est.fit(boston.data, boston.target)
# Check hall_of_fame and n_components for transformer
est = SymbolicTransformer(hall_of_fame=2000)
assert_raises(ValueError, est.fit, boston.data, boston.target)
est = SymbolicTransformer(n_components=2000)
assert_raises(ValueError, est.fit, boston.data, boston.target)
est = SymbolicTransformer(hall_of_fame=0)
assert_raises(ValueError, est.fit, boston.data, boston.target)
est = SymbolicTransformer(n_components=0)
assert_raises(ValueError, est.fit, boston.data, boston.target)
# Check regressor metrics
for m in ['mean absolute error', 'mse', 'rmse', 'rmsle']:
est = SymbolicRegressor(generations=2, metric=m)
est.fit(boston.data, boston.target)
# And check the transformer metrics as well as a fake one
for m in ['pearson', 'spearman', 'the larch']:
est = SymbolicRegressor(generations=2, metric=m)
assert_raises(ValueError, est.fit, boston.data, boston.target)
# Check transformer metrics
for m in ['pearson', 'spearman']:
est = SymbolicTransformer(generations=2, metric=m)
est.fit(boston.data, boston.target)
# And check the regressor metrics as well as a fake one
for m in ['mean absolute error', 'mse', 'rmse', 'rmsle', 'the larch']:
est = SymbolicTransformer(generations=2, metric=m)
assert_raises(ValueError, est.fit, boston.data, boston.target)