def test_sample_weight():
"""Check sample_weight param works"""
# Check constant sample_weight has no effect
sample_weight = np.ones(boston.target.shape[0])
est1 = SymbolicRegressor(generations=2, random_state=0)
est1.fit(boston.data, boston.target)
est2 = SymbolicRegressor(generations=2, random_state=0)
est2.fit(boston.data, boston.target, sample_weight=sample_weight)
# And again with a scaled sample_weight
est3 = SymbolicRegressor(generations=2, random_state=0)
est3.fit(boston.data, boston.target, sample_weight=sample_weight * 1.1)
assert_almost_equal(est1._program.fitness_, est2._program.fitness_)
assert_almost_equal(est1._program.fitness_, est3._program.fitness_)
# And again for the transformer
sample_weight = np.ones(boston.target.shape[0])
est1 = SymbolicTransformer(generations=2, random_state=0)
est1 = est1.fit_transform(boston.data, boston.target)
est2 = SymbolicTransformer(generations=2, random_state=0)
est2 = est2.fit_transform(boston.data, boston.target,
sample_weight=sample_weight)
# And again with a scaled sample_weight
est3 = SymbolicTransformer(generations=2, random_state=0)
est3 = est3.fit_transform(boston.data, boston.target,
sample_weight=sample_weight * 1.1)
assert_array_almost_equal(est1, est2)
assert_array_almost_equal(est1, est3)
def check_transformer_pickle(name, Transformer):
X, y = make_blobs(n_samples=30, centers=[[0, 0, 0], [1, 1, 1]],
random_state=0, n_features=2, cluster_std=0.1)
n_samples, n_features = X.shape
X = StandardScaler().fit_transform(X)
X -= X.min()
# catch deprecation warnings
with warnings.catch_warnings(record=True):
transformer = Transformer()
if not hasattr(transformer, 'transform'):
return
set_random_state(transformer)
set_fast_parameters(transformer)
# fit
if name in CROSS_DECOMPOSITION:
random_state = np.random.RandomState(seed=12345)
y_ = np.vstack([y, 2 * y + random_state.randint(2, size=len(y))])
y_ = y_.T
else:
y_ = y
transformer.fit(X, y_)
X_pred = transformer.fit(X, y_).transform(X)
pickled_transformer = pickle.dumps(transformer)
unpickled_transformer = pickle.loads(pickled_transformer)
pickled_X_pred = unpickled_transformer.transform(X)
assert_array_almost_equal(pickled_X_pred, X_pred)
def check_regressors_int(name, Regressor):
X, _ = _boston_subset()
X = X[:50]
rnd = np.random.RandomState(0)
y = rnd.randint(3, size=X.shape[0])
y = multioutput_estimator_convert_y_2d(name, y)
rnd = np.random.RandomState(0)
# catch deprecation warnings
with warnings.catch_warnings(record=True):
# separate estimators to control random seeds
regressor_1 = Regressor()
regressor_2 = Regressor()
set_fast_parameters(regressor_1)
set_fast_parameters(regressor_2)
set_random_state(regressor_1)
set_random_state(regressor_2)
if name in CROSS_DECOMPOSITION:
y_ = np.vstack([y, 2 * y + rnd.randint(2, size=len(y))])
y_ = y_.T
else:
y_ = y
# fit
regressor_1.fit(X, y_)
pred1 = regressor_1.predict(X)
regressor_2.fit(X, y_.astype(np.float))
pred2 = regressor_2.predict(X)
assert_array_almost_equal(pred1, pred2, 2, name)
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_pickle(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 in CROSS_DECOMPOSITION:
y_ = np.vstack([y, 2 * y + rnd.randint(2, size=len(y))])
y_ = y_.T
else:
y_ = y
regressor.fit(X, y_)
y_pred = regressor.predict(X)
# store old predictions
pickled_regressor = pickle.dumps(regressor)
unpickled_regressor = pickle.loads(pickled_regressor)
pickled_y_pred = unpickled_regressor.predict(X)
assert_array_almost_equal(pickled_y_pred, y_pred)
def check_class_weight_auto_linear_classifier(name, Classifier):
"""Test class weights with non-contiguous class labels."""
X = np.array([[-1.0, -1.0], [-1.0, 0], [-.8, -1.0],
[1.0, 1.0], [1.0, 0.0]])
y = [1, 1, 1, -1, -1]
with warnings.catch_warnings(record=True):
classifier = Classifier()
if hasattr(classifier, "n_iter"):
# This is a very small dataset, default n_iter are likely to prevent
# convergence
classifier.set_params(n_iter=1000)
set_random_state(classifier)
# Let the model compute the class frequencies
classifier.set_params(class_weight='auto')
coef_auto = classifier.fit(X, y).coef_.copy()
# Count each label occurrence to reweight manually
mean_weight = (1. / 3 + 1. / 2) / 2
class_weight = {
1: 1. / 3 / mean_weight,
-1: 1. / 2 / mean_weight,
}
classifier.set_params(class_weight=class_weight)
coef_manual = classifier.fit(X, y).coef_.copy()
assert_array_almost_equal(coef_auto, coef_manual)
def test_sample_weight():
"""Check sample_weight param works"""
# Check constant sample_weight has no effect
sample_weight = np.ones(boston.target.shape[0])
est1 = SymbolicRegressor(generations=2, random_state=0)
est1.fit(boston.data, boston.target)
est2 = SymbolicRegressor(generations=2, random_state=0)
est2.fit(boston.data, boston.target, sample_weight=sample_weight)
# And again with a scaled sample_weight
est3 = SymbolicRegressor(generations=2, random_state=0)
est3.fit(boston.data, boston.target, sample_weight=sample_weight * 1.1)
assert_almost_equal(est1._program.fitness_, est2._program.fitness_)
assert_almost_equal(est1._program.fitness_, est3._program.fitness_)
# And again for the transformer
sample_weight = np.ones(boston.target.shape[0])
est1 = SymbolicTransformer(generations=2, random_state=0)
est1 = est1.fit_transform(boston.data, boston.target)
est2 = SymbolicTransformer(generations=2, random_state=0)
est2 = est2.fit_transform(boston.data,
boston.target,
sample_weight=sample_weight)
assert_array_almost_equal(est1, est2)
def check_pipeline_consistency(name, Estimator):
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
# 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)
# check that make_pipeline(est) gives same score as est
X, y = make_blobs(n_samples=30, centers=[[0, 0, 0], [1, 1, 1]],
random_state=0, n_features=2, cluster_std=0.1)
X -= X.min()
y = multioutput_estimator_convert_y_2d(name, y)
estimator = Estimator()
set_fast_parameters(estimator)
set_random_state(estimator)
pipeline = make_pipeline(estimator)
estimator.fit(X, y)
pipeline.fit(X, y)
funcs = ["score", "fit_transform"]
for func_name in funcs:
func = getattr(estimator, func_name, None)
if func is not None:
func_pipeline = getattr(pipeline, func_name)
result = func(X, y)
result_pipe = func_pipeline(X, y)
assert_array_almost_equal(result, result_pipe)
def test_execute():
"""Check executing the program works"""
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]
X = np.reshape(random_state.uniform(size=50), (5, 10))
gp = _Program(random_state=random_state, program=test_gp, **params)
result = gp.execute(X)
expected = [-0.19656208, 0.78197782, -1.70123845, -0.60175969, -0.01082618]
assert_array_almost_equal(result, expected)
def test_compute_class_weight_auto_unordered():
# Test compute_class_weight when classes are unordered
classes = np.array([1, 0, 3])
y = np.asarray([1, 0, 0, 3, 3, 3])
cw = compute_class_weight("auto", classes, y)
assert_almost_equal(cw.sum(), classes.shape)
assert_equal(len(cw), len(classes))
assert_array_almost_equal(cw, np.array([1.636, 0.818, 0.545]), decimal=3)
def test_parallel_train():
"""Check predictions are the same for different n_jobs"""
# Check the regressor
ests = [
SymbolicRegressor(population_size=100, generations=4, n_jobs=n_jobs,
random_state=0).fit(boston.data[:100, :],
boston.target[:100])
for n_jobs in [1, 2, 3, 8, 16]
]
preds = [e.predict(boston.data[500:, :]) for e in ests]
for pred1, pred2 in zip(preds, preds[1:]):
assert_array_almost_equal(pred1, pred2)
lengths = np.array([[gp.length_ for gp in e._programs[-1]] for e in ests])
for len1, len2 in zip(lengths, lengths[1:]):
assert_array_almost_equal(len1, len2)
# Check the transformer
ests = [
SymbolicTransformer(population_size=100, hall_of_fame=50,
generations=4, n_jobs=n_jobs,
random_state=0).fit(boston.data[:100, :],
boston.target[:100])
for n_jobs in [1, 2, 3, 8, 16]
]
preds = [e.transform(boston.data[500:, :]) for e in ests]
for pred1, pred2 in zip(preds, preds[1:]):
assert_array_almost_equal(pred1, pred2)
lengths = np.array([[gp.length_ for gp in e._programs[-1]] for e in ests])
for len1, len2 in zip(lengths, lengths[1:]):
assert_array_almost_equal(len1, len2)
def test_compute_class_weight_auto_negative():
# Test compute_class_weight when labels are negative
# Test with balanced class labels.
classes = np.array([-2, -1, 0])
y = np.asarray([-1, -1, 0, 0, -2, -2])
cw = compute_class_weight("auto", classes, y)
assert_almost_equal(cw.sum(), classes.shape)
assert_equal(len(cw), len(classes))
assert_array_almost_equal(cw, np.array([1., 1., 1.]))
# Test with unbalanced class labels.
y = np.asarray([-1, 0, 0, -2, -2, -2])
cw = compute_class_weight("auto", classes, y)
assert_almost_equal(cw.sum(), classes.shape)
assert_equal(len(cw), len(classes))
assert_array_almost_equal(cw, np.array([0.545, 1.636, 0.818]), decimal=3)
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_execute():
"""Check executing the program works"""
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]
X = np.reshape(random_state.uniform(size=50), (5, 10))
gp = _Program(random_state=random_state, program=test_gp, **params)
result = gp.execute(X)
expected = [-0.19656208, 0.78197782, -1.70123845, -0.60175969, -0.01082618]
assert_array_almost_equal(result, expected)
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_data_not_an_array(name, Estimator, X, y):
if name in CROSS_DECOMPOSITION:
raise SkipTest
# catch deprecation warnings
with warnings.catch_warnings(record=True):
# separate estimators to control random seeds
estimator_1 = Estimator()
estimator_2 = Estimator()
set_fast_parameters(estimator_1)
set_fast_parameters(estimator_2)
set_random_state(estimator_1)
set_random_state(estimator_2)
y_ = NotAnArray(np.asarray(y))
X_ = NotAnArray(np.asarray(X))
# fit
estimator_1.fit(X_, y_)
pred1 = estimator_1.predict(X_)
estimator_2.fit(X, y)
pred2 = estimator_2.predict(X)
assert_array_almost_equal(pred1, pred2, 2, name)
def test_pickle():
"""Check pickability"""
# Check the regressor
est = SymbolicRegressor(generations=2, random_state=0)
est.fit(boston.data[:100, :], boston.target[:100])
score = est.score(boston.data[500:, :], boston.target[500:])
pickle_object = pickle.dumps(est)
est2 = pickle.loads(pickle_object)
assert_equal(type(est2), est.__class__)
score2 = est2.score(boston.data[500:, :], boston.target[500:])
assert_equal(score, score2)
# Check the transformer
est = SymbolicTransformer(generations=2, random_state=0)
est.fit(boston.data[:100, :], boston.target[:100])
X_new = est.transform(boston.data[500:, :])
pickle_object = pickle.dumps(est)
est2 = pickle.loads(pickle_object)
assert_equal(type(est2), est.__class__)
X_new2 = est2.transform(boston.data[500:, :])
assert_array_almost_equal(X_new, X_new2)
def test_pickle():
"""Check pickability"""
# Check the regressor
est = SymbolicRegressor(generations=2, random_state=0)
est.fit(boston.data[:100, :], boston.target[:100])
score = est.score(boston.data[500:, :], boston.target[500:])
pickle_object = pickle.dumps(est)
est2 = pickle.loads(pickle_object)
assert_equal(type(est2), est.__class__)
score2 = est2.score(boston.data[500:, :], boston.target[500:])
assert_equal(score, score2)
# Check the transformer
est = SymbolicTransformer(generations=2, random_state=0)
est.fit(boston.data[:100, :], boston.target[:100])
X_new = est.transform(boston.data[500:, :])
pickle_object = pickle.dumps(est)
est2 = pickle.loads(pickle_object)
assert_equal(type(est2), est.__class__)
X_new2 = est2.transform(boston.data[500:, :])
assert_array_almost_equal(X_new, X_new2)
def test_parallel_train():
"""Check predictions are the same for different n_jobs"""
# Check the regressor
ests = [
SymbolicRegressor(population_size=100,
generations=4,
n_jobs=n_jobs,
random_state=0).fit(boston.data[:100, :],
boston.target[:100])
for n_jobs in [1, 2, 3, 8, 16]
]
preds = [e.predict(boston.data[500:, :]) for e in ests]
for pred1, pred2 in zip(preds, preds[1:]):
assert_array_almost_equal(pred1, pred2)
lengths = np.array([[gp.length_ for gp in e._programs[-1]] for e in ests])
for len1, len2 in zip(lengths, lengths[1:]):
assert_array_almost_equal(len1, len2)
# Check the transformer
ests = [
SymbolicTransformer(population_size=100,
hall_of_fame=50,
generations=4,
n_jobs=n_jobs,
random_state=0).fit(boston.data[:100, :],
boston.target[:100])
for n_jobs in [1, 2, 3, 8, 16]
]
preds = [e.transform(boston.data[500:, :]) for e in ests]
for pred1, pred2 in zip(preds, preds[1:]):
assert_array_almost_equal(pred1, pred2)
lengths = np.array([[gp.length_ for gp in e._programs[-1]] for e in ests])
for len1, len2 in zip(lengths, lengths[1:]):
assert_array_almost_equal(len1, len2)
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 _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_sample_weight_with_subsample():
# Test compute_sample_weight with subsamples specified.
# Test with balanced classes and all samples present
y = np.asarray([1, 1, 1, 2, 2, 2])
sample_weight = compute_sample_weight("auto", y, range(6))
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
# Test with column vector of balanced classes and all samples present
y = np.asarray([[1], [1], [1], [2], [2], [2]])
sample_weight = compute_sample_weight("auto", y, range(6))
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
# Test with a subsample
y = np.asarray([1, 1, 1, 2, 2, 2])
sample_weight = compute_sample_weight("auto", y, range(4))
assert_array_almost_equal(sample_weight, [.5, .5, .5, 1.5, 1.5, 1.5])
# Test with a bootstrap subsample
y = np.asarray([1, 1, 1, 2, 2, 2])
sample_weight = compute_sample_weight("auto", y, [0, 1, 1, 2, 2, 3])
expected = np.asarray([1/3., 1/3., 1/3., 5/3., 5/3., 5/3.])
assert_array_almost_equal(sample_weight, expected)
# Test with a bootstrap subsample for multi-output
y = np.asarray([[1, 0], [1, 0], [1, 0], [2, 1], [2, 1], [2, 1]])
sample_weight = compute_sample_weight("auto", y, [0, 1, 1, 2, 2, 3])
assert_array_almost_equal(sample_weight, expected ** 2)
# Test with a missing class
y = np.asarray([1, 1, 1, 2, 2, 2, 3])
sample_weight = compute_sample_weight("auto", y, range(6))
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1., 0.])
# Test with a missing class for multi-output
y = np.asarray([[1, 0], [1, 0], [1, 0], [2, 1], [2, 1], [2, 1], [2, 2]])
sample_weight = compute_sample_weight("auto", y, range(6))
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1., 0.])
def test_compute_sample_weight():
# Test (and demo) compute_sample_weight.
# Test with balanced classes
y = np.asarray([1, 1, 1, 2, 2, 2])
sample_weight = compute_sample_weight("auto", y)
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
# Test with user-defined weights
sample_weight = compute_sample_weight({1: 2, 2: 1}, y)
assert_array_almost_equal(sample_weight, [2., 2., 2., 1., 1., 1.])
# Test with column vector of balanced classes
y = np.asarray([[1], [1], [1], [2], [2], [2]])
sample_weight = compute_sample_weight("auto", y)
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
# Test with unbalanced classes
y = np.asarray([1, 1, 1, 2, 2, 2, 3])
sample_weight = compute_sample_weight("auto", y)
expected = np.asarray([.6, .6, .6, .6, .6, .6, 1.8])
assert_array_almost_equal(sample_weight, expected)
# Test with `None` weights
sample_weight = compute_sample_weight(None, y)
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1., 1.])
# Test with multi-output of balanced classes
y = np.asarray([[1, 0], [1, 0], [1, 0], [2, 1], [2, 1], [2, 1]])
sample_weight = compute_sample_weight("auto", y)
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
# Test with multi-output with user-defined weights
y = np.asarray([[1, 0], [1, 0], [1, 0], [2, 1], [2, 1], [2, 1]])
sample_weight = compute_sample_weight([{1: 2, 2: 1}, {0: 1, 1: 2}], y)
assert_array_almost_equal(sample_weight, [2., 2., 2., 2., 2., 2.])
# Test with multi-output of unbalanced classes
y = np.asarray([[1, 0], [1, 0], [1, 0], [2, 1], [2, 1], [2, 1], [3, -1]])
sample_weight = compute_sample_weight("auto", y)
assert_array_almost_equal(sample_weight, expected ** 2)
