def test_lhs_arange():
dim = Categorical(['a', 'b', 'c'])
dim.lhs_arange(10)
dim = Integer(1, 20)
dim.lhs_arange(10)
dim = Real(-10, 20)
dim.lhs_arange(10)
def test_purely_categorical_space():
# Test reproduces the bug in #908, make sure it doesn't come back
dims = [Categorical(['a', 'b', 'c']), Categorical(['A', 'B', 'C'])]
optimizer = Optimizer(dims, n_initial_points=1, random_state=3)
x = optimizer.ask()
# before the fix this call raised an exception
optimizer.tell(x, 1.)
def test_searchcv_sklearn_compatibility():
"""
Test whether the BayesSearchCV is compatible with base sklearn methods
such as clone, set_params, get_params.
"""
X, y = load_iris(True)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
train_size=0.75,
random_state=0)
# used to try different model classes
pipe = Pipeline([('model', SVC())])
# single categorical value of 'model' parameter sets the model class
lin_search = {
'model': Categorical([LinearSVC()]),
'model__C': Real(1e-6, 1e+6, prior='log-uniform'),
}
dtc_search = {
'model': Categorical([DecisionTreeClassifier()]),
'model__max_depth': Integer(1, 32),
'model__min_samples_split': Real(1e-3, 1.0, prior='log-uniform'),
}
svc_search = {
'model': Categorical([SVC()]),
'model__C': Real(1e-6, 1e+6, prior='log-uniform'),
'model__gamma': Real(1e-6, 1e+1, prior='log-uniform'),
'model__degree': Integer(1, 8),
'model__kernel': Categorical(['linear', 'poly', 'rbf']),
}
opt = BayesSearchCV(pipe, [(lin_search, 1), svc_search], n_iter=2)
opt_clone = clone(opt)
params, params_clone = opt.get_params(), opt_clone.get_params()
assert params.keys() == params_clone.keys()
for param, param_clone in zip(params.items(), params_clone.items()):
assert param[0] == param_clone[0]
assert isinstance(param[1], type(param_clone[1]))
opt.set_params(search_spaces=[(dtc_search, 1)])
opt.fit(X_train, y_train)
opt_clone.fit(X_train, y_train)
total_evaluations = len(opt.cv_results_['mean_test_score'])
total_evaluations_clone = len(opt_clone.cv_results_['mean_test_score'])
# test if expected number of subspaces is explored
assert total_evaluations == 1
assert total_evaluations_clone == 1 + 2
def test_categorical_distance():
categories = ['car', 'dog', 'orange']
cat = Categorical(categories)
for cat1 in categories:
for cat2 in categories:
delta = cat.distance(cat1, cat2)
if cat1 == cat2:
assert delta == 0
else:
assert delta == 1
def test_Constraints_init():
space = Space([
Real(1, 10),
Real(1, 10),
Real(1, 10),
Integer(0, 10),
Integer(0, 10),
Integer(0, 10),
Categorical(list('abcdefg')),
Categorical(list('abcdefg')),
Categorical(list('abcdefg'))
])
cons_list = [Single(0,5.0,'real'),
Inclusive(1,(3.0,5.0),'real'),
Exclusive(2,(3.0,5.0),'real'),
Single(3,5,'integer'),
Inclusive(4,(3,5),'integer'),
Exclusive(5,(3,5),'integer'),
Single(6,'b','categorical'),
Inclusive(7,('c','d','e'),'categorical'),
Exclusive(8,('c','d','e'),'categorical'),
# Note that two ocnstraints are being added to dimension 4 and 5
Inclusive(4,(7,9),'integer'),
Exclusive(5,(7,9),'integer'),
]
cons = Constraints(cons_list,space)
# Test that space and constriants_list are being saved in object
assert_equal(cons.space, space)
assert_equal(cons.constraints_list, cons_list)
# Test that a correct list of single constraints have been made
assert_equal(len(cons.single),space.n_dims)
assert_equal(cons.single[1], None)
assert_equal(cons.single[-1], None)
assert_not_equal(cons.single[0], None)
assert_not_equal(cons.single[6],None)
# Test that a correct list of inclusive constraints have been made
assert_equal(len(cons.inclusive),space.n_dims)
assert_equal(cons.inclusive[0],[])
assert_equal(cons.inclusive[2],[])
assert_not_equal(not cons.inclusive[1],[])
assert_not_equal(not cons.inclusive[7],[])
assert_equal(len(cons.inclusive[4]),2)
# Test that a correct list of exclusive constraints have been made
assert_equal(len(cons.exclusive),space.n_dims)
assert_equal(cons.exclusive[3],[])
assert_equal(cons.exclusive[7],[])
assert_not_equal(cons.exclusive[2],[])
assert_not_equal(cons.exclusive[5],[])
assert_equal(len(cons.exclusive[5]),2)
def test_categorical_transform():
categories = ["apple", "orange", "banana", None, True, False, 3]
cat = Categorical(categories)
apple = [1., 0., 0., 0., 0., 0., 0.]
orange = [0., 1.0, 0.0, 0.0, 0., 0., 0.]
banana = [0., 0., 1., 0., 0., 0., 0.]
none = [0., 0., 0., 1., 0., 0., 0.]
true = [0., 0., 0., 0., 1., 0., 0.]
false = [0., 0., 0., 0., 0., 1., 0.]
three = [0., 0., 0., 0., 0., 0., 1.]
assert_equal(cat.transformed_size, 7)
assert_equal(cat.transformed_size, cat.transform(["apple"]).size)
assert_array_equal(
cat.transform(categories),
[apple, orange, banana, none, true, false, three]
)
assert_array_equal(cat.transform(["apple", "orange"]), [apple, orange])
assert_array_equal(cat.transform(["apple", "banana"]), [apple, banana])
assert_array_equal(cat.inverse_transform([apple, orange]),
["apple", "orange"])
assert_array_equal(cat.inverse_transform([apple, banana]),
["apple", "banana"])
ent_inverse = cat.inverse_transform(
[apple, orange, banana, none, true, false, three])
assert_array_equal(ent_inverse, categories)
def test_searchcv_reproducibility():
"""
Test whether results of BayesSearchCV can be reproduced with a fixed
random state.
"""
X, y = load_iris(True)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
train_size=0.75,
random_state=0)
random_state = 42
opt = BayesSearchCV(SVC(random_state=random_state), {
'C': Real(1e-6, 1e+6, prior='log-uniform'),
'gamma': Real(1e-6, 1e+1, prior='log-uniform'),
'degree': Integer(1, 8),
'kernel': Categorical(['linear', 'poly', 'rbf']),
},
n_iter=11,
random_state=random_state)
opt.fit(X_train, y_train)
best_est = opt.best_estimator_
opt2 = clone(opt).fit(X_train, y_train)
best_est2 = opt2.best_estimator_
assert getattr(best_est, 'C') == getattr(best_est2, 'C')
assert getattr(best_est, 'gamma') == getattr(best_est2, 'gamma')
assert getattr(best_est, 'degree') == getattr(best_est2, 'degree')
assert getattr(best_est, 'kernel') == getattr(best_est2, 'kernel')
def test_constraints_rvs():
space = Space([
Real(1, 10),
Real(1, 10),
Real(1, 10),
Integer(0, 10),
Integer(0, 10),
Integer(0, 10),
Categorical(list('abcdefg')),
Categorical(list('abcdefg')),
Categorical(list('abcdefg'))
])
cons_list = [Single(0,5.0,'real'),
Inclusive(1,(3.0,5.0),'real'),
Exclusive(2,(3.0,5.0),'real'),
Single(3,5,'integer'),
Inclusive(4,(3,5),'integer'),
Exclusive(5,(3,5),'integer'),
Single(6,'b','categorical'),
Inclusive(7,('c','d','e'),'categorical'),
Exclusive(8,('c','d','e'),'categorical'),
# Note that two constraints are being added to dimension 4 and 5
Inclusive(4,(7,9),'integer'),
Exclusive(5,(7,9),'integer'),
]
# Test lenght of samples
constraints = Constraints(cons_list,space)
samples = constraints.rvs(n_samples = 100)
assert_equal(len(samples),100)
assert_equal(len(samples[0]),space.n_dims)
assert_equal(len(samples[-1]),space.n_dims)
# Test random state
samples_a = constraints.rvs(n_samples = 100,random_state = 1)
samples_b = constraints.rvs(n_samples = 100,random_state = 1)
samples_c = constraints.rvs(n_samples = 100,random_state = 2)
assert_equal(samples_a,samples_b)
assert_not_equal(samples_a,samples_c)
# Test invalid constraint combinations
space = Space([Real(0, 1)])
cons_list = [Exclusive(0,(0.3,0.7),'real'), Inclusive(0,(0.5,0.6),'real')]
constraints = Constraints(cons_list,space)
with raises(RuntimeError):
samples = constraints.rvs(n_samples = 10)
def test_lhs():
SPACE = Space([
Integer(-20, 20),
Real(-10.5, 100),
Categorical(list('abc'))]
)
samples = SPACE.lhs(10)
assert len(samples) == 10
assert len(samples[0]) == 3
def test_searchcv_runs_multiple_subspaces():
"""
Test whether the BayesSearchCV runs without exceptions when
multiple subspaces are given.
"""
X, y = load_iris(True)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
train_size=0.75,
random_state=0)
# used to try different model classes
pipe = Pipeline([('model', SVC())])
# single categorical value of 'model' parameter sets the model class
lin_search = {
'model': Categorical([LinearSVC()]),
'model__C': Real(1e-6, 1e+6, prior='log-uniform'),
}
dtc_search = {
'model': Categorical([DecisionTreeClassifier()]),
'model__max_depth': Integer(1, 32),
'model__min_samples_split': Real(1e-3, 1.0, prior='log-uniform'),
}
svc_search = {
'model': Categorical([SVC()]),
'model__C': Real(1e-6, 1e+6, prior='log-uniform'),
'model__gamma': Real(1e-6, 1e+1, prior='log-uniform'),
'model__degree': Integer(1, 8),
'model__kernel': Categorical(['linear', 'poly', 'rbf']),
}
opt = BayesSearchCV(pipe, [(lin_search, 1), (dtc_search, 1), svc_search],
n_iter=2)
opt.fit(X_train, y_train)
# test if all subspaces are explored
total_evaluations = len(opt.cv_results_['mean_test_score'])
assert total_evaluations == 1 + 1 + 2, "Not all spaces were explored!"
def test_categorical_repr():
small_cat = Categorical([1, 2, 3, 4, 5])
assert (small_cat.__repr__() ==
"Categorical(categories=(1, 2, 3, 4, 5), prior=None)")
big_cat = Categorical([1, 2, 3, 4, 5, 6, 7, 8])
assert (big_cat.__repr__() ==
'Categorical(categories=(1, 2, 3, ..., 6, 7, 8), prior=None)')
def test_categorical_identity():
categories = ["cat", "dog", "rat"]
cat = Categorical(categories, transform="identity")
samples = cat.rvs(100)
assert_true(all([t in categories for t in cat.rvs(100)]))
transformed = cat.transform(samples)
assert_array_equal(transformed, samples)
assert_array_equal(samples, cat.inverse_transform(transformed))
def test_searchcv_runs(surrogate, n_jobs, n_points, cv=None):
"""
Test whether the cross validation search wrapper around sklearn
models runs properly with available surrogates and with single
or multiple workers and different number of parameter settings
to ask from the optimizer in parallel.
Parameters
----------
* `surrogate` [str or None]:
A class of the scikit-optimize surrogate used. None means
to use default surrogate.
* `n_jobs` [int]:
Number of parallel processes to use for computations.
"""
X, y = load_iris(True)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
train_size=0.75,
random_state=0)
# create an instance of a surrogate if it is not a string
if surrogate is not None:
optimizer_kwargs = {'base_estimator': surrogate}
else:
optimizer_kwargs = None
opt = BayesSearchCV(SVC(), {
'C': Real(1e-6, 1e+6, prior='log-uniform'),
'gamma': Real(1e-6, 1e+1, prior='log-uniform'),
'degree': Integer(1, 8),
'kernel': Categorical(['linear', 'poly', 'rbf']),
},
n_jobs=n_jobs,
n_iter=11,
n_points=n_points,
cv=cv,
optimizer_kwargs=optimizer_kwargs)
opt.fit(X_train, y_train)
# this normally does not hold only if something is wrong
# with the optimizaiton procedure as such
assert_greater(opt.score(X_test, y_test), 0.9)
def test_categorical_transform_binary():
categories = ["apple", "orange"]
cat = Categorical(categories)
apple = [0.]
orange = [1.]
assert_equal(cat.transformed_size, 1)
assert_equal(cat.transformed_size, cat.transform(["apple"]).size)
assert_array_equal(cat.transform(categories), [apple, orange])
assert_array_equal(cat.transform(["apple", "orange"]), [apple, orange])
assert_array_equal(cat.inverse_transform([apple, orange]),
["apple", "orange"])
ent_inverse = cat.inverse_transform([apple, orange])
assert_array_equal(ent_inverse, categories)
def pow10map(x):
return 10.0**x
def pow2intmap(x):
return int(2.0**x)
def nop(x):
return x
nnparams = {
# up to 1024 neurons
'hidden_layer_sizes': (Real(1.0, 10.0), pow2intmap),
'activation': (Categorical(['identity', 'logistic', 'tanh', 'relu']), nop),
'solver': (Categorical(['lbfgs', 'sgd', 'adam']), nop),
'alpha': (Real(-5.0, -1), pow10map),
'batch_size': (Real(5.0, 10.0), pow2intmap),
'learning_rate': (Categorical(['constant', 'invscaling',
'adaptive']), nop),
'max_iter': (Real(5.0, 8.0), pow2intmap),
'learning_rate_init': (Real(-5.0, -1), pow10map),
'power_t': (Real(0.01, 0.99), nop),
'momentum': (Real(0.1, 0.98), nop),
'nesterovs_momentum': (Categorical([True, False]), nop),
'beta_1': (Real(0.1, 0.98), nop),
'beta_2': (Real(0.1, 0.9999999), nop),
}
MODELS = {
def test_optimizer_with_constraints(acq_optimizer):
base_estimator = 'GP'
space = Space([
Real(1, 10),
Real(1, 10),
Real(1, 10),
Integer(0, 10),
Integer(0, 10),
Integer(0, 10),
Categorical(list('abcdefg')),
Categorical(list('abcdefg')),
Categorical(list('abcdefg'))
])
cons_list = [Single(0,5.0,'real'),Single(3,5,'integer')]
cons_list_2 = [Single(0,4.0,'real'),Single(3,4,'integer')]
cons = Constraints(cons_list,space)
cons_2 = Constraints(cons_list_2,space)
# Test behavior when not adding constraitns
opt = Optimizer(space, base_estimator, acq_optimizer=acq_optimizer,n_initial_points = 5)
# Test that constraint is None when no constraint has been set so far
assert_equal(opt._constraints,None)
# Test constraints are still None
for _ in range(6):
next_x= opt.ask()
f_val = np.random.random()*100
opt.tell(next_x, f_val)
assert_equal(opt._constraints,None)
opt.remove_constraints()
assert_equal(opt._constraints,None)
# Test behavior when adding constraints in an optimization setting
opt = Optimizer(space, base_estimator, acq_optimizer=acq_optimizer,n_initial_points = 3)
opt.set_constraints(cons)
assert_equal(opt._constraints,cons)
next_x= opt.ask()
assert_equal(next_x[0],5.0)
assert_equal(next_x[3],5)
f_val = np.random.random()*100
opt.tell(next_x, f_val)
assert_equal(opt._constraints,cons)
opt.set_constraints(cons_2)
next_x= opt.ask()
assert_equal(opt._constraints,cons_2)
assert_equal(next_x[0],4.0)
assert_equal(next_x[3],4)
f_val = np.random.random()*100
opt.tell(next_x, f_val)
assert_equal(opt._constraints,cons_2)
opt.remove_constraints()
assert_equal(opt._constraints,None)
next_x= opt.ask()
assert_not_equal(next_x[0],4.0)
assert_not_equal(next_x[0],5.0)
f_val = np.random.random()*100
opt.tell(next_x, f_val)
assert_equal(opt._constraints,None)
# Test that next_x is changed when adding constraints
opt = Optimizer(space, base_estimator, acq_optimizer=acq_optimizer,n_initial_points = 3)
assert_false(hasattr(opt,'_next_x'))
for _ in range(4): # We exhaust initial points
next_x= opt.ask()
f_val = np.random.random()*100
opt.tell(next_x, f_val)
assert_true(hasattr(opt,'_next_x')) # Now next_x should be in optimizer
assert_not_equal(next_x[0],4.0)
assert_not_equal(next_x[0],5.0)
next_x = opt._next_x
opt.set_constraints(cons)
assert_not_equal(opt._next_x,next_x) # Check that next_x has been changed
assert_equal(opt._next_x[0],5.0)
assert_equal(opt._next_x[3],5)
next_x = opt._next_x
opt.set_constraints(cons_2)
assert_not_equal(opt._next_x,next_x)
assert_equal(opt._next_x[0],4.0)
assert_equal(opt._next_x[3],4)
# Test that adding a Constraint or constraint_list gives the same
opt = Optimizer(space, base_estimator, acq_optimizer=acq_optimizer,n_initial_points = 3)
opt.set_constraints(cons_list)
opt2 = Optimizer(space, base_estimator, acq_optimizer=acq_optimizer,n_initial_points = 3)
opt2.set_constraints(cons)
assert_equal(opt._constraints,opt2._constraints)
# Test that constraints are satisfied
opt = Optimizer(space, base_estimator, acq_optimizer=acq_optimizer,n_initial_points = 2)
opt.set_constraints(cons)
next_x= opt.ask()
assert_equal(next_x[0],5.0)
opt = Optimizer(space, base_estimator, acq_optimizer=acq_optimizer,n_initial_points = 2)
next_x= opt.ask()
assert_not_equal(next_x[0],5.0)
f_val = np.random.random()*100
opt.tell(next_x, f_val)
opt.set_constraints(cons)
next_x= opt.ask()
assert_equal(next_x[0],5.0)
assert_equal(next_x[3],5)
opt.set_constraints(cons)
next_x= opt.ask()
f_val = np.random.random()*100
opt.tell(next_x, f_val)
opt.set_constraints(cons_2)
next_x= opt.ask()
assert_equal(next_x[0],4.0)
assert_equal(next_x[3],4)
f_val = np.random.random()*100
opt.tell(next_x, f_val)
assert_equal(next_x[0],4.0)
assert_equal(next_x[3],4)
def test_Constraints_validate_sample():
space = Space([
Real(1, 10),
Real(1, 10),
Real(1, 10),
Integer(0, 10),
Integer(0, 10),
Integer(0, 10),
Categorical(list('abcdefg')),
Categorical(list('abcdefg')),
Categorical(list('abcdefg'))
])
# Test validation of single constraints
cons_list = [Single(0,5.0,'real')]
cons = Constraints(cons_list,space)
sample = [0]*space.n_dims
sample[0] = 5.0
assert_true(cons.validate_sample(sample))
sample[0] = 5.00001
assert_false(cons.validate_sample(sample))
sample[0] = 4.99999
assert_false(cons.validate_sample(sample))
cons_list = [Single(3,5,'integer')]
cons = Constraints(cons_list,space)
sample = [0]*space.n_dims
sample[3] = 5
assert_true(cons.validate_sample(sample))
sample[3] = 6
assert_false(cons.validate_sample(sample))
sample[3] = -5
assert_false(cons.validate_sample(sample))
sample[3] = 5.000001
assert_false(cons.validate_sample(sample))
cons_list = [Single(6,'a','categorical')]
cons = Constraints(cons_list,space)
sample = [0]*space.n_dims
sample[6] = 'a'
assert_true(cons.validate_sample(sample))
sample[6] = 'b'
assert_false(cons.validate_sample(sample))
sample[6] = -5
assert_false(cons.validate_sample(sample))
sample[6] = 5.000001
assert_false(cons.validate_sample(sample))
# Test validation of inclusive constraints
cons_list = [Inclusive(0,(5.0,7.0),'real')]
cons = Constraints(cons_list,space)
sample = [0]*space.n_dims
sample[0] = 5.0
assert_true(cons.validate_sample(sample))
sample[0] = 7.0
assert_true(cons.validate_sample(sample))
sample[0] = 7.00001
assert_false(cons.validate_sample(sample))
sample[0] = 4.99999
assert_false(cons.validate_sample(sample))
sample[0] = -10
assert_false(cons.validate_sample(sample))
cons_list = [Inclusive(3,(5,7),'integer')]
cons = Constraints(cons_list,space)
sample = [0]*space.n_dims
sample[3] = 5
assert_true(cons.validate_sample(sample))
sample[3] = 6
assert_true(cons.validate_sample(sample))
sample[3] = 7
assert_true(cons.validate_sample(sample))
sample[3] = 8
assert_false(cons.validate_sample(sample))
sample[3] = 4
assert_false(cons.validate_sample(sample))
sample[3] = -4
assert_false(cons.validate_sample(sample))
cons_list = [Inclusive(6,('c','d','e'),'categorical')]
cons = Constraints(cons_list,space)
sample = [0]*space.n_dims
sample[6] = 'c'
assert_true(cons.validate_sample(sample))
sample[6] = 'e'
assert_true(cons.validate_sample(sample))
sample[6] = 'f'
assert_false(cons.validate_sample(sample))
sample[6] = -5
assert_false(cons.validate_sample(sample))
sample[6] = 3.3
assert_false(cons.validate_sample(sample))
sample[6] = 'a'
assert_false(cons.validate_sample(sample))
# Test validation of exclusive constraints
cons_list = [Exclusive(0,(5.0,7.0),'real')]
cons = Constraints(cons_list,space)
sample = [0]*space.n_dims
sample[0] = 5.0
assert_false(cons.validate_sample(sample))
sample[0] = 7.0
assert_false(cons.validate_sample(sample))
sample[0] = 7.00001
assert_true(cons.validate_sample(sample))
sample[0] = 4.99999
assert_true(cons.validate_sample(sample))
sample[0] = -10
assert_true(cons.validate_sample(sample))
cons_list = [Exclusive(3,(5,7),'integer')]
cons = Constraints(cons_list,space)
sample = [0]*space.n_dims
sample[3] = 5
assert_false(cons.validate_sample(sample))
sample[3] = 6
assert_false(cons.validate_sample(sample))
sample[3] = 7
assert_false(cons.validate_sample(sample))
sample[3] = 8
assert_true(cons.validate_sample(sample))
sample[3] = 4
assert_true(cons.validate_sample(sample))
sample[3] = -4
assert_true(cons.validate_sample(sample))
cons_list = [Exclusive(3,(5,5),'integer')]
cons = Constraints(cons_list,space)
sample = [0]*space.n_dims
sample[3] = 5
assert_false(cons.validate_sample(sample))
cons_list = [Exclusive(6,('c','d','e'),'categorical')]
cons = Constraints(cons_list,space)
sample = [0]*space.n_dims
sample[6] = 'c'
assert_false(cons.validate_sample(sample))
sample[6] = 'e'
assert_false(cons.validate_sample(sample))
sample[6] = 'f'
assert_true(cons.validate_sample(sample))
sample[6] = -5
assert_true(cons.validate_sample(sample))
sample[6] = 3.3
assert_true(cons.validate_sample(sample))
sample[6] = 'a'
assert_true(cons.validate_sample(sample))
# Test more than one constraint per dimension
cons_list = [Inclusive(0,(1.0,2.0),'real'),Inclusive(0,(3.0,4.0),'real'),Inclusive(0,(5.0,6.0),'real')]
cons = Constraints(cons_list,space)
sample = [0]*space.n_dims
sample[0] = 1.3
assert_true(cons.validate_sample(sample))
sample[0] = 6.0
assert_true(cons.validate_sample(sample))
sample[0] = 5.0
assert_true(cons.validate_sample(sample))
sample[0] = 3.0
assert_true(cons.validate_sample(sample))
sample[0] = 4.0
assert_true(cons.validate_sample(sample))
sample[0] = 5.5
assert_true(cons.validate_sample(sample))
sample[0] = 2.1
assert_false(cons.validate_sample(sample))
sample[0] = 4.9
assert_false(cons.validate_sample(sample))
sample[0] = 7.0
assert_false(cons.validate_sample(sample))
cons_list = [Exclusive(0,(1.0,2.0),'real'),Exclusive(0,(3.0,4.0),'real'),Exclusive(0,(5.0,6.0),'real')]
cons = Constraints(cons_list,space)
sample = [0]*space.n_dims
sample[0] = 1.3
assert_false(cons.validate_sample(sample))
sample[0] = 6.0
assert_false(cons.validate_sample(sample))
sample[0] = 5.0
assert_false(cons.validate_sample(sample))
sample[0] = 3.0
assert_false(cons.validate_sample(sample))
sample[0] = 4.0
assert_false(cons.validate_sample(sample))
sample[0] = 5.5
assert_false(cons.validate_sample(sample))
sample[0] = 2.1
assert_true(cons.validate_sample(sample))
sample[0] = 4.9
assert_true(cons.validate_sample(sample))
sample[0] = 7.0
assert_true(cons.validate_sample(sample))
def test_space_consistency():
# Reals (uniform)
s1 = Space([Real(0.0, 1.0)])
s2 = Space([Real(0.0, 1.0)])
s3 = Space([Real(0, 1)])
s4 = Space([(0.0, 1.0)])
s5 = Space([(0.0, 1.0, "uniform")])
s6 = Space([(0, 1.0)])
s7 = Space([(np.float64(0.0), 1.0)])
s8 = Space([(0, np.float64(1.0))])
a1 = s1.rvs(n_samples=10, random_state=0)
a2 = s2.rvs(n_samples=10, random_state=0)
a3 = s3.rvs(n_samples=10, random_state=0)
a4 = s4.rvs(n_samples=10, random_state=0)
a5 = s5.rvs(n_samples=10, random_state=0)
assert_equal(s1, s2)
assert_equal(s1, s3)
assert_equal(s1, s4)
assert_equal(s1, s5)
assert_equal(s1, s6)
assert_equal(s1, s7)
assert_equal(s1, s8)
assert_array_equal(a1, a2)
assert_array_equal(a1, a3)
assert_array_equal(a1, a4)
assert_array_equal(a1, a5)
# Reals (log-uniform)
s1 = Space([Real(10**-3.0, 10**3.0, prior="log-uniform")])
s2 = Space([Real(10**-3.0, 10**3.0, prior="log-uniform")])
s3 = Space([Real(10**-3, 10**3, prior="log-uniform")])
s4 = Space([(10**-3.0, 10**3.0, "log-uniform")])
s5 = Space([(np.float64(10**-3.0), 10**3.0, "log-uniform")])
a1 = s1.rvs(n_samples=10, random_state=0)
a2 = s2.rvs(n_samples=10, random_state=0)
a3 = s3.rvs(n_samples=10, random_state=0)
a4 = s4.rvs(n_samples=10, random_state=0)
assert_equal(s1, s2)
assert_equal(s1, s3)
assert_equal(s1, s4)
assert_equal(s1, s5)
assert_array_equal(a1, a2)
assert_array_equal(a1, a3)
assert_array_equal(a1, a4)
# Integers
s1 = Space([Integer(1, 5)])
s2 = Space([Integer(1.0, 5.0)])
s3 = Space([(1, 5)])
s4 = Space([(np.int64(1.0), 5)])
s5 = Space([(1, np.int64(5.0))])
a1 = s1.rvs(n_samples=10, random_state=0)
a2 = s2.rvs(n_samples=10, random_state=0)
a3 = s3.rvs(n_samples=10, random_state=0)
assert_equal(s1, s2)
assert_equal(s1, s3)
assert_equal(s1, s4)
assert_equal(s1, s5)
assert_array_equal(a1, a2)
assert_array_equal(a1, a3)
# Categoricals
s1 = Space([Categorical(["a", "b", "c"])])
s2 = Space([Categorical(["a", "b", "c"])])
s3 = Space([["a", "b", "c"]])
a1 = s1.rvs(n_samples=10, random_state=0)
a2 = s2.rvs(n_samples=10, random_state=0)
a3 = s3.rvs(n_samples=10, random_state=0)
assert_equal(s1, s2)
assert_array_equal(a1, a2)
assert_equal(s1, s3)
assert_array_equal(a1, a3)
s1 = Space([(True, False)])
s2 = Space([Categorical([True, False])])
s3 = Space([np.array([True, False])])
assert s1 == s2 == s3
def check_categorical(vals, random_val):
x = Categorical(vals)
assert_equal(x, Categorical(vals))
assert_not_equal(x, Categorical(vals[:-1] + ("zzz",)))
assert_equal(x.rvs(random_state=1), random_val)
from ProcessOptimizer import plots, gp_minimize
from ProcessOptimizer.plots import plot_objective
from ProcessOptimizer import bokeh_plot
# For reproducibility
import numpy as np
np.random.seed(123)
import matplotlib.pyplot as plt
plt.set_cmap("viridis")
SPACE = [
Integer(1, 20, name='max_depth'),
Integer(2, 100, name='min_samples_split'),
Integer(5, 30, name='min_samples_leaf'),
Integer(1, 30, name='max_features'),
Categorical(list('abc'), name='dummy'),
Categorical(['gini', 'entropy'], name='criterion'),
Categorical(list('def'), name='dummy'),
]
def objective(params):
clf = DecisionTreeClassifier(**{
dim.name: val
for dim, val in zip(SPACE, params) if dim.name != 'dummy'
})
return -np.mean(cross_val_score(clf, *load_breast_cancer(True)))
result = gp_minimize(objective, SPACE, n_calls=20)
@pytest.mark.fast_test
@pytest.mark.parametrize("dimensions, normalizations", [
(((1, 3), (1., 3.)), ('normalize', 'normalize')),
(((1, 3), ('a', 'b', 'c')), ('normalize', 'onehot')),
])
def test_normalize_dimensions(dimensions, normalizations):
space = normalize_dimensions(dimensions)
for dimension, normalization in zip(space, normalizations):
assert dimension.transform_ == normalization
@pytest.mark.fast_test
@pytest.mark.parametrize(
"dimension, name", [(Real(1, 2, name="learning rate"), "learning rate"),
(Integer(1, 100, name="no of trees"), "no of trees"),
(Categorical(["red, blue"], name="colors"), "colors")])
def test_normalize_dimensions(dimension, name):
space = normalize_dimensions([dimension])
assert space.dimensions[0].name == name
@pytest.mark.fast_test
def test_use_named_args():
"""
Test the function wrapper @use_named_args which is used
for wrapping an objective function with named args so it
can be called by the optimizers which only pass a single
list as the arg.
This test does not actually use the optimizers but merely
simulates how they would call the function.
assert_equal(reals.distance(4.1234, i), abs(4.1234 - i))
@pytest.mark.parametrize("dimension, bounds",
[(Real, (2, 1)), (Integer, (2, 1)),
(Real, (2, 2)), (Integer, (2, 2))])
def test_dimension_bounds(dimension, bounds):
with pytest.raises(ValueError) as exc:
dim = dimension(*bounds)
assert "has to be less than the upper bound " in exc.value.args[0]
@pytest.mark.parametrize("dimension, name",
[(Real(1, 2, name="learning rate"), "learning rate"),
(Integer(1, 100, name="no of trees"), "no of trees"),
(Categorical(["red, blue"], name="colors"), "colors")])
def test_dimension_name(dimension, name):
assert dimension.name == name
@pytest.mark.parametrize("dimension",
[Real(1, 2), Integer(1, 100), Categorical(["red, blue"])])
def test_dimension_name_none(dimension):
assert dimension.name is None
@pytest.mark.fast_test
def test_space_from_yaml():
with NamedTemporaryFile() as tmp:
tmp.write(b"""
Space:
