This repository was archived by the owner on Feb 28, 2024. It is now read-only.
This repository was archived by the owner on Feb 28, 2024. It is now read-only.
Test failures on master #461
Description
surrogate = 'gp', n_jobs = 1
@pytest.mark.parametrize("surrogate", ['gp', None])
@pytest.mark.parametrize("n_jobs", [1, -1]) # test sequential and parallel
def test_searchcv_runs(surrogate, n_jobs):
"""
Test whether the cross validation search wrapper around sklearn
models runs properly with available surrogates and with single
or multiple workers.
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
)
# None search space is only supported when only `step` function is used
assert_raises(ValueError, BayesSearchCV(SVC(), None).fit, (X, y))
# check if invalid dimensions are raising errors
with pytest.raises(ValueError):
BayesSearchCV(SVC(), {'C': '1 ... 100.0'})
with pytest.raises(TypeError):
BayesSearchCV(SVC(), ['C', (1.0, 1)])
# 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,
optimizer_kwargs=optimizer_kwargs
)
> opt.fit(X_train, y_train)
skopt/tests/test_searchcv.py:70:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
skopt/searchcv.py:575: in fit
groups=groups, n_jobs=n_jobs_adjusted
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
self = BayesSearchCV(cv=None, error_score='raise',
estimator=SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,
...s',
random_state=None, refit=False, return_train_score=True,
scoring=None, search_spaces=None, verbose=0)
X = array([[ 5.9, 3. , 4.2, 1.5],
[ 5.8, 2.6, 4. , 1.2],
[ 6.8, 3. , 5.5, 2.1],
[ 4.7, 3.2,... 2.9, 5.6, 1.8],
[ 5.8, 2.7, 4.1, 1. ],
[ 7.7, 3.8, 6.7, 2.2],
[ 4.6, 3.2, 1.4, 0.2]])
y = array([1, 1, 2, 0, 2, 0, 0, 1, 2, 2, 2, 2, 1, 2, 1, 1, 2, 2, 2, 2, 1, 2, 1,
0, 2, 1, 1, 1, 1, 2, 0, 0, 2, 1, 0,... 0, 2, 1, 2, 1, 0, 2, 0, 2, 0, 0, 2, 0, 2, 1, 1, 1,
2, 2, 1, 1, 0, 1, 2, 2, 0, 1, 1, 1, 1, 0, 0, 0, 2, 1, 2, 0])
space_id = range(0, 1), groups = None, n_jobs = 1
def step(self, X, y, space_id, groups=None, n_jobs=1):
"""Generate n_jobs parameters and evaluate them in parallel.
Having a separate function for a single step for search allows to
save easily checkpoints for the parameter search and restore from
possible failures.
Parameters
----------
X : array-like or sparse matrix, shape = [n_samples, n_features]
The training input samples. Internally, it will be converted to
``dtype=np.float32`` and if a sparse matrix is provided
to a sparse ``csc_matrix``.
y : array-like, shape = [n_samples] or [n_samples, n_outputs]
The target values (class labels) as integers or strings.
space_id : hashable
Identifier of parameter search space. Add search spaces with
groups : array-like, with shape (n_samples,), optional
Group labels for the samples used while splitting the dataset into
train/test set.
n_jobs : int, default=1
Number of parameters to evaluate in parallel.
Returns
-------
params_dict: dictionary with parameter values.
"""
# convert n_jobst to int > 0 if necessary
if n_jobs < 0:
n_jobs = max(1, cpu_count() + n_jobs + 1)
# use the cached optimizer for particular parameter space
if space_id not in self.search_spaces_:
raise ValueError("Unknown space %s" % space_id)
# get the search space for a step
search_space = self.search_spaces_[space_id]
if isinstance(search_space, tuple):
search_space, _ = search_space
# create optimizer if not created already
if space_id not in self.optimizer_:
self.optimizer_[space_id] = self._make_optimizer(search_space)
optimizer = self.optimizer_[space_id]
# get parameter values to evaluate
params = optimizer.ask(n_points=n_jobs)
params_dict = [point_asdict(search_space, p) for p in params]
# self.cv_results_ is reset at every call to _fit, keep current
all_cv_results = self.cv_results_
# record performances with different points
refit = self.refit
self.refit = False # do not fit yet - will be fit later
> self._fit(X, y, groups, params_dict)
E AttributeError: 'BayesSearchCV' object has no attribute '_fit'
skopt/searchcv.py:506: AttributeError
____________________________________________________________________________________________________________________ test_searchcv_runs[1-None] _____________________________________________________________________________________________________________________
surrogate = None, n_jobs = 1
@pytest.mark.parametrize("surrogate", ['gp', None])
@pytest.mark.parametrize("n_jobs", [1, -1]) # test sequential and parallel
def test_searchcv_runs(surrogate, n_jobs):
"""
Test whether the cross validation search wrapper around sklearn
models runs properly with available surrogates and with single
or multiple workers.
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
)
# None search space is only supported when only `step` function is used
assert_raises(ValueError, BayesSearchCV(SVC(), None).fit, (X, y))
# check if invalid dimensions are raising errors
with pytest.raises(ValueError):
BayesSearchCV(SVC(), {'C': '1 ... 100.0'})
with pytest.raises(TypeError):
BayesSearchCV(SVC(), ['C', (1.0, 1)])
# 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,
optimizer_kwargs=optimizer_kwargs
)
> opt.fit(X_train, y_train)
skopt/tests/test_searchcv.py:70:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
skopt/searchcv.py:575: in fit
groups=groups, n_jobs=n_jobs_adjusted
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
self = BayesSearchCV(cv=None, error_score='raise',
estimator=SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,
...s', random_state=None, refit=False,
return_train_score=True, scoring=None, search_spaces=None,
verbose=0)
X = array([[ 5.9, 3. , 4.2, 1.5],
[ 5.8, 2.6, 4. , 1.2],
[ 6.8, 3. , 5.5, 2.1],
[ 4.7, 3.2,... 2.9, 5.6, 1.8],
[ 5.8, 2.7, 4.1, 1. ],
[ 7.7, 3.8, 6.7, 2.2],
[ 4.6, 3.2, 1.4, 0.2]])
y = array([1, 1, 2, 0, 2, 0, 0, 1, 2, 2, 2, 2, 1, 2, 1, 1, 2, 2, 2, 2, 1, 2, 1,
0, 2, 1, 1, 1, 1, 2, 0, 0, 2, 1, 0,... 0, 2, 1, 2, 1, 0, 2, 0, 2, 0, 0, 2, 0, 2, 1, 1, 1,
2, 2, 1, 1, 0, 1, 2, 2, 0, 1, 1, 1, 1, 0, 0, 0, 2, 1, 2, 0])
space_id = range(0, 1), groups = None, n_jobs = 1
def step(self, X, y, space_id, groups=None, n_jobs=1):
"""Generate n_jobs parameters and evaluate them in parallel.
Having a separate function for a single step for search allows to
save easily checkpoints for the parameter search and restore from
possible failures.
Parameters
----------
X : array-like or sparse matrix, shape = [n_samples, n_features]
The training input samples. Internally, it will be converted to
``dtype=np.float32`` and if a sparse matrix is provided
to a sparse ``csc_matrix``.
y : array-like, shape = [n_samples] or [n_samples, n_outputs]
The target values (class labels) as integers or strings.
space_id : hashable
Identifier of parameter search space. Add search spaces with
groups : array-like, with shape (n_samples,), optional
Group labels for the samples used while splitting the dataset into
train/test set.
n_jobs : int, default=1
Number of parameters to evaluate in parallel.
Returns
-------
params_dict: dictionary with parameter values.
"""
# convert n_jobst to int > 0 if necessary
if n_jobs < 0:
n_jobs = max(1, cpu_count() + n_jobs + 1)
# use the cached optimizer for particular parameter space
if space_id not in self.search_spaces_:
raise ValueError("Unknown space %s" % space_id)
# get the search space for a step
search_space = self.search_spaces_[space_id]
if isinstance(search_space, tuple):
search_space, _ = search_space
# create optimizer if not created already
if space_id not in self.optimizer_:
self.optimizer_[space_id] = self._make_optimizer(search_space)
optimizer = self.optimizer_[space_id]
# get parameter values to evaluate
params = optimizer.ask(n_points=n_jobs)
params_dict = [point_asdict(search_space, p) for p in params]
# self.cv_results_ is reset at every call to _fit, keep current
all_cv_results = self.cv_results_
# record performances with different points
refit = self.refit
self.refit = False # do not fit yet - will be fit later
> self._fit(X, y, groups, params_dict)
E AttributeError: 'BayesSearchCV' object has no attribute '_fit'
skopt/searchcv.py:506: AttributeError
_____________________________________________________________________________________________________________________ test_searchcv_runs[-1-gp] _____________________________________________________________________________________________________________________
surrogate = 'gp', n_jobs = -1
@pytest.mark.parametrize("surrogate", ['gp', None])
@pytest.mark.parametrize("n_jobs", [1, -1]) # test sequential and parallel
def test_searchcv_runs(surrogate, n_jobs):
"""
Test whether the cross validation search wrapper around sklearn
models runs properly with available surrogates and with single
or multiple workers.
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
)
# None search space is only supported when only `step` function is used
assert_raises(ValueError, BayesSearchCV(SVC(), None).fit, (X, y))
# check if invalid dimensions are raising errors
with pytest.raises(ValueError):
BayesSearchCV(SVC(), {'C': '1 ... 100.0'})
with pytest.raises(TypeError):
BayesSearchCV(SVC(), ['C', (1.0, 1)])
# 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,
optimizer_kwargs=optimizer_kwargs
)
> opt.fit(X_train, y_train)
skopt/tests/test_searchcv.py:70:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
skopt/searchcv.py:575: in fit
groups=groups, n_jobs=n_jobs_adjusted
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
self = BayesSearchCV(cv=None, error_score='raise',
estimator=SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,
...s',
random_state=None, refit=False, return_train_score=True,
scoring=None, search_spaces=None, verbose=0)
X = array([[ 5.9, 3. , 4.2, 1.5],
[ 5.8, 2.6, 4. , 1.2],
[ 6.8, 3. , 5.5, 2.1],
[ 4.7, 3.2,... 2.9, 5.6, 1.8],
[ 5.8, 2.7, 4.1, 1. ],
[ 7.7, 3.8, 6.7, 2.2],
[ 4.6, 3.2, 1.4, 0.2]])
y = array([1, 1, 2, 0, 2, 0, 0, 1, 2, 2, 2, 2, 1, 2, 1, 1, 2, 2, 2, 2, 1, 2, 1,
0, 2, 1, 1, 1, 1, 2, 0, 0, 2, 1, 0,... 0, 2, 1, 2, 1, 0, 2, 0, 2, 0, 0, 2, 0, 2, 1, 1, 1,
2, 2, 1, 1, 0, 1, 2, 2, 0, 1, 1, 1, 1, 0, 0, 0, 2, 1, 2, 0])
space_id = range(0, 1), groups = None, n_jobs = 4
def step(self, X, y, space_id, groups=None, n_jobs=1):
"""Generate n_jobs parameters and evaluate them in parallel.
Having a separate function for a single step for search allows to
save easily checkpoints for the parameter search and restore from
possible failures.
Parameters
----------
X : array-like or sparse matrix, shape = [n_samples, n_features]
The training input samples. Internally, it will be converted to
``dtype=np.float32`` and if a sparse matrix is provided
to a sparse ``csc_matrix``.
y : array-like, shape = [n_samples] or [n_samples, n_outputs]
The target values (class labels) as integers or strings.
space_id : hashable
Identifier of parameter search space. Add search spaces with
groups : array-like, with shape (n_samples,), optional
Group labels for the samples used while splitting the dataset into
train/test set.
n_jobs : int, default=1
Number of parameters to evaluate in parallel.
Returns
-------
params_dict: dictionary with parameter values.
"""
# convert n_jobst to int > 0 if necessary
if n_jobs < 0:
n_jobs = max(1, cpu_count() + n_jobs + 1)
# use the cached optimizer for particular parameter space
if space_id not in self.search_spaces_:
raise ValueError("Unknown space %s" % space_id)
# get the search space for a step
search_space = self.search_spaces_[space_id]
if isinstance(search_space, tuple):
search_space, _ = search_space
# create optimizer if not created already
if space_id not in self.optimizer_:
self.optimizer_[space_id] = self._make_optimizer(search_space)
optimizer = self.optimizer_[space_id]
# get parameter values to evaluate
params = optimizer.ask(n_points=n_jobs)
params_dict = [point_asdict(search_space, p) for p in params]
# self.cv_results_ is reset at every call to _fit, keep current
all_cv_results = self.cv_results_
# record performances with different points
refit = self.refit
self.refit = False # do not fit yet - will be fit later
> self._fit(X, y, groups, params_dict)
E AttributeError: 'BayesSearchCV' object has no attribute '_fit'
skopt/searchcv.py:506: AttributeError
____________________________________________________________________________________________________________________ test_searchcv_runs[-1-None] ____________________________________________________________________________________________________________________
surrogate = None, n_jobs = -1
@pytest.mark.parametrize("surrogate", ['gp', None])
@pytest.mark.parametrize("n_jobs", [1, -1]) # test sequential and parallel
def test_searchcv_runs(surrogate, n_jobs):
"""
Test whether the cross validation search wrapper around sklearn
models runs properly with available surrogates and with single
or multiple workers.
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
)
# None search space is only supported when only `step` function is used
assert_raises(ValueError, BayesSearchCV(SVC(), None).fit, (X, y))
# check if invalid dimensions are raising errors
with pytest.raises(ValueError):
BayesSearchCV(SVC(), {'C': '1 ... 100.0'})
with pytest.raises(TypeError):
BayesSearchCV(SVC(), ['C', (1.0, 1)])
# 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,
optimizer_kwargs=optimizer_kwargs
)
> opt.fit(X_train, y_train)
skopt/tests/test_searchcv.py:70:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
skopt/searchcv.py:575: in fit
groups=groups, n_jobs=n_jobs_adjusted
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
self = BayesSearchCV(cv=None, error_score='raise',
estimator=SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,
...s', random_state=None,
refit=False, return_train_score=True, scoring=None,
search_spaces=None, verbose=0)
X = array([[ 5.9, 3. , 4.2, 1.5],
[ 5.8, 2.6, 4. , 1.2],
[ 6.8, 3. , 5.5, 2.1],
[ 4.7, 3.2,... 2.9, 5.6, 1.8],
[ 5.8, 2.7, 4.1, 1. ],
[ 7.7, 3.8, 6.7, 2.2],
[ 4.6, 3.2, 1.4, 0.2]])
y = array([1, 1, 2, 0, 2, 0, 0, 1, 2, 2, 2, 2, 1, 2, 1, 1, 2, 2, 2, 2, 1, 2, 1,
0, 2, 1, 1, 1, 1, 2, 0, 0, 2, 1, 0,... 0, 2, 1, 2, 1, 0, 2, 0, 2, 0, 0, 2, 0, 2, 1, 1, 1,
2, 2, 1, 1, 0, 1, 2, 2, 0, 1, 1, 1, 1, 0, 0, 0, 2, 1, 2, 0])
space_id = range(0, 1), groups = None, n_jobs = 4
def step(self, X, y, space_id, groups=None, n_jobs=1):
"""Generate n_jobs parameters and evaluate them in parallel.
Having a separate function for a single step for search allows to
save easily checkpoints for the parameter search and restore from
possible failures.
Parameters
----------
X : array-like or sparse matrix, shape = [n_samples, n_features]
The training input samples. Internally, it will be converted to
``dtype=np.float32`` and if a sparse matrix is provided
to a sparse ``csc_matrix``.
y : array-like, shape = [n_samples] or [n_samples, n_outputs]
The target values (class labels) as integers or strings.
space_id : hashable
Identifier of parameter search space. Add search spaces with
groups : array-like, with shape (n_samples,), optional
Group labels for the samples used while splitting the dataset into
train/test set.
n_jobs : int, default=1
Number of parameters to evaluate in parallel.
Returns
-------
params_dict: dictionary with parameter values.
"""
# convert n_jobst to int > 0 if necessary
if n_jobs < 0:
n_jobs = max(1, cpu_count() + n_jobs + 1)
# use the cached optimizer for particular parameter space
if space_id not in self.search_spaces_:
raise ValueError("Unknown space %s" % space_id)
# get the search space for a step
search_space = self.search_spaces_[space_id]
if isinstance(search_space, tuple):
search_space, _ = search_space
# create optimizer if not created already
if space_id not in self.optimizer_:
self.optimizer_[space_id] = self._make_optimizer(search_space)
optimizer = self.optimizer_[space_id]
# get parameter values to evaluate
params = optimizer.ask(n_points=n_jobs)
params_dict = [point_asdict(search_space, p) for p in params]
# self.cv_results_ is reset at every call to _fit, keep current
all_cv_results = self.cv_results_
# record performances with different points
refit = self.refit
self.refit = False # do not fit yet - will be fit later
> self._fit(X, y, groups, params_dict)
E AttributeError: 'BayesSearchCV' object has no attribute '_fit'
skopt/searchcv.py:506: AttributeError
_______________________________________________________________________________________________________________ test_searchcv_runs_multiple_subspaces _______________________________________________________________________________________________________________
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
)
opt = BayesSearchCV(
SVC(),
[
({
'C': Real(1e-6, 1e+6, prior='log-uniform'),
'gamma': Real(1e-6, 1e+1, prior='log-uniform'),
}, 10),
{
'degree': Integer(1, 8),
'kernel': Categorical(['linear', 'poly', 'rbf']),
}
],
n_iter=10
)
> opt.fit(X_train, y_train)
skopt/tests/test_searchcv.py:103:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
skopt/searchcv.py:575: in fit
groups=groups, n_jobs=n_jobs_adjusted
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
self = BayesSearchCV(cv=None, error_score='raise',
estimator=SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,
...s', random_state=None, refit=False,
return_train_score=True, scoring=None, search_spaces=None,
verbose=0)
X = array([[ 5.9, 3. , 4.2, 1.5],
[ 5.8, 2.6, 4. , 1.2],
[ 6.8, 3. , 5.5, 2.1],
[ 4.7, 3.2,... 2.9, 5.6, 1.8],
[ 5.8, 2.7, 4.1, 1. ],
[ 7.7, 3.8, 6.7, 2.2],
[ 4.6, 3.2, 1.4, 0.2]])
y = array([1, 1, 2, 0, 2, 0, 0, 1, 2, 2, 2, 2, 1, 2, 1, 1, 2, 2, 2, 2, 1, 2, 1,
0, 2, 1, 1, 1, 1, 2, 0, 0, 2, 1, 0,... 0, 2, 1, 2, 1, 0, 2, 0, 2, 0, 0, 2, 0, 2, 1, 1, 1,
2, 2, 1, 1, 0, 1, 2, 2, 0, 1, 1, 1, 1, 0, 0, 0, 2, 1, 2, 0])
space_id = range(0, 2), groups = None, n_jobs = 1
def step(self, X, y, space_id, groups=None, n_jobs=1):
"""Generate n_jobs parameters and evaluate them in parallel.
Having a separate function for a single step for search allows to
save easily checkpoints for the parameter search and restore from
possible failures.
Parameters
----------
X : array-like or sparse matrix, shape = [n_samples, n_features]
The training input samples. Internally, it will be converted to
``dtype=np.float32`` and if a sparse matrix is provided
to a sparse ``csc_matrix``.
y : array-like, shape = [n_samples] or [n_samples, n_outputs]
The target values (class labels) as integers or strings.
space_id : hashable
Identifier of parameter search space. Add search spaces with
groups : array-like, with shape (n_samples,), optional
Group labels for the samples used while splitting the dataset into
train/test set.
n_jobs : int, default=1
Number of parameters to evaluate in parallel.
Returns
-------
params_dict: dictionary with parameter values.
"""
# convert n_jobst to int > 0 if necessary
if n_jobs < 0:
n_jobs = max(1, cpu_count() + n_jobs + 1)
# use the cached optimizer for particular parameter space
if space_id not in self.search_spaces_:
raise ValueError("Unknown space %s" % space_id)
# get the search space for a step
search_space = self.search_spaces_[space_id]
if isinstance(search_space, tuple):
search_space, _ = search_space
# create optimizer if not created already
if space_id not in self.optimizer_:
self.optimizer_[space_id] = self._make_optimizer(search_space)
optimizer = self.optimizer_[space_id]
# get parameter values to evaluate
params = optimizer.ask(n_points=n_jobs)
params_dict = [point_asdict(search_space, p) for p in params]
# self.cv_results_ is reset at every call to _fit, keep current
all_cv_results = self.cv_results_
# record performances with different points
refit = self.refit
self.refit = False # do not fit yet - will be fit later
> self._fit(X, y, groups, params_dict)
E AttributeError: 'BayesSearchCV' object has no attribute '_fit'
skopt/searchcv.py:506: AttributeError
________________________________________________________________________________________________________________________ test_dump_and_load _________________________________________________________________________________________________________________________
@pytest.mark.fast_test
def test_dump_and_load():
res = gp_minimize(bench3,
[(-2.0, 2.0)],
x0=[0.],
acq_func="LCB",
n_calls=2,
n_random_starts=0,
random_state=1)
# Test normal dumping and loading
with tempfile.TemporaryFile() as f:
dump(res, f)
> res_loaded = load(f)
skopt/tests/test_utils.py:48:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
skopt/utils.py:172: in load
return load_(filename, **kwargs)
../scikit-learn/sklearn/externals/joblib/numpy_pickle.py:568: in load
obj = _unpickle(fobj)
../scikit-learn/sklearn/externals/joblib/numpy_pickle.py:508: in _unpickle
obj = unpickler.load()
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
self = <sklearn.externals.joblib.numpy_pickle.NumpyUnpickler object at 0x7f012a1f2828>
def load(self):
"""Read a pickled object representation from the open file.
Return the reconstituted object hierarchy specified in the file.
"""
# Check whether Unpickler was initialized correctly. This is
# only needed to mimic the behavior of _pickle.Unpickler.dump().
if not hasattr(self, "_file_read"):
raise UnpicklingError("Unpickler.__init__() was not called by "
"%s.__init__()" % (self.__class__.__name__,))
self._unframer = _Unframer(self._file_read, self._file_readline)
self.read = self._unframer.read
self.readline = self._unframer.readline
self.metastack = []
self.stack = []
self.append = self.stack.append
self.proto = 0
read = self.read
dispatch = self.dispatch
try:
while True:
key = read(1)
if not key:
> raise EOFError
E EOFError
../../anaconda3/lib/python3.6/pickle.py:1048: EOFError
___________________________________________________________________________________________________________________ test_dump_and_load_optimizer ____________________________________________________________________________________________________________________
@pytest.mark.fast_test
def test_dump_and_load_optimizer():
base_estimator = ExtraTreesRegressor(random_state=2)
opt = Optimizer([(-2.0, 2.0)], base_estimator, n_random_starts=1,
acq_optimizer="sampling")
opt.run(bench1, n_iter=3)
with tempfile.TemporaryFile() as f:
dump(opt, f)
> load(f)
skopt/tests/test_utils.py:78:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
skopt/utils.py:172: in load
return load_(filename, **kwargs)
../scikit-learn/sklearn/externals/joblib/numpy_pickle.py:568: in load
obj = _unpickle(fobj)
../scikit-learn/sklearn/externals/joblib/numpy_pickle.py:508: in _unpickle
obj = unpickler.load()
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
self = <sklearn.externals.joblib.numpy_pickle.NumpyUnpickler object at 0x7f010f9d73c8>
def load(self):
"""Read a pickled object representation from the open file.
Return the reconstituted object hierarchy specified in the file.
"""
# Check whether Unpickler was initialized correctly. This is
# only needed to mimic the behavior of _pickle.Unpickler.dump().
if not hasattr(self, "_file_read"):
raise UnpicklingError("Unpickler.__init__() was not called by "
"%s.__init__()" % (self.__class__.__name__,))
self._unframer = _Unframer(self._file_read, self._file_readline)
self.read = self._unframer.read
self.readline = self._unframer.readline
self.metastack = []
self.stack = []
self.append = self.stack.append
self.proto = 0
read = self.read
dispatch = self.dispatch
try:
while True:
key = read(1)
if not key:
> raise EOFError
E EOFError
There's also many
/home/andy/checkout/scikit-learn/sklearn/utils/deprecation.py:75: DeprecationWarning: Function y_train_mean is deprecated; Attribute y_train_mean was deprecated in version 0.19 and will be removed in 0.21.
messages, that basically make the whole test output unreadable :-/
The BayesSearchCV (and the deprecation) is probably because I'm running scikit-learn master, not sure about the rest. (I'm surprised the other people here are not running scikit-learn master?)