def test_masked_array_obj_dtype_pickleable():
marr = MaskedArray([1, None, 'a'], dtype=object)
for mask in (True, False, [0, 1, 0]):
marr.mask = mask
marr_pickled = pickle.loads(pickle.dumps(marr))
assert_array_equal(marr.data, marr_pickled.data)
assert_array_equal(marr.mask, marr_pickled.mask)
def test_masked_array_obj_dtype_pickleable():
marr = MaskedArray([1, None, 'a'], dtype=object)
for mask in (True, False, [0, 1, 0]):
marr.mask = mask
marr_pickled = pickle.loads(pickle.dumps(marr))
assert_array_equal(marr.data, marr_pickled.data)
assert_array_equal(marr.mask, marr_pickled.mask)
def create_cv_results(scores, candidate_params, n_splits, error_score,
weights):
if isinstance(scores[0], tuple):
test_scores, train_scores = zip(*scores)
else:
test_scores = scores
train_scores = None
test_scores = [error_score if s is FIT_FAILURE else s for s in test_scores]
if train_scores is not None:
train_scores = [
error_score if s is FIT_FAILURE else s for s in train_scores
]
# Construct the `cv_results_` dictionary
results = {'params': candidate_params}
n_candidates = len(candidate_params)
if weights is not None:
weights = np.broadcast_to(weights[None, :],
(len(candidate_params), len(weights)))
_store(results,
'test_score',
test_scores,
n_splits,
n_candidates,
splits=True,
rank=True,
weights=weights)
if train_scores is not None:
_store(results,
'train_score',
train_scores,
n_splits,
n_candidates,
splits=True)
# Use one MaskedArray and mask all the places where the param is not
# applicable for that candidate. Use defaultdict as each candidate may
# not contain all the params
param_results = defaultdict(
lambda: MaskedArray(np.empty(n_candidates), mask=True, dtype=object))
for cand_i, params in enumerate(candidate_params):
for name, value in params.items():
param_results["param_%s" % name][cand_i] = value
results.update(param_results)
return results
def create_cv_results(output, candidate_params, n_splits, error_score, iid,
return_train_score):
if return_train_score:
train_scores, test_scores, test_sample_counts = unzip(output, 3)
train_scores = [
error_score if s is FIT_FAILURE else s for s in train_scores
]
else:
test_scores, test_sample_counts = unzip(output, 2)
test_scores = [error_score if s is FIT_FAILURE else s for s in test_scores]
# Construct the `cv_results_` dictionary
results = {'params': candidate_params}
n_candidates = len(candidate_params)
test_sample_counts = np.array(test_sample_counts[:n_splits], dtype=int)
_store(results,
'test_score',
test_scores,
n_splits,
n_candidates,
splits=True,
rank=True,
weights=test_sample_counts if iid else None)
if return_train_score:
_store(results,
'train_score',
train_scores,
n_splits,
n_candidates,
splits=True)
# Use one MaskedArray and mask all the places where the param is not
# applicable for that candidate. Use defaultdict as each candidate may
# not contain all the params
param_results = defaultdict(
lambda: MaskedArray(np.empty(n_candidates), mask=True, dtype=object))
for cand_i, params in enumerate(candidate_params):
for name, value in params.items():
param_results["param_%s" % name][cand_i] = value
results.update(param_results)
return results
def test_masked_array_deprecated(): # TODO: remove in 0.25
with pytest.warns(FutureWarning, match='is deprecated'):
MaskedArray()