8000 [MRG+1] MacOS X testing improvements by kmike · Pull Request #2982 · scikit-learn/scikit-learn · GitHub
[go: up one dir, main page]
Skip to content

[MRG+1] MacOS X testing improvements #2982

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
Mar 24, 2014
Merged

[MRG+1] MacOS X testing improvements #2982

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
61d9c5e
TST skip `test_k_means_plus_plus_init_2_jobs` on Mac OS X 10.9. See G…
kmike Mar 20, 2014
88a85e0
TST fix sklearn.ensemble.tests.test_bagging.test_parallel
kmike Mar 20, 2014
20c45ae
TST move Mac OS checking utility to sklearn.utils.testing
kmike Mar 20, 2014
e87653d
TST skip SparsePCA n_jobs!=1 test on Mac OS X because it hangs
kmike Mar 20, 2014
261da69
TST remove n_jobs=-1 usages in tests
kmike Mar 24, 2014
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 2 additions & 10 deletions sklearn/cluster/tests/test_k_means.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,7 @@
from sklearn.utils.testing import assert_greater
from sklearn.utils.testing import assert_less
from sklearn.utils.testing import assert_warns
from sklearn.utils.testing import if_not_mac_os

from sklearn.utils.extmath import row_norms
from sklearn.metrics.cluster import v_measure_score
Expand Down Expand Up @@ -195,22 +196,13 @@ def test_k_means_new_centers():
np.testing.assert_array_equal(this_labels, labels)


def _is_mac_os_version(version):
"""Returns True iff Mac OS X and newer than specified version."""
import platform
mac_version, _, _ = platform.mac_ver()
return mac_version.split('.')[:2] == version.split('.')[:2]


def _has_blas_lib(libname):
from numpy.distutils.system_info import get_info
return libname in get_info('blas_opt').get('libraries', [])


@if_not_mac_os()
def test_k_means_plus_plus_init_2_jobs():
if _is_mac_os_version('10.7') or _is_mac_os_version('10.8'):
raise SkipTest('Multi-process bug in Mac OS X Lion (see issue #636)')

if _has_blas_lib('openblas'):
raise SkipTest('Multi-process bug with OpenBLAS (see issue #636)')

Expand Down
22 changes: 17 additions & 5 deletions sklearn/decomposition/tests/test_sparse_pca.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,7 @@
from sklearn.utils.testing import SkipTest
from sklearn.utils.testing import assert_true
from sklearn.utils.testing import assert_false
from sklearn.utils.testing import if_not_mac_os

from sklearn.decomposition import SparsePCA, MiniBatchSparsePCA
from sklearn.utils import check_random_state
Expand Down Expand Up @@ -62,18 +63,29 @@ def test_fit_transform():
spca_lars = SparsePCA(n_components=3, method='lars', alpha=alpha,
random_state=0)
spca_lars.fit(Y)

# Test that CD gives similar results
spca_lasso = SparsePCA(n_components=3, method='cd', random_state=0,
alpha=alpha)
spca_lasso.fit(Y)
assert_array_almost_equal(spca_lasso.components_, spca_lars.components_)


@if_not_mac_os()
def test_fit_transform_parallel():
alpha = 1
rng = np.random.RandomState(0)
Y, _, _ = generate_toy_data(3, 10, (8, 8), random_state=rng) # wide array
spca_lars = SparsePCA(n_components=3, method='lars', alpha=alpha,
random_state=0)
spca_lars.fit(Y)
U1 = spca_lars.transform(Y)
# Test multiple CPUs
spca = SparsePCA(n_components=3, n_jobs=2, method='lars', alpha=alpha,
random_state=0).fit(Y)
U2 = spca.transform(Y)
assert_true(not np.all(spca_lars.components_ == 8000 0))
assert_array_almost_equal(U1, U2)
# Test that CD gives similar results
spca_lasso = SparsePCA(n_components=3, method='cd', random_state=0,
alpha=alpha)
spca_lasso.fit(Y)
assert_array_almost_equal(spca_lasso.components_, spca_lars.components_)


def test_transform_nan():
Expand Down
94 changes: 48 additions & 46 deletions sklearn/ensemble/tests/test_bagging.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -285,74 +285,76 @@ def test_error():
BaggingClassifier(base).fit(X, y).decision_function, X)


def test_parallel():
"""Check parallel computations."""
def test_parallel_classification():
"""Check parallel classification."""
rng = check_random_state(0)

# Classification
X_train, X_test, y_train, y_test = train_test_split(iris.data,
iris.target,
random_state=rng)

for n_jobs in [-1, 3]:
ensemble = BaggingClassifier(DecisionTreeClassifier(),
n_jobs=n_jobs,
random_state=0).fit(X_train, y_train)
ensemble = BaggingClassifier(DecisionTreeClassifier(),
n_jobs=3,
random_state=0).fit(X_train, y_train)

# predict_proba
ensemble.set_params(n_jobs=1)
y1 = ensemble.predict_proba(X_test)
ensemble.set_params(n_jobs=2)
y2 = ensemble.predict_proba(X_test)
assert_array_almost_equal(y1, y2)
# predict_proba
ensemble.set_params(n_jobs=1)
y1 = ensemble.predict_proba(X_test)
ensemble.set_params(n_jobs=2)
y2 = ensemble.predict_proba(X_test)
assert_array_almost_equal(y1, y2)

ensemble = BaggingClassifier(DecisionTreeClassifier(),
n_jobs=1,
random_state=0).fit(X_train, y_train)
ensemble = BaggingClassifier(DecisionTreeClassifier(),
n_jobs=1,
random_state=0).fit(X_train, y_train)

y3 = ensemble.predict_proba(X_test)
assert_array_almost_equal(y1, y3)
y3 = ensemble.predict_proba(X_test)
assert_array_almost_equal(y1, y3)

# decision_function
ensemble = BaggingClassifier(SVC(),
n_jobs=n_jobs,
random_state=0).fit(X_train, y_train)
# decision_function
ensemble = BaggingClassifier(SVC(),
n_jobs=3,
random_state=0).fit(X_train, y_train)

ensemble.set_params(n_jobs=1)
decisions1 = ensemble.decision_function(X_test)
ensemble.set_params(n_jobs=2)
decisions2 = ensemble.decision_function(X_test)
assert_array_almost_equal(decisions1, decisions2)
ensemble.set_params(n_jobs=1)
decisions1 = ensemble.decision_function(X_test)
ensemble.set_params(n_jobs=2)
decisions2 = ensemble.decision_function(X_test)
assert_array_almost_equal(decisions1, decisions2)

ensemble = BaggingClassifier(SVC(),
n_jobs=1,
random_state=0).fit(X_train, y_train)
ensemble = BaggingClassifier(SVC(),
n_jobs=1,
random_state=0).fit(X_train, y_train)

decisions3 = ensemble.decision_function(X_test)
assert_array_almost_equal(decisions1, decisions3)
decisions3 = ensemble.decision_function(X_test)
assert_array_almost_equal(decisions1, decisions3)


def test_parallel_regression():
"""Check parallel regression."""
rng = check_random_state(0)

# Regression
X_train, X_test, y_train, y_test = train_test_split(boston.data,
boston.target,
random_state=rng)

for n_jobs in [-1, 3]:
ensemble = BaggingRegressor(DecisionTreeRegressor(),
n_jobs=3,
random_state=0).fit(X_train, y_train)
ensemble = BaggingRegressor(DecisionTreeRegressor(),
n_jobs=3,
random_state=0).fit(X_train, y_train)

ensemble.set_params(n_jobs=1)
y1 = ensemble.predict(X_test)
ensemble.set_params(n_jobs=2)
y2 = ensemble.predict(X_test)
assert_array_almost_equal(y1, y2)
ensemble.set_params(n_jobs=1)
y1 = ensemble.predict(X_test)
ensemble.set_params(n_jobs=2)
y2 = ensemble.predict(X_test)
assert_array_almost_equal(y1, y2)

ensemble = BaggingRegressor(DecisionTreeRegressor(),
n_jobs=1,
random_state=0).fit(X_train, y_train)
ensemble = BaggingRegressor(DecisionTreeRegressor(),
n_jobs=1,
random_state=0).fit(X_train, y_train)

y3 = ensemble.predict(X_test)
assert_array_almost_equal(y1, y3)
y3 = ensemble.predict(X_test)
assert_array_almost_equal(y1, y3)


def test_gridsearch():
Expand Down
4 changes: 0 additions & 4 deletions sklearn/ensemble/tests/test_forest.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -302,10 +302,6 @@ def test_parallel():
y2 = forest.predict(boston.data)
assert_array_almost_equal(y1, y2, 3)

# Use all cores on the classification dataset
forest = RandomForestClassifier(n_jobs=-1)
forest.fit(iris.data, iris.target)


def test_pickle():
"""Check pickability."""
Expand Down
4 changes: 2 additions & 2 deletions sklearn/metrics/tests/test_pairwise.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -123,11 +123,11 @@ def test_pairwise_parallel():
Y = func(rng.random_sample((3, 4)))

S = euclidean_distances(X)
S2 = _parallel_pairwise(X, None, euclidean_distances, n_jobs=-1)
S2 = _parallel_pairwise(X, None, euclidean_distances, n_jobs=3)
assert_array_almost_equal(S, S2)

S = euclidean_distances(X, Y)
S2 = _parallel_pairwise(X, Y, euclidean_distances, n_jobs=-1)
S2 = _parallel_pairwise(X, Y, euclidean_distances, n_jobs=3)
assert_array_almost_equal(S, S2)


Expand Down
18 changes: 18 additions & 0 deletions sklearn/utils/testing.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,7 @@
import warnings
import sys
import re
import platform

import scipy as sp
import scipy.io
Expand Down Expand Up @@ -553,6 +554,23 @@ def run_test(*args, **kwargs):
return run_test


def if_not_mac_os(versions=('10.7', '10.8', '10.9'),
message='Multi-process bug in Mac OS X >= 10.7 '
'(see issue #636)'):
"""Test decorator that skips test if OS is Mac OS X and its
major version is one of ``versions``.
"""
mac_version, _, _ = platform.mac_ver()
skip = '.'.join(mac_version.split('.')[:2]) in versions
def decorator(func):
if skip:
@wraps(func)
def func(*args, **kwargs):
raise SkipTest(message)
return func
return decorator


def clean_warning_registry():
"""Safe way to reset warniings """
warnings.resetwarnings()
Expand Down
0