def test_blobs():
blobs = SG.Blobs(n_samples=50, n_features=2, centers=[[0.0, 0.0], [1.0, 1.0], [0.0, 1.0]], random_state=0)
X, y = blobs.classification_task()
tasks.assert_classification(X, y)
assert_equal(X.shape, (50, 2), "X shape mismatch")
assert_equal(y.shape, (50,), "y shape mismatch")
assert_equal(np.unique(y).shape, (3,), "Unexpected number of blobs")
def test_blobs():
blobs = SG.Blobs(n_samples=50, n_features=2,
centers=[[0.0, 0.0], [1.0, 1.0], [0.0, 1.0]],
random_state=0)
X, y = blobs.classification_task()
tasks.assert_classification(X, y)
assert_equal(X.shape, (50, 2), "X shape mismatch")
assert_equal(y.shape, (50,), "y shape mismatch")
assert_equal(np.unique(y).shape, (3,), "Unexpected number of blobs")
def test_four_regions():
four_regions = SG.FourRegions(n_samples=100, random_state=0)
X, y = four_regions.classification_task()
tasks.assert_classification(X, y, 100)
assert_equal(X.shape, (100, 2), "X shape mismatch")
assert_equal(y.shape, (100,), "y shape mismatch")
assert_equal(np.unique(y).shape, (4,), "Unexpected number of classes")
assert_equal(sum(y == 0), 22, "Unexpected number of samples in class #0")
assert_equal(sum(y == 1), 31, "Unexpected number of samples in class #1")
assert_equal(sum(y == 2), 24, "Unexpected number of samples in class #2")
assert_equal(sum(y == 3), 23, "Unexpected number of samples in class #3")
def test_four_regions():
four_regions = SG.FourRegions(n_samples=100, random_state=0)
X, y = four_regions.classification_task()
tasks.assert_classification(X, y, 100)
assert_equal(X.shape, (100, 2), "X shape mismatch")
assert_equal(y.shape, (100,), "y shape mismatch")
assert_equal(np.unique(y).shape, (4,), "Unexpected number of classes")
assert_equal(sum(y == 0), 22, "Unexpected number of samples in class #0")
assert_equal(sum(y == 1), 31, "Unexpected number of samples in class #1")
assert_equal(sum(y == 2), 24, "Unexpected number of samples in class #2")
assert_equal(sum(y == 3), 23, "Unexpected number of samples in class #3")
def test_madelon():
madelon = SG.Madelon(n_samples=100, n_features=20, n_informative=5,
n_redundant=1, n_repeated=1, n_classes=3,
n_clusters_per_class=1, hypercube=False,
shift=None, scale=None, weights=[0.1, 0.25],
random_state=0)
X, y = madelon.classification_task()
tasks.assert_classification(X, y, 100)
assert_equal(X.shape, (100, 20), "X shape mismatch")
assert_equal(y.shape, (100,), "y shape mismatch")
assert_equal(np.unique(y).shape, (3,), "Unexpected number of classes")
assert_equal(sum(y == 0), 10, "Unexpected number of samples in class #0")
assert_equal(sum(y == 1), 25, "Unexpected number of samples in class #1")
assert_equal(sum(y == 2), 65, "Unexpected number of samples in class #2")
def test_several():
dsetnames = [
'MNIST_Basic', 'MNIST_BackgroundImages', 'MNIST_BackgroundRandom',
'Rectangles', 'RectanglesImages', 'Convex'
]
dsetnames.extend(['MNIST_Noise%i' % i for i in range(1, 7)])
for dsetname in dsetnames:
aa = dset(dsetname)
assert len(aa.meta) == sum(
[aa.descr[s] for s in 'n_train', 'n_valid', 'n_test'])
bb = dset(dsetname)
assert aa.meta == bb.meta
tasks.assert_classification(*aa.classification_task())
tasks.assert_latent_structure(aa.latent_structure_task())
def test_assert_classification(self):
# things that work:
tasks.assert_classification(rnd('float32', 4, 2), rnd('int8', 4))
tasks.assert_classification(rnd('float64', 4, 2), rnd('uint64', 4))
tasks.assert_classification(rnd('float64', 4, 2), rnd('uint64', 4), 4)
# things that break:
self.assertRaises(AssertionError, tasks.assert_classification,
rnd('int8', 4, 2), rnd('int8', 4)) # X not float
self.assertRaises(AssertionError, tasks.assert_classification,
rnd('float32', 4, 2), rnd('float64', 4)) # y not int
self.assertRaises(AssertionError, tasks.assert_classification,
rnd('float32', 4, 2), rnd('int8', 5)) # y wrong len
self.assertRaises(AssertionError, tasks.assert_classification,
rnd('float32', 4, 2), rnd('int8', 4,
1)) # y wrong rank
self.assertRaises(AssertionError, tasks.assert_classification,
rnd('float32', 4, 2), rnd('int8', 4,
7)) # y wrong rank
self.assertRaises(AssertionError, tasks.assert_classification,
rnd('float32', 4, 2, 2), rnd('int8',
4)) # X wrong rank
self.assertRaises(AssertionError, tasks.assert_classification,
rnd('float64', 4), rnd('int8', 4)) # X wrong rank
self.assertRaises(AssertionError, tasks.assert_classification,
rnd('float64', 4, 3), rnd('int8', 4),
5) # N mismatch
def test_assert_classification(self):
# things that work:
tasks.assert_classification(
rnd('float32', 4, 2), rnd('int8', 4))
tasks.assert_classification(
rnd('float64', 4, 2), rnd('uint64', 4))
tasks.assert_classification(
rnd('float64', 4, 2), rnd('uint64', 4), 4)
# things that break:
self.assertRaises(AssertionError, tasks.assert_classification,
rnd('int8', 4, 2), rnd('int8', 4)) # X not float
self.assertRaises(AssertionError, tasks.assert_classification,
rnd('float32', 4, 2), rnd('float64', 4)) # y not int
self.assertRaises(AssertionError, tasks.assert_classification,
rnd('float32', 4, 2), rnd('int8', 5)) # y wrong len
self.assertRaises(AssertionError, tasks.assert_classification,
rnd('float32', 4, 2), rnd('int8', 4, 1)) # y wrong rank
self.assertRaises(AssertionError, tasks.assert_classification,
rnd('float32', 4, 2), rnd('int8', 4, 7)) # y wrong rank
self.assertRaises(AssertionError, tasks.assert_classification,
rnd('float32', 4, 2, 2), rnd('int8', 4)) # X wrong rank
self.assertRaises(AssertionError, tasks.assert_classification,
rnd('float64', 4), rnd('int8', 4)) # X wrong rank
self.assertRaises(AssertionError, tasks.assert_classification,
rnd('float64', 4, 3), rnd('int8', 4), 5) # N mismatch
def test_madelon():
madelon = SG.Madelon(
n_samples=100,
n_features=20,
n_informative=5,
n_redundant=1,
n_repeated=1,
n_classes=3,
n_clusters_per_class=1,
hypercube=False,
shift=None,
scale=None,
weights=[0.1, 0.25],
random_state=0,
)
X, y = madelon.classification_task()
tasks.assert_classification(X, y, 100)
assert_equal(X.shape, (100, 20), "X shape mismatch")
assert_equal(y.shape, (100,), "y shape mismatch")
assert_equal(np.unique(y).shape, (3,), "Unexpected number of classes")
assert_equal(sum(y == 0), 10, "Unexpected number of samples in class #0")
assert_equal(sum(y == 1), 25, "Unexpected number of samples in class #1")
assert_equal(sum(y == 2), 65, "Unexpected number of samples in class #2")
def test_classification_train_valid_test(self):
dataset = larochelle_etal_2007.Rectangles() # smallest one with splits
assert not hasattr(dataset, 'classification_train_valid_test_task')
train, valid, test = tasks.classification_train_valid_test(dataset)
tasks.assert_classification(*train)
tasks.assert_classification(*valid)
tasks.assert_classification(*test)
assert len(train[0]) == dataset.descr['n_train']
assert len(valid[0]) == dataset.descr['n_valid']
assert len(test[0]) == dataset.descr['n_test']
tasks.assert_classification_train_valid_test(train, valid, test)
def test_classification_train_valid_test(self):
dataset = larochelle_etal_2007.Rectangles() # smallest one with splits
assert not hasattr(dataset, 'classification_train_valid_test_task')
train, valid, test = tasks.classification_train_valid_test(dataset)
tasks.assert_classification(*train)
tasks.assert_classification(*valid)
tasks.assert_classification(*test)
assert len(train[0]) == dataset.descr['n_train']
assert len(valid[0]) == dataset.descr['n_valid']
assert len(test[0]) == dataset.descr['n_test']
tasks.assert_classification_train_valid_test(train, valid, test)
def test_classification():
cifar = cifar10.CIFAR10() # just make sure we can create the class
cifar.DOWNLOAD_IF_MISSING = False
X, y = cifar.classification_task()
tasks.assert_classification(X, y, 60000)
def check_classification_Xy(X, y, N=None):
assert_classification(X, y, N)
assert aa.meta[10000] == dict(id=10000, label=3, split='valid')
assert aa.meta[11999] == dict(id=11999, label=3, split='valid')
assert aa.meta[12000] == dict(id=12000, label=7, split='test')
assert aa.meta[50000] == dict(id=50000, label=3, split='test')
assert aa.meta[61989] == dict(id=61989, label=4, split='test')
assert len(aa.meta) == 62000
bb = dset(dsetname)
assert bb.meta == aa.meta
def test_several():
dsetnames = ['MNIST_Basic',
'MNIST_BackgroundImages',
'MNIST_BackgroundRandom',
'Rectangles',
'RectanglesImages',
'Convex']
dsetnames.extend(['MNIST_Noise%i' % i for i in range(1,7)])
for dsetname in dsetnames:
aa = dset(dsetname)
assert len(aa.meta) == sum(
[aa.descr[s] for s in 'n_train', 'n_valid', 'n_test'])
bb = dset(dsetname)
assert aa.meta == bb.meta
tasks.assert_classification(*aa.classification_task())
tasks.assert_latent_structure(aa.latent_structure_task())
def test_MNIST_classification():
M = mnist.MNIST() # just make sure we can create the class
M.DOWNLOAD_IF_MISSING = False
X, y = M.classification_task()
tasks.assert_classification(X, y, 70000)
def check_classification_Xy(X, y, N=None):
assert_classification(X, y, N)
def test_classification():
cifar = cifar10.CIFAR10() # just make sure we can create the class
cifar.DOWNLOAD_IF_MISSING = False
X, y = cifar.classification_task()
tasks.assert_classification(X, y, 60000)
