def test_eep_load():
eb = EEPBin(os.path.join(pymvpa_dataroot, 'eep.bin'))
ds = [ eep_dataset(source, targets=[1, 2]) for source in
(eb, os.path.join(pymvpa_dataroot, 'eep.bin')) ]
for d in ds:
assert_equal(d.nsamples, 2)
assert_equal(d.nfeatures, 128)
assert_equal(np.unique(d.fa.channels[4*23:4*23+4]), 'Pz')
assert_array_almost_equal([np.arange(-0.002, 0.005, 0.002)] * 32,
d.a.mapper.reverse1(d.fa.timepoints))
def test_streamline_equal_mapper(self):
self.build_streamline_things()
self.prototypes_equal = self.dataset.samples
self.pm = PrototypeMapper(similarities=self.similarities,
prototypes=self.prototypes_equal,
demean=False)
self.pm.train(self.dataset.samples)
## debug("MAP","projected data: "+str(self.pm.proj))
# check size:
assert_array_equal(self.pm.proj.shape, (len(self.dataset.samples), len(self.prototypes_equal)*len(self.similarities)))
# test symmetry
assert_array_almost_equal(self.pm.proj, self.pm.proj.T)
def test_streamline_equal_mapper(self):
self.build_streamline_things()
self.prototypes_equal = self.dataset.samples
self.pm = PrototypeMapper(similarities=self.similarities,
prototypes=self.prototypes_equal,
demean=False)
self.pm.train(self.dataset.samples)
## debug("MAP","projected data: "+str(self.pm.proj))
# check size:
assert_array_equal(self.pm.proj.shape, (len(self.dataset.samples), len(self.prototypes_equal)*len(self.similarities)))
# test symmetry
assert_array_almost_equal(self.pm.proj, self.pm.proj.T)
def test_eep_load():
eb = EEPBin(os.path.join(pymvpa_dataroot, 'eep.bin'))
ds = [
eep_dataset(source, targets=[1, 2])
for source in (eb, os.path.join(pymvpa_dataroot, 'eep.bin'))
]
for d in ds:
assert_equal(d.nsamples, 2)
assert_equal(d.nfeatures, 128)
assert_equal(np.unique(d.fa.channels[4 * 23:4 * 23 + 4]), 'Pz')
assert_array_almost_equal([np.arange(-0.002, 0.005, 0.002)] * 32,
d.a.mapper.reverse1(d.fa.timepoints))
def test_array_collectable():
c = ArrayCollectable()
# empty by default
assert_equal(c.name, None)
assert_equal(c.value, None)
# late assignment
c.name = 'somename'
assert_raises(ValueError, c._set, 12345)
assert_equal(c.value, None)
c.value = np.arange(5)
assert_equal(c.name, 'somename')
assert_array_equal(c.value, np.arange(5))
# immediate content
data = np.random.random(size=(3,10))
c = ArrayCollectable(data.copy(), 'myname',
"This is a test", length=3)
assert_equal(c.name, 'myname')
assert_array_equal(c.value, data)
assert_equal(c.__doc__, "This is a test")
assert_equal(str(c), 'myname')
# repr
from numpy import array
e = eval(repr(c))
assert_equal(e.name, 'myname')
assert_array_almost_equal(e.value, data)
assert_equal(e.__doc__, "This is a test")
# cannot assign array of wrong length
assert_raises(ValueError, c._set, np.arange(5))
assert_equal(len(c), 3)
# shallow copy DOES create a view of value array
c.value = np.arange(3)
d = copy.copy(c)
assert_true(d.value.base is c.value)
# names starting with _ are not allowed
assert_raises(ValueError, c._set_name, "_underscore")
def test_array_collectable():
c = ArrayCollectable()
# empty by default
assert_equal(c.name, None)
assert_equal(c.value, None)
# late assignment
c.name = 'somename'
assert_raises(ValueError, c._set, 12345)
assert_equal(c.value, None)
c.value = np.arange(5)
assert_equal(c.name, 'somename')
assert_array_equal(c.value, np.arange(5))
# immediate content
data = np.random.random(size=(3, 10))
c = ArrayCollectable(data.copy(), 'myname', "This is a test", length=3)
assert_equal(c.name, 'myname')
assert_array_equal(c.value, data)
assert_equal(c.__doc__, "This is a test")
assert_equal(str(c), 'myname')
# repr
from numpy import array
e = eval(repr(c))
assert_equal(e.name, 'myname')
assert_array_almost_equal(e.value, data)
assert_equal(e.__doc__, "This is a test")
# cannot assign array of wrong length
assert_raises(ValueError, c._set, np.arange(5))
assert_equal(len(c), 3)
# shallow copy DOES create a view of value array
c.value = np.arange(3)
d = copy.copy(c)
assert_true(d.value.base is c.value)
# names starting with _ are not allowed
assert_raises(ValueError, c._set_name, "_underscore")
def test_mapper_vs_zscore():
"""Test by comparing to results of elderly z-score function
"""
# data: 40 sample feature line in 20d space (40x20; samples x features)
dss = [
dataset_wizard(np.concatenate(
[np.arange(40) for i in range(20)]).reshape(20,-1).T,
targets=1, chunks=1),
] + datasets.values()
for ds in dss:
ds1 = deepcopy(ds)
ds2 = deepcopy(ds)
zsm = ZScoreMapper(chunks_attr=None)
assert_raises(RuntimeError, zsm.forward, ds1.samples)
zsm.train(ds1)
ds1z = zsm.forward(ds1.samples)
zscore(ds2, chunks_attr=None)
assert_array_almost_equal(ds1z, ds2.samples)
assert_array_equal(ds1.samples, ds.samples)
def test_mapper_vs_zscore():
"""Test by comparing to results of elderly z-score function
"""
# data: 40 sample feature line in 20d space (40x20; samples x features)
dss = [
dataset_wizard(np.concatenate(
[np.arange(40) for i in range(20)]).reshape(20,-1).T,
targets=1, chunks=1),
] + datasets.values()
for ds in dss:
ds1 = deepcopy(ds)
ds2 = deepcopy(ds)
zsm = ZScoreMapper(chunks_attr=None)
assert_raises(RuntimeError, zsm.forward, ds1.samples)
zsm.train(ds1)
ds1z = zsm.forward(ds1.samples)
zscore(ds2, chunks_attr=None)
assert_array_almost_equal(ds1z, ds2.samples)
assert_array_equal(ds1.samples, ds.samples)
def test_symmetry(self):
self.build_vector_based_pm()
assert_array_almost_equal(self.pm.proj[:,self.samples.shape[0]],
self.pm.proj.T[self.samples.shape[0],:])
assert_array_equal(self.pm.proj[:,self.samples.shape[0]],
self.pm.proj.T[self.samples.shape[0],:])
def test_zscore():
"""Test z-scoring transformation
"""
# dataset: mean=2, std=1
samples = np.array((0, 1, 3, 4, 2, 2, 3, 1, 1, 3, 3, 1, 2, 2, 2, 2)).\
reshape((16, 1))
data = dataset_wizard(samples.copy(), targets=range(16), chunks=[0] * 16)
assert_equal(data.samples.mean(), 2.0)
assert_equal(data.samples.std(), 1.0)
zscore(data, chunks_attr='chunks')
# check z-scoring
check = np.array([-2, -1, 1, 2, 0, 0, 1, -1, -1, 1, 1, -1, 0, 0, 0, 0],
dtype='float64').reshape(16, 1)
assert_array_equal(data.samples, check)
data = dataset_wizard(samples.copy(), targets=range(16), chunks=[0] * 16)
zscore(data, chunks_attr=None)
assert_array_equal(data.samples, check)
# check z-scoring taking set of labels as a baseline
data = dataset_wizard(samples.copy(),
targets=[0, 2, 2, 2, 1] + [2] * 11,
chunks=[0] * 16)
zscore(data, param_est=('targets', [0, 1]))
assert_array_equal(samples, data.samples + 1.0)
# check that zscore modifies in-place; only guaranteed if no upcasting is
# necessary
samples = samples.astype('float')
data = dataset_wizard(samples,
targets=[0, 2, 2, 2, 1] + [2] * 11,
chunks=[0] * 16)
zscore(data, param_est=('targets', [0, 1]))
assert_array_equal(samples, data.samples)
# these might be duplicating code above -- but twice is better than nothing
# dataset: mean=2, std=1
raw = np.array((0, 1, 3, 4, 2, 2, 3, 1, 1, 3, 3, 1, 2, 2, 2, 2))
# dataset: mean=12, std=1
raw2 = np.array((0, 1, 3, 4, 2, 2, 3, 1, 1, 3, 3, 1, 2, 2, 2, 2)) + 10
# zscore target
check = [-2, -1, 1, 2, 0, 0, 1, -1, -1, 1, 1, -1, 0, 0, 0, 0]
ds = dataset_wizard(raw.copy(), targets=range(16), chunks=[0] * 16)
pristine = dataset_wizard(raw.copy(), targets=range(16), chunks=[0] * 16)
zm = ZScoreMapper()
# should do global zscore by default
zm.train(ds) # train
assert_array_almost_equal(zm.forward(ds), np.transpose([check]))
# should not modify the source
assert_array_equal(pristine, ds)
# if we tell it a different mean it should obey the order
zm = ZScoreMapper(params=(3,1))
zm.train(ds)
assert_array_almost_equal(zm.forward(ds), np.transpose([check]) - 1 )
assert_array_equal(pristine, ds)
# let's look at chunk-wise z-scoring
ds = dataset_wizard(np.hstack((raw.copy(), raw2.copy())),
targets=range(32),
chunks=[0] * 16 + [1] * 16)
# by default chunk-wise
zm = ZScoreMapper()
zm.train(ds) # train
assert_array_almost_equal(zm.forward(ds), np.transpose([check + check]))
# we should be able to do that same manually
zm = ZScoreMapper(params={0: (2,1), 1: (12,1)})
zm.train(ds) # train
assert_array_almost_equal(zm.forward(ds), np.transpose([check + check]))
def test_symmetry(self):
self.build_vector_based_pm()
assert_array_almost_equal(self.pm.proj[:,self.samples.shape[0]],
self.pm.proj.T[self.samples.shape[0],:])
assert_array_equal(self.pm.proj[:,self.samples.shape[0]],
self.pm.proj.T[self.samples.shape[0],:])
def test_zscore():
"""Test z-scoring transformation
"""
# dataset: mean=2, std=1
samples = np.array((0, 1, 3, 4, 2, 2, 3, 1, 1, 3, 3, 1, 2, 2, 2, 2)).\
reshape((16, 1))
data = dataset_wizard(samples.copy(), targets=range(16), chunks=[0] * 16)
assert_equal(data.samples.mean(), 2.0)
assert_equal(data.samples.std(), 1.0)
data_samples = data.samples.copy()
zscore(data, chunks_attr='chunks')
# copy should stay intact
assert_equal(data_samples.mean(), 2.0)
assert_equal(data_samples.std(), 1.0)
# we should be able to operate on ndarrays
# But we can't change type inplace for an array, can't we?
assert_raises(TypeError, zscore, data_samples, chunks_attr=None)
# so lets do manually
data_samples = data_samples.astype(float)
zscore(data_samples, chunks_attr=None)
assert_array_equal(data.samples, data_samples)
print data_samples
# check z-scoring
check = np.array([-2, -1, 1, 2, 0, 0, 1, -1, -1, 1, 1, -1, 0, 0, 0, 0],
dtype='float64').reshape(16, 1)
assert_array_equal(data.samples, check)
data = dataset_wizard(samples.copy(), targets=range(16), chunks=[0] * 16)
zscore(data, chunks_attr=None)
assert_array_equal(data.samples, check)
# check z-scoring taking set of labels as a baseline
data = dataset_wizard(samples.copy(),
targets=[0, 2, 2, 2, 1] + [2] * 11,
chunks=[0] * 16)
zscore(data, param_est=('targets', [0, 1]))
assert_array_equal(samples, data.samples + 1.0)
# check that zscore modifies in-place; only guaranteed if no upcasting is
# necessary
samples = samples.astype('float')
data = dataset_wizard(samples,
targets=[0, 2, 2, 2, 1] + [2] * 11,
chunks=[0] * 16)
zscore(data, param_est=('targets', [0, 1]))
assert_array_equal(samples, data.samples)
# these might be duplicating code above -- but twice is better than nothing
# dataset: mean=2, std=1
raw = np.array((0, 1, 3, 4, 2, 2, 3, 1, 1, 3, 3, 1, 2, 2, 2, 2))
# dataset: mean=12, std=1
raw2 = np.array((0, 1, 3, 4, 2, 2, 3, 1, 1, 3, 3, 1, 2, 2, 2, 2)) + 10
# zscore target
check = [-2, -1, 1, 2, 0, 0, 1, -1, -1, 1, 1, -1, 0, 0, 0, 0]
ds = dataset_wizard(raw.copy(), targets=range(16), chunks=[0] * 16)
pristine = dataset_wizard(raw.copy(), targets=range(16), chunks=[0] * 16)
zm = ZScoreMapper()
# should do global zscore by default
zm.train(ds) # train
assert_array_almost_equal(zm.forward(ds), np.transpose([check]))
# should not modify the source
assert_array_equal(pristine, ds)
# if we tell it a different mean it should obey the order
zm = ZScoreMapper(params=(3,1))
zm.train(ds)
assert_array_almost_equal(zm.forward(ds), np.transpose([check]) - 1 )
assert_array_equal(pristine, ds)
# let's look at chunk-wise z-scoring
ds = dataset_wizard(np.hstack((raw.copy(), raw2.copy())),
targets=range(32),
chunks=[0] * 16 + [1] * 16)
# by default chunk-wise
zm = ZScoreMapper()
zm.train(ds) # train
assert_array_almost_equal(zm.forward(ds), np.transpose([check + check]))
# we should be able to do that same manually
zm = ZScoreMapper(params={0: (2,1), 1: (12,1)})
zm.train(ds) # train
assert_array_almost_equal(zm.forward(ds), np.transpose([check + check]))
