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)
idhashes = (idhash(ds1), idhash(ds1.samples))
zsm.train(ds1)
idhashes_train = (idhash(ds1), idhash(ds1.samples))
assert_equal(idhashes, idhashes_train)
# forward dataset
ds1z_ds = zsm.forward(ds1)
idhashes_forwardds = (idhash(ds1), idhash(ds1.samples))
# must not modify samples in place!
assert_equal(idhashes, idhashes_forwardds)
# forward samples explicitly
ds1z = zsm.forward(ds1.samples)
idhashes_forward = (idhash(ds1), idhash(ds1.samples))
assert_equal(idhashes, idhashes_forward)
zscore(ds2, chunks_attr=None)
assert_array_almost_equal(ds1z, ds2.samples)
assert_array_equal(ds1.samples, ds.samples)
def test_dataset_summary():
for ds in datasets.values() + [Dataset(np.array([None], dtype=object))]:
s = ds.summary()
ok_(s.startswith(str(ds)[1:-1])) # we strip surrounding '<...>'
# TODO: actual test of what was returned; to do that properly
# RF the summary() so it is a dictionary
summaries = []
if 'targets' in ds.sa:
summaries += ['Sequence statistics']
if 'chunks' in ds.sa:
summaries += ['Summary for targets', 'Summary for chunks']
# By default we should get all kinds of summaries
if not 'Number of unique targets >' in s:
for summary in summaries:
ok_(summary in s)
# If we give "wrong" targets_attr we should see none of summaries
s2 = ds.summary(targets_attr='bogus')
for summary in summaries:
ok_(not summary in s2)
def test_dataset_summary():
for ds in datasets.values() + [Dataset(np.array([None], dtype=object))]:
s = ds.summary()
ok_(s.startswith(str(ds)[1:-1])) # we strip surrounding '<...>'
# TODO: actual test of what was returned; to do that properly
# RF the summary() so it is a dictionary
summaries = []
if 'targets' in ds.sa:
summaries += ['Sequence statistics']
if 'chunks' in ds.sa:
summaries += ['Summary for targets', 'Summary for chunks']
# By default we should get all kinds of summaries
if not 'Number of unique targets >' in s:
for summary in summaries:
ok_(summary in s)
# If we give "wrong" targets_attr we should see none of summaries
s2 = ds.summary(targets_attr='bogus')
for summary in summaries:
ok_(not summary in s2)
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)
idhashes = (idhash(ds1), idhash(ds1.samples))
zsm.train(ds1)
idhashes_train = (idhash(ds1), idhash(ds1.samples))
assert_equal(idhashes, idhashes_train)
# forward dataset
ds1z_ds = zsm.forward(ds1)
idhashes_forwardds = (idhash(ds1), idhash(ds1.samples))
# must not modify samples in place!
assert_equal(idhashes, idhashes_forwardds)
# forward samples explicitly
ds1z = zsm.forward(ds1.samples)
idhashes_forward = (idhash(ds1), idhash(ds1.samples))
assert_equal(idhashes, idhashes_forward)
zscore(ds2, chunks_attr=None)
assert_array_almost_equal(ds1z, ds2.samples)
assert_array_equal(ds1.samples, ds.samples)
from mvpa2.base import externals
from mvpa2.datasets import dataset_wizard
from mvpa2.measures.fx import BinaryFxFeaturewiseMeasure
from mvpa2.measures.fx import targets_dcorrcoef
if externals.exists('statsmodels'):
from mvpa2.measures.fx import targets_mutualinfo_kde
from mvpa2.testing import sweepargs
from mvpa2.testing.datasets import datasets as tdatasets
from mvpa2.testing import assert_array_almost_equal, assert_array_less, assert_equal, ok_
if __debug__:
from mvpa2.base import debug
@sweepargs(ds=iter(tdatasets.values()))
def test_BinaryFxFeatureMeasure(ds):
if not isinstance(ds.samples, np.ndarray):
return
# some simple function
f = lambda x, y: np.sum((x.T*y).T, axis=0)
fx = BinaryFxFeaturewiseMeasure(f, uni=False, numeric=True)
fx_uni = BinaryFxFeaturewiseMeasure(f, uni=True, numeric=True)
out = fx(ds)
out_uni = fx_uni(ds)
assert(len(out) == 1)
assert_array_almost_equal(out.samples, out_uni)
assert_equal(out.fa, out_uni.fa)
ok_(str(fx).startswith("<BinaryFxFeaturewiseMeasure: lambda x, y:"))
_nonlin_tests = [(dataset_wizard([0, 1-0.01, 0, 1],
# things that might behave in surprising ways
# lists -- first axis is samples, hence single feature
ds = Dataset(range(5))
assert_equal(ds.nfeatures, 1)
assert_equal(ds.shape, (5, 1))
# arrays of objects
data = np.array([{}, {}])
ds = Dataset(data)
assert_equal(ds.shape, (2, 1))
assert_equal(ds.nsamples, 2)
# Nothing to index, hence no features
assert_equal(ds.nfeatures, 1)
@sweepargs(ds=datasets.values() + [
Dataset(np.array([None], dtype=object)),
dataset_wizard(np.arange(3), targets=['a', 'bc', 'd'], chunks=np.arange(3)),
dataset_wizard(np.arange(4), targets=['a', 'bc', 'a', 'bc'], chunks=[1, 1, 2, 2]),
dataset_wizard(np.arange(4), targets=['a', 'bc', 'a', None], chunks=[1, 1, 2, 2]),
])
def test_dataset_summary(ds):
s = ds.summary()
ok_(s.startswith(str(ds)[1:-1])) # we strip surrounding '<...>'
# TODO: actual test of what was returned; to do that properly
# RF the summary() so it is a dictionary
summaries = []
if 'targets' in ds.sa:
summaries += ['Sequence statistics']
if 'chunks' in ds.sa:
# things that might behave in surprising ways
# lists -- first axis is samples, hence single feature
ds = Dataset(range(5))
assert_equal(ds.nfeatures, 1)
assert_equal(ds.shape, (5, 1))
# arrays of objects
data = np.array([{}, {}])
ds = Dataset(data)
assert_equal(ds.shape, (2, 1))
assert_equal(ds.nsamples, 2)
# Nothing to index, hence no features
assert_equal(ds.nfeatures, 1)
@sweepargs(ds=datasets.values() + [
Dataset(np.array([None], dtype=object)),
dataset_wizard(np.arange(3), targets=['a', 'bc', 'd'], chunks=np.arange(3)),
dataset_wizard(np.arange(4), targets=['a', 'bc', 'a', 'bc'], chunks=[1, 1, 2, 2]),
dataset_wizard(np.arange(4), targets=['a', 'bc', 'a', None], chunks=[1, 1, 2, 2]),
])
def test_dataset_summary(ds):
s = ds.summary()
ok_(s.startswith(str(ds)[1:-1])) # we strip surrounding '<...>'
# TODO: actual test of what was returned; to do that properly
# RF the summary() so it is a dictionary
summaries = []
if 'targets' in ds.sa:
summaries += ['Sequence statistics']
if 'chunks' in ds.sa:
# things that might behave in surprising ways
# lists -- first axis is samples, hence single feature
ds = Dataset(list(range(5)))
assert_equal(ds.nfeatures, 1)
assert_equal(ds.shape, (5, 1))
# arrays of objects
data = np.array([{}, {}])
ds = Dataset(data)
assert_equal(ds.shape, (2, 1))
assert_equal(ds.nsamples, 2)
# Nothing to index, hence no features
assert_equal(ds.nfeatures, 1)
@sweepargs(ds=list(datasets.values()) + [
Dataset(np.array([None], dtype=object)),
dataset_wizard(np.arange(3), targets=['a', 'bc', 'd'], chunks=np.arange(3)),
dataset_wizard(np.arange(4), targets=['a', 'bc', 'a', 'bc'], chunks=[1, 1, 2, 2]),
dataset_wizard(np.arange(4), targets=['a', 'bc', 'a', None], chunks=[1, 1, 2, 2]),
])
def test_dataset_summary(ds):
s = ds.summary()
ok_(s.startswith(str(ds)[1:-1])) # we strip surrounding '<...>'
# TODO: actual test of what was returned; to do that properly
# RF the summary() so it is a dictionary
summaries = []
if 'targets' in ds.sa:
summaries += ['Sequence statistics']
if 'chunks' in ds.sa: