def test_correct_dimensions_order(self, clf):
"""To check if known/present Classifiers are working properly
with samples being first dimension. Started to worry about
possible problems while looking at sg where samples are 2nd
dimension
"""
# specially crafted dataset -- if dimensions are flipped over
# the same storage, problem becomes unseparable. Like in this case
# incorrect order of dimensions lead to equal samples [0, 1, 0]
traindatas = [
dataset_wizard(samples=np.array([[0, 0, 1.0], [1, 0, 0]]),
targets=[0, 1]),
dataset_wizard(samples=np.array([[0, 0.0], [1, 1]]),
targets=[0, 1])
]
clf.ca.change_temporarily(enable_ca=['training_stats'])
for traindata in traindatas:
clf.train(traindata)
self.assertEqual(
clf.ca.training_stats.percent_correct, 100.0,
"Classifier %s must have 100%% correct learning on %s. Has %f"
% ( ` clf `, traindata.samples,
clf.ca.training_stats.percent_correct))
# and we must be able to predict every original sample thus
for i in xrange(traindata.nsamples):
sample = traindata.samples[i, :]
predicted = clf.predict([sample])
self.assertEqual(
[predicted], traindata.targets[i],
"We must be able to predict sample %s using " % sample +
"classifier %s" % ` clf `)
clf.ca.reset_changed_temporarily()
def test_correct_dimensions_order(self, clf):
"""To check if known/present Classifiers are working properly
with samples being first dimension. Started to worry about
possible problems while looking at sg where samples are 2nd
dimension
"""
# specially crafted dataset -- if dimensions are flipped over
# the same storage, problem becomes unseparable. Like in this case
# incorrect order of dimensions lead to equal samples [0, 1, 0]
traindatas = [
dataset_wizard(samples=np.array([ [0, 0, 1.0],
[1, 0, 0] ]), targets=[0, 1]),
dataset_wizard(samples=np.array([ [0, 0.0],
[1, 1] ]), targets=[0, 1])]
clf.ca.change_temporarily(enable_ca = ['training_stats'])
for traindata in traindatas:
clf.train(traindata)
self.assertEqual(clf.ca.training_stats.percent_correct, 100.0,
"Classifier %s must have 100%% correct learning on %s. Has %f" %
(`clf`, traindata.samples, clf.ca.training_stats.percent_correct))
# and we must be able to predict every original sample thus
for i in xrange(traindata.nsamples):
sample = traindata.samples[i,:]
predicted = clf.predict([sample])
self.assertEqual([predicted], traindata.targets[i],
"We must be able to predict sample %s using " % sample +
"classifier %s" % `clf`)
clf.ca.reset_changed_temporarily()
def test_feature_selection_classifier(self):
from mvpa2.featsel.base import \
SensitivityBasedFeatureSelection
from mvpa2.featsel.helpers import \
FixedNElementTailSelector
# should give lowest weight to the feature with lowest index
sens_ana = SillySensitivityAnalyzer()
# should give lowest weight to the feature with highest index
sens_ana_rev = SillySensitivityAnalyzer(mult=-1)
# corresponding feature selections
feat_sel = SensitivityBasedFeatureSelection(
sens_ana, FixedNElementTailSelector(1, mode='discard'))
feat_sel_rev = SensitivityBasedFeatureSelection(
sens_ana_rev, FixedNElementTailSelector(1))
samples = np.array([[0, 0, -1], [1, 0, 1], [-1, -1, 1], [-1, 0, 1],
[1, -1, 1]])
testdata3 = dataset_wizard(samples=samples, targets=1)
# dummy train data so proper mapper gets created
traindata = dataset_wizard(samples=np.array([[0, 0, -1], [1, 0, 1]]),
targets=[1, 2])
# targets
res110 = [1, 1, 1, -1, -1]
res011 = [-1, 1, -1, 1, -1]
# first classifier -- 0th feature should be discarded
clf011 = FeatureSelectionClassifier(self.clf_sign,
feat_sel,
enable_ca=['feature_ids'])
self.clf_sign.ca.change_temporarily(enable_ca=['estimates'])
clf011.train(traindata)
self.assertEqual(clf011.predict(testdata3.samples), res011)
# just silly test if we get values assigned in the 'ProxyClassifier'
self.assertTrue(len(clf011.ca.estimates) == len(res110),
msg="We need to pass values into ProxyClassifier")
self.clf_sign.ca.reset_changed_temporarily()
self.assertEqual(clf011.mapper._oshape, (2, ))
"Feature selection classifier had to be trained on 2 features"
# first classifier -- last feature should be discarded
clf011 = FeatureSelectionClassifier(self.clf_sign, feat_sel_rev)
clf011.train(traindata)
self.assertEqual(clf011.predict(testdata3.samples), res110)
def test_feature_selection_classifier(self):
from mvpa2.featsel.base import \
SensitivityBasedFeatureSelection
from mvpa2.featsel.helpers import \
FixedNElementTailSelector
# should give lowest weight to the feature with lowest index
sens_ana = SillySensitivityAnalyzer()
# should give lowest weight to the feature with highest index
sens_ana_rev = SillySensitivityAnalyzer(mult=-1)
# corresponding feature selections
feat_sel = SensitivityBasedFeatureSelection(sens_ana,
FixedNElementTailSelector(1, mode='discard'))
feat_sel_rev = SensitivityBasedFeatureSelection(sens_ana_rev,
FixedNElementTailSelector(1))
samples = np.array([ [0, 0, -1], [1, 0, 1], [-1, -1, 1],
[-1, 0, 1], [1, -1, 1] ])
testdata3 = dataset_wizard(samples=samples, targets=1)
# dummy train data so proper mapper gets created
traindata = dataset_wizard(samples=np.array([ [0, 0, -1], [1, 0, 1] ]),
targets=[1, 2])
# targets
res110 = [1, 1, 1, -1, -1]
res011 = [-1, 1, -1, 1, -1]
# first classifier -- 0th feature should be discarded
clf011 = FeatureSelectionClassifier(self.clf_sign, feat_sel,
enable_ca=['feature_ids'])
self.clf_sign.ca.change_temporarily(enable_ca=['estimates'])
clf011.train(traindata)
self.assertEqual(clf011.predict(testdata3.samples), res011)
# just silly test if we get values assigned in the 'ProxyClassifier'
self.assertTrue(len(clf011.ca.estimates) == len(res110),
msg="We need to pass values into ProxyClassifier")
self.clf_sign.ca.reset_changed_temporarily()
self.assertEqual(clf011.mapper._oshape, (2,))
"Feature selection classifier had to be trained on 2 features"
# first classifier -- last feature should be discarded
clf011 = FeatureSelectionClassifier(self.clf_sign, feat_sel_rev)
clf011.train(traindata)
self.assertEqual(clf011.predict(testdata3.samples), res110)
def test_coarsen_chunks(self):
"""Just basic testing for now"""
chunks = [1,1,2,2,3,3,4,4]
ds = dataset_wizard(samples=np.arange(len(chunks)).reshape(
(len(chunks),1)), targets=[1]*8, chunks=chunks)
coarsen_chunks(ds, nchunks=2)
chunks1 = coarsen_chunks(chunks, nchunks=2)
self.assertTrue((chunks1 == ds.chunks).all())
self.assertTrue((chunks1 == np.asarray([0,0,0,0,1,1,1,1])).all())
ds2 = dataset_wizard(samples=np.arange(len(chunks)).reshape(
(len(chunks),1)), targets=[1]*8, chunks=list(range(len(chunks))))
coarsen_chunks(ds2, nchunks=2)
self.assertTrue((chunks1 == ds.chunks).all())
def test_coarsen_chunks(self):
"""Just basic testing for now"""
chunks = [1,1,2,2,3,3,4,4]
ds = dataset_wizard(samples=np.arange(len(chunks)).reshape(
(len(chunks),1)), targets=[1]*8, chunks=chunks)
coarsen_chunks(ds, nchunks=2)
chunks1 = coarsen_chunks(chunks, nchunks=2)
self.assertTrue((chunks1 == ds.chunks).all())
self.assertTrue((chunks1 == np.asarray([0,0,0,0,1,1,1,1])).all())
ds2 = dataset_wizard(samples=np.arange(len(chunks)).reshape(
(len(chunks),1)), targets=[1]*8, chunks=range(len(chunks)))
coarsen_chunks(ds2, nchunks=2)
self.assertTrue((chunks1 == ds.chunks).all())
def test_mergeds2():
"""Test composition of new datasets by addition of existing ones
"""
data = dataset_wizard([range(5)], targets=1, chunks=1)
assert_array_equal(data.UT, [1])
# simple sequence has to be a single pattern
assert_equal(data.nsamples, 1)
# check correct pattern layout (1x5)
assert_array_equal(data.samples, [[0, 1, 2, 3, 4]])
# check for single labels and origin
assert_array_equal(data.targets, [1])
assert_array_equal(data.chunks, [1])
# now try adding pattern with wrong shape
assert_raises(ValueError, vstack,
(data, dataset_wizard(np.ones((2, 3)), targets=1, chunks=1)))
# now add two real patterns
dss = datasets['uni2large'].samples
data = vstack((data, dataset_wizard(dss[:2, :5], targets=2, chunks=2)))
assert_equal(data.nfeatures, 5)
assert_array_equal(data.targets, [1, 2, 2])
assert_array_equal(data.chunks, [1, 2, 2])
# test automatic origins
data = vstack((data, (dataset_wizard(dss[3:5, :5],
targets=3,
chunks=[0, 1]))))
assert_array_equal(data.chunks, [1, 2, 2, 0, 1])
# test unique class labels
assert_array_equal(data.UT, [1, 2, 3])
# test wrong label length
assert_raises(ValueError,
dataset_wizard,
dss[:4, :5],
targets=[1, 2, 3],
chunks=2)
# test wrong origin length
assert_raises(ValueError,
dataset_wizard,
dss[:4, :5],
targets=[1, 2, 3, 4],
chunks=[2, 2, 2])
def test_origid_handling():
ds = dataset_wizard(np.atleast_2d(np.arange(35)).T)
ds.init_origids('both')
ok_(ds.nsamples == 35)
assert_equal(len(np.unique(ds.sa.origids)), 35)
assert_equal(len(np.unique(ds.fa.origids)), 1)
selector = [3, 7, 10, 15]
subds = ds[selector]
assert_array_equal(subds.sa.origids, ds.sa.origids[selector])
# Now if we request new origids if they are present we could
# expect different behavior
assert_raises(ValueError, subds.init_origids, 'both', mode='raises')
sa_origids = subds.sa.origids.copy()
fa_origids = subds.fa.origids.copy()
for s in ('both', 'samples', 'features'):
assert_raises(RuntimeError, subds.init_origids, s, mode='raise')
subds.init_origids(s, mode='existing')
# we should have the same origids as before
assert_array_equal(subds.sa.origids, sa_origids)
assert_array_equal(subds.fa.origids, fa_origids)
# Lets now change, which should be default behavior
subds.init_origids('both')
assert_equal(len(sa_origids), len(subds.sa.origids))
assert_equal(len(fa_origids), len(subds.fa.origids))
# values should change though
ok_((sa_origids != subds.sa.origids).any())
ok_((fa_origids != subds.fa.origids).any())
def test_idhash():
ds = dataset_wizard(np.arange(12).reshape((4, 3)),
targets=1, chunks=1)
origid = ds.idhash
#XXX BUG -- no assurance that labels would become an array... for now -- do manually
ds.targets = np.array([3, 1, 2, 3]) # change all labels
ok_(origid != ds.idhash,
msg="Changing all targets should alter dataset's idhash")
origid = ds.idhash
z = ds.targets[1]
assert_equal(origid, ds.idhash,
msg="Accessing shouldn't change idhash")
z = ds.chunks
assert_equal(origid, ds.idhash,
msg="Accessing shouldn't change idhash")
z[2] = 333
ok_(origid != ds.idhash,
msg="Changing value in attribute should change idhash")
origid = ds.idhash
ds.samples[1, 1] = 1000
ok_(origid != ds.idhash,
msg="Changing value in data should change idhash")
origid = ds.idhash
orig_labels = ds.targets #.copy()
ds.sa.targets = range(len(ds))
ok_(origid != ds.idhash,
msg="Chaging attribute also changes idhash")
ds.targets = orig_labels
ok_(origid == ds.idhash,
msg="idhash should be restored after reassigning orig targets")
def test_DissimilarityConsistencyMeasure():
targets = np.tile(xrange(3),2)
chunks = np.repeat(np.array((0,1)),3)
# correct results
cres1 = 0.41894348
cres2 = np.array([[ 0.16137995, 0.73062639, 0.59441713]])
dc1 = data[0:3,:] - np.mean(data[0:3,:],0)
dc2 = data[3:6,:] - np.mean(data[3:6,:],0)
center = squareform(np.corrcoef(pdist(dc1,'correlation'),pdist(dc2,'correlation')),
checks=False).reshape((1,-1))
dsm1 = stats.rankdata(pdist(data[0:3,:],'correlation').reshape((1,-1)))
dsm2 = stats.rankdata(pdist(data[3:6,:],'correlation').reshape((1,-1)))
spearman = squareform(np.corrcoef(np.vstack((dsm1,dsm2))),
checks=False).reshape((1,-1))
ds = dataset_wizard(samples=data, targets=targets, chunks=chunks)
dscm = DissimilarityConsistencyMeasure()
res1 = dscm(ds)
dscm_c = DissimilarityConsistencyMeasure(center_data=True)
res2 = dscm_c(ds)
dscm_sp = DissimilarityConsistencyMeasure(consistency_metric='spearman')
res3 = dscm_sp(ds)
ds.append(ds)
chunks = np.repeat(np.array((0,1,2,)),4)
ds.sa['chunks'] = chunks
res4 = dscm(ds)
assert_almost_equal(np.mean(res1.samples),cres1)
assert_array_almost_equal(res2.samples, center)
assert_array_almost_equal(res3.samples, spearman)
assert_array_almost_equal(res4.samples,cres2)
def dumb_feature_binary_dataset():
"""Very simple binary (2 labels) dataset
"""
data = [
[1, 0],
[1, 1],
[2, 0],
[2, 1],
[3, 0],
[3, 1],
[4, 0],
[4, 1],
[5, 0],
[5, 1],
[6, 0],
[6, 1],
[7, 0],
[7, 1],
[8, 0],
[8, 1],
[9, 0],
[9, 1],
[10, 0],
[10, 1],
[11, 0],
[11, 1],
[12, 0],
[12, 1],
]
regs = ([0] * 12) + ([1] * 12)
return dataset_wizard(samples=np.array(data), targets=regs, chunks=range(len(regs)))
def dumb_feature_dataset():
"""Create a very simple dataset with 2 features and 3 labels
"""
data = [
[1, 0],
[1, 1],
[2, 0],
[2, 1],
[3, 0],
[3, 1],
[4, 0],
[4, 1],
[5, 0],
[5, 1],
[6, 0],
[6, 1],
[7, 0],
[7, 1],
[8, 0],
[8, 1],
[9, 0],
[9, 1],
[10, 0],
[10, 1],
[11, 0],
[11, 1],
[12, 0],
[12, 1],
]
regs = ([1] * 8) + ([2] * 8) + ([3] * 8)
return dataset_wizard(samples=np.array(data), targets=regs, chunks=range(len(regs)))
def linear1d_gaussian_noise(size=100, slope=0.5, intercept=1.0, x_min=-2.0, x_max=3.0, sigma=0.2):
"""A straight line with some Gaussian noise.
"""
x = np.linspace(start=x_min, stop=x_max, num=size)
noise = np.random.randn(size) * sigma
y = x * slope + intercept + noise
return dataset_wizard(samples=x[:, None], targets=y)
def pure_multivariate_signal(patterns,
signal2noise=1.5,
chunks=None,
targets=[0, 1]):
""" Create a 2d dataset with a clear multivariate signal, but no
univariate information.
::
%%%%%%%%%
% O % X %
%%%%%%%%%
% X % O %
%%%%%%%%%
"""
# start with noise
data = np.random.normal(size=(4 * patterns, 2))
# add signal
data[:2 * patterns, 1] += signal2noise
data[2 * patterns:4 * patterns, 1] -= signal2noise
data[:patterns, 0] -= signal2noise
data[2 * patterns:3 * patterns, 0] -= signal2noise
data[patterns:2 * patterns, 0] += signal2noise
data[3 * patterns:4 * patterns, 0] += signal2noise
# two conditions
regs = np.array((targets[0:1] * patterns) + (targets[1:2] * 2 * patterns) +
(targets[0:1] * patterns))
if chunks is None:
chunks = range(len(data))
return dataset_wizard(samples=data, targets=regs, chunks=chunks)
def test_feature_selection_classifier_with_regression(self):
from mvpa2.featsel.base import \
SensitivityBasedFeatureSelection
from mvpa2.featsel.helpers import \
FixedNElementTailSelector
if sample_clf_reg is None:
# none regression was found, so nothing to test
return
# should give lowest weight to the feature with lowest index
sens_ana = SillySensitivityAnalyzer()
# corresponding feature selections
feat_sel = SensitivityBasedFeatureSelection(
sens_ana, FixedNElementTailSelector(1, mode='discard'))
# now test with regression-based classifier. The problem is
# that it is determining predictions twice from values and
# then setting the values from the results, which the second
# time is set to predictions. The final outcome is that the
# values are actually predictions...
dat = dataset_wizard(samples=np.random.randn(4, 10),
targets=[-1, -1, 1, 1])
clf_reg = FeatureSelectionClassifier(sample_clf_reg, feat_sel)
clf_reg.train(dat)
_ = clf_reg.predict(dat.samples)
self.failIf(
(np.array(clf_reg.ca.estimates) -
clf_reg.ca.predictions).sum() == 0,
msg="Values were set to the predictions in %s." % sample_clf_reg)
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_PDist():
targets = np.tile(xrange(3), 2)
chunks = np.repeat(np.array((0, 1)), 3)
ds = dataset_wizard(samples=data, targets=targets, chunks=chunks)
data_c = data - np.mean(data, 0)
# DSM matrix elements should come out as samples of one feature
# to be in line with what e.g. a classifier returns -- facilitates
# collection in a searchlight ...
euc = pdist(data, 'euclidean')[None].T
pear = pdist(data, 'correlation')[None].T
city = pdist(data, 'cityblock')[None].T
center_sq = squareform(pdist(data_c, 'correlation'))
# Now center each chunk separately
dsm1 = PDist()
dsm2 = PDist(pairwise_metric='euclidean')
dsm3 = PDist(pairwise_metric='cityblock')
dsm4 = PDist(center_data=True, square=True)
assert_array_almost_equal(dsm1(ds).samples, pear)
assert_array_almost_equal(dsm2(ds).samples, euc)
dsm_res = dsm3(ds)
assert_array_almost_equal(dsm_res.samples, city)
# length correspondings to a single triangular matrix
assert_equal(len(dsm_res.sa.pairs), len(ds) * (len(ds) - 1) / 2)
# generate label pairs actually reflect the vectorform generated by
# squareform()
dsm_res_square = squareform(dsm_res.samples.T[0])
for i, p in enumerate(dsm_res.sa.pairs):
assert_equal(dsm_res_square[p[0], p[1]], dsm_res.samples[i, 0])
dsm_res = dsm4(ds)
assert_array_almost_equal(dsm_res.samples, center_sq)
# sample attributes are carried over
assert_almost_equal(ds.sa.targets, dsm_res.sa.targets)
def test_PDist():
targets = np.tile(xrange(3),2)
chunks = np.repeat(np.array((0,1)),3)
ds = dataset_wizard(samples=data, targets=targets, chunks=chunks)
data_c = data - np.mean(data,0)
# DSM matrix elements should come out as samples of one feature
# to be in line with what e.g. a classifier returns -- facilitates
# collection in a searchlight ...
euc = pdist(data, 'euclidean')[None].T
pear = pdist(data, 'correlation')[None].T
city = pdist(data, 'cityblock')[None].T
center_sq = squareform(pdist(data_c,'correlation'))
# Now center each chunk separately
dsm1 = PDist()
dsm2 = PDist(pairwise_metric='euclidean')
dsm3 = PDist(pairwise_metric='cityblock')
dsm4 = PDist(center_data=True,square=True)
assert_array_almost_equal(dsm1(ds).samples,pear)
assert_array_almost_equal(dsm2(ds).samples,euc)
dsm_res = dsm3(ds)
assert_array_almost_equal(dsm_res.samples,city)
# length correspondings to a single triangular matrix
assert_equal(len(dsm_res.sa.pairs), len(ds) * (len(ds) - 1) / 2)
# generate label pairs actually reflect the vectorform generated by
# squareform()
dsm_res_square = squareform(dsm_res.samples.T[0])
for i, p in enumerate(dsm_res.sa.pairs):
assert_equal(dsm_res_square[p[0], p[1]], dsm_res.samples[i, 0])
dsm_res = dsm4(ds)
assert_array_almost_equal(dsm_res.samples,center_sq)
# sample attributes are carried over
assert_almost_equal(ds.sa.targets, dsm_res.sa.targets)
def pure_multivariate_signal(patterns, signal2noise = 1.5, chunks=None, targets=[0, 1]):
""" Create a 2d dataset with a clear multivariate signal, but no
univariate information.
::
%%%%%%%%%
% O % X %
%%%%%%%%%
% X % O %
%%%%%%%%%
"""
# start with noise
data = np.random.normal(size=(4*patterns, 2))
# add signal
data[:2*patterns, 1] += signal2noise
data[2*patterns:4*patterns, 1] -= signal2noise
data[:patterns, 0] -= signal2noise
data[2*patterns:3*patterns, 0] -= signal2noise
data[patterns:2*patterns, 0] += signal2noise
data[3*patterns:4*patterns, 0] += signal2noise
# two conditions
regs = np.array((targets[0:1] * patterns) + (targets[1:2] * 2 * patterns) + (targets[0:1] * patterns))
if chunks is None:
chunks = range(len(data))
return dataset_wizard(samples=data, targets=regs, chunks=chunks)
def test_feature_selection_classifier_with_regression(self):
from mvpa2.featsel.base import \
SensitivityBasedFeatureSelection
from mvpa2.featsel.helpers import \
FixedNElementTailSelector
if sample_clf_reg is None:
# none regression was found, so nothing to test
return
# should give lowest weight to the feature with lowest index
sens_ana = SillySensitivityAnalyzer()
# corresponding feature selections
feat_sel = SensitivityBasedFeatureSelection(sens_ana,
FixedNElementTailSelector(1, mode='discard'))
# now test with regression-based classifier. The problem is
# that it is determining predictions twice from values and
# then setting the values from the results, which the second
# time is set to predictions. The final outcome is that the
# values are actually predictions...
dat = dataset_wizard(samples=np.random.randn(4, 10),
targets=[-1, -1, 1, 1])
clf_reg = FeatureSelectionClassifier(sample_clf_reg, feat_sel)
clf_reg.train(dat)
_ = clf_reg.predict(dat.samples)
self.failIf((np.array(clf_reg.ca.estimates)
- clf_reg.ca.predictions).sum()==0,
msg="Values were set to the predictions in %s." %
sample_clf_reg)
def load_fcmri_dataset(data, subjects, conditions, group, level, n_run=3):
attributes = []
samples = []
for ic, c in enumerate(conditions):
for isb, s in enumerate(subjects):
for i in range(n_run):
matrix = data[ic, isb, i, :]
fmatrix = flatten_matrix(matrix)
samples.append(fmatrix)
attributes.append([c, s, i, group[isb], level[isb]])
attributes = np.array(attributes)
ds = dataset_wizard(np.array(samples),
targets=attributes.T[0],
chunks=attributes.T[1])
ds.sa['run'] = attributes.T[2]
ds.sa['group'] = attributes.T[3]
ds.sa['level'] = np.int_(attributes.T[4])
ds.sa['meditation'] = attributes.T[0]
return ds
def test_origid_handling():
ds = dataset_wizard(np.atleast_2d(np.arange(35)).T)
ds.init_origids('both')
ok_(ds.nsamples == 35)
assert_equal(len(np.unique(ds.sa.origids)), 35)
assert_equal(len(np.unique(ds.fa.origids)), 1)
selector = [3, 7, 10, 15]
subds = ds[selector]
assert_array_equal(subds.sa.origids, ds.sa.origids[selector])
# Now if we request new origids if they are present we could
# expect different behavior
assert_raises(ValueError, subds.init_origids, 'both', mode='raises')
sa_origids = subds.sa.origids.copy()
fa_origids = subds.fa.origids.copy()
for s in ('both', 'samples', 'features'):
assert_raises(RuntimeError, subds.init_origids, s, mode='raise')
subds.init_origids(s, mode='existing')
# we should have the same origids as before
assert_array_equal(subds.sa.origids, sa_origids)
assert_array_equal(subds.fa.origids, fa_origids)
# Lets now change, which should be default behavior
subds.init_origids('both')
assert_equal(len(sa_origids), len(subds.sa.origids))
assert_equal(len(fa_origids), len(subds.fa.origids))
# values should change though
ok_((sa_origids != subds.sa.origids).any())
ok_((fa_origids != subds.fa.origids).any())
def test_idhash():
ds = dataset_wizard(np.arange(12).reshape((4, 3)), targets=1, chunks=1)
origid = ds.idhash
#XXX BUG -- no assurance that labels would become an array... for now -- do manually
ds.targets = np.array([3, 1, 2, 3]) # change all labels
ok_(origid != ds.idhash,
msg="Changing all targets should alter dataset's idhash")
origid = ds.idhash
z = ds.targets[1]
assert_equal(origid, ds.idhash, msg="Accessing shouldn't change idhash")
z = ds.chunks
assert_equal(origid, ds.idhash, msg="Accessing shouldn't change idhash")
z[2] = 333
ok_(origid != ds.idhash,
msg="Changing value in attribute should change idhash")
origid = ds.idhash
ds.samples[1, 1] = 1000
ok_(origid != ds.idhash, msg="Changing value in data should change idhash")
origid = ds.idhash
orig_labels = ds.targets #.copy()
ds.sa.targets = range(len(ds))
ok_(origid != ds.idhash, msg="Chaging attribute also changes idhash")
ds.targets = orig_labels
ok_(origid == ds.idhash,
msg="idhash should be restored after reassigning orig targets")
def _test_mcasey20120222(): # pragma: no cover
# http://lists.alioth.debian.org/pipermail/pkg-exppsy-pymvpa/2012q1/002034.html
# This one is conditioned on allowing # of samples to be changed
# by the mapper provided to MappedClassifier. See
# https://github.com/yarikoptic/PyMVPA/tree/_tent/allow_ch_nsamples
import numpy as np
from mvpa2.datasets.base import dataset_wizard
from mvpa2.generators.partition import NFoldPartitioner
from mvpa2.mappers.base import ChainMapper
from mvpa2.mappers.svd import SVDMapper
from mvpa2.mappers.fx import mean_group_sample
from mvpa2.clfs.svm import LinearCSVMC
from mvpa2.clfs.meta import MappedClassifier
from mvpa2.measures.base import CrossValidation
mapper = ChainMapper([mean_group_sample(['targets','chunks']),
SVDMapper()])
clf = MappedClassifier(LinearCSVMC(), mapper)
cvte = CrossValidation(clf, NFoldPartitioner(),
enable_ca=['repetition_results', 'stats'])
ds = dataset_wizard(
samples=np.arange(32).reshape((8, -1)),
targets=[1, 1, 2, 2, 1, 1, 2, 2],
chunks=[1, 1, 1, 1, 2, 2, 2, 2])
errors = cvte(ds)
def test_aggregation(self):
data = dataset_wizard(np.arange( 20 ).reshape((4, 5)), targets=1, chunks=1)
ag_data = aggregate_features(data, np.mean)
ok_(ag_data.nsamples == 4)
ok_(ag_data.nfeatures == 1)
assert_array_equal(ag_data.samples[:, 0], [2, 7, 12, 17])
def test_str():
args = (np.arange(12, dtype=np.int8).reshape(
(4, 3)), range(4), [1, 1, 2, 2])
for iargs in range(1, len(args)):
ds = dataset_wizard(*(args[:iargs]))
ds_s = str(ds)
ok_(ds_s.startswith('<Dataset: 4x3@int8'))
ok_(ds_s.endswith('>'))
def test_aggregation(self):
data = dataset_wizard(np.arange( 20 ).reshape((4, 5)), targets=1, chunks=1)
ag_data = aggregate_features(data, np.mean)
ok_(ag_data.nsamples == 4)
ok_(ag_data.nfeatures == 1)
assert_array_equal(ag_data.samples[:, 0], [2, 7, 12, 17])
def linear1d_gaussian_noise(size=100, slope=0.5, intercept=1.0,
x_min=-2.0, x_max=3.0, sigma=0.2):
"""A straight line with some Gaussian noise.
"""
x = np.linspace(start=x_min, stop=x_max, num=size)
noise = np.random.randn(size)*sigma
y = x * slope + intercept + noise
return dataset_wizard(samples=x[:, None], targets=y)
def setUp(self):
self.clf_sign = SameSignClassifier()
self.clf_less1 = Less1Classifier()
# simple binary dataset
self.data_bin_1 = dataset_wizard(
samples=[[0, 0], [-10, -1], [1, 0.1], [1, -1], [-1, 1]],
targets=[1, 1, 1, -1, -1], # labels
chunks=[0, 1, 2, 2, 3]) # chunks
def test_str():
args = ( np.arange(12, dtype=np.int8).reshape((4, 3)),
range(4),
[1, 1, 2, 2])
for iargs in range(1, len(args)):
ds = dataset_wizard(*(args[:iargs]))
ds_s = str(ds)
ok_(ds_s.startswith('<Dataset: 4x3@int8'))
ok_(ds_s.endswith('>'))
def setUp(self):
self.clf_sign = SameSignClassifier()
self.clf_less1 = Less1Classifier()
# simple binary dataset
self.data_bin_1 = dataset_wizard(
samples=[[0,0],[-10,-1],[1,0.1],[1,-1],[-1,1]],
targets=[1, 1, 1, -1, -1], # labels
chunks=[0, 1, 2, 2, 3]) # chunks
def test_nfold_random_counted_selection_partitioner_huge(self):
# Just test that it completes in a reasonable time and does
# not blow up as if would do if it was not limited by count
kwargs = dict(count=10)
ds = dataset_wizard(np.arange(1000).reshape((-1, 1)), targets=range(1000), chunks=range(500) * 2)
split_partitions_random = [
tuple(x.sa.partitions) for x in NFoldPartitioner(100, selection_strategy="random", **kwargs).generate(ds)
]
assert_equal(len(split_partitions_random), 10) # we get just 10
def test_nonfinite_features_removal(self):
r = np.random.normal(size=(4, 5))
ds = dataset_wizard(r, targets=1, chunks=1)
ds.samples[2,0]=np.NaN
ds.samples[3,3]=np.Inf
dsc = remove_nonfinite_features(ds)
self.assertTrue(dsc.nfeatures == 3)
assert_array_equal(ds[:, [1, 2, 4]].samples, dsc.samples)
def dumb_feature_binary_dataset():
"""Very simple binary (2 labels) dataset
"""
data = [[1, 0], [1, 1], [2, 0], [2, 1], [3, 0], [3, 1], [4, 0], [4, 1],
[5, 0], [5, 1], [6, 0], [6, 1], [7, 0], [7, 1], [8, 0], [8, 1],
[9, 0], [9, 1], [10, 0], [10, 1], [11, 0], [11, 1], [12, 0],
[12, 1]]
regs = ([0] * 12) + ([1] * 12)
return dataset_wizard(samples=np.array(data), targets=regs, chunks=range(len(regs)))
def test_invar_features_removal(self):
r = np.random.normal(size=(3, 1))
ds = dataset_wizard(samples=np.hstack((np.zeros((3, 2)), r)), targets=1)
self.failUnless(ds.nfeatures == 3)
dsc = remove_invariant_features(ds)
self.failUnless(dsc.nfeatures == 1)
self.failUnless((dsc.samples == r).all())
def test_nonfinite_features_removal(self):
r = np.random.normal(size=(4, 5))
ds = dataset_wizard(r, targets=1, chunks=1)
ds.samples[2,0]=np.NaN
ds.samples[3,3]=np.Inf
dsc = remove_nonfinite_features(ds)
self.assertTrue(dsc.nfeatures == 3)
assert_array_equal(ds[:, [1, 2, 4]].samples, dsc.samples)
def dumb_feature_dataset():
"""Create a very simple dataset with 2 features and 3 labels
"""
data = [[1, 0], [1, 1], [2, 0], [2, 1], [3, 0], [3, 1], [4, 0], [4, 1],
[5, 0], [5, 1], [6, 0], [6, 1], [7, 0], [7, 1], [8, 0], [8, 1],
[9, 0], [9, 1], [10, 0], [10, 1], [11, 0], [11, 1], [12, 0],
[12, 1]]
regs = ([1] * 8) + ([2] * 8) + ([3] * 8)
return dataset_wizard(samples=np.array(data), targets=regs, chunks=range(len(regs)))
def get_dataset(self):
zresults = self.results
new_shape = list(zresults.shape[-2:])
new_shape.insert(0, -1)
zreshaped = zresults.reshape(new_shape)
upper_mask = np.ones_like(zreshaped[0])
upper_mask[np.tril_indices(zreshaped[0].shape[0])] = 0
upper_mask = np.bool_(upper_mask)
# Reshape data to have samples x features
ds_data = zreshaped[:, upper_mask]
labels = []
n_runs = zresults.shape[2]
n_subj = zresults.shape[1]
for l in self.conditions.keys():
labels += [l for _ in range(n_runs * n_subj)]
ds_labels = np.array(labels)
ds_subjects = []
for s in self.subjects:
ds_subjects += [s for _ in range(n_runs)]
ds_subjects = np.array(ds_subjects)
ds_info = []
for _ in self.conditions.keys():
ds_info.append(ds_subjects)
ds_info = np.vstack(ds_info)
logger.debug(ds_info)
logger.debug(ds_info.shape)
logger.debug(ds_data.shape)
self.ds = dataset_wizard(ds_data,
targets=ds_labels,
chunks=np.int_(ds_info.T[5]))
self.ds.sa['subjects'] = ds_info.T[0]
self.ds.sa['groups'] = ds_info.T[1]
self.ds.sa['chunks_1'] = ds_info.T[2]
self.ds.sa['expertise'] = ds_info.T[3]
self.ds.sa['age'] = ds_info.T[4]
self.ds.sa['chunks_2'] = ds_info.T[5]
self.ds.sa['meditation'] = ds_labels
logger.debug(ds_info.T[4])
logger.debug(self.ds.sa.keys())
return self.ds
def test_mergeds2():
"""Test composition of new datasets by addition of existing ones
"""
data = dataset_wizard([range(5)], targets=1, chunks=1)
assert_array_equal(data.UT, [1])
# simple sequence has to be a single pattern
assert_equal(data.nsamples, 1)
# check correct pattern layout (1x5)
assert_array_equal(data.samples, [[0, 1, 2, 3, 4]])
# check for single labels and origin
assert_array_equal(data.targets, [1])
assert_array_equal(data.chunks, [1])
# now try adding pattern with wrong shape
assert_raises(DatasetError,
data.append,
dataset_wizard(np.ones((2,3)), targets=1, chunks=1))
# now add two real patterns
dss = datasets['uni2large'].samples
data.append(dataset_wizard(dss[:2, :5], targets=2, chunks=2))
assert_equal(data.nfeatures, 5)
assert_array_equal(data.targets, [1, 2, 2])
assert_array_equal(data.chunks, [1, 2, 2])
# test automatic origins
data.append(dataset_wizard(dss[3:5, :5], targets=3, chunks=[0, 1]))
assert_array_equal(data.chunks, [1, 2, 2, 0, 1])
# test unique class labels
assert_array_equal(data.UT, [1, 2, 3])
# test wrong label length
assert_raises(ValueError, dataset_wizard, dss[:4, :5], targets=[ 1, 2, 3 ],
chunks=2)
# test wrong origin length
assert_raises(ValueError, dataset_wizard, dss[:4, :5],
targets=[ 1, 2, 3, 4 ], chunks=[ 2, 2, 2 ])
def test_invar_features_removal(self):
r = np.random.normal(size=(3,1))
ds = dataset_wizard(samples=np.hstack((np.zeros((3,2)), r)),
targets=1)
self.assertTrue(ds.nfeatures == 3)
dsc = remove_invariant_features(ds)
self.assertTrue(dsc.nfeatures == 1)
self.assertTrue((dsc.samples == r).all())
def test_nfold_random_counted_selection_partitioner_huge(self):
# Just test that it completes in a reasonable time and does
# not blow up as if would do if it was not limited by count
kwargs = dict(count=10)
ds = dataset_wizard(np.arange(1000).reshape((-1, 1)),
targets=range(1000),
chunks=range(500) * 2)
split_partitions_random = [
tuple(x.sa.partitions) for x in NFoldPartitioner(
100, selection_strategy='random', **kwargs).generate(ds)
]
assert_equal(len(split_partitions_random), 10) # we get just 10
def get_dataset(self):
zresults = self.results
new_shape = list(zresults.shape[-2:])
new_shape.insert(0, -1)
zreshaped = zresults.reshape(new_shape)
upper_mask = np.ones_like(zreshaped[0])
upper_mask[np.tril_indices(zreshaped[0].shape[0])] = 0
upper_mask = np.bool_(upper_mask)
# Reshape data to have samples x features
ds_data = zreshaped[:,upper_mask]
labels = []
n_runs = zresults.shape[2]
n_subj = zresults.shape[1]
for l in self.conditions.keys():
labels += [l for _ in range(n_runs * n_subj)]
ds_labels = np.array(labels)
ds_subjects = []
for s in self.subjects:
ds_subjects += [s for _ in range(n_runs)]
ds_subjects = np.array(ds_subjects)
ds_info = []
for _ in self.conditions.keys():
ds_info.append(ds_subjects)
ds_info = np.vstack(ds_info)
logger.debug(ds_info)
logger.debug(ds_info.shape)
logger.debug(ds_data.shape)
self.ds = dataset_wizard(ds_data, targets=ds_labels, chunks=np.int_(ds_info.T[5]))
self.ds.sa['subjects'] = ds_info.T[0]
self.ds.sa['groups'] = ds_info.T[1]
self.ds.sa['chunks_1'] = ds_info.T[2]
self.ds.sa['expertise'] = ds_info.T[3]
self.ds.sa['age'] = ds_info.T[4]
self.ds.sa['chunks_2'] = ds_info.T[5]
self.ds.sa['meditation'] = ds_labels
logger.debug(ds_info.T[4])
logger.debug(self.ds.sa.keys())
return self.ds
def load_connectivity_ds(path, subjects, extra_sa_file=None):
"""
Loads txt connectivity matrices in the form of n_roi x n_roi matrix
Parameters
----------
path : string
Pathname of the data folder
subjects : list
List of subjects included in the analysis
it is always a directory in the path
extra_sa : dictionary
Dictionary of extra fields to be included.
The dictionary must be in the form of
'field': list of extra fields
dictionary must include the field 'subject'
Returns
-------
ds : pympva dataset
The loaded dataset
"""
data, attributes = load_txt_matrices(path, subjects)
n_roi = data.shape[1]
indices = np.triu_indices(n_roi, k=1)
n_samples = data.shape[0]
n_features = len(indices[0])
samples = np.zeros((n_samples, n_features))
for i in range(n_samples):
samples[i] = data[i][indices]
mask = np.isnan(samples).sum(0)
ds = dataset_wizard(samples)
for key, value in attributes.iteritems():
ds.sa[key] = value
ds.fa['nan_mask'] = np.bool_(mask)
if extra_sa_file != None:
_, fextra_sa = load_subject_file(extra_sa_file)
ds = add_subject_attributes(ds, fextra_sa)
return ds
def test_reflection(self, rep=10):
for i in range(rep):
from mvpa2.testing.datasets import get_random_rotation
d = np.random.random((100, 2))
T = get_random_rotation(d.shape[1])
d2 = np.dot(d, T)
# scale it up a bit
d2 *= 1.2
# add a reflection by flipping the first dimension
d2[:, 0] *= -1
ds = dataset_wizard(samples=d, targets=d2)
norm0 = np.linalg.norm(d - d2)
mapper = ProcrusteanMapper(scaling=False, reflection=False)
mapper.train(ds)
norm1 = np.linalg.norm(d2 - mapper.forward(ds).samples)
eps = 1e-7
self.assertLess(norm1,
norm0 + eps,
msg='Procrustes should reduce difference, '
'but %f > %f' % (norm1, norm0))
mapper = ProcrusteanMapper(scaling=True, reflection=False)
mapper.train(ds)
norm2 = np.linalg.norm(d2 - mapper.forward(ds).samples)
self.assertLess(norm2,
norm1 + eps,
msg='Procrustes with scaling should work better, '
'but %f > %f' % (norm2, norm1))
mapper = ProcrusteanMapper(scaling=False, reflection=True)
mapper.train(ds)
norm3 = np.linalg.norm(d2 - mapper.forward(ds).samples)
self.assertLess(
norm3,
norm1 + eps,
msg='Procrustes with reflection should work better, '
'but %f > %f' % (norm3, norm1))
mapper = ProcrusteanMapper(scaling=True, reflection=True)
mapper.train(ds)
norm4 = np.linalg.norm(d2 - mapper.forward(ds).samples)
self.assertLess(norm4,
norm3 + eps,
msg='Procrustes with scaling should work better, '
'but %f > %f' % (norm4, norm3))
self.assertLess(
norm4,
norm2 + eps,
msg='Procrustes with reflection should work better, '
'but %f > %f' % (norm4, norm2))
def test_surface_dset_h5py_io_with_unicode(self, fn):
skip_if_no_external('h5py')
from mvpa2.base.hdf5 import h5save, h5load
ds = dataset_wizard(np.arange(20).reshape((4, 5)), targets=1, chunks=1)
ds.sa['unicode'] = ['u1', 'uu2', 'uuu3', 'uuuu4']
ds.sa['str'] = ['s1', 'ss2', 'sss3', 'ssss4']
ds.fa['node_indices'] = np.arange(5)
# test h5py I/O
h5save(fn, ds)
ds2 = h5load(fn)
assert_datasets_equal(ds, ds2)
def test_surface_dset_h5py_io_with_unicode(self, fn):
skip_if_no_external('h5py')
from mvpa2.base.hdf5 import h5save, h5load
ds = dataset_wizard(np.arange(20).reshape((4, 5)), targets=1, chunks=1)
ds.sa['unicode'] = [u'u1', u'uu2', u'uuu3', u'uuuu4']
ds.sa['str'] = ['s1', 'ss2', 'sss3', 'ssss4']
ds.fa['node_indices'] = np.arange(5)
# test h5py I/O
h5save(fn, ds)
ds2 = h5load(fn)
assert_datasets_equal(ds, ds2)
def sin_modulated(n_instances, n_features, flat=False, noise=0.4):
""" Generate a (quite) complex multidimensional non-linear dataset
Used for regression testing. In the data label is a sin of a x^2 +
uniform noise
"""
if flat:
data = np.arange(0.0, 1.0, 1.0 / n_instances) * np.pi
data.resize(n_instances, n_features)
else:
data = np.random.rand(n_instances, n_features) * np.pi
label = np.sin((data ** 2).sum(1)).round()
label += np.random.rand(label.size) * noise
return dataset_wizard(samples=data, targets=label)
def sin_modulated(n_instances, n_features, flat=False, noise=0.4):
""" Generate a (quite) complex multidimensional non-linear dataset
Used for regression testing. In the data label is a sin of a x^2 +
uniform noise
"""
if flat:
data = (np.arange(0.0, 1.0, 1.0 / n_instances) * np.pi)
data.resize(n_instances, n_features)
else:
data = np.random.rand(n_instances, n_features) * np.pi
label = np.sin((data**2).sum(1)).round()
label += np.random.rand(label.size) * noise
return dataset_wizard(samples=data, targets=label)
def load_connectivity_ds(path, subjects, extra_sa_file=None):
"""
Loads txt connectivity matrices in the form of n_roi x n_roi matrix
Parameters
----------
path : string
Pathname of the data folder
subjects : list
List of subjects included in the analysis
it is always a directory in the path
extra_sa : dictionary
Dictionary of extra fields to be included.
The dictionary must be in the form of
'field': list of extra fields
dictionary must include the field 'subject'
Returns
-------
ds : pympva dataset
The loaded dataset
"""
data, attributes = load_txt_matrices(path, subjects)
n_roi = data.shape[1]
indices = np.triu_indices(n_roi, k=1)
n_samples = data.shape[0]
n_features = len(indices[0])
samples = np.zeros((n_samples, n_features))
for i in range(n_samples):
samples[i] = data[i][indices]
mask = np.isnan(samples).sum(0)
ds = dataset_wizard(samples)
for key, value in attributes.iteritems():
ds.sa[key] = value
ds.fa['nan_mask'] = np.bool_(mask)
if extra_sa_file != None:
_, fextra_sa = load_subject_file(extra_sa_file)
ds = add_subject_attributes(ds, fextra_sa)
return ds
def pure_multivariate_signal(patterns,
signal2noise=1.5,
chunks=None,
targets=None):
""" Create a 2d dataset with a clear purely multivariate signal.
This is known is the XOR problem.
::
%%%%%%%%%
% O % X %
%%%%%%%%%
% X % O %
%%%%%%%%%
Parameters
----------
patterns: int
Number of data points in each of the four dot clouds
signal2noise: float, optional
Univariate signal pedestal.
chunks: array, optional
Vector for chunk labels for all generated samples.
targets: list, optional
Length-2 sequence of target values for both classes. If None,
[0, 1] is used.
"""
if targets is None:
targets = [0, 1]
# start with noise
data = np.random.normal(size=(4 * patterns, 2))
# add signal
data[:2 * patterns, 1] += signal2noise
data[2 * patterns:4 * patterns, 1] -= signal2noise
data[:patterns, 0] -= signal2noise
data[2 * patterns:3 * patterns, 0] -= signal2noise
data[patterns:2 * patterns, 0] += signal2noise
data[3 * patterns:4 * patterns, 0] += signal2noise
# two conditions
regs = np.array((targets[0:1] * patterns) + (targets[1:2] * 2 * patterns) +
(targets[0:1] * patterns))
if chunks is None:
chunks = range(len(data))
return dataset_wizard(samples=data, targets=regs, chunks=chunks)
def test_combined_samplesfeature_selection():
data = dataset_wizard(np.arange(20).reshape((4, 5)).view(myarray),
targets=[1,2,3,4],
chunks=[5,6,7,8])
# array subclass survives
ok_(isinstance(data.samples, myarray))
ok_(data.nsamples == 4)
ok_(data.nfeatures == 5)
sel = data[[0, 3], [1, 2]]
ok_(sel.nsamples == 2)
ok_(sel.nfeatures == 2)
assert_array_equal(sel.targets, [1, 4])
assert_array_equal(sel.chunks, [5, 8])
assert_array_equal(sel.samples, [[1, 2], [16, 17]])
# array subclass survives
ok_(isinstance(sel.samples, myarray))
# should yield the same result if done sequentially
sel2 = data[:, [1, 2]]
sel2 = sel2[[0, 3]]
assert_array_equal(sel.samples, sel2.samples)
ok_(sel2.nsamples == 2)
ok_(sel2.nfeatures == 2)
# array subclass survives
ok_(isinstance(sel.samples, myarray))
assert_raises(ValueError, data.__getitem__, (1, 2, 3))
# test correct behavior when selecting just single rows/columns
single = data[0]
ok_(single.nsamples == 1)
ok_(single.nfeatures == 5)
assert_array_equal(single.samples, [[0, 1, 2, 3, 4]])
single = data[:, 0]
ok_(single.nsamples == 4)
ok_(single.nfeatures == 1)
assert_array_equal(single.samples, [[0], [5], [10], [15]])
single = data[1, 1]
ok_(single.nsamples == 1)
ok_(single.nfeatures == 1)
assert_array_equal(single.samples, [[6]])
# array subclass survives
ok_(isinstance(single.samples, myarray))
def test_combined_samplesfeature_selection():
data = dataset_wizard(np.arange(20).reshape((4, 5)).view(myarray),
targets=[1,2,3,4],
chunks=[5,6,7,8])
# array subclass survives
ok_(isinstance(data.samples, myarray))
ok_(data.nsamples == 4)
ok_(data.nfeatures == 5)
sel = data[[0, 3], [1, 2]]
ok_(sel.nsamples == 2)
ok_(sel.nfeatures == 2)
assert_array_equal(sel.targets, [1, 4])
assert_array_equal(sel.chunks, [5, 8])
assert_array_equal(sel.samples, [[1, 2], [16, 17]])
# array subclass survives
ok_(isinstance(sel.samples, myarray))
# should yield the same result if done sequentially
sel2 = data[:, [1, 2]]
sel2 = sel2[[0, 3]]
assert_array_equal(sel.samples, sel2.samples)
ok_(sel2.nsamples == 2)
ok_(sel2.nfeatures == 2)
# array subclass survives
ok_(isinstance(sel.samples, myarray))
assert_raises(ValueError, data.__getitem__, (1, 2, 3))
# test correct behavior when selecting just single rows/columns
single = data[0]
ok_(single.nsamples == 1)
ok_(single.nfeatures == 5)
assert_array_equal(single.samples, [[0, 1, 2, 3, 4]])
single = data[:, 0]
ok_(single.nsamples == 4)
ok_(single.nfeatures == 1)
assert_array_equal(single.samples, [[0], [5], [10], [15]])
single = data[1, 1]
ok_(single.nsamples == 1)
ok_(single.nfeatures == 1)
assert_array_equal(single.samples, [[6]])
# array subclass survives
ok_(isinstance(single.samples, myarray))
def pure_multivariate_signal(patterns, signal2noise=1.5, chunks=None,
targets=None):
""" Create a 2d dataset with a clear purely multivariate signal.
This is known is the XOR problem.
::
%%%%%%%%%
% O % X %
%%%%%%%%%
% X % O %
%%%%%%%%%
Parameters
----------
patterns: int
Number of data points in each of the four dot clouds
signal2noise: float, optional
Univariate signal pedestal.
chunks: array, optional
Vector for chunk labels for all generated samples.
targets: list, optional
Length-2 sequence of target values for both classes. If None,
[0, 1] is used.
"""
if targets is None:
targets = [0, 1]
# start with noise
data = np.random.normal(size=(4 * patterns, 2))
# add signal
data[:2 * patterns, 1] += signal2noise
data[2 * patterns:4 * patterns, 1] -= signal2noise
data[:patterns, 0] -= signal2noise
data[2 * patterns:3 * patterns, 0] -= signal2noise
data[patterns:2 * patterns, 0] += signal2noise
data[3 * patterns:4 * patterns, 0] += signal2noise
# two conditions
regs = np.array((targets[0:1] * patterns) + (targets[1:2] * 2 * patterns) + (targets[0:1] * patterns))
if chunks is None:
chunks = range(len(data))
return dataset_wizard(samples=data, targets=regs, chunks=chunks)
def chirp_linear(n_instances, n_features=4, n_nonbogus_features=2, data_noise=0.4, noise=0.1):
""" Generates simple dataset for linear regressions
Generates chirp signal, populates n_nonbogus_features out of
n_features with it with different noise level and then provides
signal itself with additional noise as labels
"""
x = np.linspace(0, 1, n_instances)
y = np.sin((10 * np.pi * x ** 2))
data = np.random.normal(size=(n_instances, n_features)) * data_noise
for i in xrange(n_nonbogus_features):
data[:, i] += y[:]
labels = y + np.random.normal(size=(n_instances,)) * noise
return dataset_wizard(samples=data, targets=labels)
def test_samplesgroup_mapper():
data = np.arange(24).reshape(8,3)
labels = [0, 1] * 4
chunks = np.repeat(np.array((0,1)),4)
# correct results
csamples = [[3, 4, 5], [6, 7, 8], [15, 16, 17], [18, 19, 20]]
clabels = [0, 1, 0, 1]
cchunks = [0, 0, 1, 1]
ds = dataset_wizard(samples=data, targets=labels, chunks=chunks)
# add some feature attribute -- just to check
ds.fa['checker'] = np.arange(3)
ds.init_origids('samples')
m = mean_group_sample(['targets', 'chunks'])
mds = m.forward(ds)
assert_array_equal(mds.samples, csamples)
# FAs should simply remain the same
assert_array_equal(mds.fa.checker, np.arange(3))
# now without grouping
m = mean_sample()
# forwarding just the samples should yield the same result
assert_array_equal(m.forward(ds.samples),
m.forward(ds).samples)
# directly apply to dataset
# using untrained mapper
m = mean_group_sample(['targets', 'chunks'])
mapped = ds.get_mapped(m)
assert_equal(mapped.nsamples, 4)
assert_equal(mapped.nfeatures, 3)
assert_array_equal(mapped.samples, csamples)
assert_array_equal(mapped.targets, clabels)
assert_array_equal(mapped.chunks, cchunks)
# make sure origids get regenerated
assert_array_equal([s.count('+') for s in mapped.sa.origids], [1] * 4)
# disbalanced dataset -- lets remove 0th sample so there is no target
# 0 in 0th chunk
ds_ = ds[[0, 1, 3, 5]]
mapped = ds_.get_mapped(m)
ok_(len(mapped) == 3)
ok_(not None in mapped.sa.origids)
def test_surface_dset_niml_io_with_unicode(self, fn):
ds = dataset_wizard(np.arange(20).reshape((4, 5)), targets=1, chunks=1)
ds.sa['unicode'] = [u'u1', u'uu2', u'uuu3', u'uuuu4']
ds.sa['str'] = ['s1', 'ss2', 'sss3', 'ssss4']
ds.fa['node_indices'] = np.arange(5)
# ensure sample attributes are of String type (not array)
niml_dict = afni_niml_dset.dset2rawniml(niml.to_niml(ds))
expected_dtypes = dict(PYMVPA_SA_unicode='String',
PYMVPA_SA_str='String',
PYMVPA_SA_targets='1*int32')
def assert_has_expected_datatype(name, expected_dtype, niml):
"""helper function"""
nodes = niml_dict['nodes']
for node in nodes:
if node['name'] == name:
assert_equal(node['ni_type'], expected_dtype)
return
raise ValueError('not found: %s', name)
for name, expected_dtype in expected_dtypes.iteritems():
assert_has_expected_datatype(name, expected_dtype, niml)
# test NIML I/O
niml.write(fn, ds)
# remove extra fields added when reading the file
ds2 = niml.from_any(fn)
ds2.a.pop('history')
ds2.a.pop('filename')
ds2.sa.pop('labels')
ds2.sa.pop('stats')
# NIML does not support int64, only int32;
# compare equality of values in samples by setting the
# datatype the same as in the input (int32 or int64 depending
# on the platform)
ds2.samples = np.asarray(ds2.samples, dtype=ds.samples.dtype)
assert_datasets_equal(ds, ds2)
def test_samplesgroup_mapper():
data = np.arange(24).reshape(8, 3)
labels = [0, 1] * 4
chunks = np.repeat(np.array((0, 1)), 4)
# correct results
csamples = [[3, 4, 5], [6, 7, 8], [15, 16, 17], [18, 19, 20]]
clabels = [0, 1, 0, 1]
cchunks = [0, 0, 1, 1]
ds = dataset_wizard(samples=data, targets=labels, chunks=chunks)
# add some feature attribute -- just to check
ds.fa['checker'] = np.arange(3)
ds.init_origids('samples')
m = mean_group_sample(['targets', 'chunks'])
mds = m.forward(ds)
assert_array_equal(mds.samples, csamples)
# FAs should simply remain the same
assert_array_equal(mds.fa.checker, np.arange(3))
# now without grouping
m = mean_sample()
# forwarding just the samples should yield the same result
assert_array_equal(m.forward(ds.samples), m.forward(ds).samples)
# directly apply to dataset
# using untrained mapper
m = mean_group_sample(['targets', 'chunks'])
mapped = ds.get_mapped(m)
assert_equal(mapped.nsamples, 4)
assert_equal(mapped.nfeatures, 3)
assert_array_equal(mapped.samples, csamples)
assert_array_equal(mapped.targets, clabels)
assert_array_equal(mapped.chunks, cchunks)
# make sure origids get regenerated
assert_array_equal([s.count('+') for s in mapped.sa.origids], [1] * 4)
# disbalanced dataset -- lets remove 0th sample so there is no target
# 0 in 0th chunk
ds_ = ds[[0, 1, 3, 5]]
mapped = ds_.get_mapped(m)
ok_(len(mapped) == 3)
ok_(not None in mapped.sa.origids)
def chirp_linear(n_instances, n_features=4, n_nonbogus_features=2,
data_noise=0.4, noise=0.1):
""" Generates simple dataset for linear regressions
Generates chirp signal, populates n_nonbogus_features out of
n_features with it with different noise level and then provides
signal itself with additional noise as labels
"""
x = np.linspace(0, 1, n_instances)
y = np.sin((10 * np.pi * x **2))
data = np.random.normal(size=(n_instances, n_features ))*data_noise
for i in xrange(n_nonbogus_features):
data[:, i] += y[:]
labels = y + np.random.normal(size=(n_instances,))*noise
return dataset_wizard(samples=data, targets=labels)
def test_classifier(self):
clf = ParametrizedClassifier()
self.assertEqual(len(clf.params.items()), 2) # + retrainable
self.assertEqual(len(clf.kernel_params.items()), 1)
clfe = ParametrizedClassifierExtended()
self.assertEqual(len(clfe.params.items()), 2)
self.assertEqual(len(clfe.kernel_params.items()), 2)
self.assertEqual(len(clfe.kernel_params.listing), 2)
# check assignment once again
self.assertEqual(clfe.kernel_params.kp2, 200.0)
clfe.kernel_params.kp2 = 201.0
self.assertEqual(clfe.kernel_params.kp2, 201.0)
self.assertEqual(clfe.kernel_params.is_set("kp2"), True)
clfe.train(dataset_wizard(samples=[[0, 0]], targets=[1], chunks=[1]))
self.assertEqual(clfe.kernel_params.is_set("kp2"), False)
self.assertEqual(clfe.kernel_params.is_set(), False)
self.assertEqual(clfe.params.is_set(), False)
