def test_corrstability_smoketest(ds):
if not 'chunks' in ds.sa:
return
if len(ds.sa['targets'].unique) > 30:
# was regression dataset
return
# very basic testing since
cs = CorrStability()
#ds = datasets['uni2small']
out = cs(ds)
assert_equal(out.shape, (ds.nfeatures,))
ok_(np.all(out >= -1.001)) # it should be a correlation after all
ok_(np.all(out <= 1.001))
# and theoretically those nonbogus features should have higher values
if 'nonbogus_targets' in ds.fa:
bogus_features = np.array([x==None for x in ds.fa.nonbogus_targets])
assert_array_less(np.mean(out[bogus_features]), np.mean(out[~bogus_features]))
# and if we move targets to alternative location
ds = ds.copy(deep=True)
ds.sa['alt'] = ds.T
ds.sa.pop('targets')
assert_raises(KeyError, cs, ds)
cs = CorrStability('alt')
out_ = cs(ds)
assert_array_equal(out, out_)
def test_exclude_targets_combinations_subjectchunks():
partitioner = ChainNode([NFoldPartitioner(attr='subjects'),
ExcludeTargetsCombinationsPartitioner(
k=1,
targets_attr='chunks',
space='partitions')],
space='partitions')
# targets do not need even to be defined!
ds = Dataset(np.arange(18).reshape(9, 2),
sa={'chunks': np.arange(9) // 3,
'subjects': np.arange(9) % 3})
dss = list(partitioner.generate(ds))
assert_equal(len(dss), 9)
testing_subjs, testing_chunks = [], []
for ds_ in dss:
testing_partition = ds_.sa.partitions == 2
training_partition = ds_.sa.partitions == 1
# must be scalars -- so implicit test here
# if not -- would be error
testing_subj = np.asscalar(np.unique(ds_.sa.subjects[testing_partition]))
testing_subjs.append(testing_subj)
testing_chunk = np.asscalar(np.unique(ds_.sa.chunks[testing_partition]))
testing_chunks.append(testing_chunk)
# and those must not appear for training
ok_(not testing_subj in ds_.sa.subjects[training_partition])
ok_(not testing_chunk in ds_.sa.chunks[training_partition])
# and we should have gone through all chunks/subjs pairs
testing_pairs = set(zip(testing_subjs, testing_chunks))
assert_equal(len(testing_pairs), 9)
# yoh: equivalent to set(itertools.product(range(3), range(3))))
# but .product is N/A for python2.5
assert_equal(testing_pairs, set(zip(*np.where(np.ones((3,3))))))
def test_corrstability_smoketest(ds):
if not 'chunks' in ds.sa:
return
if len(ds.sa['targets'].unique) > 30:
# was regression dataset
return
# very basic testing since
cs = CorrStability()
#ds = datasets['uni2small']
out = cs(ds)
assert_equal(out.shape, (ds.nfeatures, ))
ok_(np.all(out >= -1.001)) # it should be a correlation after all
ok_(np.all(out <= 1.001))
# and theoretically those nonbogus features should have higher values
if 'nonbogus_targets' in ds.fa:
bogus_features = np.array([x == None for x in ds.fa.nonbogus_targets])
assert_array_less(np.mean(out[bogus_features]),
np.mean(out[~bogus_features]))
# and if we move targets to alternative location
ds = ds.copy(deep=True)
ds.sa['alt'] = ds.T
ds.sa.pop('targets')
assert_raises(KeyError, cs, ds)
cs = CorrStability('alt')
out_ = cs(ds)
assert_array_equal(out, out_)
def test_exclude_targets_combinations_subjectchunks():
partitioner = ChainNode([NFoldPartitioner(attr='subjects'),
ExcludeTargetsCombinationsPartitioner(
k=1,
targets_attr='chunks',
space='partitions')],
space='partitions')
# targets do not need even to be defined!
ds = Dataset(np.arange(18).reshape(9, 2),
sa={'chunks': np.arange(9) // 3,
'subjects': np.arange(9) % 3})
dss = list(partitioner.generate(ds))
assert_equal(len(dss), 9)
testing_subjs, testing_chunks = [], []
for ds_ in dss:
testing_partition = ds_.sa.partitions == 2
training_partition = ds_.sa.partitions == 1
# must be scalars -- so implicit test here
# if not -- would be error
testing_subj = np.asscalar(np.unique(ds_.sa.subjects[testing_partition]))
testing_subjs.append(testing_subj)
testing_chunk = np.asscalar(np.unique(ds_.sa.chunks[testing_partition]))
testing_chunks.append(testing_chunk)
# and those must not appear for training
ok_(not testing_subj in ds_.sa.subjects[training_partition])
ok_(not testing_chunk in ds_.sa.chunks[training_partition])
# and we should have gone through all chunks/subjs pairs
testing_pairs = set(zip(testing_subjs, testing_chunks))
assert_equal(len(testing_pairs), 9)
# yoh: equivalent to set(itertools.product(range(3), range(3))))
# but .product is N/A for python2.5
assert_equal(testing_pairs, set(zip(*np.where(np.ones((3,3))))))
def test_zcore_repr():
# Just basic test if everything is sane... no proper comparison
for m in (ZScoreMapper(chunks_attr=None),
ZScoreMapper(params=(3, 1)),
ZScoreMapper()):
mr = eval(repr(m))
ok_(isinstance(mr, ZScoreMapper))
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_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_attrmap_conflicts():
am_n = AttributeMap({'a':1, 'b':2, 'c':1})
am_t = AttributeMap({'a':1, 'b':2, 'c':1}, collisions_resolution='tuple')
am_l = AttributeMap({'a':1, 'b':2, 'c':1}, collisions_resolution='lucky')
q_f = ['a', 'b', 'a', 'c']
# should have no effect on forward mapping
ok_(np.all(am_n.to_numeric(q_f) == am_t.to_numeric(q_f)))
ok_(np.all(am_t.to_numeric(q_f) == am_l.to_numeric(q_f)))
assert_raises(ValueError, am_n.to_literal, [2])
r_t = am_t.to_literal([2, 1])
r_l = am_l.to_literal([2, 1])
def test_attrmap_conflicts():
am_n = AttributeMap({'a':1, 'b':2, 'c':1})
am_t = AttributeMap({'a':1, 'b':2, 'c':1}, collisions_resolution='tuple')
am_l = AttributeMap({'a':1, 'b':2, 'c':1}, collisions_resolution='lucky')
q_f = ['a', 'b', 'a', 'c']
# should have no effect on forward mapping
ok_(np.all(am_n.to_numeric(q_f) == am_t.to_numeric(q_f)))
ok_(np.all(am_t.to_numeric(q_f) == am_l.to_numeric(q_f)))
assert_raises(ValueError, am_n.to_literal, [2])
r_t = am_t.to_literal([2, 1])
r_l = am_l.to_literal([2, 1])
def test_subset_filler():
sm = StaticFeatureSelection(np.arange(3))
sm_f0 = StaticFeatureSelection(np.arange(3), filler=0)
sm_fm1 = StaticFeatureSelection(np.arange(3), filler= -1)
sm_fnan = StaticFeatureSelection(np.arange(3), filler=np.nan)
data = np.arange(12).astype(float).reshape((2, -1))
sm.train(data)
data_forwarded = sm.forward(data)
for m in (sm, sm_f0, sm_fm1, sm_fnan):
m.train(data)
assert_array_equal(data_forwarded, m.forward(data))
data_back_fm1 = sm_fm1.reverse(data_forwarded)
ok_(np.all(data_back_fm1[:, 3:] == -1))
data_back_fnan = sm_fnan.reverse(data_forwarded)
ok_(np.all(np.isnan(data_back_fnan[:, 3:])))
def test_subset_filler():
sm = StaticFeatureSelection(np.arange(3))
sm_f0 = StaticFeatureSelection(np.arange(3), filler=0)
sm_fm1 = StaticFeatureSelection(np.arange(3), filler=-1)
sm_fnan = StaticFeatureSelection(np.arange(3), filler=np.nan)
data = np.arange(12).astype(float).reshape((2, -1))
sm.train(data)
data_forwarded = sm.forward(data)
for m in (sm, sm_f0, sm_fm1, sm_fnan):
m.train(data)
assert_array_equal(data_forwarded, m.forward(data))
data_back_fm1 = sm_fm1.reverse(data_forwarded)
ok_(np.all(data_back_fm1[:, 3:] == -1))
data_back_fnan = sm_fnan.reverse(data_forwarded)
ok_(np.all(np.isnan(data_back_fnan[:, 3:])))
def test_cached_query_engine():
"""Test cached query engine
"""
sphere = ne.Sphere(1)
# dataset with just one "space"
ds = datasets['3dlarge']
qe0 = ne.IndexQueryEngine(myspace=sphere)
qec = ne.CachedQueryEngine(qe0)
# and ground truth one
qe = ne.IndexQueryEngine(myspace=sphere)
results_ind = []
results_kw = []
def cmp_res(res1, res2):
comp = [x == y for x, y in zip(res1, res2)]
ok_(np.all(comp))
for iq, q in enumerate((qe, qec)):
q.train(ds)
# sequential train on the same should be ok in both cases
q.train(ds)
res_ind = [q[fid] for fid in xrange(ds.nfeatures)]
res_kw = [q(myspace=x) for x in ds.fa.myspace]
# test if results match
cmp_res(res_ind, res_kw)
results_ind.append(res_ind)
results_kw.append(res_kw)
# now check if results of cached were the same as of regular run
cmp_res(results_ind[0], results_ind[1])
# Now do sanity checks
assert_raises(ValueError, qec.train, ds[:, :-1])
assert_raises(ValueError, qec.train, ds.copy())
ds2 = ds.copy()
qec.untrain()
qec.train(ds2)
# should be the same results on the copy
cmp_res(results_ind[0], [qec[fid] for fid in xrange(ds.nfeatures)])
cmp_res(results_kw[0], [qec(myspace=x) for x in ds.fa.myspace])
ok_(qec.train(ds2) is None)
def test_cached_query_engine():
"""Test cached query engine
"""
sphere = ne.Sphere(1)
# dataset with just one "space"
ds = datasets['3dlarge']
qe0 = ne.IndexQueryEngine(myspace=sphere)
qec = ne.CachedQueryEngine(qe0)
# and ground truth one
qe = ne.IndexQueryEngine(myspace=sphere)
results_ind = []
results_kw = []
def cmp_res(res1, res2):
comp = [x == y for x, y in zip(res1, res2)]
ok_(np.all(comp))
for iq, q in enumerate((qe, qec)):
q.train(ds)
# sequential train on the same should be ok in both cases
q.train(ds)
res_ind = [q[fid] for fid in xrange(ds.nfeatures)]
res_kw = [q(myspace=x) for x in ds.fa.myspace]
# test if results match
cmp_res(res_ind, res_kw)
results_ind.append(res_ind)
results_kw.append(res_kw)
# now check if results of cached were the same as of regular run
cmp_res(results_ind[0], results_ind[1])
# Now do sanity checks
assert_raises(ValueError, qec.train, ds[:, :-1])
assert_raises(ValueError, qec.train, ds.copy())
ds2 = ds.copy()
qec.untrain()
qec.train(ds2)
# should be the same results on the copy
cmp_res(results_ind[0], [qec[fid] for fid in xrange(ds.nfeatures)])
cmp_res(results_kw[0], [qec(myspace=x) for x in ds.fa.myspace])
ok_(qec.train(ds2) is None)
def test_sphere():
# test sphere initialization
s = ne.Sphere(1)
center0 = (0, 0, 0)
center1 = (1, 1, 1)
assert_equal(len(s(center0)), 7)
target = array([array([-1, 0, 0]),
array([ 0, -1, 0]),
array([ 0, 0, -1]),
array([0, 0, 0]),
array([0, 0, 1]),
array([0, 1, 0]),
array([1, 0, 0])])
# test of internals -- no recomputation of increments should be done
prev_increments = s._increments
assert_array_equal(s(center0), target)
ok_(prev_increments is s._increments)
# query lower dimensionality
_ = s((0, 0))
ok_(not prev_increments is s._increments)
# test Sphere call
target = [array([0, 1, 1]),
array([1, 0, 1]),
array([1, 1, 0]),
array([1, 1, 1]),
array([1, 1, 2]),
array([1, 2, 1]),
array([2, 1, 1])]
res = s(center1)
assert_array_equal(array(res), target)
# They all should be tuples
ok_(np.all([isinstance(x, tuple) for x in res]))
# test for larger diameter
s = ne.Sphere(4)
assert_equal(len(s(center1)), 257)
# test extent keyword
#s = ne.Sphere(4,extent=(1,1,1))
#assert_array_equal(array(s((0,0,0))), array([[0,0,0]]))
# test Errors during initialisation and call
#assert_raises(ValueError, ne.Sphere, 2)
#assert_raises(ValueError, ne.Sphere, 1.0)
# no longer extent available
assert_raises(TypeError, ne.Sphere, 1, extent=(1))
assert_raises(TypeError, ne.Sphere, 1, extent=(1.0, 1.0, 1.0))
s = ne.Sphere(1)
#assert_raises(ValueError, s, (1))
if __debug__:
# No float coordinates allowed for now...
# XXX might like to change that ;)
#
assert_raises(ValueError, s, (1.0, 1.0, 1.0))
def test_samples_attributes(self):
sa = SampleAttributes(os.path.join(pymvpa_dataroot,
'attributes_literal.txt'),
literallabels=True)
ok_(sa.nrows == 1452, msg='There should be 1452 samples')
# convert to event list, with some custom attr
ev = find_events(**sa)
ok_(len(ev) == 17 * (max(sa.chunks) + 1),
msg='Not all events got detected.')
ok_(ev[0]['targets'] == ev[-1]['targets'] == 'rest',
msg='First and last event are rest condition.')
ok_(ev[-1]['onset'] + ev[-1]['duration'] == sa.nrows,
msg='Something is wrong with the timiing of the events')
def test_samples_attributes(self):
sa = SampleAttributes(pathjoin(pymvpa_dataroot,
'attributes_literal.txt'),
literallabels=True)
ok_(sa.nrows == 1452, msg='There should be 1452 samples')
# convert to event list, with some custom attr
ev = find_events(**sa)
ok_(len(ev) == 17 * (max(sa.chunks) + 1),
msg='Not all events got detected.')
ok_(ev[0]['targets'] == ev[-1]['targets'] == 'rest',
msg='First and last event are rest condition.')
ok_(ev[-1]['onset'] + ev[-1]['duration'] == sa.nrows,
msg='Something is wrong with the timiing of the events')
def test_sphere_distance_func():
# Test some other distance
se = ne.Sphere(3)
sm = ne.Sphere(3, distance_func=manhatten_distance)
rese = se((10, 5))
resm = sm((10, 5))
for res in rese, resm:
# basic test for duplicates (I think we forgotten to test for them)
ok_(len(res) == len(set(res)))
# in manhatten distance we should all be no further than 3 "steps" away
ok_(np.all([np.sum(np.abs(np.array(x) - (10, 5))) <= 3 for x in resm]))
# in euclidean we are taking shortcuts ;)
ok_(np.any([np.sum(np.abs(np.array(x) - (10, 5))) > 3 for x in rese]))
def test_sphere_distance_func():
# Test some other distance
se = ne.Sphere(3)
sm = ne.Sphere(3, distance_func=manhatten_distance)
rese = se((10, 5))
resm = sm((10, 5))
for res in rese, resm:
# basic test for duplicates (I think we forgotten to test for them)
ok_(len(res) == len(set(res)))
# in manhatten distance we should all be no further than 3 "steps" away
ok_(np.all([np.sum(np.abs(np.array(x) - (10, 5))) <= 3 for x in resm]))
# in euclidean we are taking shortcuts ;)
ok_(np.any([np.sum(np.abs(np.array(x) - (10, 5))) > 3 for x in rese]))
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)
# 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)
# verify that if param_est is set but chunks_attr is None
# performs zscoring across entire dataset correctly
data = data.copy()
data_01 = data.select({'targets': [0, 1]})
zscore(data_01, chunks_attr=None)
zscore(data, chunks_attr=None, param_est=('targets', [0, 1]))
assert_array_equal(data_01.samples, data.select({'targets': [0, 1]}))
# 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]))
# And just a smoke test for warnings reporting whenever # of
# samples per chunk is low.
# on 1 sample per chunk
zds1 = ZScoreMapper(chunks_attr='chunks', auto_train=True)(
ds[[0, -1]])
ok_(np.all(zds1.samples == 0)) # they all should be 0
# on 2 samples per chunk
zds2 = ZScoreMapper(chunks_attr='chunks', auto_train=True)(
ds[[0, 1, -10, -1]])
assert_array_equal(np.unique(zds2.samples), [-1., 1]) # they all should be -1 or 1
# on 3 samples per chunk -- different warning
ZScoreMapper(chunks_attr='chunks', auto_train=True)(
ds[[0, 1, 2, -3, -2, -1]])
# test if std provided as a list not as an array is handled
# properly -- should zscore all features (not just first/none
# as it was before)
ds = dataset_wizard(np.arange(32).reshape((8,-1)),
targets=range(8), chunks=[0] * 8)
means = [0, 1, -10, 10]
std0 = np.std(ds[:, 0]) # std deviation of first one
stds = [std0, 10, .1, 1]
zm = ZScoreMapper(params=(means, stds),
auto_train=True)
dsz = zm(ds)
assert_array_almost_equal((np.mean(ds, axis=0) - np.asanyarray(means))/np.array(stds),
np.mean(dsz, axis=0))
assert_array_almost_equal(np.std(ds, axis=0)/np.array(stds),
np.std(dsz, axis=0))
def test_attrmap():
map_default = {'eins': 0, 'zwei': 2, 'sieben': 1}
map_custom = {'eins': 11, 'zwei': 22, 'sieben': 33}
literal = ['eins', 'zwei', 'sieben', 'eins', 'sieben', 'eins']
literal_nonmatching = ['uno', 'dos', 'tres']
num_default = [0, 2, 1, 0, 1, 0]
num_custom = [11, 22, 33, 11, 33, 11]
# no custom mapping given
am = AttributeMap()
assert_false(am)
ok_(len(am) == 0)
assert_array_equal(am.to_numeric(literal), num_default)
assert_array_equal(am.to_literal(num_default), literal)
ok_(am)
ok_(len(am) == 3)
#
# Tests for recursive mapping + preserving datatype
class myarray(np.ndarray):
pass
assert_raises(KeyError, am.to_literal, [(1, 2), 2, 0])
literal_fancy = [(1, 2), 2, [0], np.array([0, 1]).view(myarray)]
literal_fancy_tuple = tuple(literal_fancy)
literal_fancy_array = np.array(literal_fancy, dtype=object)
for l in (literal_fancy, literal_fancy_tuple, literal_fancy_array):
res = am.to_literal(l, recurse=True)
assert_equal(res[0], ('sieben', 'zwei'))
assert_equal(res[1], 'zwei')
assert_equal(res[2], ['eins'])
assert_array_equal(res[3], ['eins', 'sieben'])
# types of result and subsequences should be preserved
ok_(isinstance(res, l.__class__))
ok_(isinstance(res[0], tuple))
ok_(isinstance(res[1], str))
ok_(isinstance(res[2], list))
ok_(isinstance(res[3], myarray))
# yet another example
a = np.empty(1, dtype=object)
a[0] = (0, 1)
res = am.to_literal(a, recurse=True)
ok_(isinstance(res[0], tuple))
#
# with custom mapping
am = AttributeMap(map=map_custom)
assert_array_equal(am.to_numeric(literal), num_custom)
assert_array_equal(am.to_literal(num_custom), literal)
# if not numeric nothing is mapped
assert_array_equal(am.to_numeric(num_custom), num_custom)
# even if the map doesn't fit
assert_array_equal(am.to_numeric(num_default), num_default)
# need to_numeric first
am = AttributeMap()
assert_raises(RuntimeError, am.to_literal, [1, 2, 3])
# stupid args
assert_raises(ValueError, AttributeMap, map=num_custom)
# map mismatch
am = AttributeMap(map=map_custom)
if __debug__:
# checked only in __debug__
assert_raises(KeyError, am.to_numeric, literal_nonmatching)
# needs reset and should work afterwards
am.clear()
assert_array_equal(am.to_numeric(literal_nonmatching), [2, 0, 1])
# and now reverse
am = AttributeMap(map=map_custom)
assert_raises(KeyError, am.to_literal, num_default)
# dict-like interface
am = AttributeMap()
ok_([(k, v) for k, v in am.items()] == [])
def test_attrmap():
map_default = {'eins': 0, 'zwei': 2, 'sieben': 1}
map_custom = {'eins': 11, 'zwei': 22, 'sieben': 33}
literal = ['eins', 'zwei', 'sieben', 'eins', 'sieben', 'eins']
literal_nonmatching = ['uno', 'dos', 'tres']
num_default = [0, 2, 1, 0, 1, 0]
num_custom = [11, 22, 33, 11, 33, 11]
# no custom mapping given
am = AttributeMap()
assert_false(am)
ok_(len(am) == 0)
assert_array_equal(am.to_numeric(literal), num_default)
assert_array_equal(am.to_literal(num_default), literal)
ok_(am)
ok_(len(am) == 3)
#
# Tests for recursive mapping + preserving datatype
class myarray(np.ndarray):
pass
assert_raises(KeyError, am.to_literal, [(1, 2), 2, 0])
literal_fancy = [(1, 2), 2, [0], np.array([0, 1]).view(myarray)]
literal_fancy_tuple = tuple(literal_fancy)
literal_fancy_array = np.array(literal_fancy, dtype=object)
for l in (literal_fancy, literal_fancy_tuple,
literal_fancy_array):
res = am.to_literal(l, recurse=True)
assert_equal(res[0], ('sieben', 'zwei'))
assert_equal(res[1], 'zwei')
assert_equal(res[2], ['eins'])
assert_array_equal(res[3], ['eins', 'sieben'])
# types of result and subsequences should be preserved
ok_(isinstance(res, l.__class__))
ok_(isinstance(res[0], tuple))
ok_(isinstance(res[1], str))
ok_(isinstance(res[2], list))
ok_(isinstance(res[3], myarray))
# yet another example
a = np.empty(1, dtype=object)
a[0] = (0, 1)
res = am.to_literal(a, recurse=True)
ok_(isinstance(res[0], tuple))
#
# with custom mapping
am = AttributeMap(map=map_custom)
assert_array_equal(am.to_numeric(literal), num_custom)
assert_array_equal(am.to_literal(num_custom), literal)
# if not numeric nothing is mapped
assert_array_equal(am.to_numeric(num_custom), num_custom)
# even if the map doesn't fit
assert_array_equal(am.to_numeric(num_default), num_default)
# need to_numeric first
am = AttributeMap()
assert_raises(RuntimeError, am.to_literal, [1,2,3])
# stupid args
assert_raises(ValueError, AttributeMap, map=num_custom)
# map mismatch
am = AttributeMap(map=map_custom)
if __debug__:
# checked only in __debug__
assert_raises(KeyError, am.to_numeric, literal_nonmatching)
# needs reset and should work afterwards
am.clear()
assert_array_equal(am.to_numeric(literal_nonmatching), [2, 0, 1])
# and now reverse
am = AttributeMap(map=map_custom)
assert_raises(KeyError, am.to_literal, num_default)
# dict-like interface
am = AttributeMap()
ok_([(k, v) for k, v in am.iteritems()] == [])
def test_flatten():
samples_shape = (2, 2, 4)
data_shape = (4,) + samples_shape
data = np.arange(np.prod(data_shape)).reshape(data_shape).view(myarray)
pristinedata = data.copy()
target = [[ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15],
[16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31],
[32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47],
[48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63]]
target = np.array(target).view(myarray)
index_target = np.array([[0, 0, 0], [0, 0, 1], [0, 0, 2], [0, 0, 3],
[0, 1, 0], [0, 1, 1], [0, 1, 2], [0, 1, 3],
[1, 0, 0], [1, 0, 1], [1, 0, 2], [1, 0, 3],
[1, 1, 0], [1, 1, 1], [1, 1, 2], [1, 1, 3]])
# test only flattening the first two dimensions
fm_max = FlattenMapper(maxdims=2)
fm_max.train(data)
assert_equal(fm_max(data).shape, (4, 4, 4))
# array subclass survives
ok_(isinstance(data, myarray))
# actually, there should be no difference between a plain FlattenMapper and
# a chain that only has a FlattenMapper as the one element
for fm in [FlattenMapper(space='voxel'),
ChainMapper([FlattenMapper(space='voxel'),
StaticFeatureSelection(slice(None))])]:
# not working if untrained
assert_raises(RuntimeError,
fm.forward1,
np.arange(np.sum(samples_shape) + 1))
fm.train(data)
ok_(isinstance(fm.forward(data), myarray))
ok_(isinstance(fm.forward1(data[2]), myarray))
assert_array_equal(fm.forward(data), target)
assert_array_equal(fm.forward1(data[2]), target[2])
assert_raises(ValueError, fm.forward, np.arange(4))
# all of that leaves that data unmodified
assert_array_equal(data, pristinedata)
# reverse mapping
ok_(isinstance(fm.reverse(target), myarray))
ok_(isinstance(fm.reverse1(target[0]), myarray))
ok_(isinstance(fm.reverse(target[1:2]), myarray))
assert_array_equal(fm.reverse(target), data)
assert_array_equal(fm.reverse1(target[0]), data[0])
assert_array_equal(fm.reverse1(target[0]),
_verified_reverse1(fm, target[0]))
assert_array_equal(fm.reverse(target[1:2]), data[1:2])
assert_raises(ValueError, fm.reverse, np.arange(14))
# check one dimensional data, treated as scalar samples
oned = np.arange(5)
fm.train(Dataset(oned))
# needs 2D
assert_raises(ValueError, fm.forward, oned)
# doesn't match mapper, since Dataset turns `oned` into (5,1)
assert_raises(ValueError, fm.forward, oned)
assert_equal(Dataset(oned).nfeatures, 1)
# try dataset mode, with some feature attribute
fattr = np.arange(np.prod(samples_shape)).reshape(samples_shape)
ds = Dataset(data, fa={'awesome': fattr.copy()})
assert_equal(ds.samples.shape, data_shape)
fm.train(ds)
dsflat = fm.forward(ds)
ok_(isinstance(dsflat, Dataset))
ok_(isinstance(dsflat.samples, myarray))
assert_array_equal(dsflat.samples, target)
assert_array_equal(dsflat.fa.awesome, np.arange(np.prod(samples_shape)))
assert_true(isinstance(dsflat.fa['awesome'], ArrayCollectable))
# test index creation
assert_array_equal(index_target, dsflat.fa.voxel)
# and back
revds = fm.reverse(dsflat)
ok_(isinstance(revds, Dataset))
ok_(isinstance(revds.samples, myarray))
assert_array_equal(revds.samples, data)
assert_array_equal(revds.fa.awesome, fattr)
assert_true(isinstance(revds.fa['awesome'], ArrayCollectable))
assert_false('voxel' in revds.fa)
def test_flatten():
samples_shape = (2, 2, 4)
data_shape = (4,) + samples_shape
data = np.arange(np.prod(data_shape)).reshape(data_shape).view(myarray)
pristinedata = data.copy()
target = [[ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15],
[16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31],
[32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47],
[48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63]]
target = np.array(target).view(myarray)
index_target = np.array([[0, 0, 0], [0, 0, 1], [0, 0, 2], [0, 0, 3],
[0, 1, 0], [0, 1, 1], [0, 1, 2], [0, 1, 3],
[1, 0, 0], [1, 0, 1], [1, 0, 2], [1, 0, 3],
[1, 1, 0], [1, 1, 1], [1, 1, 2], [1, 1, 3]])
# test only flattening the first two dimensions
fm_max = FlattenMapper(maxdims=2)
fm_max.train(data)
assert_equal(fm_max(data).shape, (4, 4, 4))
# array subclass survives
ok_(isinstance(data, myarray))
# actually, there should be no difference between a plain FlattenMapper and
# a chain that only has a FlattenMapper as the one element
for fm in [FlattenMapper(space='voxel'),
ChainMapper([FlattenMapper(space='voxel'),
StaticFeatureSelection(slice(None))])]:
# not working if untrained
assert_raises(RuntimeError,
fm.forward1,
np.arange(np.sum(samples_shape) + 1))
fm.train(data)
ok_(isinstance(fm.forward(data), myarray))
ok_(isinstance(fm.forward1(data[2]), myarray))
assert_array_equal(fm.forward(data), target)
assert_array_equal(fm.forward1(data[2]), target[2])
assert_raises(ValueError, fm.forward, np.arange(4))
# all of that leaves that data unmodified
assert_array_equal(data, pristinedata)
# reverse mapping
ok_(isinstance(fm.reverse(target), myarray))
ok_(isinstance(fm.reverse1(target[0]), myarray))
ok_(isinstance(fm.reverse(target[1:2]), myarray))
assert_array_equal(fm.reverse(target), data)
assert_array_equal(fm.reverse1(target[0]), data[0])
assert_array_equal(fm.reverse(target[1:2]), data[1:2])
assert_raises(ValueError, fm.reverse, np.arange(14))
# check one dimensional data, treated as scalar samples
oned = np.arange(5)
fm.train(Dataset(oned))
# needs 2D
assert_raises(ValueError, fm.forward, oned)
# doesn't match mapper, since Dataset turns `oned` into (5,1)
assert_raises(ValueError, fm.forward, oned)
assert_equal(Dataset(oned).nfeatures, 1)
# try dataset mode, with some feature attribute
fattr = np.arange(np.prod(samples_shape)).reshape(samples_shape)
ds = Dataset(data, fa={'awesome': fattr.copy()})
assert_equal(ds.samples.shape, data_shape)
fm.train(ds)
dsflat = fm.forward(ds)
ok_(isinstance(dsflat, Dataset))
ok_(isinstance(dsflat.samples, myarray))
assert_array_equal(dsflat.samples, target)
assert_array_equal(dsflat.fa.awesome, np.arange(np.prod(samples_shape)))
assert_true(isinstance(dsflat.fa['awesome'], ArrayCollectable))
# test index creation
assert_array_equal(index_target, dsflat.fa.voxel)
# and back
revds = fm.reverse(dsflat)
ok_(isinstance(revds, Dataset))
ok_(isinstance(revds.samples, myarray))
assert_array_equal(revds.samples, data)
assert_array_equal(revds.fa.awesome, fattr)
assert_true(isinstance(revds.fa['awesome'], ArrayCollectable))
assert_false('voxel' in revds.fa)
def test_zcore_repr():
# Just basic test if everything is sane... no proper comparison
for m in (ZScoreMapper(chunks_attr=None), ZScoreMapper(params=(3, 1)),
ZScoreMapper()):
mr = eval(repr(m))
ok_(isinstance(mr, ZScoreMapper))
def cmp_res(res1, res2):
comp = [x == y for x, y in zip(res1, res2)]
ok_(np.all(comp))
def test_sphere_scaled():
s1 = ne.Sphere(3)
s = ne.Sphere(3, element_sizes=(1, 1))
# Should give exactly the same results since element_sizes are 1s
for p in ((0, 0), (-23, 1)):
assert_array_equal(s1(p), s(p))
ok_(len(s(p)) == len(set(s(p))))
# Raise exception if query dimensionality does not match element_sizes
assert_raises(ValueError, s, (1, ))
s = ne.Sphere(3, element_sizes=(1.5, 2))
assert_array_equal(s((0, 0)), [(-2, 0), (-1, -1), (-1, 0), (-1, 1),
(0, -1), (0, 0), (0, 1), (1, -1), (1, 0),
(1, 1), (2, 0)])
s = ne.Sphere(1.5, element_sizes=(1.5, 1.5, 1.5))
res = s((0, 0, 0))
ok_(np.all([np.sqrt(np.sum(np.array(x)**2)) <= 1.5 for x in res]))
ok_(len(res) == 7)
# all neighbors so no more than 1 voxel away -- just a cube, for
# some "sphere" effect radius had to be 3.0 ;)
td = np.sqrt(3 * 1.5**2)
s = ne.Sphere(td, element_sizes=(1.5, 1.5, 1.5))
res = s((0, 0, 0))
ok_(np.all([np.sqrt(np.sum(np.array(x)**2)) <= td for x in res]))
ok_(np.all([np.sum(np.abs(x) > 1) == 0 for x in res]))
ok_(len(res) == 27)
def test_sphere_scaled():
s1 = ne.Sphere(3)
s = ne.Sphere(3, element_sizes=(1, 1))
# Should give exactly the same results since element_sizes are 1s
for p in ((0, 0), (-23, 1)):
assert_array_equal(s1(p), s(p))
ok_(len(s(p)) == len(set(s(p))))
# Raise exception if query dimensionality does not match element_sizes
assert_raises(ValueError, s, (1,))
s = ne.Sphere(3, element_sizes=(1.5, 2))
assert_array_equal(s((0, 0)),
[(-2, 0), (-1, -1), (-1, 0), (-1, 1),
(0, -1), (0, 0), (0, 1),
(1, -1), (1, 0), (1, 1), (2, 0)])
s = ne.Sphere(1.5, element_sizes=(1.5, 1.5, 1.5))
res = s((0, 0, 0))
ok_(np.all([np.sqrt(np.sum(np.array(x)**2)) <= 1.5 for x in res]))
ok_(len(res) == 7)
# all neighbors so no more than 1 voxel away -- just a cube, for
# some "sphere" effect radius had to be 3.0 ;)
td = np.sqrt(3*1.5**2)
s = ne.Sphere(td, element_sizes=(1.5, 1.5, 1.5))
res = s((0, 0, 0))
ok_(np.all([np.sqrt(np.sum(np.array(x)**2)) <= td for x in res]))
ok_(np.all([np.sum(np.abs(x) > 1) == 0 for x in res]))
ok_(len(res) == 27)
def test_sphere():
# test sphere initialization
s = ne.Sphere(1)
center0 = (0, 0, 0)
center1 = (1, 1, 1)
assert_equal(len(s(center0)), 7)
target = array([
array([-1, 0, 0]),
array([0, -1, 0]),
array([0, 0, -1]),
array([0, 0, 0]),
array([0, 0, 1]),
array([0, 1, 0]),
array([1, 0, 0])
])
# test of internals -- no recomputation of increments should be done
prev_increments = s._increments
assert_array_equal(s(center0), target)
ok_(prev_increments is s._increments)
# query lower dimensionality
_ = s((0, 0))
ok_(not prev_increments is s._increments)
# test Sphere call
target = [
array([0, 1, 1]),
array([1, 0, 1]),
array([1, 1, 0]),
array([1, 1, 1]),
array([1, 1, 2]),
array([1, 2, 1]),
array([2, 1, 1])
]
res = s(center1)
assert_array_equal(array(res), target)
# They all should be tuples
ok_(np.all([isinstance(x, tuple) for x in res]))
# test for larger diameter
s = ne.Sphere(4)
assert_equal(len(s(center1)), 257)
# test extent keyword
#s = ne.Sphere(4,extent=(1,1,1))
#assert_array_equal(array(s((0,0,0))), array([[0,0,0]]))
# test Errors during initialisation and call
#assert_raises(ValueError, ne.Sphere, 2)
#assert_raises(ValueError, ne.Sphere, 1.0)
# no longer extent available
assert_raises(TypeError, ne.Sphere, 1, extent=(1))
assert_raises(TypeError, ne.Sphere, 1, extent=(1.0, 1.0, 1.0))
s = ne.Sphere(1)
#assert_raises(ValueError, s, (1))
if __debug__:
# No float coordinates allowed for now...
# XXX might like to change that ;)
#
assert_raises(ValueError, s, (1.0, 1.0, 1.0))
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)
# 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]))
# And just a smoke test for warnings reporting whenever # of
# samples per chunk is low.
# on 1 sample per chunk
zds1 = ZScoreMapper(chunks_attr='chunks', auto_train=True)(ds[[0, -1]])
ok_(np.all(zds1.samples == 0)) # they all should be 0
# on 2 samples per chunk
zds2 = ZScoreMapper(chunks_attr='chunks',
auto_train=True)(ds[[0, 1, -10, -1]])
assert_array_equal(np.unique(zds2.samples),
[-1., 1]) # they all should be -1 or 1
# on 3 samples per chunk -- different warning
ZScoreMapper(chunks_attr='chunks',
auto_train=True)(ds[[0, 1, 2, -3, -2, -1]])
# test if std provided as a list not as an array is handled
# properly -- should zscore all features (not just first/none
# as it was before)
ds = dataset_wizard(np.arange(32).reshape((8, -1)),
targets=range(8),
chunks=[0] * 8)
means = [0, 1, -10, 10]
std0 = np.std(ds[:, 0]) # std deviation of first one
stds = [std0, 10, .1, 1]
zm = ZScoreMapper(params=(means, stds), auto_train=True)
dsz = zm(ds)
assert_array_almost_equal(
(np.mean(ds, axis=0) - np.asanyarray(means)) / np.array(stds),
np.mean(dsz, axis=0))
assert_array_almost_equal(
np.std(ds, axis=0) / np.array(stds), np.std(dsz, axis=0))
def test_gnbsearchlight_permutations():
import mvpa2
from mvpa2.base.node import ChainNode
from mvpa2.clfs.gnb import GNB
from mvpa2.generators.base import Repeater
from mvpa2.generators.partition import NFoldPartitioner, OddEvenPartitioner
#import mvpa2.generators.permutation
#reload(mvpa2.generators.permutation)
from mvpa2.generators.permutation import AttributePermutator
from mvpa2.testing.datasets import datasets
from mvpa2.measures.base import CrossValidation
from mvpa2.measures.gnbsearchlight import sphere_gnbsearchlight
from mvpa2.measures.searchlight import sphere_searchlight
from mvpa2.mappers.fx import mean_sample
from mvpa2.misc.errorfx import mean_mismatch_error
from mvpa2.clfs.stats import MCNullDist
from mvpa2.testing.tools import assert_raises, ok_, assert_array_less
# mvpa2.debug.active = ['APERM', 'SLC'] #, 'REPM']
# mvpa2.debug.metrics += ['pid']
count = 10
nproc = 1 + int(mvpa2.externals.exists('pprocess'))
ds = datasets['3dsmall'].copy()
ds.fa['voxel_indices'] = ds.fa.myspace
slkwargs = dict(radius=3, space='voxel_indices', enable_ca=['roi_sizes'],
center_ids=[1, 10, 70, 100])
mvpa2.seed(mvpa2._random_seed)
clf = GNB()
splt = NFoldPartitioner(cvtype=2, attr='chunks')
repeater = Repeater(count=count)
permutator = AttributePermutator('targets', limit={'partitions': 1}, count=1)
null_sl = sphere_gnbsearchlight(clf, ChainNode([splt, permutator], space=splt.get_space()),
postproc=mean_sample(), errorfx=mean_mismatch_error,
**slkwargs)
distr_est = MCNullDist(repeater, tail='left', measure=null_sl,
enable_ca=['dist_samples'])
sl = sphere_gnbsearchlight(clf, splt,
reuse_neighbors=True,
null_dist=distr_est, postproc=mean_sample(),
errorfx=mean_mismatch_error,
**slkwargs)
if __debug__: # assert is done only without -O mode
assert_raises(NotImplementedError, sl, ds)
# "ad-hoc searchlights can't handle yet varying targets across partitions"
if False:
# after above limitation is removed -- enable
sl_map = sl(ds)
sl_null_prob = sl.ca.null_prob.samples.copy()
mvpa2.seed(mvpa2._random_seed)
### 'normal' Searchlight
clf = GNB()
splt = NFoldPartitioner(cvtype=2, attr='chunks')
repeater = Repeater(count=count)
permutator = AttributePermutator('targets', limit={'partitions': 1}, count=1)
# rng=np.random.RandomState(0)) # to trigger failure since the same np.random state
# would be reused across all pprocesses
null_cv = CrossValidation(clf, ChainNode([splt, permutator], space=splt.get_space()),
postproc=mean_sample())
null_sl_normal = sphere_searchlight(null_cv, nproc=nproc, **slkwargs)
distr_est_normal = MCNullDist(repeater, tail='left', measure=null_sl_normal,
enable_ca=['dist_samples'])
cv = CrossValidation(clf, splt, errorfx=mean_mismatch_error,
enable_ca=['stats'], postproc=mean_sample() )
sl = sphere_searchlight(cv, nproc=nproc, null_dist=distr_est_normal, **slkwargs)
sl_map_normal = sl(ds)
sl_null_prob_normal = sl.ca.null_prob.samples.copy()
# For every feature -- we should get some variance in estimates In
# case of failure they are all really close to each other (up to
# numerical precision), so variance will be close to 0
assert_array_less(-np.var(distr_est_normal.ca.dist_samples.samples[0],
axis=1), -1e-5)
for s in distr_est_normal.ca.dist_samples.samples[0]:
ok_(len(np.unique(s)) > 1)
def test_multiclass_pairs_svm_searchlight():
from mvpa2.measures.searchlight import sphere_searchlight
import mvpa2.clfs.meta
#reload(mvpa2.clfs.meta)
from mvpa2.clfs.meta import MulticlassClassifier
from mvpa2.datasets import Dataset
from mvpa2.clfs.svm import LinearCSVMC
#import mvpa2.testing.datasets
#reload(mvpa2.testing.datasets)
from mvpa2.testing.datasets import datasets
from mvpa2.generators.partition import NFoldPartitioner, OddEvenPartitioner
from mvpa2.measures.base import CrossValidation
from mvpa2.testing import ok_, assert_equal, assert_array_equal
from mvpa2.sandbox.multiclass import get_pairwise_accuracies
# Some parameters used in the test below
nproc = 1 + int(mvpa2.externals.exists('pprocess'))
ntargets = 4 # number of targets
npairs = ntargets*(ntargets-1)/2
center_ids = [35, 55, 1]
ds = datasets['3dsmall'].copy()
# redefine C,T so we have a multiclass task
nsamples = len(ds)
ds.sa.targets = range(ntargets) * (nsamples//ntargets)
ds.sa.chunks = np.arange(nsamples) // ntargets
# and add some obvious signal where it is due
ds.samples[:, 55] += 15*ds.sa.targets # for all 4 targets
ds.samples[:, 35] += 15*(ds.sa.targets % 2) # so we have conflicting labels
# while 35 would still be just for 2 categories which would conflict
mclf = MulticlassClassifier(LinearCSVMC(),
pass_attr=['sa.chunks', 'ca.raw_predictions_ds'],
enable_ca=['raw_predictions_ds'])
label_pairs = mclf._get_binary_pairs(ds)
def place_sa_as_samples(ds):
# add a degenerate dimension for the hstacking in the searchlight
ds.samples = ds.sa.raw_predictions_ds[:, None]
ds.sa.pop('raw_predictions_ds') # no need to drag the copy
return ds
mcv = CrossValidation(mclf, OddEvenPartitioner(), errorfx=None,
postproc=place_sa_as_samples)
sl = sphere_searchlight(mcv, nproc=nproc, radius=2, space='myspace',
center_ids=center_ids)
slmap = sl(ds)
ok_('chunks' in slmap.sa)
ok_('cvfolds' in slmap.sa)
ok_('targets' in slmap.sa)
# so for each SL we got all pairwise tests
assert_equal(slmap.shape, (nsamples, len(center_ids), npairs))
assert_array_equal(np.unique(slmap.sa.cvfolds), [0, 1])
# Verify that we got right labels in each 'pair'
# all searchlights should have the same set of labels for a given
# pair of targets
label_pairs_ = np.apply_along_axis(
np.unique, 0,
## reshape slmap so we have only simple pairs in the columns
np.reshape(slmap, (-1, npairs))).T
# need to prep that list of pairs obtained from MulticlassClassifier
# and since it is 1-vs-1, they all should be just pairs of lists of
# 1 element so should work
assert_equal(len(label_pairs_), npairs)
assert_array_equal(np.squeeze(np.array(label_pairs)), label_pairs_)
assert_equal(label_pairs_.shape, (npairs, 2)) # for this particular case
out = get_pairwise_accuracies(slmap)
out123 = get_pairwise_accuracies(slmap, select=[1, 2, 3])
assert_array_equal(np.unique(out123.T), np.arange(1, 4)) # so we got at least correct targets
# test that we extracted correct accuracies
# First 3 in out.T should have category 0, so skip them and compare otherwise
assert_array_equal(out.samples[3:], out123.samples)
ok_(np.all(out.samples[:, 1] == 1.), "This was with super-strong result")
def cmp_res(res1, res2):
comp = [x == y for x, y in zip(res1, res2)]
ok_(np.all(comp))