def test_hpal_svd_combo(self):
# get seed dataset
ds4l = datasets['uni4large']
ds_orig = ds4l[:, ds4l.a.nonbogus_features]
# XXX Is this SVD mapping required?
svm = SVDMapper()
svm.train(ds_orig)
ds_svs = svm.forward(ds_orig)
ds_orig.samples = ds_svs.samples
nf_true = ds_orig.nfeatures
n = 4 # # of datasets to generate
# Adding non-shared dimensions for each subject
dss_rotated = [[]] * n
for i in range(n):
dss_rotated[i] = hstack(
(ds_orig, ds4l[:, ds4l.a.bogus_features[i * 4:i * 4 + 4]]))
# rotate data
nf = dss_rotated[0].nfeatures
dss_rotated = [
random_affine_transformation(dss_rotated[i]) for i in xrange(n)
]
# Test if it is close to doing hpal+SVD in sequence outside hpal
# First, as we do in sequence outside hpal
ha = Hyperalignment()
mappers_orig = ha(dss_rotated)
dss_back = [
m.forward(ds_) for m, ds_ in zip(mappers_orig, dss_rotated)
]
dss_mean = np.mean([sd.samples for sd in dss_back], axis=0)
svm = SVDMapper()
svm.train(dss_mean)
dss_sv = [svm.forward(sd) for sd in dss_back]
# Test for SVD dimensionality reduction even with 2 training subjects
for output_dim in [1, 4]:
ha = Hyperalignment(output_dim=output_dim)
ha.train(dss_rotated[:2])
mappers = ha(dss_rotated)
dss_back = [m.forward(ds_) for m, ds_ in zip(mappers, dss_rotated)]
for sd in dss_back:
assert (sd.nfeatures == output_dim)
# Check if combined hpal+SVD works as expected
sv_corrs = []
for sd1, sd2 in zip(dss_sv, dss_back):
ndcs = np.diag(np.corrcoef(sd1.samples.T, sd2.samples.T)[nf:, :nf],
k=0)
sv_corrs.append(ndcs)
self.assertTrue(
np.all(np.abs(np.array(sv_corrs)) >= 0.95),
msg="Hyperalignment with dimensionality reduction should have "
"reconstructed SVD dataset. Got correlations %s." % sv_corrs)
# Check if it recovers original SVs
sv_corrs_orig = []
for sd in dss_back:
ndcs = np.diag(np.corrcoef(sd.samples.T,
ds_orig.samples.T)[nf_true:, :nf_true],
k=0)
sv_corrs_orig.append(ndcs)
self.assertTrue(np.all(np.abs(np.array(sv_corrs_orig)) >= 0.9),
msg="Expected original dimensions after "
"SVD. Got correlations %s." % sv_corrs_orig)
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_simple_svd(self):
pm = SVDMapper()
# train SVD
pm.train(self.ndlin)
self.assertEqual(pm.proj.shape, (20, 20))
# now project data into PCA space
p = pm.forward(self.ndlin)
# only first eigenvalue significant
self.assertTrue(pm.sv[:1] > 1.0)
self.assertTrue((pm.sv[1:] < 0.0001).all())
# only variance of first component significant
var = p.var(axis=0)
# test that only one component has variance
self.assertTrue(var[:1] > 1.0)
self.assertTrue((var[1:] < 0.0001).all())
# check that the mapped data can be fully recovered by 'reverse()'
pr = pm.reverse(p)
self.assertEqual(pr.shape, (40, 20))
self.assertTrue(np.abs(pm.reverse(p) - self.ndlin).sum() < 0.0001)
def _get_hypesvs(self, sl_connectomes, local_common_model=None):
'''
Hyperalign connectomes and return mapppers
and trained SVDMapper of common space.
Parameters
----------
sl_connectomes: a list of connectomes to hyperalign
local_common_model: a reference common model to be used.
Returns
-------
a tuple (sl_hmappers, svm, local_common_model)
sl_hmappers: a list of mappers corresponding to input list in that order.
svm: a svm mapper based on the input data. if given a common model, this is None.
local_common_model: If local_common_model is provided as input, this will be None.
Otherwise, local_common_model will be computed here and returned.
'''
# TODO Should we z-score sl_connectomes?
return_model = False if self.params.save_model is None else True
if local_common_model is not None:
ha = Hyperalignment(level2_niter=0)
if not is_datasetlike(local_common_model):
local_common_model = Dataset(samples=local_common_model)
ha.train([local_common_model])
sl_hmappers = ha(sl_connectomes)
return sl_hmappers, None, None
ha = Hyperalignment()
sl_hmappers = ha(sl_connectomes)
sl_connectomes = [
slhm.forward(slc) for slhm, slc in zip(sl_hmappers, sl_connectomes)
]
_ = [zscore(slc, chunks_attr=None) for slc in sl_connectomes]
sl_connectomes = np.dstack(sl_connectomes).mean(axis=-1)
svm = SVDMapper(force_train=True)
svm.train(sl_connectomes)
if return_model:
local_common_model = svm.forward(sl_connectomes)
else:
local_common_model = None
return sl_hmappers, svm, local_common_model
def test_simple_svd(self):
pm = SVDMapper()
# train SVD
pm.train(self.ndlin)
self.failUnlessEqual(pm.proj.shape, (20, 20))
# now project data into PCA space
p = pm.forward(self.ndlin)
# only first eigenvalue significant
self.failUnless(pm.sv[:1] > 1.0)
self.failUnless((pm.sv[1:] < 0.0001).all())
# only variance of first component significant
var = p.var(axis=0)
# test that only one component has variance
self.failUnless(var[:1] > 1.0)
self.failUnless((var[1:] < 0.0001).all())
# check that the mapped data can be fully recovered by 'reverse()'
pr = pm.reverse(p)
self.failUnlessEqual(pr.shape, (40,20))
self.failUnless(np.abs(pm.reverse(p) - self.ndlin).sum() < 0.0001)
def _get_hypesvs(self, sl_connectomes, local_common_model=None):
'''
Hyperalign connectomes and return mapppers
and trained SVDMapper of common space.
Parameters
----------
sl_connectomes: a list of connectomes to hyperalign
local_common_model: a reference common model to be used.
Returns
-------
a tuple (sl_hmappers, svm, local_common_model)
sl_hmappers: a list of mappers corresponding to input list in that order.
svm: a svm mapper based on the input data. if given a common model, this is None.
local_common_model: If local_common_model is provided as input, this will be None.
Otherwise, local_common_model will be computed here and returned.
'''
# TODO Should we z-score sl_connectomes?
return_model = False if self.params.save_model is None else True
if local_common_model is not None:
ha = Hyperalignment(level2_niter=0)
if not is_datasetlike(local_common_model):
local_common_model = Dataset(samples=local_common_model)
ha.train([local_common_model])
sl_hmappers = ha(sl_connectomes)
return sl_hmappers, None, None
ha = Hyperalignment()
sl_hmappers = ha(sl_connectomes)
sl_connectomes = [slhm.forward(slc) for slhm, slc in zip(sl_hmappers, sl_connectomes)]
_ = [zscore(slc, chunks_attr=None) for slc in sl_connectomes]
sl_connectomes = np.dstack(sl_connectomes).mean(axis=-1)
svm = SVDMapper(force_train=True)
svm.train(sl_connectomes)
if return_model:
local_common_model = svm.forward(sl_connectomes)
else:
local_common_model = None
return sl_hmappers, svm, local_common_model
def test_more_svd(self):
pm = SVDMapper()
# train SVD
pm.train(self.largefeat)
# mixing matrix cannot be square
self.assertEqual(pm.proj.shape, (40, 10))
# only first singular value significant
self.assertTrue(pm.sv[:1] > 10)
self.assertTrue((pm.sv[1:] < 10).all())
# now project data into SVD space
p = pm.forward(self.largefeat)
# only variance of first component significant
var = p.var(axis=0)
# test that only one component has variance
self.assertTrue(var[:1] > 1.0)
self.assertTrue((var[1:] < 0.0001).all())
# check that the mapped data can be fully recovered by 'reverse()'
rp = pm.reverse(p)
self.assertEqual(rp.shape, self.largefeat.shape)
self.assertTrue((np.round(rp) == self.largefeat).all())
# copy mapper
pm2 = deepcopy(pm)
# now make new random data and do forward->reverse check
data = np.random.normal(size=(98, 40))
data_f = pm.forward(data)
self.assertEqual(data_f.shape, (98, 10))
data_r = pm.reverse(data_f)
self.assertEqual(data_r.shape, (98, 40))
def test_more_svd(self):
pm = SVDMapper()
# train SVD
pm.train(self.largefeat)
# mixing matrix cannot be square
self.failUnlessEqual(pm.proj.shape, (40, 10))
# only first singular value significant
self.failUnless(pm.sv[:1] > 10)
self.failUnless((pm.sv[1:] < 10).all())
# now project data into SVD space
p = pm.forward(self.largefeat)
# only variance of first component significant
var = p.var(axis=0)
# test that only one component has variance
self.failUnless(var[:1] > 1.0)
self.failUnless((var[1:] < 0.0001).all())
# check that the mapped data can be fully recovered by 'reverse()'
rp = pm.reverse(p)
self.failUnlessEqual(rp.shape, self.largefeat.shape)
self.failUnless((np.round(rp) == self.largefeat).all())
# copy mapper
pm2 = deepcopy(pm)
# now make new random data and do forward->reverse check
data = np.random.normal(size=(98,40))
data_f = pm.forward(data)
self.failUnlessEqual(data_f.shape, (98,10))
data_r = pm.reverse(data_f)
self.failUnlessEqual(data_r.shape, (98,40))
def train(self, datasets):
"""Derive a common feature space from a series of datasets.
Parameters
----------
datasets : sequence of datasets
Returns
-------
A list of trained Mappers matching the number of input datasets.
"""
params = self.params # for quicker access ;)
ca = self.ca
# Check to make sure we get a list of datasets as input.
if not isinstance(datasets, (list, tuple, np.ndarray)):
raise TypeError("Input datasets should be a sequence "
"(of type list, tuple, or ndarray) of datasets.")
ndatasets = len(datasets)
nfeatures = [ds.nfeatures for ds in datasets]
alpha = params.alpha
residuals = None
if ca['training_residual_errors'].enabled:
residuals = np.zeros((1 + params.level2_niter, ndatasets))
ca.training_residual_errors = Dataset(
samples=residuals,
sa={
'levels':
['1'] + ['2:%i' % i for i in xrange(params.level2_niter)]
})
if __debug__:
debug('HPAL',
"Hyperalignment %s for %i datasets" % (self, ndatasets))
if params.ref_ds is None:
ref_ds = np.argmax(nfeatures)
else:
ref_ds = params.ref_ds
# Making sure that ref_ds is within range.
#Parameter() already checks for it being a non-negative integer
if ref_ds >= ndatasets:
raise ValueError, "Requested reference dataset %i is out of " \
"bounds. We have only %i datasets provided" \
% (ref_ds, ndatasets)
ca.chosen_ref_ds = ref_ds
# zscore all data sets
# ds = [ zscore(ds, chunks_attr=None) for ds in datasets]
# TODO since we are doing in-place zscoring create deep copies
# of the datasets with pruned targets and shallow copies of
# the collections (if they would come needed in the transformation)
# TODO: handle floats and non-floats differently to prevent
# waste of memory if there is no need (e.g. no z-scoring)
#otargets = [ds.sa.targets for ds in datasets]
datasets = [ds.copy(deep=False) for ds in datasets]
#datasets = [Dataset(ds.samples.astype(float), sa={'targets': [None] * len(ds)})
#datasets = [Dataset(ds.samples, sa={'targets': [None] * len(ds)})
# for ds in datasets]
if params.zscore_all:
if __debug__:
debug('HPAL', "Z-scoring all datasets")
for ids in xrange(len(datasets)):
zmapper = ZScoreMapper(chunks_attr=None)
zmapper.train(datasets[ids])
datasets[ids] = zmapper.forward(datasets[ids])
if alpha < 1:
datasets, wmappers = self._regularize(datasets, alpha)
# initial common space is the reference dataset
commonspace = datasets[ref_ds].samples
# the reference dataset might have been zscored already, don't do it
# twice
if params.zscore_common and not params.zscore_all:
if __debug__:
debug(
'HPAL_', "Creating copy of a commonspace and assuring "
"it is of a floating type")
commonspace = commonspace.astype(float)
zscore(commonspace, chunks_attr=None)
# If there is only one dataset in training phase, there is nothing to be done
# just use that data as the common space
if len(datasets) < 2:
self.commonspace = commonspace
else:
# create a mapper per dataset
# might prefer some other way to initialize... later
mappers = [deepcopy(params.alignment) for ds in datasets]
#
# Level 1 -- initial projection
#
lvl1_projdata = self._level1(datasets, commonspace, ref_ds,
mappers, residuals)
#
# Level 2 -- might iterate multiple times
#
# this is the final common space
self.commonspace = self._level2(datasets, lvl1_projdata, mappers,
residuals)
if params.output_dim is not None:
mappers = self._level3(datasets)
self._svd_mapper = SVDMapper()
self._svd_mapper.train(self._map_and_mean(datasets, mappers))
self._svd_mapper = StaticProjectionMapper(
proj=self._svd_mapper.proj[:, :params.output_dim])
from mvpa2.mappers.mdp_adaptor import ICAMapper, PCAMapper
from mvpa2 import cfg
center = [10, 20]
axis_range = 7
##REF: Name was automagically refactored
def plot_proj_dir(p):
pl.plot([0, p[0, 0]], [0, p[0, 1]], linewidth=3, hold=True, color='y')
pl.plot([0, p[1, 0]], [0, p[1, 1]], linewidth=3, hold=True, color='k')
mappers = {
'PCA': PCAMapper(),
'SVD': SVDMapper(),
'ICA': ICAMapper(alg='CuBICA'),
}
datasets = [
noisy_2d_fx(100, lambda x: x, [lambda x: x], center, noise_std=0.5),
noisy_2d_fx(50,
lambda x: x, [lambda x: x, lambda x: -x],
center,
noise_std=0.5),
noisy_2d_fx(50,
lambda x: x, [lambda x: x, lambda x: 0],
center,
noise_std=0.5),
]
ndatasets = len(datasets)
def test_hpal_svd_combo(self):
# get seed dataset
ds4l = datasets['uni4large']
ds_orig = ds4l[:, ds4l.a.nonbogus_features]
# XXX Is this SVD mapping required?
svm = SVDMapper()
svm.train(ds_orig)
ds_svs = svm.forward(ds_orig)
ds_orig.samples = ds_svs.samples
nf_true = ds_orig.nfeatures
n = 4 # # of datasets to generate
# Adding non-shared dimensions for each subject
dss_rotated = [[]]*n
for i in range(n):
dss_rotated[i] = hstack(
(ds_orig, ds4l[:, ds4l.a.bogus_features[i * 4: i * 4 + 4]]))
# rotate data
nf = dss_rotated[0].nfeatures
dss_rotated = [random_affine_transformation(dss_rotated[i])
for i in xrange(n)]
# Test if it is close to doing hpal+SVD in sequence outside hpal
# First, as we do in sequence outside hpal
ha = Hyperalignment()
mappers_orig = ha(dss_rotated)
dss_back = [m.forward(ds_)
for m, ds_ in zip(mappers_orig, dss_rotated)]
dss_mean = np.mean([sd.samples for sd in dss_back], axis=0)
svm = SVDMapper()
svm.train(dss_mean)
dss_sv = [svm.forward(sd) for sd in dss_back]
# Test for SVD dimensionality reduction even with 2 training subjects
for output_dim in [1, 4]:
ha = Hyperalignment(output_dim=output_dim)
ha.train(dss_rotated[:2])
mappers = ha(dss_rotated)
dss_back = [m.forward(ds_)
for m, ds_ in zip(mappers, dss_rotated)]
for sd in dss_back:
assert (sd.nfeatures == output_dim)
# Check if combined hpal+SVD works as expected
sv_corrs = []
for sd1, sd2 in zip(dss_sv, dss_back):
ndcs = np.diag(np.corrcoef(sd1.samples.T, sd2.samples.T)[nf:, :nf],
k=0)
sv_corrs.append(ndcs)
self.assertTrue(
np.all(np.abs(np.array(sv_corrs)) >= 0.95),
msg="Hyperalignment with dimensionality reduction should have "
"reconstructed SVD dataset. Got correlations %s."
% sv_corrs)
# Check if it recovers original SVs
sv_corrs_orig = []
for sd in dss_back:
ndcs = np.diag(
np.corrcoef(sd.samples.T, ds_orig.samples.T)[nf_true:, :nf_true],
k=0)
sv_corrs_orig.append(ndcs)
self.assertTrue(
np.all(np.abs(np.array(sv_corrs_orig)) >= 0.9),
msg="Expected original dimensions after "
"SVD. Got correlations %s."
% sv_corrs_orig)
