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 __call__(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.
"""
if self.commonspace is None:
self.train(datasets)
else:
# 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.")
# place datasets into a copy of the list since items
# will be reassigned
datasets = list(datasets)
params = self.params # for quicker access ;)
alpha = params.alpha # for letting me be lazy ;)
if params.zscore_all:
if __debug__:
debug('HPAL', "Z-scoring all datasets")
# zscore them once while storing corresponding ZScoreMapper's
# so we can assemble a comprehensive mapper at the end
# (together with procrustes)
zmappers = []
for ids in xrange(len(datasets)):
zmapper = ZScoreMapper(chunks_attr=None)
zmappers.append(zmapper)
zmapper.train(datasets[ids])
datasets[ids] = zmapper.forward(datasets[ids])
if alpha < 1:
datasets, wmappers = self._regularize(datasets, alpha)
#
# Level 3 -- final, from-scratch, alignment to final common space
#
mappers = self._level3(datasets)
# return trained mappers for projection from all datasets into the
# common space
if params.zscore_all:
# We need to construct new mappers which would chain
# zscore and then final transformation
if params.alpha < 1:
mappers = [ChainMapper([zm, wm, m]) for zm, wm, m in zip(zmappers, wmappers, mappers)]
else:
mappers = [ChainMapper([zm, m]) for zm, m in zip(zmappers, mappers)]
elif params.alpha < 1:
mappers = [ChainMapper([wm, m]) for wm, m in zip(wmappers, mappers)]
if params.output_dim is not None:
mappers = [ChainMapper([m, self._svd_mapper]) for m in mappers]
return mappers
class FeatureWiseNormalizer(Transformer):
def __init__(self, chunks_attr='chunks', param_est=None, **kwargs):
self.node = ZScoreMapper(chunks_attr=chunks_attr, param_est=param_est)
Transformer.__init__(self, name='feature_normalizer', **kwargs)
def transform(self, ds):
logger.info('Dataset preprocessing: Normalization feature-wise...')
self.node.train(ds)
return self.node.forward(ds)
def __call__(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.
"""
if self.commonspace is None:
self.train(datasets)
# place datasets into a copy of the list since items
# will be reassigned
datasets = list(datasets)
params = self.params # for quicker access ;)
alpha = params.alpha # for letting me be lazy ;)
if params.zscore_all:
if __debug__:
debug('HPAL', "Z-scoring all datasets")
# zscore them once while storing corresponding ZScoreMapper's
# so we can assemble a comprehensive mapper at the end
# (together with procrustes)
zmappers = []
for ids in xrange(len(datasets)):
zmapper = ZScoreMapper(chunks_attr=None)
zmappers.append(zmapper)
zmapper.train(datasets[ids])
datasets[ids] = zmapper.forward(datasets[ids])
if alpha < 1:
datasets, wmappers = self._regularize(datasets, alpha)
#
# Level 3 -- final, from-scratch, alignment to final common space
#
mappers = self._level3(datasets)
# return trained mappers for projection from all datasets into the
# common space
if params.zscore_all:
# We need to construct new mappers which would chain
# zscore and then final transformation
if params.alpha < 1:
return [ChainMapper([zm, wm, m]) for zm, wm, m in zip(zmappers, wmappers, mappers)]
else:
return [ChainMapper([zm, m]) for zm, m in zip(zmappers, mappers)]
else:
if params.alpha < 1:
return [ChainMapper([wm, m]) for wm, m in zip(wmappers, mappers)]
else:
return mappers
class FeatureWiseNormalizer(Transformer):
def __init__(self, chunks_attr='chunks', param_est=None, **kwargs):
self.node = ZScoreMapper(chunks_attr=chunks_attr, param_est=param_est)
Transformer.__init__(self, name='feature_normalizer', **kwargs)
def transform(self, ds):
logger.info('Dataset preprocessing: Normalization feature-wise...')
self.node.train(ds)
return self.node.forward(ds)
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 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])
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
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
if ref_ds < 0 and ref_ds >= ndatasets:
raise ValueError, "Requested reference dataset %i is out of " \
"bounds. We have only %i datasets provided" \
% (ref_ds, ndatasets)
ca.choosen_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)
# 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)
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 __call__(self, datasets):
"""Estimate mappers for each dataset
Parameters
----------
datasets : list or tuple of datasets
Returns
-------
A list of trained Mappers of the same length as datasets
"""
params = self.params # for quicker access ;)
ca = self.ca
ndatasets = len(datasets)
nfeatures = [ds.nfeatures for ds in datasets]
residuals = None
if ca['residual_errors'].enabled:
residuals = np.zeros((2 + params.level2_niter, ndatasets))
ca.residual_errors = Dataset(
samples = residuals,
sa = {'levels' :
['1'] +
['2:%i' % i for i in xrange(params.level2_niter)] +
['3']})
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
if ref_ds < 0 and ref_ds >= ndatasets:
raise ValueError, "Requested reference dataset %i is out of " \
"bounds. We have only %i datasets provided" \
% (ref_ds, ndatasets)
ca.choosen_ref_ds = ref_ds
# might prefer some other way to initialize... later
mappers = [deepcopy(params.alignment) for ds in datasets]
# zscore all data sets
# ds = [ zscore(ds, chunks_attr=None) for ds in datasets]
# Level 1 (first)
# 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")
# zscore them once while storing corresponding ZScoreMapper's
zmappers = []
for ids in xrange(len(datasets)):
zmapper = ZScoreMapper(chunks_attr=None)
zmappers.append(zmapper)
zmapper.train(datasets[ids])
datasets[ids] = zmapper.forward(datasets[ids])
commonspace = np.asanyarray(datasets[ref_ds])
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)
data_mapped = [np.asanyarray(ds) for ds in datasets]
#zscore(data_mapped[ref_ds],chunks_attr=None)
for i, (m, ds_new) in enumerate(zip(mappers, datasets)):
if __debug__:
debug('HPAL_', "Level 1: ds #%i" % i)
if i == ref_ds:
continue
#ds_new = ds.copy()
#zscore(ds_new, chunks_attr=None);
ds_new.targets = commonspace
m.train(ds_new)
ds_ = m.forward(np.asanyarray(ds_new))
if params.zscore_common:
zscore(ds_, chunks_attr=None)
data_mapped[i] = ds_
if residuals is not None:
residuals[0, i] = np.linalg.norm(ds_ - commonspace)
## if ds_mapped == []:
## ds_mapped = [zscore(m.forward(d), chunks_attr=None)]
## else:
## ds_mapped += [zscore(m.forward(d), chunks_attr=None)]
# zscore before adding
# TODO: make just a function so we dont' waste space
commonspace = params.combiner1(data_mapped[i], commonspace)
if params.zscore_common:
zscore(commonspace, chunks_attr=None)
# update commonspace to mean of ds_mapped
commonspace = params.combiner2(data_mapped)
#if params.zscore_common:
#zscore(commonspace, chunks_attr=None)
# Level 2 -- might iterate multiple times
for loop in xrange(params.level2_niter):
for i, (m, ds_new) in enumerate(zip(mappers, datasets)):
if __debug__:
debug('HPAL_', "Level 2 (%i-th iteration): ds #%i" % (loop, i))
ds_temp = (commonspace*ndatasets - data_mapped[i])/(ndatasets-1)
if params.zscore_common:
zscore(ds_temp, chunks_attr=None)
#ds_new = ds.copy()
#zscore(ds_new, chunks_attr=None)
ds_new.targets = ds_temp #commonspace #PRJ ds_temp
m.train(ds_new) # ds_temp)
ds_ = m.forward(np.asanyarray(ds_new))
if params.zscore_common:
zscore(ds_, chunks_attr=None)
data_mapped[i] = ds_
if residuals is not None:
residuals[1+loop, i] = np.linalg.norm(ds_ - commonspace)
#ds_mapped[i] = zscore( m.forward(ds_temp), chunks_attr=None)
commonspace = params.combiner2(data_mapped)
#if params.zscore_common:
#zscore(commonspace, chunks_attr=None)
# Level 3 (last) to params.levels
for i, (m, ds_new) in enumerate(zip(mappers, datasets)):
if __debug__:
debug('HPAL_', "Level 3: ds #%i" % i)
#ds_new = ds.copy() # shallow copy so we could assign new labels
#zscore(ds_new, chunks_attr=None)
ds_temp = (commonspace*ndatasets - data_mapped[i])/(ndatasets-1)
if params.zscore_common:
zscore(ds_temp, chunks_attr=None)
ds_new.targets = ds_temp #commonspace #PRJ ds_temp#
m.train(ds_new) #ds_temp)
data_mapped[i] = m.forward(np.asanyarray(ds_new))
if residuals is not None:
residuals[-1, i] = np.linalg.norm(data_mapped[i] - commonspace)
if params.zscore_all:
# We need to construct new mappers which would chain
# zscore and then final transformation
return [ChainMapper([zm, m]) for zm, m in zip(zmappers, mappers)]
else:
return mappers
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]))
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_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 __init__(self, chunks_attr='chunks', param_est=None, **kwargs):
self.node = ZScoreMapper(chunks_attr=chunks_attr, param_est=param_est)
Transformer.__init__(self, name='feature_normalizer', **kwargs)
def __init__(self, chunks_attr='chunks', param_est=None, **kwargs):
self.node = ZScoreMapper(chunks_attr=chunks_attr, param_est=param_est)
Transformer.__init__(self, name='feature_normalizer', **kwargs)
