def test_repr():
attr_repr = "SampleAttribute(name='TestAttr', doc='my own test', " \
"value=array([0, 1, 2, 3, 4]), length=None)"
sattr = SampleAttribute(name='TestAttr', doc='my own test',
value=np.arange(5))
# check precise formal representation
ok_(repr(sattr) == attr_repr)
# check that it actually works as a Python expression
from numpy import array
eattr = eval(repr(sattr))
ok_(repr(eattr), attr_repr)
# should also work for a simple dataset
# Does not work due to bug in numpy:
# python -c "from numpy import *; print __version__; r=repr(array(['s', None])); print r; eval(r)"
# would give "array([s, None], dtype=object)" without '' around s
#ds = datasets['uni2small']
ds = Dataset([[0, 1]],
a={'dsa1': 'v1'},
sa={'targets': [0]},
fa={'targets': ['b', 'n']})
ds_repr = repr(ds)
cfg_repr = cfg.get('datasets', 'repr', 'full')
if cfg_repr == 'full':
try:
ok_(repr(eval(ds_repr)) == ds_repr)
except SyntaxError, e:
raise AssertionError, "%r cannot be evaluated" % ds_repr
def test_repr():
attr_repr = "SampleAttribute(name='TestAttr', doc='my own test', " \
"value=array([0, 1, 2, 3, 4]), length=None)"
sattr = SampleAttribute(name='TestAttr',
doc='my own test',
value=np.arange(5))
# check precise formal representation
ok_(repr(sattr) == attr_repr)
# check that it actually works as a Python expression
from numpy import array
eattr = eval(repr(sattr))
ok_(repr(eattr), attr_repr)
# should also work for a simple dataset
# Does not work due to bug in numpy:
# python -c "from numpy import *; print __version__; r=repr(array(['s', None])); print r; eval(r)"
# would give "array([s, None], dtype=object)" without '' around s
#ds = datasets['uni2small']
ds = Dataset([[0, 1]],
a={'dsa1': 'v1'},
sa={'targets': [0]},
fa={'targets': ['b', 'n']})
ds_repr = repr(ds)
cfg_repr = cfg.get('datasets', 'repr', 'full')
if cfg_repr == 'full':
try:
ok_(repr(eval(ds_repr)) == ds_repr)
except SyntaxError, e:
raise AssertionError, "%r cannot be evaluated" % ds_repr
__docformat__ = 'restructuredtext'
import numpy as np
import copy
from mvpa2.base import externals, cfg, warning
from mvpa2.base.collections import SampleAttributesCollection, \
FeatureAttributesCollection, DatasetAttributesCollection
from mvpa2.base.types import is_datasetlike
from mvpa2.base.dochelpers import _str, _strid
if __debug__:
from mvpa2.base import debug
__REPR_STYLE__ = cfg.get('datasets', 'repr', 'full')
if not __REPR_STYLE__ in ('full', 'str'):
raise ValueError, "Incorrect value %r for option datasets.repr." \
" Valid are 'full' and 'str'." % __REPR_STYLE__
class AttrDataset(object):
"""Generic storage class for datasets with multiple attributes.
A dataset consists of four pieces. The core is a two-dimensional
array that has variables (so-called `features`) in its columns and
the associated observations (so-called `samples`) in the rows. In
addition a dataset may have any number of attributes for features
and samples. Unsurprisingly, these are called 'feature attributes'
and 'sample attributes'. Each attribute is a vector of any datatype
that contains a value per each item (feature or sample). Both types
# commit hash to be filled in by Git upon export/archive
hashfilename = pathjoin(os.path.dirname(__file__), 'COMMIT_HASH')
__hash__ = ''
if os.path.exists(hashfilename):
hashfile = open(hashfilename, 'r')
__hash__ = hashfile.read().strip()
hashfile.close()
#
# Data paths
#
# locate data root -- data might not be installed, but if it is, it should be at
# this location
pymvpa_dataroot = \
cfg.get('data', 'root',
default=pathjoin(os.path.dirname(__file__), 'data'))
# locate PyMVPA data database root -- also might not be installed, but if it is,
# it should be at this location
pymvpa_datadbroot = \
cfg.get('datadb', 'root',
default=pathjoin(os.getcwd(), 'datadb'))
#
# Debugging and optimization
#
if not __debug__:
try:
import psyco
psyco.profile()
# commit hash to be filled in by Git upon export/archive
hashfilename = os.path.join(os.path.dirname(__file__), 'COMMIT_HASH')
__hash__ = ''
if os.path.exists(hashfilename):
hashfile = open(hashfilename, 'r')
__hash__ = hashfile.read().strip()
hashfile.close()
#
# Data paths
#
# locate data root -- data might not be installed, but if it is, it should be at
# this location
pymvpa_dataroot = \
cfg.get('data', 'root',
default=os.path.join(os.path.dirname(__file__), 'data'))
# locate PyMVPA data database root -- also might not be installed, but if it is,
# it should be at this location
pymvpa_datadbroot = \
cfg.get('datadb', 'root',
default=os.path.join(os.curdir, 'datadb'))
#
# Debugging and optimization
#
if not __debug__:
try:
import psyco
psyco.profile()
__docformat__ = 'restructuredtext'
import numpy as np
import copy
from mvpa2.base import externals, cfg
from mvpa2.base.collections import SampleAttributesCollection, \
FeatureAttributesCollection, DatasetAttributesCollection
from mvpa2.base.types import is_datasetlike
from mvpa2.base.dochelpers import _str, _strid
if __debug__:
from mvpa2.base import debug
__REPR_STYLE__ = cfg.get('datasets', 'repr', 'full')
if not __REPR_STYLE__ in ('full', 'str'):
raise ValueError, "Incorrect value %r for option datasets.repr." \
" Valid are 'full' and 'str'." % __REPR_STYLE__
class AttrDataset(object):
"""Generic storage class for datasets with multiple attributes.
A dataset consists of four pieces. The core is a two-dimensional
array that has variables (so-called `features`) in its columns and
the associated observations (so-called `samples`) in the rows. In
addition a dataset may have any number of attributes for features
and samples. Unsurprisingly, these are called 'feature attributes'
and 'sample attributes'. Each attribute is a vector of any datatype
# commit hash to be filled in by Git upon export/archive
hashfilename = os.path.join(os.path.dirname(__file__), 'COMMIT_HASH')
__hash__ = ''
if os.path.exists(hashfilename):
hashfile = open(hashfilename, 'r')
__hash__ = hashfile.read().strip()
hashfile.close()
#
# Data paths
#
# locate data root -- data might not be installed, but if it is, it should be at
# this location
pymvpa_dataroot = \
cfg.get('data', 'root',
default=os.path.join(os.path.dirname(__file__), 'data'))
# locate PyMVPA data database root -- also might not be installed, but if it is,
# it should be at this location
pymvpa_datadbroot = \
cfg.get('datadb', 'root',
default=os.path.join(os.curdir, 'datadb'))
#
# Debugging and optimization
#
if not __debug__:
try:
import psyco
psyco.profile()
except ImportError:
# commit hash to be filled in by Git upon export/archive
hashfilename = os.path.join(os.path.dirname(__file__), "COMMIT_HASH")
__hash__ = ""
if os.path.exists(hashfilename):
hashfile = open(hashfilename, "r")
__hash__ = hashfile.read().strip()
hashfile.close()
#
# Data paths
#
# locate data root -- data might not be installed, but if it is, it should be at
# this location
pymvpa_dataroot = cfg.get("data", "root", default=os.path.join(os.path.dirname(__file__), "data"))
# locate PyMVPA data database root -- also might not be installed, but if it is,
# it should be at this location
pymvpa_datadbroot = cfg.get("datadb", "root", default=os.path.join(os.curdir, "datadb"))
#
# Debugging and optimization
#
if not __debug__:
try:
import psyco
psyco.profile()
except ImportError:
# commit hash to be filled in by Git upon export/archive
hashfilename = pathjoin(os.path.dirname(__file__), 'COMMIT_HASH')
__hash__ = ''
if os.path.exists(hashfilename):
hashfile = open(hashfilename, 'r')
__hash__ = hashfile.read().strip()
hashfile.close()
#
# Data paths
#
# locate data root -- data might not be installed, but if it is, it should be at
# this location
pymvpa_dataroot = \
cfg.get('data', 'root',
default=pathjoin(os.path.dirname(__file__), 'data'))
# locate PyMVPA data database root -- also might not be installed, but if it is,
# it should be at this location
pymvpa_datadbroot = \
cfg.get('datadb', 'root',
default=pathjoin(os.getcwd(), 'datadb'))
#
# Debugging and optimization
#
if not __debug__:
try:
import psyco
psyco.profile()
except ImportError:
"""Multi-purpose dataset container with support for attributes."""
__docformat__ = "restructuredtext"
import numpy as np
import copy
from mvpa2.base import externals, cfg, warning
from mvpa2.base.collections import SampleAttributesCollection, FeatureAttributesCollection, DatasetAttributesCollection
from mvpa2.base.types import is_datasetlike
from mvpa2.base.dochelpers import _str, _strid
if __debug__:
from mvpa2.base import debug
__REPR_STYLE__ = cfg.get("datasets", "repr", "full")
if not __REPR_STYLE__ in ("full", "str"):
raise ValueError, "Incorrect value %r for option datasets.repr." " Valid are 'full' and 'str'." % __REPR_STYLE__
class AttrDataset(object):
"""Generic storage class for datasets with multiple attributes.
A dataset consists of four pieces. The core is a two-dimensional
array that has variables (so-called `features`) in its columns and
the associated observations (so-called `samples`) in the rows. In
addition a dataset may have any number of attributes for features
and samples. Unsurprisingly, these are called 'feature attributes'
and 'sample attributes'. Each attribute is a vector of any datatype
that contains a value per each item (feature or sample). Both types
# BLR
from mvpa2.clfs.blr import BLR
clfswh += RegressionAsClassifier(BLR(descr="BLR()"), descr="BLR Classifier")
#PLR
from mvpa2.clfs.plr import PLR
clfswh += PLR(descr="PLR()")
if externals.exists('scipy'):
clfswh += PLR(reduced=0.05, descr="PLR(reduced=0.01)")
# SVM stuff
if len(clfswh['linear', 'svm']) > 0:
linearSVMC = clfswh['linear', 'svm',
cfg.get('svm', 'backend', default='libsvm').lower()][0]
# "Interesting" classifiers
clfswh += \
FeatureSelectionClassifier(
linearSVMC.clone(),
SensitivityBasedFeatureSelection(
SMLRWeights(SMLR(lm=0.1, implementation="C"),
postproc=maxofabs_sample()),
RangeElementSelector(mode='select')),
descr="LinSVM on SMLR(lm=0.1) non-0")
_rfeclf = linearSVMC.clone()
clfswh += \
FeatureSelectionClassifier(
_rfeclf,
from mvpa2.clfs.blr import BLR
clfswh += RegressionAsClassifier(BLR(descr="BLR()"),
descr="BLR Classifier")
#PLR
from mvpa2.clfs.plr import PLR
clfswh += PLR(descr="PLR()")
if externals.exists('scipy'):
clfswh += PLR(reduced=0.05, descr="PLR(reduced=0.01)")
# SVM stuff
if len(clfswh['linear', 'svm']) > 0:
linearSVMC = clfswh['linear', 'svm',
cfg.get('svm', 'backend', default='libsvm').lower()
][0]
# "Interesting" classifiers
clfswh += \
FeatureSelectionClassifier(
linearSVMC.clone(),
SensitivityBasedFeatureSelection(
SMLRWeights(SMLR(lm=0.1, implementation="C"),
postproc=maxofabs_sample()),
RangeElementSelector(mode='select')),
descr="LinSVM on SMLR(lm=0.1) non-0")
clfswh += \
FeatureSelectionClassifier(
from mvpa2.clfs.blr import BLR
clfswh += RegressionAsClassifier(BLR(descr="BLR()"), descr="BLR Classifier")
# PLR
from mvpa2.clfs.plr import PLR
clfswh += PLR(descr="PLR()")
if externals.exists("scipy"):
clfswh += PLR(reduced=0.05, descr="PLR(reduced=0.01)")
# SVM stuff
if len(clfswh["linear", "svm"]) > 0:
linearSVMC = clfswh["linear", "svm", cfg.get("svm", "backend", default="libsvm").lower()][0]
# "Interesting" classifiers
clfswh += FeatureSelectionClassifier(
linearSVMC.clone(),
SensitivityBasedFeatureSelection(
SMLRWeights(SMLR(lm=0.1, implementation="C"), postproc=maxofabs_sample()),
RangeElementSelector(mode="select"),
),
descr="LinSVM on SMLR(lm=0.1) non-0",
)
clfswh += FeatureSelectionClassifier(
linearSVMC.clone(),
SensitivityBasedFeatureSelection(
SMLRWeights(SMLR(lm=1.0, implementation="C"), postproc=maxofabs_sample()),
