def __init__(self,
sensitivity_analyzer,
split_by_labels,
select_common_features=True,
probability_label=None,
probability_combiner=None,
selector=FractionTailSelector(0.05),
**kwargs):
'''
Parameters
----------
sensitivity_analyzer: FeaturewiseMeasure
Sensitivity analyzer to come up with sensitivity.
split_by_labels: str or list of str
Sample labels on which input datasets are split before
data is selected.
select_common_features: bool
True means that the same features are selected after the split.
probablity_label: None or str
If None, then the output dataset ds from the
sensitivity_analyzer is taken to select the samples.
If not None it takes ds.sa['probablity_label'].
For example if sensitivity_analyzer=OneWayAnova then
probablity_label='fprob' is a sensible value.
probability_combiner: function
If select_common_features is True, then this function is
applied to the feature scores across splits. If None,
it uses lambda x:np.sum(-np.log(x)) which is sensible if
the scores are probability values
selector: Selector
function that returns the indices to keep.
'''
SliceMapper.__init__(self, None, **kwargs)
if probability_combiner is None:
def f(x):
y = -np.log(x.ravel())
# address potential NaNs
# set to max value in y
m = np.isnan(y)
if np.all(m):
return 0 # p=1
y[m] = np.max(y[np.logical_not(m)])
return np.sum(y)
probability_combiner = f # avoid lambda as h5py doesn't like it
self._sensitivity_analyzer = sensitivity_analyzer
self._split_by_labels = split_by_labels
self._select_common_features = select_common_features
self._probability_label = probability_label
self._probability_combiner = probability_combiner
self._selector = selector
def __init__(self,
sensitivity_analyzer,
split_by_labels,
select_common_features=True,
probability_label=None,
probability_combiner=None,
selector=FractionTailSelector(0.05),
**kwargs):
'''
Parameters
----------
sensitivity_analyzer: FeaturewiseMeasure
Sensitivity analyzer to come up with sensitivity.
split_by_labels: str or list of str
Sample labels on which input datasets are split before
data is selected.
select_common_features: bool
True means that the same features are selected after the split.
probablity_label: None or str
If None, then the output dataset ds from the
sensitivity_analyzer is taken to select the samples.
If not None it takes ds.sa['probablity_label'].
For example if sensitivity_analyzer=OneWayAnova then
probablity_label='fprob' is a sensible value.
probability_combiner: function
If select_common_features is True, then this function is
applied to the feature scores across splits. If None,
it uses lambda x:np.sum(-np.log(x)) which is sensible if
the scores are probability values
selector: Selector
function that returns the indices to keep.
'''
SliceMapper.__init__(self, None, **kwargs)
if probability_combiner is None:
def f(x):
y = -np.log(x.ravel())
# address potential NaNs
# set to max value in y
m = np.isnan(y)
if np.all(m):
return 0 # p=1
y[m] = np.max(y[np.logical_not(m)])
return np.sum(y)
probability_combiner = f # avoid lambda as h5py doesn't like it
self._sensitivity_analyzer = sensitivity_analyzer
self._split_by_labels = split_by_labels
self._select_common_features = select_common_features
self._probability_label = probability_label
self._probability_combiner = probability_combiner
self._selector = selector
def __init__(self, filler=0, **kwargs):
"""
Parameters
----------
filler : optional
Value to fill empty entries upon reverse operation
"""
# init slicearg with None
SliceMapper.__init__(self, None, **kwargs)
self._dshape = None
self._oshape = None
self.filler = filler