def plot_samples_distance(dataset, sortbyattr=None):
"""Plot the euclidean distances between all samples of a dataset.
Parameters
----------
dataset : Dataset
Providing the samples.
sortbyattr : None or str
If None, the samples distances will be in the same order as their
appearance in the dataset. Alternatively, the name of a samples
attribute can be given, which wil then be used to sort/group the
samples, e.g. to investigate the similarity samples by label or by
chunks.
"""
if sortbyattr is not None:
slicer = []
for attr in dataset.sa[sortbyattr].unique:
slicer += \
get_samples_by_attr(dataset, sortbyattr, attr).tolist()
samples = dataset.samples[slicer]
else:
samples = dataset.samples
ed = np.sqrt(squared_euclidean_distance(samples))
pl.imshow(ed)
pl.colorbar()
def plot_samples_distance(dataset, sortbyattr=None):
"""Plot the euclidean distances between all samples of a dataset.
Parameters
----------
dataset : Dataset
Providing the samples.
sortbyattr : None or str
If None, the samples distances will be in the same order as their
appearance in the dataset. Alternatively, the name of a samples
attribute can be given, which wil then be used to sort/group the
samples, e.g. to investigate the similarity samples by label or by
chunks.
"""
if sortbyattr is not None:
slicer = []
for attr in dataset.sa[sortbyattr].unique:
slicer += \
get_samples_by_attr(dataset, sortbyattr, attr).tolist()
samples = dataset.samples[slicer]
else:
samples = dataset.samples
ed = np.sqrt(squared_euclidean_distance(samples))
pl.imshow(ed)
pl.colorbar()
def _train(self, ds):
# local binding
chunks_attr = self.__chunks_attr
params = self.__params
param_est = self.__param_est
# populate a dictionary with tuples of (mean,std) for all chunks, or
# a global value that is is used for the whole data
if not params is None:
# we got mean and std already
if not isinstance(params, dict):
# turn into dict, otherwise assume that we have parameters per
# chunk
params = {'__all__': params}
else:
# no parameters given, need to estimate
if not param_est is None:
est_attr, est_attr_values = param_est
# which samples to use for estimation
est_ids = set(get_samples_by_attr(ds, est_attr,
est_attr_values))
else:
est_ids = slice(None)
# now we can either do it one for all, or per chunk
if not chunks_attr is None:
# per chunk estimate
params = {}
for c in ds.sa[chunks_attr].unique:
slicer = np.where(ds.sa[chunks_attr].value == c)[0]
if not isinstance(est_ids, slice):
slicer = list(est_ids.intersection(set(slicer)))
params[c] = self._compute_params(ds.samples[slicer])
else:
# global estimate
params = {'__all__': self._compute_params(ds.samples[est_ids])}
self.__params_dict = params
def _train(self, ds):
# local binding
chunks_attr = self.__chunks_attr
params = self.__params
param_est = self.__param_est
# populate a dictionary with tuples of (mean,std) for all chunks, or
# a global value that is is used for the whole data
if not params is None:
# we got mean and std already
if not isinstance(params, dict):
# turn into dict, otherwise assume that we have parameters per
# chunk
params = {'__all__': params}
else:
# no parameters given, need to estimate
if not param_est is None:
est_attr, est_attr_values = param_est
# which samples to use for estimation
est_ids = set(get_samples_by_attr(ds, est_attr,
est_attr_values))
else:
est_ids = slice(None)
# now we can either do it one for all, or per chunk
if not chunks_attr is None:
# per chunk estimate
params = {}
for c in ds.sa[chunks_attr].unique:
slicer = np.where(ds.sa[chunks_attr].value == c)[0]
if not isinstance(est_ids, slice):
slicer = list(est_ids.intersection(set(slicer)))
params[c] = self._compute_params(ds.samples[slicer])
else:
# global estimate
params = {'__all__': self._compute_params(ds.samples[est_ids])}
self.__params_dict = params