def test_subset_descriptor(self):
import numpy as np
from pyrsa.util.descriptor_utils import subset_descriptor
descriptors = {'foo': ['bar', 'bar2']}
self.assertEqual(subset_descriptor(descriptors, 0), {'foo': ['bar']})
self.assertEqual(
subset_descriptor(descriptors, np.array([True, False])),
{'foo': ['bar']})
self.assertEqual(subset_descriptor(descriptors, (0, 1)),
{'foo': ['bar', 'bar2']})
def subset_time(self, by, t_from, t_to):
""" Returns a subsetted TemporalDataset with time between t_from to t_to
Args:
by(String): the descriptor by which the subset selection is
made from channel dimension
t_from: time-point from which onwards data should be subsetted
t_to: time-point until which data should be subsetted
Returns:
TemporalDataset, with subset defined by the selected time_descriptor
"""
time = get_unique_unsorted(self.time_descriptors[by])
sel_time = [t for t in time if t <= t_to and t>=t_from]
selection = bool_index(self.time_descriptors[by], sel_time)
measurements = self.measurements[:, :, selection]
descriptors = self.descriptors
obs_descriptors = self.obs_descriptors
channel_descriptors = self.channel_descriptors
time_descriptors = subset_descriptor(
self.time_descriptors, selection)
dataset = TemporalDataset(measurements=measurements,
descriptors=descriptors,
obs_descriptors=obs_descriptors,
channel_descriptors=channel_descriptors,
time_descriptors=time_descriptors)
return dataset
def subset_channel(self, by, value):
""" Returns a subsetted TemporalDataset defined by certain channel value
Args:
by(String): the descriptor by which the subset selection is
made from channel dimension
value: the value by which the subset selection is made
from channel dimension
Returns:
TemporalDataset, with subset defined by the selected channel_descriptor
"""
selection = bool_index(self.channel_descriptors[by], value)
measurements = self.measurements[:, selection]
descriptors = self.descriptors
obs_descriptors = self.obs_descriptors
channel_descriptors = subset_descriptor(
self.channel_descriptors, selection)
time_descriptors = self.time_descriptors
dataset = TemporalDataset(measurements=measurements,
descriptors=descriptors,
obs_descriptors=obs_descriptors,
channel_descriptors=channel_descriptors,
time_descriptors=time_descriptors)
return dataset
def split_time(self, by):
""" Returns a list TemporalDataset splited by time
Args:
by(String): the descriptor by which the splitting is made
Returns:
list of TemporalDataset, splitted by the selected time_descriptor
"""
time = get_unique_unsorted(self.time_descriptors[by])
dataset_list = []
for v in time:
selection = (self.time_descriptors[by] == v)
measurements = self.measurements[:, :, selection]
descriptors = self.descriptors
obs_descriptors = self.obs_descriptors
channel_descriptors = self.channel_descriptors
time_descriptors = subset_descriptor(
self.time_descriptors, selection)
dataset = TemporalDataset(measurements=measurements,
descriptors=descriptors,
obs_descriptors=obs_descriptors,
channel_descriptors=channel_descriptors,
time_descriptors=time_descriptors)
dataset_list.append(dataset)
return dataset_list
def split_channel(self, by):
""" Returns a list TemporalDataset splited by channels
Args:
by(String): the descriptor by which the splitting is made
Returns:
list of TemporalDataset, splitted by the selected channel_descriptor
"""
unique_values = get_unique_unsorted(self.channel_descriptors[by])
dataset_list = []
for v in unique_values:
selection = (self.channel_descriptors[by] == v)
measurements = self.measurements[:, selection, :]
descriptors = self.descriptors.copy()
descriptors[by] = v
obs_descriptors = self.obs_descriptors
channel_descriptors = subset_descriptor(
self.channel_descriptors, selection)
time_descriptors = self.time_descriptors
dataset = TemporalDataset(measurements=measurements,
descriptors=descriptors,
obs_descriptors=obs_descriptors,
channel_descriptors=channel_descriptors,
time_descriptors=time_descriptors)
dataset_list.append(dataset)
return dataset_list
def sort_by(self, by):
""" sorts the dataset by a given observation descriptor
Args:
by(String): the descriptor by which the dataset shall be sorted
Returns:
---
"""
desc = self.obs_descriptors[by]
order = np.argsort(desc)
self.measurements = self.measurements[order]
self.obs_descriptors = subset_descriptor(self.obs_descriptors, order)
def __getitem__(self, idx):
"""
allows indexing with []
and iterating over RDMs with `for rdm in rdms:`
"""
idx = np.array(idx)
dissimilarities = self.dissimilarities[idx].reshape(
-1, self.dissimilarities.shape[1])
rdm_descriptors = subset_descriptor(self.rdm_descriptors, idx)
rdms = RDMs(dissimilarities,
dissimilarity_measure=self.dissimilarity_measure,
descriptors=self.descriptors,
rdm_descriptors=rdm_descriptors,
pattern_descriptors=self.pattern_descriptors)
return rdms
def subset_obs(self, by, value):
""" Returns a subsetted Dataset defined by certain obs value
Args:
by(String): the descriptor by which the subset selection
is made from obs dimension
value: the value by which the subset selection is made
from obs dimension
Returns:
Dataset, with subset defined by the selected obs_descriptor
"""
selection = bool_index(self.obs_descriptors[by], value)
measurements = self.measurements[selection, :]
descriptors = self.descriptors
obs_descriptors = subset_descriptor(
self.obs_descriptors, selection)
channel_descriptors = self.channel_descriptors
dataset = Dataset(measurements=measurements,
descriptors=descriptors,
obs_descriptors=obs_descriptors,
channel_descriptors=channel_descriptors)
return dataset
def split_obs(self, by):
""" Returns a list Datasets splited by obs
Args:
by(String): the descriptor by which the splitting is made
Returns:
list of Datasets, splitted by the selected obs_descriptor
"""
unique_values = get_unique_unsorted(self.obs_descriptors[by])
dataset_list = []
for v in unique_values:
selection = (self.obs_descriptors[by] == v)
measurements = self.measurements[selection, :]
descriptors = self.descriptors
obs_descriptors = subset_descriptor(
self.obs_descriptors, selection)
channel_descriptors = self.channel_descriptors
dataset = Dataset(measurements=measurements,
descriptors=descriptors,
obs_descriptors=obs_descriptors,
channel_descriptors=channel_descriptors)
dataset_list.append(dataset)
return dataset_list