pymvpa2-searchlight - Online in the Cloud

PROGRAM:

NAME

pymvpa2-searchlight - traveling ROI analysis

SYNOPSIS

pymvpa2 searchlight [--version] [-h] -i DATASET [DATASET ...] --payload PAYLOAD
--neighbors SPEC [--nproc NPROC] [--multiproc-backend {native,hdf5}] [--aggregate-fx
AGGREGATE_FX] [--ds-preproc-fx DS_PREPROC_FX] [--enable-ca NAME [NAME ...]] [--disable-ca
NAME [NAME ...]] [--scatter-rois SPEC] [--roi-attr ATTR/EXPR [ATTR/EXPR ...]] [--cv-
learner CV_LEARNER] [--cv-learner-space CV_LEARNER_SPACE] [--cv-partitioner
CV_PARTITIONER] [--cv-errorfx CV_ERRORFX] [--cv-avg-datafold-results] [--cv-balance-
training CV_BALANCE_TRAINING] [--cv-sampling-repetitions CV_SAMPLING_REPETITIONS] [--cv-
permutations CV_PERMUTATIONS] [--cv-prob-tail {left,right}] -o OUTPUT [--hdf5-compression
TYPE]

DESCRIPTION

Traveling ROI analysis

OPTIONS

--version
show program's version and license information and exit

-h, --help, --help-np
show this help message and exit. --help-np forcefully disables the use of a pager
for displaying the help.

-i DATASET [DATASET ...], --input DATASET [DATASET ...]
path(s) to one or more PyMVPA dataset files. All datasets will be merged into a
single dataset (vstack'ed) in order of specification. In some cases this option may
need to be specified more than once if multiple, but separate, input datasets are
required.

Options for searchlight setup:
--payload PAYLOAD
switch to select a particular analysis type to be run in a searchlight fashion on a
dataset. Depending on the choice the corresponding analysis setup options are
evaluated. 'cv' computes a cross-validation analysis. Alternatively, the argument
to this option can also be a script filename in which a custom measure is built
that is then ran as a searchlight.

--neighbors SPEC
define the size and shape of an ROI with respect to a center/seed location. If a
single integer number is given, it is interpreted as the radius (in number of grid
elements) around a seed location. By default grid coordinates for features are
taken from a 'voxel_indices' feature attribute in the input dataset. If coordinates
shall be taken from a different attribute, the radius value can be prefixed with
the attribute name, i.e. 'altcoords:2'. For ROI shapes other than spheres (with
potentially additional parameters), the shape name can be specified as well, i.e.
'voxel_indices:HollowSphere:3:2'. All neighborhood objects from the
mvpa2.misc.neighborhood module are supported. For custom ROI shapes it is also
possible to pass a script filename, or an attribute name plus script filename
combination, i.e. 'voxel_indices:myownshape.py' (advanced). It is possible to
specify this option multiple times to define multi-space ROI shapes for, e.g.,
spatiotemporal searchlights.

--nproc NPROC
Use the specific number or worker processes for computing.

--multiproc-backend {native,hdf5}
Specifies the way results are provided back from a processing block in case of
--nproc > 1. 'native' is pickling/unpickling of results, while 'hdf5' uses HDF5
based file storage. 'hdf5' might be more time and memory efficient in some cases.

--aggregate-fx AGGREGATE_FX
use a custom result aggregation function for the searchlight

--ds-preproc-fx DS_PREPROC_FX
custom preprocessing function to be applied immediately after loading the data

Options for conditional attributes:
--enable-ca NAME [NAME ...]
list of conditional attributes to be enabled

--disable-ca NAME [NAME ...]
list of conditional attributes to be disabled

Options for constraining the searchlight:
--scatter-rois SPEC
scatter ROI locations across the available space. The arguments supported by this
option are identical to those of --neighbors. ROI locations are randomly picked
from all possible locations with the constraint that the center coordinates of any
ROI is NOT within the neighborhood (as defined by this option's argument) of a
second ROI. Increasing the size of the neighborhood therefore increases the
scarceness of the sampling.

--roi-attr ATTR/EXPR [ATTR/EXPR ...]
name of a feature attribute whose non-zero values define possible ROI
seeds/centers. Alternatively, this can also be an expression like: parcellation_roi
eq 16 (see the 'select' command on information what expressions are supported).

Options for cross-validation setup:
--cv-learner CV_LEARNER
select a learner (trainable node) via its description in the learner warehouse (see
'info' command for a listing), a colon-separated list of capabilities, or by a file
path to a Python script that creates a classifier instance (advanced).

--cv-learner-space CV_LEARNER_SPACE
name of a sample attribute that defines the model to be learned by a learner. By
default this is an attribute named 'targets'.

--cv-partitioner CV_PARTITIONER
select a data folding scheme. Supported arguments are: 'half' for split-half
partitioning, 'oddeven' for partitioning into odd and even chunks, 'group-X' where
X can be any positive integer for partitioning in X groups, 'n-X' where X can be
any positive integer for leave-X-chunks out partitioning. By default partitioners
operate on dataset chunks that are defined by a 'chunks' sample attribute. The name
of the "chunking" attribute can be changed by appending a colon and the name of the
attribute (e.g. 'oddeven:run'). optionally an argument to this option can also be
a file path to a Python script that creates a custom partitioner instance
(advanced).

--cv-errorfx CV_ERRORFX
error function to be applied to the targets and predictions of each
cross-validation data fold. This can either be a name of any error function in
PyMVPA's mvpa2.misc.errorfx module, or a file path to a Python script that creates
a custom error function (advanced).

--cv-avg-datafold-results
average result values across data folds generated by the partitioner. For example
to compute a mean prediction error across all folds of a crossvalidation procedure.

--cv-balance-training CV_BALANCE_TRAINING
If enabled, training samples are balanced within each data fold. If the keyword
'equal' is given as argument an equal number of random samples for each unique
target value is chosen. The number of samples per category is determined by the
category with the least number of samples in the respective training set. An
integer argument will cause the a corresponding number of samples per category to
be randomly selected. A floating point number argument (interval [0,1]) indicates
what fraction of the available samples shall be selected.

--cv-sampling-repetitions CV_SAMPLING_REPETITIONS
If training set balancing is enabled, how often should random sample selection be
performed for each data fold. Default: 1

--cv-permutations CV_PERMUTATIONS
Number of Monte-Carlo permutation runs to be computed for estimating an H0
distribution for all crossvalidation results. Enabling this option will make
reports of corresponding p-values available in the result summary and output.

--cv-prob-tail {left,right}
which tail of the probability distribution to report p-values from when evaluating
permutation test results. For example, a cross-validation computing mean prediction
error could report left-tail p-value for a single-sided test.

Output options:
-o OUTPUT, --output OUTPUT
output filename ('.hdf5' extension is added automatically if necessary). NOTE: The
output format is suitable for data exchange between PyMVPA commands, but is not
recommended for long-term storage or exchange as its specific content may vary
depending on the actual software environment. For long-term storage consider
conversion into other data formats (see 'dump' command).

--hdf5-compression TYPE
compression type for HDF5 storage. Available values depend on the specific HDF5
installation. Typical values are: 'gzip', 'lzf', 'szip', or integers from 1 to 9
indicating gzip compression levels.

Use pymvpa2-searchlight online using onworks.net services