Package Organization

The mvpa package contains the following subpackages and modules:

Author: Michael Hanke, Yaroslav Halchenko, Per B. Sederberg

Requires: Python 2.4+

Version: 0.4.1

See Also:: The PyMVPA webpage, GIT Repository Browser

License: The MIT License <http://www.opensource.org/licenses/mit-license.php>

Copyright:

Contributors (Alphabetical Order):

Submodules

[hide private]

mvpa.suite: MultiVariate Pattern Analysis -- load helper

Algorithms

mvpa.algorithms: Import helper for PyMVPA algorithms.
- mvpa.algorithms.cvtranserror: Cross-validate a classifier on a dataset

Anatomical Atlases

mvpa.atlases: Import helper for PyMVPA anatomical atlases
- mvpa.atlases.base: Base classes for Anatomy atlases support
- mvpa.atlases.fsl: FSL atlases interfaces
- mvpa.atlases.transformation: Coordinate transformations
- mvpa.atlases.warehouse: Collection of the known atlases

Basic Data Structures

mvpa.datasets: PyMVPA datasets and helper classes such as splitters
- mvpa.datasets.base: Dataset container
- mvpa.datasets.channel: Dataset handling data structured in channels.
- mvpa.datasets.eep: Dataset that gets its samples from an EEP binary file
- mvpa.datasets.event: Event-based dataset type
- mvpa.datasets.mapped: Mapped dataset
- mvpa.datasets.masked: Dataset with applied mask
- mvpa.datasets.meta: Dataset container
- mvpa.datasets.miscfx: Misc function performing operations on datasets.
- mvpa.datasets.miscfx_sp: Misc function performing operations on datasets which are based on scipy
- mvpa.datasets.nifti: Dataset that gets its samples from a NIfTI file
- mvpa.datasets.splitters: Collection of dataset splitters.

Classifiers (supervised learners)

mvpa.clfs: Import helper for PyMVPA classifiers
- mvpa.clfs._svmbase: Common to all SVM implementations functionality.
- mvpa.clfs.base: Base class for all classifiers.
- mvpa.clfs.blr: Bayesian Linear Regression (BLR).
- mvpa.clfs.distance: Distance functions to be used in kernels and elsewhere
- mvpa.clfs.gpr: Gaussian Process Regression (GPR).
- mvpa.clfs.kernel: Kernels for Gaussian Process Regression and Classification.
- mvpa.clfs.knn: k-Nearest-Neighbour classifier.
- mvpa.clfs.lars: Least angle regression (LARS) classifier.
- mvpa.clfs.libsmlrc: Wraper for the stepwise_regression function for SMLR.
  - mvpa.clfs.libsmlrc.ctypes_helper: Helpers for wrapping C libraries with ctypes.
- mvpa.clfs.libsvmc: Classifiers provied by LibSVM library
  - mvpa.clfs.libsvmc._svm: Python interface to the SWIG-wrapped libsvm
  - mvpa.clfs.libsvmc.sens: Provide sensitivity measures for libsvm's SVM.
  - mvpa.clfs.libsvmc.svm: Wrap the libsvm package into a very simple class interface.
- mvpa.clfs.meta: Classes for meta classifiers -- classifiers which use other classifiers
- mvpa.clfs.model_selector: Model selction.
- mvpa.clfs.plr: Penalized logistic regression classifier.
- mvpa.clfs.ridge: Ridge regression classifier.
- mvpa.clfs.sg: Classifiers provied by shogun (sg) library
  - mvpa.clfs.sg.sens: Provide sensitivity measures for sg's SVM.
  - mvpa.clfs.sg.svm: Wrap the libsvm package into a very simple class interface.
- mvpa.clfs.smlr: Sparse Multinomial Logistic Regression classifier.
- mvpa.clfs.stats: Estimator for classifier error distributions.
- mvpa.clfs.svm: Importer for the available SVM and SVR machines.
- mvpa.clfs.transerror: Utility class to compute the transfer error of classifiers.
- mvpa.clfs.warehouse: Collection of classifiers to ease the exploration.

Feature Selections

mvpa.featsel: Feature selection methods.
- mvpa.featsel.base: Feature selection base class and related stuff base classes and helpers.
- mvpa.featsel.helpers
- mvpa.featsel.ifs: Incremental feature search (IFS).
- mvpa.featsel.rfe: Recursive feature elimination.

Mappers (usually unsupervised learners)

mvpa.mappers: PyMVPA mappers.
- mvpa.mappers.array: Data mapper
- mvpa.mappers.base: Data mapper
- mvpa.mappers.boxcar: Data mapper
- mvpa.mappers.ica: Data mapper
- mvpa.mappers.mask: Data mapper which applies mask to the data
- mvpa.mappers.metric: Classes and functions to provide sense of distances between sample points
- mvpa.mappers.pca: Data mapper
- mvpa.mappers.samplegroup: Data mapper
- mvpa.mappers.svd: Data mapper
- mvpa.mappers.wavelet: Wavelet mappers

Measures

mvpa.measures: PyMVPA measures.
- mvpa.measures.anova: FeaturewiseDatasetMeasure performing a univariate ANOVA.
- mvpa.measures.base: Base class for data measures: algorithms that quantify properties of datasets.
- mvpa.measures.corrcoef: FeaturewiseDatasetMeasure of correlation with the labels.
- mvpa.measures.irelief: FeaturewiseDatasetMeasure performing multivariate Iterative RELIEF (I-RELIEF) algorithm.
- mvpa.measures.noiseperturbation: This is a FeaturewiseDatasetMeasure that uses a scalar DatasetMeasure and selective noise perturbation to compute a sensitivity map.
- mvpa.measures.pls
- mvpa.measures.searchlight: Implementation of the Searchlight algorithm
- mvpa.measures.splitmeasure: This is a FeaturewiseDatasetMeasure that uses another FeaturewiseDatasetMeasure and runs it multiple times on differents splits of a Dataset.

Miscellaneous

mvpa.base: Base functionality of PyMVPA
- mvpa.base.config: Registry-like monster
- mvpa.base.dochelpers: Various helpers to improve docstrings and textual output
- mvpa.base.externals: Helper to verify presence of external libraries and modules
- mvpa.base.verbosity: Verbose output and debugging facility
mvpa.misc: Import helper for PyMVPA misc modules
- mvpa.misc.args: Helpers for arguments handling.
- mvpa.misc.bv: Import helper for Brain Voyager
  - mvpa.misc.bv.base: Tiny snippets to interface with FSL easily.
- mvpa.misc.cmdline: Common functions and options definitions for command line
- mvpa.misc.data_generators: Miscelaneous data generators for unittests and demos
- mvpa.misc.errorfx: Error functions helpers.
- mvpa.misc.exceptions: Exception classes which might get thrown
- mvpa.misc.fsl: Import helper for FSL
  - mvpa.misc.fsl.base: Tiny snippets to interface with FSL easily.
  - mvpa.misc.fsl.flobs: Wrapper around FSLs halfcosbasis to generate HRF kernels
  - mvpa.misc.fsl.melodic: Wrapper around the output of MELODIC (part of FSL)
- mvpa.misc.fx: Misc.
- mvpa.misc.io: Import helper for IO helpers
  - mvpa.misc.io.base: Some little helper for reading (and writing) common formats from and to disk.
  - mvpa.misc.io.eepbin: Reader for binary EEP files.
  - mvpa.misc.io.hamster: Helper for simple storage facility via cPickle and zlib
  - mvpa.misc.io.meg: IO helper for MEG datasets.
- mvpa.misc.param: Parameter representation
- mvpa.misc.plot: Import helper for miscalaneouse PyMVPA plotting functions (mvpa.misc.plot)
  - mvpa.misc.plot.base: Misc.
  - mvpa.misc.plot.erp: Basic ERP (here ERP = Event Related Plot ;-)) plotting
  - mvpa.misc.plot.topo: Plot parameter distributions on a head surface (topography plots).
- mvpa.misc.state: Classes to control and store state information.
- mvpa.misc.stats: Little statistics helper
- mvpa.misc.support: Support function -- little helpers in everyday life
- mvpa.misc.transformers: Simply functors that transform something.
- mvpa.misc.vproperty: C++-like virtual properties
mvpa.support: Import helper for PyMVPA support modules
- mvpa.support._copy: Generic (shallow and deep) copying operations.
- mvpa.support.copy: Support for python's copy module.
- mvpa.support.stats: Fixer for rdist in scipy

Unittests

mvpa.tests: Unit test interface for PyMVPA
- mvpa.tests.main: Unit test console interface for PyMVPA
- mvpa.tests.runner: Helper module to enable profiling of the testcase
- mvpa.tests.test_args: Unit tests for PyMVPA args helpers
- mvpa.tests.test_arraymapper: Unit tests for PyMVPA dense array mapper
- mvpa.tests.test_atlases: Unit tests for PyMVPA atlases
- mvpa.tests.test_base: Test some base functionality which did not make it into a separate unittests
- mvpa.tests.test_boxcarmapper: Unit tests for PyMVPA Boxcar mapper
- mvpa.tests.test_clf: Unit tests for PyMVPA basic Classifiers
- mvpa.tests.test_clfcrossval: Unit tests for PyMVPA classifier cross-validation
- mvpa.tests.test_cmdline: Unit tests for PyMVPA cmdline helpers
- mvpa.tests.test_config: Unit tests for PyMVPA dense array mapper
- mvpa.tests.test_datameasure: Unit tests for PyMVPA SplittingSensitivityAnalyzer
- mvpa.tests.test_dataset: Unit tests for PyMVPA dataset handling
- mvpa.tests.test_datasetfx: Unit tests for PyMVPA miscelaneouse functions operating on datasets
- mvpa.tests.test_datasetfx_sp: Unit tests for PyMVPA miscelaneouse functions operating on datasets and requiring SciPy
- mvpa.tests.test_dochelpers: Unit tests for PyMVPA dochelpers
- mvpa.tests.test_eepdataset: Unit tests for PyMVPA EEP dataset
- mvpa.tests.test_hamster: Unit tests for PyMVPA Hamster
- mvpa.tests.test_icamapper: Unit tests for PyMVPA ICA mapper
- mvpa.tests.test_ifs: Unit tests for PyMVPA incremental feature search.
- mvpa.tests.test_iohelpers: Unit tests for PyMVPA IO helpers
- mvpa.tests.test_kernel: Unit tests for PyMVPA kernels
- mvpa.tests.test_knn: Unit tests for PyMVPA kNN classifier
- mvpa.tests.test_lars: Unit tests for PyMVPA least angle regression (LARS) classifier
- mvpa.tests.test_maskeddataset: Unit tests for PyMVPA pattern handling
- mvpa.tests.test_meg: Unit tests for PyMVPA MEG stuff
- mvpa.tests.test_metadataset: Unit tests for PyMVPA meta dataset handling
- mvpa.tests.test_neighbor: Unit tests for PyMVPA metrics
- mvpa.tests.test_niftidataset: Unit tests for PyMVPA nifti dataset
- mvpa.tests.test_params: Unit tests for PyMVPA Parameter class.
- mvpa.tests.test_pcamapper: Unit tests for PyMVPA PCA mapper
- mvpa.tests.test_perturbsensana: Unit tests for PyMVPA perturbation sensitivity analyzer.
- mvpa.tests.test_plr: Unit tests for PyMVPA logistic regression classifier
- mvpa.tests.test_pls: Unit tests for Partial Least Squares measures.
- mvpa.tests.test_regr: Unit tests for PyMVPA Regressions
- mvpa.tests.test_rfe: Unit tests for PyMVPA recursive feature elimination
- mvpa.tests.test_ridge: Unit tests for PyMVPA ridge regression classifier
- mvpa.tests.test_samplegroupmapper: Unit tests for PyMVPA SampleGroup mapper
- mvpa.tests.test_searchlight: Unit tests for PyMVPA searchlight algorithm
- mvpa.tests.test_smlr: Unit tests for PyMVPA sparse multinomial logistic regression classifier
- mvpa.tests.test_splitsensana: Unit tests for PyMVPA SplittingSensitivityAnalyzer
- mvpa.tests.test_splitter: Unit tests for PyMVPA pattern handling
- mvpa.tests.test_state: Unit tests for PyMVPA State parent class
- mvpa.tests.test_stats: Unit tests for PyMVPA stats helpers
- mvpa.tests.test_suite: Unit test for PyMVPA mvpa.suite() of being loading ok
- mvpa.tests.test_support: Unit tests for PyMVPA serial feature inclusion algorithm
- mvpa.tests.test_svdmapper: Unit tests for PyMVPA SVD mapper
- mvpa.tests.test_svm: Unit tests for SVM classifier
- mvpa.tests.test_transerror: Unit tests for PyMVPA classifier cross-validation
- mvpa.tests.test_transformers: Unit tests for PyMVPA transformers.
- mvpa.tests.test_verbosity: Unit tests for PyMVPA verbose and debug output
- mvpa.tests.test_waveletmapper: Unit tests for PyMVPA Wavelet mappers
- mvpa.tests.tests_warehouse: Miscelaneous functions/datasets to be used in the unit tests
- mvpa.tests.tests_warehouse_clfs: Provides clfs dictionary with instances of all available classifiers.

Functions

[hide private]

seed(random_seed)
Uniform and combined seeding of all relevant random number generators.

source code

Variables

[hide private]

pymvpa_version = '0.4.1'

__version__ = '0.4.1'

pymvpa_dataroot = os.path.join(os.path.dirname(__file__), 'data')

_random_seed = int(N.random.uniform()*(2** 31-1))