mvpa2.testing.datasetsΒΆ

Provides convenience datasets for unittesting.

Also performs testing of storing/reloading datasets into hdf5 file if cfg.getboolean(‘tests’, ‘use hdf datasets’

Functions

autocorrelated_noise(ds, sr, cutoff[, lfnl, ...]) Generate a dataset with samples being temporally autocorrelated noise.
chirp_linear(n_instances[, n_features, ...]) Generates simple dataset for linear regressions
dumb_feature_binary_dataset() Very simple binary (2 labels) dataset
dumb_feature_dataset() Create a very simple dataset with 2 features and 3 labels
generate_testing_datasets(*arg, **kwargs)
get_mv_pattern(s2n) Simple multivariate dataset
get_random_rotation(ns[, nt, data]) Return some random rotation (or rotation + dim reduction) matrix
linear1d_gaussian_noise([size, slope, ...]) A straight line with some Gaussian noise.
linear_awgn([size, intercept, slope, ...]) Generate a dataset from a linear function with AWGN (Added White Gaussian Noise).
load_datadb_demo_blockfmri([path, roi]) Loads the block-design demo dataset from PyMVPA dataset DB.
load_datadb_tutorial_data([path, roi]) Loads the block-design demo dataset from PyMVPA dataset DB.
load_example_fmri_dataset() Load minimal fMRI dataset that is shipped with PyMVPA.
multiple_chunks(func, n_chunks, *args, **kwargs) Replicate datasets multiple times raising different chunks Given some randomized (noisy) generator of a dataset with a single chunk call generator multiple times and place results into a distinct chunks.
noisy_2d_fx(size_per_fx, dfx, sfx, center[, ...]) Yet another generator of random dataset
normal_feature_dataset([perlabel, nlabels, ...]) Generate a univariate dataset with normal noise and specified means.
pure_multivariate_signal(patterns[, ...]) Create a 2d dataset with a clear multivariate signal, but no univariate information.
random_affine_transformation(ds[, ...]) Distort a dataset by random scale, shift, and rotation.
reseed_rng() Decorator to assure the use of MVPA_SEED while running the test It resets random number generators (both python and numpy) to the initial value of the seed value which was set while importing mvpa, which could be controlled through configuration/environment.
saveload_warehouse() Store all warehouse datasets into HDF5 and reload them.
sin_modulated(n_instances, n_features[, ...]) Generate a (quite) complex multidimensional non-linear dataset Used for regression testing.
wr1996([size]) Generate ‘6d robot arm’ dataset (Williams and Rasmussen 1996) Was originally created in order to test the correctness of the implementation of kernel ARD.

Classes

Dataset(samples[, sa, fa, a]) Generic storage class for datasets with multiple attributes.
HollowSamples([shape, sid, fid, dtype]) Samples container that doesn’t store samples.
OddEvenPartitioner([usevalues]) Create odd and even partitions based on a sample attribute.

NeuroDebian

NITRC-listed