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
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
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
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
wr1996([size]) Generate ‘6d robot arm’ dataset (Williams and Rasmussen 1996)

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