nimare.meta.kernel
.ALEKernel
- class ALEKernel(fwhm=None, sample_size=None, memory_limit=None)[source]
Bases:
nimare.meta.kernel.KernelTransformer
Generate ALE modeled activation images from coordinates and sample size.
By default (if neither
fwhm
norsample_size
is provided), the FWHM of the kernel will be determined on a study-wise basis based on the sample sizes available in the input, via the method described in 1.Changed in version 0.0.8:
[ENH] Add low-memory option for kernel transformers.
- Parameters
fwhm (
float
, optional) – Full-width half-max for Gaussian kernel, if you want to have a constant kernel across Contrasts. Mutually exclusive withsample_size
.sample_size (
int
, optional) – Sample size, used to derive FWHM for Gaussian kernel based on formulae from Eickhoff et al. (2012). This sample size overwrites the Contrast-specific sample sizes in the dataset, in order to hold kernel constant across Contrasts. Mutually exclusive withfwhm
.memory_limit (
str
or None, optional) – Memory limit to apply to data. If None, no memory management will be applied. Otherwise, the memory limit will be used to (1) assign memory-mapped files and (2) restrict memory during array creation to the limit. Default is None.
References
- 1
Eickhoff, Simon B., et al. “Activation likelihood estimation meta-analysis revisited.” Neuroimage 59.3 (2012): 2349-2361.
- set_params(**params)[source]
Set the parameters of this estimator.
The method works on simple estimators as well as on nested objects (such as pipelines). The latter have parameters of the form
<component>__<parameter>
so that it’s possible to update each component of a nested object.- Returns
self
- transform(dataset, masker=None, return_type='image')[source]
Generate modeled activation images for each Contrast in dataset.
- Parameters
dataset (
nimare.dataset.Dataset
orpandas.DataFrame
) – Dataset for which to make images. Can be a DataFrame if necessary.masker (img_like or None, optional) – Mask to apply to MA maps. Required if
dataset
is a DataFrame. If None (anddataset
is a Dataset), the Dataset’s masker attribute will be used. Default is None.return_type ({‘array’, ‘image’, ‘dataset’}, optional) – Whether to return a numpy array (‘array’), a list of niimgs (‘image’), or a Dataset with MA images saved as files (‘dataset’). Default is ‘image’.
- Returns
imgs ((C x V)
numpy.ndarray
orlist
ofnibabel.Nifti1Image
ornimare.dataset.Dataset
) – If return_type is ‘array’, a 2D numpy array (C x V), where C is contrast and V is voxel. If return_type is ‘image’, a list of modeled activation images (one for each of the Contrasts in the input dataset). If return_type is ‘dataset’, a new Dataset object with modeled activation images saved to files and referenced in the Dataset.images attribute.- Variables