nimare.meta.cbma.ale
.SCALE
- class SCALE(xyz, n_iters=10000, n_cores=1, kernel_transformer=<class 'nimare.meta.kernel.ALEKernel'>, **kwargs)[source]
Bases:
nimare.meta.cbma.base.CBMAEstimator
Specific coactivation likelihood estimation.
Changed in version 0.0.12:
Remove unused parameters
voxel_thresh
andmemory_limit
.Use memmapped array for null distribution.
Changed in version 0.0.10: Replace
ijk
withxyz
. This should be easier for users to collect.- Parameters
xyz ((N x 3)
numpy.ndarray
) –Numpy array with XYZ coordinates. Voxels are rows and x, y, z (meaning coordinates) values are the three columnns.
Changed in version 0.0.12: This parameter was previously incorrectly labeled as “optional” and indicated that it supports tab-delimited files, which it does not (yet).
n_iters (int, optional) – Number of iterations for statistical inference. Default: 10000
n_cores (int, optional) – Number of processes to use for meta-analysis. If -1, use all available cores. Default: 1
kernel_transformer (
KernelTransformer
, optional) – Kernel with which to convolve coordinates from dataset. Default isALEKernel
.**kwargs – Keyword arguments. Arguments for the kernel_transformer can be assigned here, with the prefix ‘kernel__’ in the variable name.
- Variables
~SCALE.masker (
NiftiMasker
or similar) – Masker object.~SCALE.inputs_ (
dict
) – Inputs to the Estimator. For CBMA estimators, there is only one key: coordinates. This is an edited version of the dataset’s coordinates DataFrame.~SCALE.null_distributions_ (
dict
ofnumpy.ndarray
) –Null distribution information. Entries are added to this attribute if and when the corresponding method is applied.
Important
The voxel-wise null distributions used by this Estimator are very large, so they are not retained as Estimator attributes.
If
fit()
is applied:histogram_bins
: Array of bin centers for the null distribution histogram, ranging from zero to the maximum possible summary statistic value for the Dataset.
References
Langner, Robert, et al. “Meta-analytic connectivity modeling revisited: controlling for activation base rates.” NeuroImage 99 (2014): 559-570. https://doi.org/10.1016/j.neuroimage.2014.06.007
Methods
Perform Monte Carlo-based FWE correction.
fit
(dataset[, drop_invalid])Fit Estimator to Dataset.
get_params
([deep])Get parameters for this estimator.
load
(filename[, compressed])Load a pickled class instance from file.
save
(filename[, compress])Pickle the class instance to the provided file.
set_params
(**params)Set the parameters of this estimator.
- correct_fwe_montecarlo()[source]
Perform Monte Carlo-based FWE correction.
Warning
This method is not implemented for this class.
- fit(dataset, drop_invalid=True)[source]
Fit Estimator to Dataset.
- Parameters
- Returns
Results of Estimator fitting.
- Return type
- Variables
~Estimator.fit.inputs_ (
dict
) – Inputs used in _fit.
- classmethod load(filename, compressed=True)[source]
Load a pickled class instance from file.
- Parameters
- Returns
obj – Loaded class object.
- Return type
class object
- 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.- Return type
self