nimare.decode.continuous
.CorrelationDecoder
- class CorrelationDecoder(feature_group=None, features=None, frequency_threshold=0.001, meta_estimator=None, target_image='z_desc-association', n_cores=1)[source]
Bases:
Decoder
Decode an unthresholded image by correlating the image with meta-analytic maps.
Changed in version 0.1.0:
New method:
load_imgs
. Load pre-generated meta-analytic maps for decoding.New attribute: results_. MetaResult object containing masker, meta-analytic maps, and tables. This attribute replaces masker, features_, and images_.
Changed in version 0.0.13:
New parameter: n_cores. Number of cores to use for parallelization.
Changed in version 0.0.12:
Remove low-memory option in favor of sparse arrays.
- Parameters:
feature_group (
str
, optional) – Feature groupfeatures (
list
, optional) – Featuresfrequency_threshold (
float
, optional) – Frequency thresholdmeta_estimator (
CBMAEstimator
, optional) – Meta-analysis estimator. Default isMKDAChi2
.target_image (
str
, optional) – Name of meta-analysis results image to use for decoding.n_cores (
int
, optional) – Number of cores to use for parallelization. If <=0, defaults to using all available cores. Default is 1.
Warning
Coefficients from correlating two maps have very large degrees of freedom, so almost all results will be statistically significant. Do not attempt to evaluate results based on significance.
Methods
fit
(dataset[, drop_invalid])Fit Decoder to Dataset.
get_params
([deep])Get parameters for this estimator.
load
(filename[, compressed])Load a pickled class instance from file.
load_imgs
(features_imgs[, mask])Load pregenerated maps from disk.
save
(filename[, compress])Pickle the class instance to the provided file.
set_params
(**params)Set the parameters of this estimator.
transform
(img)Correlate target image with each feature-specific meta-analytic map.
- fit(dataset, drop_invalid=True)[source]
Fit Decoder to Dataset.
- Parameters:
Notes
The
fit
method is a light wrapper that runs input validation and preprocessing before fitting the actual model. Decoders’ individual “fitting” methods are implemented as_fit
, although users should callfit
.Selection of features based on requested features and feature group is performed in
Decoder._preprocess_input
.
- classmethod load(filename, compressed=True)[source]
Load a pickled class instance from file.
- Parameters:
- Returns:
obj – Loaded class object.
- Return type:
class object
- load_imgs(features_imgs, mask=None)[source]
Load pregenerated maps from disk.
Added in version 0.1.0.
- Parameters:
features_imgs (
dict
, or str) – Dictionary with feature names as keys and paths to images as values. If a string is provided, it is assumed to be a path to a folder with NIfTI images, where the file’s name (without the extension .nii.gz) will be considered as the feature name by the decoder.mask (str,
nibabel.nifti1.Nifti1Image
, or any nilearn Masker) – Mask to apply to pre-generated maps.
- Variables:
results (
MetaResult
) – MetaResult with meta-analytic maps and masker added.
- 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
- transform(img)[source]
Correlate target image with each feature-specific meta-analytic map.
- Parameters:
img (
Nifti1Image
) – Image to decode. Must be in same space asdataset
.- Returns:
out_df – DataFrame with one row for each feature, an index named “feature”, and one column: “r”.
- Return type: