Sampling_freq – sampling freq in hertz (i.e. Nilearn implementation, but this can be overridden using kwargs. Does not default to detrending and standardizing like Out filter ( sampling_freq = None, high_pass = None, low_pass = None, ** kwargs ) ¶Īpply 5th order butterworth filter to data. Mean within each ROI across images Return type : N_components – if metric=’pca’, number of components to return (takes any input into ) Metric – type of extraction method, (default=mean) Mask – (nifti) nibabel mask can be binary or numbered for Initalize Brain_Data.data as empty extract_roi ( mask, metric = 'mean', n_components = None ) ¶ empty ( data = True, Y = True, X = True ) ¶ (Adjacency) Outputs a 2D distance matrix. Metric – (str) type of distance metric (can use any scikit learn or Out distance ( metric = 'euclidean', ** kwargs ) ¶Ĭalculate distance between images within a Brain_Data() instance. (Brain_Data) detrended Brain_Data instance Return type : Type – (‘linear’,’constant’, optional) type of detrending Returns : Remove linear trend from each voxel Parameters : If None then retainĪ dictionary of decomposition parameters Return type : N_components – (int) number of components. decompose ( algorithm = 'pca', axis = 'voxels', n_components = None, * args, ** kwargs ) ¶Īlgorithm – (str) Algorithm to perform decomposition bootstrap ( 'predict', n_samples = 5000, save_weights = True ) copy ( ) ¶Ĭreate a copy of a Brain_Data instance. bootstrap ( 'predict', n_samples = 5000, algorithm = 'ridge' ) > b = dat. bootstrap ( 'mean', n_samples = 5000 ) > b = dat. Summarized studentized bootstrap output Return type : N_jobs – (int) The number of CPUs to use to do the computation. Save_weights – (bool) Save each bootstrap iteration (useful for aggregating N_samples – (int) number of samples to bootstrap with replacement Parameters :įunction – (str) method to apply to data for each bootstrap Parameters :īrain_Data instance with new datatype Return type :īrain_Data bootstrap ( function, n_samples = 5000, save_weights = False, n_jobs = -1, random_state = None, * args, ** kwargs ) ¶īootstrap a Brain_Data method. (Brain_Data) masked Brain_Data object Return type :Ĭast Brain_Data.data as type. Resample_mask_to_brain – (bool) Will resample mask to brain space before applying mask (default=False). Mask – (Brain_Data or nifti object) mask to apply to Brain_Data object. Resampled into the Brain_Data space, then set resample_mask_to_brain=True. Note target data will be resampled into the same space as the mask. Out apply_mask ( mask, resample_mask_to_brain = False ) ¶ (Brain_Data) new appended Brain_Data instance Return type : Kwargs – optional inputs to Design_Matrix append > original_data = np.dot(out.data,out.T)Īppend data to Brain_Data instance Parameters :ĭata – (Brain_Data) Brain_Data instance to append Transformation matrix, and the shared response matrix Return type : (dict) a dictionary containing transformed object, Target – (Brain_Data) object to align to. See for aligning multiple Brain_Data instances Parameters : Projected to original data using Tranformation matrix. When using SRM, target must be a previouslyĮstimated common model stored as a numpy array. Using hyperalignment, target image can be another subject or anĪlready estimated common model. **kwargs – Additional keyword arguments to pass to the predictionĬreate new Brain_Data instance that aggregages func over mask align ( target, method = 'procrustes', axis = 0, * args, ** kwargs ) ¶Īlign Brain_Data instance to target object using functional alignmentĪlignment type can be hyperalignment or Shared Response Model. Mask – binary nifiti file to mask brain data X – Pandas DataFrame Design Matrix for running univariate models Rather than a 3-dimensional matrix.This makes it easier to perform dataĭata – nibabel data instance or list of files Brain_Data ( data = None, Y = None, X = None, mask = None, ** kwargs ) ¶īrain_Data is a class to represent neuroimaging data in python as a vector nltools.data: Data Types ¶ class nltools.data. Methods in the current release of Neurolearn. This reference provides detailed documentation for all modules, classes, and
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |