maxfuse.utils

General utility functions

Functions

cca_embedding	Filter bad matched pairs, align arr1 and arr2 using init_matching, fit CCA, and get CCA embeddings of arr1 and arr2.
cdist_correlation	Calculate pair-wise 1 - Pearson correlation between X and Y.
center_scale	Column-wise center and scale by standard deviation.
dict_to_list	Convert dict_ into a list.
drop_zero_variability_columns	Drop columns for which its standard deviation is zero in any one of the arrays in arr_list.
filter_bad_matches	Filter bad matches according to the distances of matched pairs.
get_centroids	Compute the centroids (cluster mean) of arr.
graph_smoothing	For each row of arr, shrink it towards the average of its neighborhood by taking wt*raw_data + (1-wt)*nhbd_avg
list_to_dict	Convert list_ to a dict.
pearson_correlation	Calculate the vector of pearson correlations between each row of arr1 and arr2.
process_count_data	Process count data according to scanpy pipeline.
recode	Recode the cluster labels to 0, 1, ..., num_clusters-1
robust_svd	Do deterministic or randomized SVD on arr.
shrink_towards_centroids	For each row of arr, shrink it towards its cluster centroid by taking wt*raw_data + (1-wt)*centroid
sort_dict	Return a copy of dict_ with both keys and values sorted.
summarize_clustering	Compute the majority cell type for each cluster.
svd_denoise	Compute best rank-n_components approximation of arr by SVD.
svd_embedding	Compute rank-n_components SVD embeddings of arr.