tangram.mapping_optimizer.MapperConstrained

class tangram.mapping_optimizer.MapperConstrained(S, G, d, lambda_d=1, lambda_g1=1, lambda_g2=1, lambda_r=0, lambda_count=1, lambda_f_reg=1, target_count=None, device='cpu', adata_map=None, random_state=None)

Allows instantiating and running the optimizer for Tangram, with filtering. Once instantiated, the optimizer is run with the ‘train’ method, which also returns the mapping and filter results.

MapperConstrained.train(num_epochs[, …])

Run the optimizer and returns the mapping outcome.