fftRtsne: Wraper for running FIt-SNE. Code from KlugerLab...

fftRtsneR Documentation

Wraper for running FIt-SNE. Code from KlugerLab (https://github.com/KlugerLab/FIt-SNE)

Description

Wraper for running FIt-SNE. Code from KlugerLab (https://github.com/KlugerLab/FIt-SNE)

Usage

fftRtsne(
  X,
  dims = 2,
  perplexity = 30,
  theta = 0.5,
  max_iter = 1000,
  fft_not_bh = TRUE,
  ann_not_vptree = TRUE,
  stop_early_exag_iter = 250,
  exaggeration_factor = 12,
  no_momentum_during_exag = FALSE,
  start_late_exag_iter = -1,
  late_exag_coeff = 1,
  mom_switch_iter = 250,
  momentum = 0.5,
  final_momentum = 0.8,
  learning_rate = 200,
  n_trees = 50,
  search_k = -1,
  rand_seed = -1,
  nterms = 3,
  intervals_per_integer = 1,
  min_num_intervals = 50,
  K = -1,
  sigma = -30,
  initialization = NULL,
  data_path = NULL,
  result_path = NULL,
  out_prefix = NULL,
  load_affinities = NULL,
  fast_tsne_path = NULL,
  nthreads = 0,
  perplexity_list = NULL,
  get_costs = FALSE,
  df = 1
)

Arguments

X

matrix; samples in rows and variables in columns

dims

integer; dimentionality of the returned matrix

perplexity

double; perplexity parameter of tSNE (effective nearest neighbours)

theta

double; theta

max_iter

integer; max_iter

fft_not_bh

logical; fft_not_bh (default: TRUE)

ann_not_vptree

logical; (default: TRUE)

stop_early_exag_iter

integer; (default 250)

exaggeration_factor

double;

no_momentum_during_exag

logical;

start_late_exag_iter

double;

late_exag_coeff

double;

mom_switch_iter

double;

momentum

double;

final_momentum

double;

learning_rate

double;

n_trees

integer;

search_k

double;

rand_seed

double;

nterms

integer;

intervals_per_integer

integer;

min_num_intervals

integer;

K

integer;

sigma

double;

initialization

matrix

data_path

character;

result_path

character;

out_prefix

character; temporary files prefix for fast_tsne (default: NULL)

load_affinities

character;

fast_tsne_path

character; full path of the installed fast_tsne programe (default: NULL)

nthreads

integer; number of threads (default: 0)

perplexity_list

list;

get_costs

logical;

df

numeric;

Details

Run FIt-SNE

Value

a matrix with samples in rows and tSNE coordinate in columns


Japrin/sscClust documentation built on Dec. 15, 2022, 1:04 p.m.