[−][src]Function bhtsne::run
pub fn run(
x: &mut [f64],
n: usize,
d: usize,
y: &mut [f64],
no_dims: usize,
perplexity: f64,
theta: f64,
skip_random_init: bool,
max_iter: u64,
stop_lying_iter: u64,
mom_switch_iter: u64
)
Performs t-SNE.
Arguments
-
x
- A&mut [f64]
containing the data to embed. -
n
- Ausize
that represents the number ofd
-dimensional points inx
. -
d
- Ausize
that represents the dimension of each point. -
y
- A&mut [f64]
where to store the resultant embedding. -
no_dims
- Ausize
that represents the dimension of the embedded points. -
perplexity
- Anf64
representing perplexity value. -
theta
- Anf64
representing the theta value. Iftheta
is set to0.0
the exact version of t-SNE will be used, if set to greater values the Barnes-Hut version will be used instead. -
skip_random_init
- Abool
stating wether to skip the random initialization ofy
. In most cases it should be set tofalse
. -
max_iter
- Au64
indicating the maximum number of iterations to perform the fitting. -
stop_lying_iter
- Au64
indicating the number of the iteration after which the P distribution values become “true“. -
mom_switch_iter
- Au64
indicating the number of the iteration after which the momentum's value is set to its final value.