Docstring:
Usage: qiime diversity tsne [OPTIONS]
Apply t-distributed stochastic neighbor embedding.
Inputs:
--i-distance-matrix ARTIFACT
DistanceMatrix The distance matrix on which t-SNE should be
computed. [required]
Parameters:
--p-number-of-dimensions INTEGER
Range(2, None) Dimensions to reduce the distance matrix to.
[default: 2]
--p-perplexity NUMBER Provide the balance between local and global
Range(1, None) structure. Low values concentrate on local structure.
Large values sacrifice local details for a broader
global embedding. The default value is 25 to achieve
better results for small microbiome datasets.
[default: 25.0]
--p-n-iter INTEGER
Range(1, None) [default: 1000]
--p-learning-rate NUMBER
Range(10.0, None) Controls how much the weights are adjusted at each
update. [default: 200.0]
--p-early-exaggeration NUMBER
Range(0, None) Affects the tightness of the shown clusters. Larger
values increase the distance between natural clusters
in the embedded space. [default: 12.0]
--p-random-state INTEGER
Seed used by random number generator. [optional]
Outputs:
--o-tsne ARTIFACT The resulting t-SNE matrix.
PCoAResults [required]
Miscellaneous:
--output-dir PATH Output unspecified results to a directory
--verbose / --quiet Display verbose output to stdout and/or stderr
during execution of this action. Or silence output if
execution is successful (silence is golden).
--example-data PATH Write example data and exit.
--citations Show citations and exit.
--help Show this message and exit.
Import:
from qiime2.plugins.diversity.methods import tsne
Docstring:
t-distributed stochastic neighbor embedding
Apply t-distributed stochastic neighbor embedding.
Parameters
----------
distance_matrix : DistanceMatrix
The distance matrix on which t-SNE should be computed.
number_of_dimensions : Int % Range(2, None), optional
Dimensions to reduce the distance matrix to.
perplexity : Float % Range(1, None), optional
Provide the balance between local and global structure. Low values
concentrate on local structure. Large values sacrifice local details
for a broader global embedding. The default value is 25 to achieve
better results for small microbiome datasets.
n_iter : Int % Range(1, None), optional
learning_rate : Float % Range(10.0, None), optional
Controls how much the weights are adjusted at each update.
early_exaggeration : Float % Range(0, None), optional
Affects the tightness of the shown clusters. Larger values increase the
distance between natural clusters in the embedded space.
random_state : Int, optional
Seed used by random number generator.
Returns
-------
tsne : PCoAResults
The resulting t-SNE matrix.
