Fork me on GitHub

tsne: t-distributed stochastic neighbor embeddingΒΆ

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.
  --use-cache DIRECTORY  Specify the cache to be used for the intermediate
                         work of this action. If not provided, the default
                         cache under $TMP/qiime2/ will be used.
                         IMPORTANT FOR HPC USERS: If you are on an HPC system
                         and are using parallel execution it is important to
                         set this to a location that is globally accessible to
                         all nodes in the cluster.
  --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.