Fork me on GitHub

split-table: Split a feature table into training and testing sets.ΒΆ

Docstring:

Usage: qiime sample-classifier split-table [OPTIONS]

  Split a feature table into training and testing sets. By default
  stratifies training and test sets on a metadata column, such that values
  in that column are evenly represented across training and test sets.

Options:
  --i-table ARTIFACT PATH FeatureTable[Frequency]
                                  Feature table containing all features that
                                  should be used for target prediction.
                                  [required]
  --m-metadata-file MULTIPLE FILE
                                  Metadata file or artifact viewable as
                                  metadata. This option may be supplied
                                  multiple times to merge metadata.
                                  [required]
  --m-metadata-column MetadataColumn[Categorical | Numeric]
                                  Column from metadata file or artifact
                                  viewable as metadata. Numeric metadata
                                  column to use as prediction target.
                                  [required]
  --p-test-size FLOAT             Fraction of input samples to exclude from
                                  training set and use for classifier testing.
                                  [default: 0.2]
  --p-random-state INTEGER        Seed used by random number generator.
                                  [optional]
  --p-stratify / --p-no-stratify  Evenly stratify training and test data among
                                  metadata categories. If True, all values in
                                  column must match at least two samples.
                                  [default: True]
  --p-missing-samples [ignore|error]
                                  How to handle missing samples in metadata.
                                  "error" will fail if missing samples are
                                  detected. "ignore" will cause the feature
                                  table and metadata to be filtered, so that
                                  only samples found in both files are
                                  retained.  [default: error]
  --o-training-table ARTIFACT PATH FeatureTable[Frequency]
                                  Feature table containing training samples
                                  [required if not passing --output-dir]
  --o-test-table ARTIFACT PATH FeatureTable[Frequency]
                                  Feature table containing test samples
                                  [required if not passing --output-dir]
  --output-dir DIRECTORY          Output unspecified results to a directory
  --cmd-config FILE               Use config file for command options
  --verbose                       Display verbose output to stdout and/or
                                  stderr during execution of this action.
                                  [default: False]
  --quiet                         Silence output if execution is successful
                                  (silence is golden).  [default: False]
  --citations                     Show citations and exit.
  --help                          Show this message and exit.

Import:

from qiime2.plugins.sample_classifier.methods import split_table

Docstring:

Split a feature table into training and testing sets.

Split a feature table into training and testing sets. By default stratifies
training and test sets on a metadata column, such that values in that
column are evenly represented across training and test sets.

Parameters
----------
table : FeatureTable[Frequency]
    Feature table containing all features that should be used for target
    prediction.
metadata : MetadataColumn[Categorical | Numeric]
    Numeric metadata column to use as prediction target.
test_size : Float % Range(0.0, 1.0, inclusive_start=False), optional
    Fraction of input samples to exclude from training set and use for
    classifier testing.
random_state : Int, optional
    Seed used by random number generator.
stratify : Bool, optional
    Evenly stratify training and test data among metadata categories. If
    True, all values in column must match at least two samples.
missing_samples : Str % Choices({'error', 'ignore'}), optional
    How to handle missing samples in metadata. "error" will fail if missing
    samples are detected. "ignore" will cause the feature table and
    metadata to be filtered, so that only samples found in both files are
    retained.

Returns
-------
training_table : FeatureTable[Frequency]
    Feature table containing training samples
test_table : FeatureTable[Frequency]
    Feature table containing test samples