Fork me on GitHub

feature-volatility: Feature volatility analysisΒΆ

Docstring:

Usage: qiime longitudinal feature-volatility [OPTIONS]

  Identify features that are predictive of a numeric metadata column,
  state_column (e.g., time), and plot their relative frequencies across
  states using interactive feature volatility plots. A supervised learning
  regressor is used to identify important features and assess their ability
  to predict sample states. state_column will typically be a measure of
  time, but any numeric metadata column can be used.

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. Sample
                                  metadata file containing
                                  individual_id_column.  [required]
  --p-state-column TEXT           Metadata containing collection time (state)
                                  values for each sample. Must contain
                                  exclusively numeric values.  [required]
  --p-individual-id-column TEXT   Metadata column containing IDs for
                                  individual subjects.  [optional]
  --p-cv INTEGER RANGE            Number of k-fold cross-validations to
                                  perform.  [default: 5]
  --p-random-state INTEGER        Seed used by random number generator.
                                  [optional]
  --p-n-jobs INTEGER              Number of jobs to run in parallel.
                                  [default: 1]
  --p-n-estimators INTEGER RANGE  Number of trees to grow for estimation. More
                                  trees will improve predictive accuracy up to
                                  a threshold level, but will also increase
                                  time and memory requirements. This parameter
                                  only affects ensemble estimators, such as
                                  Random Forest, AdaBoost, ExtraTrees, and
                                  GradientBoosting.  [default: 100]
  --p-estimator [SVR|ElasticNet|ExtraTreesRegressor|RandomForestRegressor|LinearSVR|Ridge|AdaBoostRegressor|Lasso|KNeighborsRegressor|GradientBoostingRegressor]
                                  Estimator method to use for sample
                                  prediction.  [default:
                                  RandomForestRegressor]
  --p-parameter-tuning / --p-no-parameter-tuning
                                  Automatically tune hyperparameters using
                                  random grid search.  [default: False]
  --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-filtered-table ARTIFACT PATH FeatureTable[RelativeFrequency]
                                  Feature table containing only important
                                  features.  [required if not passing
                                  --output-dir]
  --o-feature-importance ARTIFACT PATH FeatureData[Importance]
                                  Importance of each input feature to model
                                  accuracy.  [required if not passing
                                  --output-dir]
  --o-volatility-plot VISUALIZATION PATH
                                  Interactive volatility plot visualization.
                                  [required if not passing --output-dir]
  --o-accuracy-results VISUALIZATION PATH
                                  Accuracy results visualization.  [required
                                  if not passing --output-dir]
  --o-sample-estimator ARTIFACT PATH SampleEstimator[Regressor]
                                  Trained sample regressor.  [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.longitudinal.pipelines import feature_volatility

Docstring:

Feature volatility analysis

Identify features that are predictive of a numeric metadata column,
state_column (e.g., time), and plot their relative frequencies across
states using interactive feature volatility plots. A supervised learning
regressor is used to identify important features and assess their ability
to predict sample states. state_column will typically be a measure of time,
but any numeric metadata column can be used.

Parameters
----------
table : FeatureTable[Frequency]
    Feature table containing all features that should be used for target
    prediction.
metadata : Metadata
    Sample metadata file containing individual_id_column.
state_column : Str
    Metadata containing collection time (state) values for each sample.
    Must contain exclusively numeric values.
individual_id_column : Str, optional
    Metadata column containing IDs for individual subjects.
cv : Int % Range(1, None), optional
    Number of k-fold cross-validations to perform.
random_state : Int, optional
    Seed used by random number generator.
n_jobs : Int, optional
    Number of jobs to run in parallel.
n_estimators : Int % Range(1, None), optional
    Number of trees to grow for estimation. More trees will improve
    predictive accuracy up to a threshold level, but will also increase
    time and memory requirements. This parameter only affects ensemble
    estimators, such as Random Forest, AdaBoost, ExtraTrees, and
    GradientBoosting.
estimator : Str % Choices({'AdaBoostRegressor', 'ElasticNet', 'ExtraTreesRegressor', 'GradientBoostingRegressor', 'KNeighborsRegressor', 'Lasso', 'LinearSVR', 'RandomForestRegressor', 'Ridge', 'SVR'}), optional
    Estimator method to use for sample prediction.
parameter_tuning : Bool, optional
    Automatically tune hyperparameters using random grid search.
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
-------
filtered_table : FeatureTable[RelativeFrequency]
    Feature table containing only important features.
feature_importance : FeatureData[Importance]
    Importance of each input feature to model accuracy.
volatility_plot : Visualization
    Interactive volatility plot visualization.
accuracy_results : Visualization
    Accuracy results visualization.
sample_estimator : SampleEstimator[Regressor]
    Trained sample regressor.