mv_feature_filter {structToolbox}R Documentation

filter features by fraction of missing values

Description

Filters features by the percent number of missing values, based on class labels if required.

Usage

mv_feature_filter(
  threshold = 20,
  qc_label = "QC",
  method = "QC",
  factor_name,
  ...
)

Arguments

threshold

The max percentage missing values in a feature, above which the feature is removed. Default is 20.

qc_label

The label of the QC samples in the named sample_meta column.

method

"within_all" applies filter within classes,"within_one" applies filter within any one class, "QC" applies filter within QC samples, "across" applies filter ignoring class.

factor_name

The name of the sample_meta column to use.

...

additional slots and values passed to struct_class

Value

struct object

Examples

D = iris_DatasetExperiment()
M = mv_feature_filter(factor_name='Species',qc_label='versicolor')
M = model_apply(M,D)

[Package structToolbox version 1.0.1 Index]