create_IDA14_attributes: Generate IDA'14 Attributes

In unmnn/evoxploit: Augment Evolution Features to a Longitudinal Study Dataset

Description

Generate sequence features as described in \insertCiteHielscher:IDA14evoxploit.

Usage

create_IDA14_attributes(
  df,
  label,
  train_lgc = rep(TRUE, nrow(df)),
  suffix,
  kdist_sample_size = 50,
  seed = 123,
  verbose = FALSE
)

Arguments

df	A data frame.
label	The class labels given as factor vector.
train_lgc	A logical vector. TRUE elements represent training instances of df. If not set, all instances of df are treated as training instances.
suffix	A string indicating the start of the wave index suffix.
kdist_sample_size	The number of randomly sampled epsilon values drawn from dist_to_line used as candidates for clustering. Weighted random sampling is used: the larger dist_to_line, the higher the probability of being drawn.
seed	Random seed. Used to draw a random sample from the k-distances.
verbose	Whether or not to show some diagnostic messages. Defaults to FALSE.

Value

A data frame. For each attribute a, the data frame contains an attribute a_seq.

References

\insertAllCited

See Also

create_CBMS15_attributes, create_simple_attributes

unmnn/evoxploit documentation built on Oct. 28, 2020, 12:24 p.m.