mfe (version 0.1.5)

clustering: Clustering Meta-features

Description

Clustering measures extract information about validation index.

Usage

clustering(...)
# S3 method for default
clustering(
  x,
  y,
  features = "all",
  summary = c("mean", "sd"),
  transform = TRUE,
  ...
)
# S3 method for formula
clustering(
  formula,
  data,
  features = "all",
  summary = c("mean", "sd"),
  transform = TRUE,
  ...
)

Arguments

...

Further arguments passed to the summarization functions.

x

A data.frame contained only the input attributes.

y

A factor response vector with one label for each row/component of x.

features

A list of features names or "all" to include all them.

summary

A list of summarization functions or empty for all values. See post.processing method to more information. (Default: c("mean", "sd"))

transform

A logical value indicating if the categorical attributes should be transformed. If FALSE they will be ignored. (Default: TRUE)

formula

A formula to define the class column.

data

A data.frame dataset contained the input attributes and class. The details section describes the valid values for this group.

Value

A list named by the requested meta-features.

Details

The following features are allowed for this method:

"vdu"

Calculate the Dunn Index.

"vdb"

Calculate the Davies and Bouldin Index.

"int"

Calculate the INT index.

"sil"

Calculate the mean silhouette value from data.

"pb"

Pearson Correlation between class matching and instance distances.

"ch"

Calinski and Harabaz index.

"nre"

Normalized relative entropy.

"sc"

Mean of the number of examples per class.

References

Bruno A. Pimentel, and Andre C. P. L. F. de Carvalho. A new data characterization for selecting clustering algorithms using meta-learning. Information Sciences, volume 477, pages 203 - 219, 2019.

See Also

Other meta-features: complexity(), concept(), general(), infotheo(), itemset(), landmarking(), model.based(), relative(), statistical()

Examples

# NOT RUN {
## Extract all meta-features using formula
clustering(Species ~ ., iris)

## Extract some meta-features
clustering(iris[1:4], iris[5], c("vdu", "vdb", "sil"))

## Use another summarization function
clustering(Species ~ ., iris, summary=c("min", "median", "max"))
# }