map.kmeans.features: Kmeans distance to center feature mappings

In XanderHorn/lazy: Automated data pre-processing and machine learning

Description

Creates mapping tables for each numerical feature containing the center for each feature's min and max value. These tables can then be applied using the function 'apply.kmeans.mappings' to calculate the distance to cluster center for each feature. Each feature is scaled by converting it to a range between 0 and 1 before clustering.

Usage

map.kmeans.features(data, x, clusters = 3, sample.size = 0.3,
  seed = 1, progress = TRUE)

Arguments

data	[required | data.frame] Dataset containing categorical features
x	[required | character] A vector of categorical feature names present in the dataset
clusters	[optional | integer | default=3] The number of clusters to create in each feature
sample.size	[optional | numeric | default=0.3] Percentage to down sample data for decreased computation time
seed	[optional | integer| default=1] The random number seed for reproducable results
progress	[optional | logical | default=TRUE] Display a progress bar

Value

List of data frames containing mapping tables

Author(s)

Xander Horn

Examples

res <- map.kmeans.features(data = iris, x = setdiff(names(iris), "Species"))

XanderHorn/lazy documentation built on Jan. 16, 2021, 6:15 p.m.