createCentroidPlot: Create plot of cluster centroids.

In toaster: Big Data in-Database Analytics that Scales with Teradata Aster Distributed Platform

Description

Visualize centroids produced by clustering function like k-means. Plots available are line plot, bar plot, or heatmap. Parameter format specifies which one to create.

Usage

createCentroidPlot(km, format = "line", groupByCluster = TRUE,
  clusters = rownames(km$centers), dims = colnames(km$centers),
  baseSize = 12, baseFamily = "serif", title = paste("Cluster Centroids",
  format, "Plot"), xlab, ylab = ifelse(format == "heatmap", "cluster",
  ifelse(!is.null(km$scale) && km$scale, "scaled value", "value")),
  legendPosition = ifelse(format == "bar", "none", "right"),
  coordFlip = FALSE, ticks = FALSE, defaultTheme = theme_tufte(base_size =
  baseSize, base_family = baseFamily, ticks = ticks), themeExtra = NULL)

Arguments

km	an object of class "toakmeans" returned by computeKmeans or of class "kmeans" returned by kmeans.
format	type of plot to use: "line", "bar", "bar_dodge" or "heatmap".
groupByCluster	logical: indicates if centroids are grouped by clusters or variables. groupByCluster has no effect when format="heatmap".
clusters	optional vector with clusters to include. If vector has named values then names are used for cluster labels. By default, all clusters are included.
dims	optional vector with dimensions to include. Vector may be contain either dimension indices or names. By default, all dimensions are included.
baseSize	theme base font size.
baseFamily	theme base font family.
title	plot title.
xlab	a label for the x axis, defaults to a description of x.
ylab	a label for the y axis, defaults to a description of y.
legendPosition	the position of legends. ("left", "right", "bottom", "top", or two-element numeric vector). "none" is no legend.
coordFlip	logical flipped cartesian coordinates so that horizontal becomes vertical, and vertical horizontal (see coord_flip).
ticks	logical Show axis ticks using default theme settings (see defaultTheme)?
defaultTheme	plot theme settings with default value theme_tufte. More themes are available here: ggtheme (by ggplot2) and ggthemes.
themeExtra	any additional theme settings that override default theme.

Value

ggplot object

Examples

if(interactive()){
# initialize connection to Lahman baseball database in Aster 
conn = odbcDriverConnect(connection="driver={Aster ODBC Driver};
                         server=<dbhost>;port=2406;database=<dbname>;uid=<user>;pwd=<pw>")
                         
km = computeKmeans(conn, "batting", centers=5, iterMax = 25,
                   aggregates = c("COUNT(*) cnt", "AVG(g) avg_g", "AVG(r) avg_r", "AVG(h) avg_h"),
                   id="playerid || '-' || stint || '-' || teamid || '-' || yearid", 
                   include=c('g','r','h'), scaledTableName='kmeans_test_scaled', 
                   centroidTableName='kmeans_test_centroids',
                   where="yearid > 2000")
createCentroidPlot(km)
# As clusters fluctuate from run to run cluster names may be inconsistent
createCentroidPlot(km, format="bar_dodge", 
                   clusters=c(Stars=3, Reserve=4), dims=c('g','h'))
createCentroidPlot(km, format="heatmap", coordFlip=TRUE)
}

Example output

Loading required package: RODBC

toaster documentation built on May 30, 2017, 3:51 a.m.