/
treemap.Rd
337 lines (270 loc) · 20.8 KB
/
treemap.Rd
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/treemap.R
\name{treemap}
\alias{treemap}
\title{Create a treemap}
\usage{
treemap(dtf, index, vSize, vColor = NULL, stdErr = NULL, type = "index",
fun.aggregate = "sum", title = NA, title.legend = NA,
algorithm = "pivotSize", sortID = "-size", mirror.x = FALSE,
mirror.y = FALSE, palette = NA, palette.HCL.options = NULL,
range = NA, mapping = NA, n = 7, fontsize.title = 14,
fontsize.labels = 11, fontsize.legend = 12, fontcolor.labels = NULL,
fontface.labels = c("bold", rep("plain", length(index) - 1)),
fontfamily.title = "sans", fontfamily.labels = "sans",
fontfamily.legend = "sans", border.col = "black",
border.lwds = c(length(index) + 1, (length(index) - 1):1),
lowerbound.cex.labels = 0.4, inflate.labels = FALSE, bg.labels = NULL,
force.print.labels = FALSE, overlap.labels = 0.5,
align.labels = c("center", "center"), xmod.labels = 0, ymod.labels = 0,
eval.labels = FALSE, position.legend = NULL, drop.unused.levels = TRUE,
aspRatio = NA, vp = NULL, draw = TRUE, ...)
}
\arguments{
\item{dtf}{a data.frame. Required.}
\item{index}{vector of column names in \code{dtf} that specify the aggregation indices. It could contain only one column name, which results in a treemap without hierarchy. If multiple column names are provided, the first name is the highest aggregation level, the second name the second-highest aggregation level, and so on. Required.}
\item{vSize}{name of the column in \code{dtf} that specifies the sizes of the rectangles. Required.}
\item{vColor}{name of the column that, in combination with \code{type}, determines the colors of the rectangles. The variable can be scaled by the addition of "*<scale factor>" or "/<scale factor>". Note: when omitted for \code{"value"} treemaps, a contant value of 1 is taken.}
\item{stdErr}{name of the column that contains standard errors. These are not used for the treemaps, but only aggregated accordingly and returned as item of the output list.}
\item{type}{type of the treemap, which determines how the rectangles are colored:
\describe{
\item{\code{"index"}:}{colors are determined by the \code{index} variables. Different branches in the hierarchical tree get different colors. For this type, \code{vColor} is not needed.}
\item{\code{"value"}:}{the numeric \code{vColor}-column is directly mapped to a color palette. This palette is diverging, so that values of 0 are assigned to the mid color (white or yellow), and negative and positive values are assigned to color based on two different hues colors (by default reds for negative and greens for positive values). For more freedom, see \code{"manual"}.}
\item{\code{"comp"}:}{colors indicate change of the \code{vSize}-column with respect to the numeric \code{vColor}-column in percentages. Note: the negative scale may be different from the positive scale in order to compensate for the ratio distribution.}
\item{\code{"dens"}:}{colors indicate density. This is analogous to a population density map where \code{vSize}-values are area sizes, \code{vColor}-values are populations per area, and colors are computed as densities (i.e. population per squared km).}
\item{\code{"depth"}:}{each aggregation level (defined by \code{index}) has a distinct color. For this type, \code{vColor} is not needed.}
\item{\code{"categorical"}:}{\code{vColor} is a factor column that determines the color.}
\item{\code{"color"}:}{\code{vColor} is a vector of colors in the hexadecimal (#RRGGBB) format}
\item{\code{"manual"}:}{The numeric \code{vColor}-column is directly mapped to a color palette. Both palette and range should be provided. The palette is mapped linearly to the range.}}}
\item{fun.aggregate}{aggregation function, only used in \code{"value"} treemaps. This function determines how values of the lowest aggregation level are aggregated. By default, it takes the \code{sum}. Other sensible functions are \code{mean} and \code{weighted.mean}. In the latter case, the weights are determined by the \code{vSize} variable. Other arguments can be passed on. For \code{weighted.mean}, it is possible to assign a variable name for its \code{w} argument.}
\item{title}{title of the treemap.}
\item{title.legend}{title of the legend.}
\item{algorithm}{name of the used algorithm: \code{"squarified"} or \code{"pivotSize"}. The squarified treemap algorithm (Bruls et al., 2000) produces good aspect ratios, but ignores the sorting order of the rectangles (\code{sortID}). The ordered treemap, pivot-by-size, algorithm (Bederson et al., 2002) takes the sorting order (\code{sortID}) into account while aspect ratios are still acceptable.}
\item{sortID}{name of the variable that determines the order in which the rectangles are placed from top left to bottom right. Only applicable when \code{algorithm=="pivotSize"}. Also the values "size" and "color" can be used, which refer to \code{vSize} and \code{vColor} respectively. To inverse the sorting order, use "-" in the prefix. By default, large rectangles are placed top left.}
\item{mirror.x}{logical that determines whether the rectangles are mirrored horizontally}
\item{mirror.y}{logical that determines whether the rectangles are mirrored vertically}
\item{palette}{one of the following:
\describe{
\item{a color palette:}{i.e., a vector of hexadecimal colors (#RRGGBB)}
\item{a name of a Brewer palette:}{See \code{RColorBrewer::display.brewer.all()} for the options. The palette can be reversed by prefixing with a "-". For treemap types "value" and "comp", a diverging palette should be chosen (default="RdYlGn"), for type "dens" a sequential (default="OrRd"). The default value for "depth" is "Set2".}
\item{"HCL":}{Tree Colors are color schemes derived from the Hue-Chroma-Luminance color space model. This is only applicable for qualitative palettes, which are applied to the treemap types "index", "depth", and "categorical". For "index" and "categorical" this is the default value.}}}
\item{palette.HCL.options}{list of advanced options to obtain Tree Colors from the HCL space (when \code{palette="HCL"}). This list contains:
\describe{
\item{\code{hue_start}:}{number between 0 and 360 that determines the starting hue value (default: 30)}
\item{\code{hue_end}:}{number between \code{hue_start} and \code{hue_start + 360} that determines the ending hue value (default: 390)}
\item{\code{hue_perm}:}{boolean that determines whether the colors are permuted such that adjacent levels get more distinguishable colors. If \code{FALSE}, then the colors are equally distributed from \code{hue_start} to \code{hue_end} (default: TRUE)}
\item{\code{hue_rev}:}{boolean that determines whether the colors of even-numbered branched are reversed (to increase discrimination among branches)}
\item{\code{hue_fraction}:}{number between 0 and 1 that determines the fraction of the hue circle that is used for recursive color picking: if 1 then the full hue circle is used, which means that the hue of the colors of lower-level nodes are spread maximally. If 0, then the hue of the colors of lower-level nodes are identical of the hue of their parents. (default: .5)}
\item{\code{chroma}:}{chroma value of colors of the first-level nodes, that are determined by the first index variable (default: 60)}
\item{\code{luminance}:}{luminance value of colors of the first-level nodes, i.e. determined by the first index variable (default: 70)}
\item{\code{chroma_slope}:}{slope value for chroma of the non-first-level nodes. The chroma values for the second-level nodes are \code{chroma+chroma_slope}, for the third-level nodes \code{chroma+2*chroma_slope}, etc. (default: 5)}
\item{\code{luminance_slope}:}{slope value for luminance of the non-first-level nodes (default: -10)}} For "depth" and "categorical" types, only the first two items are used. Use \code{\link{treecolors}} to experiment with these parameters.}
\item{range}{range of values (so vector of two) that correspond to the color legend. By default, the range of actual values, determined by \code{vColor}, is used. Only applicable for numeric types, i.e. "value", "comp", "dens", and "manual". Note that the range doesn't affect the colors in the treemap itself for "value" and "manual" types; this is controlled by \code{mapping}.}
\item{mapping}{vector of three values that specifies the mapping of the actual values, determined by \code{vColor}, to \code{palette}. The three values are respectively the minimum value, the mid value, and the maximum value. The mid value is particularly useful for diverging color palettes, where it defined the middle, neutral, color which is typically white or yellow. The \code{mapping} should cover the \code{range}. By default, for "value" treemaps, it is \code{c(-max(abs(values)), 0, max(abs(values)))}, where values are the actual values defined by \code{vColor}. For "manual" treemaps, the default setting is \code{c(min(values), mean(range(values)), max(values))}. A vector of two can also be specified. In that case, the mid value will be the average of those. Only applicable for "value" and "manual" type treemaps.}
\item{n}{preferred number of categories by which numeric variables are discretized.}
\item{fontsize.title}{font size of the title}
\item{fontsize.labels}{font size(s) of the data labels, which is either a single number that specifies the font size for all aggregation levels, or a vector that specifies the font size for each aggregation level. Use value \code{0} to omit the labels for the corresponding aggregation level.}
\item{fontsize.legend}{font size for the legend}
\item{fontcolor.labels}{Specifies the label colors. Either a single color value, or a vector of color values one for each aggregation level. By default, white and black colors are used, depending on the background (\code{bg.labels}).}
\item{fontface.labels}{either a single value, or a vector of values one for each aggregation level. Values can be integers If an integer, following the R base graphics standard: 1 = plain, 2 = bold, 3 = italic, 4 = bold italic, or characters: \code{"plain"}, \code{"bold"}, \code{"italic"}, \code{"oblique"}, and \code{"bold.italic"}.}
\item{fontfamily.title}{font family of the title. Standard values are "serif", "sans", "mono", "symbol". Mapping is device dependent.}
\item{fontfamily.labels}{font family of the labels in each rectangle. Standard values are "serif", "sans", "mono", "symbol". Mapping is device dependent.}
\item{fontfamily.legend}{font family of the legend. Standard values are "serif", "sans", "mono", "symbol". Mapping is device dependent.}
\item{border.col}{color of borders drawn around each rectangle. Either one color for all rectangles or a vector of colors, or one for each aggregation level}
\item{border.lwds}{thicknesses of border lines. Either one number specifies the line thicknesses (widths) for all rectangles or a vector of line thicknesses for each aggregation level.}
\item{lowerbound.cex.labels}{multiplier between 0 and 1 that sets the lowerbound for the data label font sizes: 0 means draw all data labels, and 1 means only draw data labels if they fit (given \code{fontsize.labels}).}
\item{inflate.labels}{logical that determines whether data labels are inflated inside the rectangles. If \code{TRUE}, \code{fontsize.labels} does not determine the fontsize anymore, but it still determines the minimum fontsize in combination with \code{lowerbound.cex.labels}.}
\item{bg.labels}{background color of high aggregation labels. Either a color, or a number between 0 and 255 that determines the transparency of the labels. In the latter case, the color itself is determined by the color of the underlying rectangle. For "value" and "categorical" treemaps, the default is (slightly) transparent grey (\code{"#CCCCCCDC"}), and for the other types slightly transparent: \code{220}.}
\item{force.print.labels}{logical that determines whether data labels are being forced to be printed if they don't fit.}
\item{overlap.labels}{number between 0 and 1 that determines the tolerance of the overlap between labels. 0 means that labels of lower levels are not printed if higher level labels overlap, 1 means that labels are always printed. In-between values, for instance the default value .5, means that lower level labels are printed if other labels do not overlap with more than .5 times their area size.}
\item{align.labels}{object that specifies the alignment of the labels. Either a character vector of two values specifying the horizontal alignment (\code{"left"}, \code{"center"}, or \code{"right"}) and the vertical alignment (\code{"top"}, \code{"center"}, or \code{"bottom"}), or a list of sush character vectors, one for each aggregation level.}
\item{xmod.labels}{the horizontal position modification of the labels in inches. Either a single value, or a vector that specifies the modification for each aggregation level.}
\item{ymod.labels}{the vertical position modification of the labels in inches. Either a single value, or a vector that specifies the modification for each aggregation level.}
\item{eval.labels}{should the text labels, i.e. the factor labels of the \code{index} variables, be evaluated as expressions? Useful for printing mathematical symbols or equations.}
\item{position.legend}{position of the legend: \code{"bottom"}, \code{"right"}, or \code{"none"}. For "categorical" and "index" treemaps, \code{"right"} is the default value, for "index" treemap, \code{"none"}, and for the other types, \code{"bottom"}.}
\item{drop.unused.levels}{logical that determines whether unused levels (if any) are shown in the legend. Applicable for "categorical" treemap type.}
\item{aspRatio}{preferred aspect ratio of the main rectangle, defined by width/height. When set to \code{NA}, the available window size is used.}
\item{vp}{\code{\link[grid:viewport]{viewport}} to draw in. By default it is not specified, which means that a new plot is created. Useful when drawing small multiples, or when placing a treemap in a custom grid based plot.}
\item{draw}{logical that determines whether to draw the treemap.}
\item{...}{arguments to be passed to other functions. Currently, only \code{fun.aggregate} takes optional arguments.}
}
\value{
A list is silently returned:
\item{tm}{a \code{data.frame} containing information about the rectangles: indices, sizes, original color values, derived color values, depth level, position (x0, y0, w, h), and color.}
\item{type}{argument type}
\item{vSize}{argument vSize}
\item{vColor}{argument vColor}
\item{stdErr}{standard errors}
\item{algorithm}{argument algorithm}
\item{vpCoorX}{x-coordinates of the treemap within the whole plot}
\item{vpCoorY}{y-coordinates of the treemap within the whole plot}
\item{aspRatio}{aspect ratio of the treemap}
\item{range}{range of the color values scale}
}
\description{
A treemap is a space-filling visualization of hierarchical structures. This function offers great flexibility to draw treemaps. Required is a data.frame (\code{dtf}) that contains one or more hierarchical index columns given by \code{index}, a column that determines the rectangle area sizes (\code{vSize}), and optionally a column that determines the rectangle colors (\code{vColor}). The way how rectangles are colored is determined by the argument \code{type}.
}
\examples{
#########################################
### quick example with Gross National Income data
#########################################
data(GNI2014)
treemap(GNI2014,
index=c("continent", "iso3"),
vSize="population",
vColor="GNI",
type="value")
#########################################
### extended examples with fictive business statistics data
#########################################
data(business)
#########################################
### treemap types
#########################################
# index treemap: colors are determined by the index argument
\dontrun{
# large example which takes some time...
treemap(business,
index=c("NACE1", "NACE2", "NACE3"),
vSize="turnover",
type="index")
}
treemap(business[business$NACE1=="C - Manufacturing",],
index=c("NACE2", "NACE3"),
vSize=c("employees"),
type="index")
# value treemap: colors are derived from a numeric variable given by vColor
# (when omited, all values are set to 1 as in the following example)
treemap(business,
index=c("NACE1", "NACE2"),
vSize="employees",
title.legend="number of NACE4 categories",
type="value")
# comparisson treemaps: colors indicate change of vSize with respect to vColor
treemap(business,
index=c("NACE1", "NACE2"),
vSize="employees",
vColor="employees.prev",
type="comp")
# density treemaps: colors indicate density (like a population density map)
treemap(business,
index=c("NACE1", "NACE2"),
vSize="turnover",
vColor="employees/1000",
type="dens")
\dontrun{
# depth treemap: show depth
treemap(business,
index=c("NACE1", "NACE2", "NACE3"),
vSize="turnover",
type="depth")
}
# categorical treemap: colors are determined by a categorical variable
business <- transform(business, data.available = factor(!is.na(turnover)), x = 1)
treemap(business,
index=c("NACE1", "NACE2"),
vSize="x",
vColor="data.available",
type="categorical")
\dontrun{
# color treemap
business$color <- rainbow(nlevels(business$NACE2))[business$NACE2]
treemap(business,
index=c("NACE1", "NACE2"),
vSize="x",
vColor="color",
type="color")
# manual
business$color <- rainbow(nlevels(business$NACE2))[business$NACE2]
treemap(business,
index=c("NACE1", "NACE2"),
vSize="turnover",
vColor="employees",
type="manual",
palette=terrain.colors(10))
}
#########################################
### graphical options: control fontsizes
#########################################
\dontrun{
# draw labels of first index at fontsize 12 at the center,
# and labels of second index at fontsize 8 top left
treemap(business,
index=c("NACE1", "NACE2"),
vSize="employees",
fontsize.labels=c(12, 8),
align.labels=list(c("center", "center"), c("left", "top")),
lowerbound.cex.labels=1)
# draw all labels at fontsize 12 (only if they fit)
treemap(business,
index=c("NACE1", "NACE2"),
vSize="employees",
fontsize.labels=12,
lowerbound.cex.labels=1)
# draw all labels at fontsize 12, and if they don't fit, reduce to a minimum of .6*12
treemap(business,
index=c("NACE1", "NACE2"),
vSize="employees",
fontsize.labels=12,
lowerbound.cex.labels=.6)
# draw all labels at maximal fontsize
treemap(business,
index=c("NACE1", "NACE2"),
vSize="employees",
lowerbound.cex.labels=0,
inflate.labels = TRUE)
# draw all labels at fixed fontsize, even if they don't fit
treemap(business,
index=c("NACE1", "NACE2"),
vSize="employees",
fontsize.labels=10,
lowerbound.cex.labels=1,
force.print.labels=TRUE)
#########################################
### graphical options: color palettes
#########################################
## for comp and value typed treemaps all diverging brewer palettes can be chosen
treemap(business,
index=c("NACE1", "NACE2"),
vSize="employees",
vColor="employees.prev",
type="comp",
palette="RdBu")
## draw warm-colored index treemap
palette.HCL.options <- list(hue_start=270, hue_end=360+150)
treemap(business,
index=c("NACE1", "NACE2"),
vSize="employees",
type="index",
palette.HCL.options=palette.HCL.options)
# terrain colors
business$employees.growth <- business$employees - business$employees.prev
treemap(business,
index=c("NACE1", "NACE2"),
vSize="employees",
vColor="employees.growth",
type="value",
palette=terrain.colors(10))
# Brewer's Red-White-Grey palette reversed with predefined legend range
treemap(business,
index=c("NACE1", "NACE2"),
vSize="employees",
vColor="employees.growth",
type="value",
palette="-RdGy",
range=c(-20000,30000))
# More control over the color palette can be achieved with mapping
treemap(business,
index=c("NACE1", "NACE2"),
vSize="employees",
vColor="employees.growth",
type="value",
palette="RdYlGn",
range=c(-20000,30000), # this is shown in the legend
mapping=c(-30000, 10000, 40000)) # Rd is mapped to -30k, Yl to 10k, and Gn to 40k
}
}
\references{
Bederson, B., Shneiderman, B., Wattenberg, M. (2002) Ordered and Quantum Treemaps: Making Effective Use of 2D Space to Display Hierarchies. ACM Transactions on Graphics, 21(4): 833-854.
Bruls, D.M., C. Huizing, J.J. van Wijk. Squarified Treemaps. In: W. de Leeuw, R. van Liere (eds.), Data Visualization 2000, Proceedings of the joint Eurographics and IEEE TCVG Symposium on Visualization, 2000, Springer, Vienna, p. 33-42.
}