作者：李誉辉
四川大学在读研究生
简介
对于多个变量之间的相关关系，常常使用相关关系图来可视化，R自带有pairs()函数，
可以画相关关系图，但是比较复杂，我们先介绍基于ggplot2的GGally包。
等介绍完，再介绍pairs()函数。
ggmatrix()可以将多个ggplot2绘图对象，按照矩阵进行排列。
1.1
1library(ggplot2)
2data(tips, package = "reshape")
3
4head(tips)
5
6g1 <- ggplot(tips, aes(x = total_bill, fill = sex)) +
7 geom_density(show.legend = FALSE)
8
9g2 <- ggplot(tips, aes(x = total_bill, fill = sex)) +
10 geom_histogram(position = position_stack(), show.legend = FALSE) +
11 facet_grid(rows = vars(time))# 以time变量行分面
12
13g3 <- ggplot(tips, aes(x = total_bill, y = tip, color = sex)) +
14 geom_point(show.legend = FALSE)
15
1.2
1library(ggplot2)
2
3g4 <- ggplot(tips, aes(x = time, y = total_bill, fill = sex)) +
4 geom_boxplot(show.legend = FALSE)
5
6g5 <- ggplot(tips, aes(x = time, fill = sex)) +
7 geom_bar(position = position_stack(), show.legend = FALSE)
8
9g6 <- ggplot(tips, aes(x = tip, fill = sex)) +
10 geom_histogram(position = position_stack(), show.legend = FALSE) +
11 coord_flip() +
12 facet_grid(cols = vars(time))
13
1.3
1library(ggplot2)
2library(dplyr)
3library(tibble)
4
5# 第一个图
6text_1 <- round(cor(tips$total_bill, tips$tip), 3)
7tips_female <- as.tibble(tips) %>% filter(sex == "Female") %>% as.data.frame()
8tips_male <- as.tibble(tips) %>% filter(sex == "Male") %>% as.data.frame()
9text_2 <- round(cor(tips_female$total_bill, tips_female$tip), 3)
10text_3 <- round(cor(tips_male$total_bill, tips_male$tip), 3)
11mytext <- c(text_1, text_2, text_3)
12mytext <- paste0(c("Cor", "Female", "Male"), ":", mytext)
13mytext <- data.frame(text = mytext,
14 x = 5,
15 y = c(6, 4, 2),
16 stringsAsFactors = FALSE)
17
18g7 <- ggplot(data = mytext[-1, ], aes(x = x, y = y, label = text, color = text)) +
19 geom_text(show.legend = F) +
20 geom_text(data = mytext[1,], aes(x = x, y = y, label = text),
21 color = "black")
22
23rm(text_1, tips_female, tips_male, text_2, text_3, mytext)
24
25# 第2个图
26g8 <- ggplot(tips, aes(x = time, y = tip, fill = sex)) +
27 geom_boxplot(show.legend = FALSE) +
28 coord_flip()
29
30# 第3个图
31g9 <- ggplot(tips, aes(x = tip, fill = sex)) +
32 geom_density(show.legend = FALSE)
33
1.4
1library(customLayout)
2# 创建画布
3mylay <- lay_new(
4 mat = matrix(1:9, ncol = 3))
5
6plot_list <- list(g1, g2, g3, g4, g5, g6, g7, g8, g9)
7
8lay_grid(plot_list, mylay) # ggplot2绘图列表传参，传递到画布mylay
9
10rm(g1, g2, g3, g4, g5, g6, g7, g8, g9, mylay)
1.5
1library(GGally)
2
3gg_m <- ggmatrix(
4 plots = plot_list, # 绘图对象列表
5 nrow = 3, ncol = 3, # 行数和列数
6 xAxisLabels = c("Total Bill", "Time of Day", "Tip"),
7 yAxisLabels = c("Total Bill", "Time of Day", "Tip"),
8 byrow = FALSE, # 按列排
9 title = "ggmatrix合并图形"
10)
11
12# 添加主题
13gg_m + theme_bw()
14
15# 提取子集,只能提取其中一个
16gg_m[1,2]
17
18rm(plot_list, gg_m)
GGally通过添加几个函数来扩展ggplot2，以降低geom与转换数据组合的复杂性。
其中一些功能包括配对图矩阵，散点图矩阵，平行坐标图，生存图，以及绘制网络的几个函数。
2.1
语法：
1ggpairs(data, mapping = NULL, columns = 1:ncol(data), title = NULL,
2 upper = list(continuous = "cor", combo = "box_no_facet", discrete =
3 "facetbar", na = "na"), lower = list(continuous = "points", combo =
4 "facethist", discrete = "facetbar", na = "na"), diag = list(continuous =
5 "densityDiag", discrete = "barDiag", na = "naDiag"), params = NULL, ...,
6 xlab = NULL, ylab = NULL, axisLabels = c("show", "internal", "none"),
7 columnLabels = colnames(data[columns]), labeller = "label_value",
8 switch = NULL, showStrips = NULL, legend = NULL,
9 cardinality_threshold = 15, progress = NULL,
10 legends = stop("deprecated"))
关键参数：
mapping, 表示要叠加到x,y上的aes()映射变量，这里是全局映射。
column, 表示选择要绘图的列，可以用变量索引值指定，也可以用变量名指定。
columnLabels, 指定矩阵列名称。
title, xlab, ylab, 表示指定标题和坐标轴名称。
lower,upper,表示指定下三角和上三角的plot类型，列表传参。
diag,表示指定对角线的plot类型，列表传参。
axisLabels, 指定变量名称的显示位置，默认显示在外侧，"internal"则显示在内测，"none"则不显示。
labeller, 表示指定分面标签，
switch, 表示指定分面标签位置，与ggplot2:facet_grid中一致，默认在顶部和右侧，
若switch = "x",则显示在底部和右侧，若switch = "y"则显示在顶部和左侧，
若swith = "both"则显示在底部和左侧。
showStrips, 布尔运算决定是否显示plots的条带，默认NULL只显示顶部和右侧的条带。TRUE则显示所有的条带，FALSE则不显示所有的条带。
legend, 默认NULL不显示，可以通过theme(legend.position = "bottom")调整图例的位置。
有3种指定图例类型的方式：
长度为2的数字向量，表示给矩阵所在的行和列增加图例。如c(2,3)表示第2行第3列增加图例。
长度为1的数字向量，表示根据矩阵的顺序，给相应的panel添加图例，
如legend=3表示给1行第3列增加图例。
预先使用grab_legend()提取ggplot2对象的图例，然后指定给legend。
cardinality_threshold, 表示允许因子变量的最大因子水平数量，默认最多15个因子水平。NULL则因子变量不会绘图。
progress, 表示是否显示进度条，默认NULL当超过15个plots时显示进度条,
对绘图结果没有任何影响，不需要关注。TRUE则显示进度条，FALSE则不显示进度条，
也可用ggmatrix_progress()生成进度条，然后指定。
plot类型：
通过5个参数控制plot类型：continuous,combo,discret, na, mapping
continuous, 表示如果变量x,y都是连续的，应该是什么plot。
对于lower和upper参数：
可以是
"point", "smooth","smooth_loess", "density", "cor", "blank"。
对于diag参数: 可以是
"densityDiag", "barDiag", "blankDiag"
combo, 表示如果变量一个连续，一个离散，应该是什么plot。
只能用于lower和upper不能用于diag。
离散变量只能计数，不能映射坐标，所以可能存在坐标翻转。
可以是
"box", "box_no_facet", "dot",
"dot_no_facet","facethist", "facetdensity",
"denstrip", "blank"
discrete, 表示2个变量都是离散的，应该是什么plot。
对于upper和lower参数：
可以是：
"facetbar", "ratio", "blank"。
对于diag参数: 可以是"barDiag", "blankDiag"。
na, 表示指定变量为na的情况,
对于lower和upper，可以是："na", "blank"。
对于diag,可以是
"naDiag"，"blankDiag"。
mapping, 表示aes()映射。若指定mapping参数，则叠加到x,y上去。
默认
lower = list(continuous = "point", combo = "facetthist", discrete = "facetbar")
默认
upper = list(continuous = "cor", combo = "box_no_facet", discrete = "box")
默认
diag = list(continuous = "density", discrete = "barDiag")
2.2
1library(GGally)
2library(ggplot2)
3
4ggpairs(tips, mapping = aes(color = sex),
5 columns = c("total_bill", "time", "tip"),
6 columnLabels = c("Total_Bill(连续变量)", "Time(离散变量)", "Tip(连续变量)"),
7 title = "变量名指定column")
8
9ggpairs(tips, mapping = aes(color = sex),
10 columns = c(1, 6, 2),
11 columnLabels = c("Total_Bill(连续变量)", "Time(离散变量)", "Tip(连续变量)"),
12 title = "索引值指定column")
2.3
2.3.1 自定义lower
一个离散变量，lower的discrete参数无效。
1ggpairs(tips, mapping = aes(color = day),
2 columns = c("total_bill", "time", "tip"),
3 columnLabels = c("Total_Bill(连续变量)", "Time(离散变量)", "Tip(连续变量)"),
4 lower = list(
5 continuous = "cor",
6 combo = "dot_no_facet" # 没有2个离散变量，不需要discrete参数
7 ),
8 upper = list(
9 continuous = "blank",
10 combo = "blank"
11 ),
12 diag = list(
13 continuous = "blankDiag",
14 discrete = "blankDiag"
15 ),
16 title = "自定义lower\n(lower$continuous = \"cor\", lower$combo = \"dot_no_facet\")"
17)
两个离散变量，lower的continuous参数无效。
1ggpairs(tips, mapping = aes(color = day),
2 columns = c("total_bill", "time", "sex"),
3 columnLabels = c("Total_Bill(连续变量)", "Time(离散变量)", "Sex(离散变量)"),
4 lower = list(
5 combo = "dot_no_facet", #
6 discrete = "blank"
7 ),
8 upper = list(
9 combo = "blank",
10 discrete = "blank"
11 ),
12 diag = list(
13 continuous = "blankDiag",
14 discrete = "blankDiag"
15 ),
16 title = "自定义lower\n(lower$combo = \"dot_no_facet\",lower$discrete = \"blank\" )"
17)
upper一个离散变量，upper的discrete参数无效。
1ggpairs(tips, mapping = aes(color = day),
2 columns = c("total_bill", "time", "tip"),
3 columnLabels = c("Total_Bill(连续变量)", "Time(离散变量)", "Tip(连续变量)"),
4 upper = list(
5 continuous = "density",
6 combo = "dot_no_facet" # 没有2个离散变量，不需要discrete参数
7 ),
8 lower = list(
9 continuous = "blank",
10 combo = "blank"
11 ),
12 diag = list(
13 continuous = "blankDiag",
14 discrete = "blankDiag"
15 ),
16 title = "自定义upper\n(upper$continuous = \"density\", upper$combo = \"dot_no_facet\")"
17)
两个离散变量，upper的continuous参数无效。
1ggpairs(tips, mapping = aes(color = day),
2 columns = c("total_bill", "time", "sex"),
3 columnLabels = c("Total_Bill(连续变量)", "Time(离散变量)", "Sex(离散变量)"),
4 upper = list(
5 combo = "dot_no_facet", #
6 discrete = "ratio"
7 ),
8 lower = list(
9 combo = "blank",
10 discrete = "blank"
11 ),
12 diag = list(
13 continuous = "blankDiag",
14 discrete = "blankDiag"
15 ),
16 title = "自定义upper\n(lower$combo = \"dot_no_facet\",upper$discrete = \"ratio\" )"
17)
diagdiag没有combo参数。
1ggpairs(tips, mapping = aes(color = day),
2 columns = c("total_bill", "time", "tip"),
3 columnLabels = c("Total_Bill(连续变量)", "Time(离散变量)", "Tip(连续变量)"),
4 diag = list(
5 continuous = "barDiag",
6 discrete = "blankDiag" #
7 ),
8 lower = list(
9 continuous = "blank",
10 combo = "blank"
11 ),
12 upper = list(
13 continuous = "blank",
14 combo = "blank"
15 ),
16 title = "自定义diag\n(diag$continuous = \"barDiag\", diag$discrete = \"blankDiag\")"
17)
1ggpairs(tips, mapping = aes(color = day),
2 columns = c("total_bill", "time", "sex"),
3 columnLabels = c("Total_Bill(连续变量)", "Time(离散变量)", "Sex(离散变量)"),
4 diag = list(
5 continuous = "barDiag", #
6 discrete = "barDiag"
7 ),
8 lower = list(
9 discrete = "blank",
10 combo = "blank"
11 ),
12 upper = list(
13 discrete = "blank",
14 combo = "blank"
15 ),
16 title = "自定义diag\n(lower$continuous = \"barDiag\",diag$barDiag = \"barDiag\" )"
17)
mapping参数1library(ggplot2)
2library(GGally)
3data(tips, package = "reshape")
4
5ggpairs(tips,
6 columns = c("total_bill", "time", "tip"),
7 columnLabels = c("Total_Bill(连续变量)", "Time(离散变量)", "Tip(连续变量)"),
8 title = "无mapping"
9)
1ggpairs(tips,
2 columns = c("total_bill", "time", "tip"),
3 columnLabels = c("Total_Bill(连续变量)", "Time(离散变量)", "Tip(连续变量)"),
4 lower = list(mapping = aes(color = time)),
5 title = "自定义lower(lower$mapping = \"time\")" # 局部映射
6)
1ggpairs(tips,
2 columns = c("total_bill", "tip", "size"),
3 columnLabels = c("Total_Bill(连续变量)", "Tip(连续变量)", "Size(连续变量)"),
4 lower = list(
5 continuous = "cor",
6 mapping = aes(color = sex)
7 ),
8 upper = list(
9 continuous = "cor",
10 mapping = aes(color = smoker)
11 ),
12 diag = list(
13 continuous = "barDiag",
14 mapping = aes(color = time)
15 ),
16 title = "自定义lower,upper,diag\n(下三角颜色为sex,上三角颜色为smoker,对角颜色为time)"
17)
lower,upper,diag2个连续变量，1个离散变量。
1ggpairs(tips, mapping = aes(color = day),
2 columns = c("total_bill", "tip", "time"),
3 columnLabels = c("Total_Bill(连续变量)", "Tip(连续变量)", "Time(离散变量)"),
4 lower = list(
5 continuous = "cor",
6 combo = "dot_no_facet" # 没有2个离散变量，不需要discrete参数
7 ),
8 upper = list(
9 continuous = "density",
10 combo = "dot_no_facet" # 没有2个离散变量，不需要discrete参数
11 ),
12 diag = list(
13 continuous = "barDiag",
14 discrete = "blankDiag" #
15 ),
16 title = "自定义lower,upper,diag(两个连续变量，一个离散变量)"
17)
1个连续变量，2个离散变量。
1ggpairs(tips, mapping = aes(color = day),
2 columns = c("total_bill", "time", "sex"),
3 columnLabels = c("Total_Bill(连续变量)", "Time(离散变量)", "Sex(离散变量)"),
4 lower = list(
5 combo = "dot_no_facet", #
6 discrete = "blank"
7 ),
8 upper = list(
9 combo = "dot_no_facet", #
10 discrete = "ratio"
11 ),
12 diag = list(
13 continuous = "barDiag", #
14 discrete = "barDiag"
15 ),
16 title = "自定义lower,upper,diag(一个连续变量，两个离散变量)"
17)
——————————————
往期精彩：
