ggplot2：更复杂的分面
ggplot2: More complex faceting
我的热图越来越复杂。熔化数据示例：
head(df2)
Class Subclass Family variable value
1 A chemosensory family_1005117 caenorhabditis_elegans 10
2 A chemosensory family_1011230 caenorhabditis_elegans 4
3 A chemosensory family_1022539 caenorhabditis_elegans 10
4 A other family_1025293 caenorhabditis_elegans NA
5 A chemosensory family_1031345 caenorhabditis_elegans 10
6 A chemosensory family_1033309 caenorhabditis_elegans 10
tail(df2)
Class Subclass Family variable value
6496 C class c family_455391 trichuris_muris 1
6497 C class c family_812893 trichuris_muris NA
6498 F class f family_225491 trichuris_muris 1
6499 F class f family_236822 trichuris_muris 1
6500 F class f family_276074 trichuris_muris 1
6501 F class f family_768194 trichuris_muris NA
使用 ggplot2 和 geom_tile，我能够生成漂亮的数据热图。我为代码感到自豪（这是我第一次使用 R 语言），所以将其发布在下面：
df2[df2 == 0] <- NA
df2[df2 > 11] <- 10
df2.t <- data.table(df2)
df2.t[, clade := ifelse(variable %in% c("pristionchus_pacificus", "caenorhabditis_elegans", "ancylostoma_ceylanicum", "necator_americanus", "nippostrongylus_brasiliensis", "angiostrongylus_costaricensis", "dictyocaulus_viviparus", "haemonchus_contortus"), "Clade V",
ifelse(variable %in% c("meloidogyne_hapla","panagrellus_redivivus", "rhabditophanes_kr3021", "strongyloides_ratti"), "Clade IV",
ifelse(variable %in% c("toxocara_canis", "dracunculus_medinensis", "loa_loa", "onchocerca_volvulus", "ascaris_suum", "brugia_malayi", "litomosoides_sigmodontis", "syphacia_muris", "thelazia_callipaeda"), "Clade III",
ifelse(variable %in% c("romanomermis_culicivorax", "trichinella_spiralis", "trichuris_muris"), "Clade I",
ifelse(variable %in% c("echinococcus_multilocularis", "hymenolepis_microstoma", "mesocestoides_corti", "taenia_solium", "schistocephalus_solidus"), "Cestoda",
ifelse(variable %in% c("clonorchis_sinensis", "fasciola_hepatica", "schistosoma_japonicum", "schistosoma_mansoni"), "Trematoda", NA))))))]
df2.t$clade <- factor(df2.t$clade, levels = c("Clade I", "Clade III", "Clade IV", "Clade V", "Cestoda", "Trematoda"))
plot2 <- ggplot(df2.t, aes(variable, Family))
tile2 <- plot2 + geom_tile(aes(fill = value)) + facet_grid(Class ~ clade, scales = "free", space = "free")
tile2 <- tile2 + scale_x_discrete(expand = c(0,0)) + scale_y_discrete(expand = c(0,0))
tile2 <- tile2 + theme(axis.text.y = element_blank(), axis.ticks.y = element_blank(), legend.position = "right", axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.55), axis.text.y = element_text(size = rel(0.35)), panel.border = element_rect(fill=NA,color="grey", size=0.5, linetype="solid"))
tile2 <- tile2 + xlab(NULL)
tile2 <- tile2 + scale_fill_gradientn(breaks = c(1,2,3,4,5,6,7,8,9,10),labels = c("1", "2", "3", "4", "5", "6", "7", "8", "9", ">10"), limits = c(1, 10), colours = palette(11), na.value = "white", name = "Members")'
如您所见，涉及到相当多的手动重新排序，否则代码非常简单。这是图像输出：
但是，您可能会注意到一整列信息 "Subclass" 没有被利用。基本上，每个 Subclass 都适合 Class。如果我能够在已经显示的 Class 构面中对这些 Subclasses 进行构面，那将是完美的。据我所知，这是不可能的。准确地说，只有 Class A 有不同的 Subclasses。其他 Classes 只是将它们的 class 名称镜像 (F = class f)。有没有另一种方法来组织这个热图，以便我可以显示所有相关信息？缺失的 Subclasses 包含一些最关键的数据，对于从数据中得出推论是最必要的。
另一种方法是对子类而不是 Class 进行分面，手动重新排序它们以便 Class 聚集在一起，然后在它们周围绘制某种框以划定每个 Class。我不知道这将如何完成。
任何帮助都会非常有用。如果您需要任何其他信息，请告诉我。
用一些简单的演示数据将我的评论变成答案：
这并不难（?facet_grid 中甚至有示例，尽管它们在底部）。
# generate some nested data
dat = data.frame(x = rnorm(12), y = rnorm(12), class = rep(LETTERS[1:2], each = 6),
subclass = rep(letters[1:6], each = 2))
# plot it
ggplot(dat, aes(x, y)) + geom_point() +
facet_grid(subclass + class ~ .)
你可以用 ~ 两边的任意多个因素来做到这一点！
这将在原始条带的右侧和图例的左侧放置一个新条带。
library(ggplot2)
library(gtable)
library(grid)
p <- ggplot(mtcars, aes(mpg, wt, colour = factor(vs))) + geom_point()
p <- p + facet_grid(cyl ~ gear)
# Convert the plot to a grob
gt <- ggplotGrob(p)
# Get the positions of the right strips in the layout: t = top, l = left, ...
strip <-c(subset(gt$layout, grepl("strip-r", gt$layout$name), select = t:r))
# New column to the right of current strip
gt <- gtable_add_cols(gt, gt$widths[max(strip$r)], max(strip$r))
# Add grob, the new strip, into new column
gt <- gtable_add_grob(gt,
list(rectGrob(gp = gpar(col = NA, fill = "grey85", size = .5)),
textGrob("Number of Cylinders", rot = -90, vjust = .27,
gp = gpar(cex = .75, fontface = "bold", col = "black"))),
t = min(strip$t), l = max(strip$r) + 1, b = max(strip$b), name = c("a", "b"))
# Add small gap between strips
gt <- gtable_add_cols(gt, unit(1/5, "line"), max(strip$r))
# Draw it
grid.newpage()
grid.draw(gt)
我的热图越来越复杂。熔化数据示例：
head(df2)
Class Subclass Family variable value
1 A chemosensory family_1005117 caenorhabditis_elegans 10
2 A chemosensory family_1011230 caenorhabditis_elegans 4
3 A chemosensory family_1022539 caenorhabditis_elegans 10
4 A other family_1025293 caenorhabditis_elegans NA
5 A chemosensory family_1031345 caenorhabditis_elegans 10
6 A chemosensory family_1033309 caenorhabditis_elegans 10
tail(df2)
Class Subclass Family variable value
6496 C class c family_455391 trichuris_muris 1
6497 C class c family_812893 trichuris_muris NA
6498 F class f family_225491 trichuris_muris 1
6499 F class f family_236822 trichuris_muris 1
6500 F class f family_276074 trichuris_muris 1
6501 F class f family_768194 trichuris_muris NA
使用 ggplot2 和 geom_tile，我能够生成漂亮的数据热图。我为代码感到自豪（这是我第一次使用 R 语言），所以将其发布在下面：
df2[df2 == 0] <- NA
df2[df2 > 11] <- 10
df2.t <- data.table(df2)
df2.t[, clade := ifelse(variable %in% c("pristionchus_pacificus", "caenorhabditis_elegans", "ancylostoma_ceylanicum", "necator_americanus", "nippostrongylus_brasiliensis", "angiostrongylus_costaricensis", "dictyocaulus_viviparus", "haemonchus_contortus"), "Clade V",
ifelse(variable %in% c("meloidogyne_hapla","panagrellus_redivivus", "rhabditophanes_kr3021", "strongyloides_ratti"), "Clade IV",
ifelse(variable %in% c("toxocara_canis", "dracunculus_medinensis", "loa_loa", "onchocerca_volvulus", "ascaris_suum", "brugia_malayi", "litomosoides_sigmodontis", "syphacia_muris", "thelazia_callipaeda"), "Clade III",
ifelse(variable %in% c("romanomermis_culicivorax", "trichinella_spiralis", "trichuris_muris"), "Clade I",
ifelse(variable %in% c("echinococcus_multilocularis", "hymenolepis_microstoma", "mesocestoides_corti", "taenia_solium", "schistocephalus_solidus"), "Cestoda",
ifelse(variable %in% c("clonorchis_sinensis", "fasciola_hepatica", "schistosoma_japonicum", "schistosoma_mansoni"), "Trematoda", NA))))))]
df2.t$clade <- factor(df2.t$clade, levels = c("Clade I", "Clade III", "Clade IV", "Clade V", "Cestoda", "Trematoda"))
plot2 <- ggplot(df2.t, aes(variable, Family))
tile2 <- plot2 + geom_tile(aes(fill = value)) + facet_grid(Class ~ clade, scales = "free", space = "free")
tile2 <- tile2 + scale_x_discrete(expand = c(0,0)) + scale_y_discrete(expand = c(0,0))
tile2 <- tile2 + theme(axis.text.y = element_blank(), axis.ticks.y = element_blank(), legend.position = "right", axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.55), axis.text.y = element_text(size = rel(0.35)), panel.border = element_rect(fill=NA,color="grey", size=0.5, linetype="solid"))
tile2 <- tile2 + xlab(NULL)
tile2 <- tile2 + scale_fill_gradientn(breaks = c(1,2,3,4,5,6,7,8,9,10),labels = c("1", "2", "3", "4", "5", "6", "7", "8", "9", ">10"), limits = c(1, 10), colours = palette(11), na.value = "white", name = "Members")'
如您所见，涉及到相当多的手动重新排序，否则代码非常简单。这是图像输出：
但是，您可能会注意到一整列信息 "Subclass" 没有被利用。基本上，每个 Subclass 都适合 Class。如果我能够在已经显示的 Class 构面中对这些 Subclasses 进行构面，那将是完美的。据我所知，这是不可能的。准确地说，只有 Class A 有不同的 Subclasses。其他 Classes 只是将它们的 class 名称镜像 (F = class f)。有没有另一种方法来组织这个热图，以便我可以显示所有相关信息？缺失的 Subclasses 包含一些最关键的数据，对于从数据中得出推论是最必要的。
另一种方法是对子类而不是 Class 进行分面，手动重新排序它们以便 Class 聚集在一起，然后在它们周围绘制某种框以划定每个 Class。我不知道这将如何完成。
任何帮助都会非常有用。如果您需要任何其他信息，请告诉我。
用一些简单的演示数据将我的评论变成答案：
这并不难（?facet_grid 中甚至有示例，尽管它们在底部）。
# generate some nested data
dat = data.frame(x = rnorm(12), y = rnorm(12), class = rep(LETTERS[1:2], each = 6),
subclass = rep(letters[1:6], each = 2))
# plot it
ggplot(dat, aes(x, y)) + geom_point() +
facet_grid(subclass + class ~ .)
你可以用 ~ 两边的任意多个因素来做到这一点！
这将在原始条带的右侧和图例的左侧放置一个新条带。
library(ggplot2)
library(gtable)
library(grid)
p <- ggplot(mtcars, aes(mpg, wt, colour = factor(vs))) + geom_point()
p <- p + facet_grid(cyl ~ gear)
# Convert the plot to a grob
gt <- ggplotGrob(p)
# Get the positions of the right strips in the layout: t = top, l = left, ...
strip <-c(subset(gt$layout, grepl("strip-r", gt$layout$name), select = t:r))
# New column to the right of current strip
gt <- gtable_add_cols(gt, gt$widths[max(strip$r)], max(strip$r))
# Add grob, the new strip, into new column
gt <- gtable_add_grob(gt,
list(rectGrob(gp = gpar(col = NA, fill = "grey85", size = .5)),
textGrob("Number of Cylinders", rot = -90, vjust = .27,
gp = gpar(cex = .75, fontface = "bold", col = "black"))),
t = min(strip$t), l = max(strip$r) + 1, b = max(strip$b), name = c("a", "b"))
# Add small gap between strips
gt <- gtable_add_cols(gt, unit(1/5, "line"), max(strip$r))
# Draw it
grid.newpage()
grid.draw(gt)