复杂的dotplot - 每行多个点

Question

首先，这是我的数据：

structure(c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 
0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 1, 0, 0, 0, 0, 0, 0, 3.9, 
6.4, 7.4, 8.1, 9, 9.4, 7.8, 12.8, 14.8, 16.2, 18, 18.8), .Dim = c(6L, 
22L), .Dimnames = list(c("Merc", "Peug", "Fera", "Fiat", "Opel", 
        "Volv"), c("10", "33.95", "58.66", 
"84.42", "110.21", "134.16", "164.69", "199.1", "234.35", "257.19", 
"361.84", "432.74", "506.34", "581.46", "651.71", "732.59", "817.56", 
"896.24", "971.77", "1038.91", "Reduction", "Price")))

为了更容易解释我想要实现的目标，我将展示矩阵：

> head(data)
     10 33.95 58.66 84.42 110.21 134.16 164.69 199.1 234.35 257.19 361.84 432.74 506.34 581.46 651.71 732.59 817.56 896.24 971.77 1038.91 Reduction Price
Merc  0     0     0     0      0      0      0     0      0      0      0      0      1      0      0      0      0      0      0       0 3.9      7.8
Peug  0     0     0     0      0      0      0     0      0      0      0      0      0      0      0      0      0      0      1       0 6.4     12.8
Fera  0     0     0     0      0      0      0     0      0      0      0      0      0      0      0      0      0      0      1       0 7.4     14.8
Fiat  0     0     0     0      0      0      0     0      0      0      0      0      0      0      0      0      1      0      1       0 8.1     16.2
Opel  0     0     0     0      0      0      0     0      0      0      0      0      0      0      0      0      0      0      0       0 9.0     18.0
Volv  0     0     0     0      0      0      0     0      0      0      0      0      0      0      0      1      0      0      1       0 9.4     18.8

如您所见，所有行只有两种类型的数字（0和1）。有时每行可以超过1个。在xaxis我想要列出Reduction列中的数字，而yaxis应该使用列名称。两个轴都应该从0到1200缩放。

现在是棘手的部分。我想在图表中添加您可以找到数字1的行中的值。如果每行中有多个1，则图表上应该有多个点。

Answer 1

我真的很喜欢使用dplyr这些东西，因为它可以让你的代码既紧凑又易于阅读，即使你从现在开始三个月就把它拿起来。

require(dplyr)
require(tidyr)
require(ggplot2)

d <- data %>%
    as.data.frame %>%
    mutate(Maker = rownames(data)) %>%
    gather(Column, Bool, -Maker, -Reduction, -Price) %>%
    filter(Bool == 1) %>%
    mutate(Column = as.numeric(levels(Column))[Column]) # Is factor otherwise

ggplot(d, aes(x=Reduction, y=Column, shape=Maker)) +
    geom_point() +
    scale_x_continuous(limits=c(0, 1200), breaks=c(0, 400, 800, 1200)) +
    scale_y_continuous(limits=c(0, 1200), breaks=c(0, 400, 800, 1200))

Answer 2

我认为以下应该解决你的问题，

df = structure(c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
            0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
            0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
            0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 
            0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 
            0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 1, 0, 0, 0, 0, 0, 0, 3.9, 
            6.4, 7.4, 8.1, 9, 9.4, 7.8, 12.8, 14.8, 16.2, 18, 18.8), 
          .Dim = c(6L,  22L), 
          .Dimnames = list(c("Merc", "Peug", "Fera", "Fiat", "Opel", 
                             "Volv"), 
                           c("10", "33.95", "58.66", 
                             "84.42", "110.21", "134.16", "164.69", "199.1", "234.35", "257.19", 
                             "361.84", "432.74", "506.34", "581.46", "651.71", "732.59", "817.56", 
                             "896.24", "971.77", "1038.91", "Reduction", "Price")))
df = as.data.frame(df)
df$Price = NULL
library(reshape)
meltDF = melt(df, id.vars = 'Reduction')
library(ggplot2)
ggplot(meltDF[meltDF$value == 1,]) + geom_point(aes(x = Reduction, y = variable))