使用学年作为x轴标签

Question

考虑以下示例：

library(ggplot2)

input_data <- as.matrix(read.table("SpectData.txt"))
colnames(input_data) <- c("x1", "x2")

#1- Define Weights matrix
W <- matrix(0,nrow = nrow(input_data),ncol = nrow(input_data))

#2- Define Degree Matrix
D <- matrix(0,nrow = nrow(input_data),ncol = nrow(input_data))

calculateWeight <- function(x1,x2,sigma) {
  result <- exp(- (norm(x2-x1,type = "2"))^2/ (2*sigma^2))
  result
}

calcWieghtMatrix <- function(sigma) {
  for(i in 1: nrow(W)){
   for(j in 1: nrow(W)){
    if(i == j){
      next
    }
    if( W[i,j] != 0){
      next
    }

    W[i,j] <<- calculateWeight(input_data[i,],input_data[j,],sigma)
    W[j,i] <<- W[i,j]
  }
 }
}    

calcDegreeMatrix <- function()  {
  for( i in 1:nrow(input_data)){
    D[i,i] <<- sum(W[i,])
  }
}

executeSpectralClustring <- function (sigma,numberOfClusters){
  calcWieghtMatrix(sigma)
  calcDegreeMatrix()
  L <<- D - W
  eigenDecompostion <- eigen(L,symmetric = FALSE)
  index <- ncol(eigenDecompostion$vectors)-1
  eigenVector <- eigenDecompostion$vectors[,index] 
  cl <- kmeans(eigenVector,numberOfClusters)
  ggplot(input_data,col = cl$cluster)
}    

executeSpectralClustring(0.01,2)

如上所示，x轴上的library(ggplot2) library(dplyr) set.seed(30) data <- data.frame(group = factor(1:11), year = c(rep("2013-2014", times = 11), rep("2014-2015", times = 11), rep("2015-2016", times = 11), rep("2016-2017", times = 11)), value = runif(44), stringsAsFactors = FALSE) data$plot_year <- as.Date(paste0("01/01/", substr(data$year, start = 1, stop = 4)), format = "%m/%d/%Y") ggplot(data, aes(x = plot_year, y = value, color = group)) + geom_point() + geom_line(linetype = "dotted") + geom_line(data= data %>% filter(as.numeric(substr(plot_year, start = 1, stop = 4)) < 2015), aes(x = plot_year, y = value, color = group)) + theme_bw() 与2013相对应，2013-2014与2014相对应，依此类推。

如何使用这些轴标签 - 即2014-2015，2013-2014等 - 代替当前的x轴标签？我在网上找到的每个解决方案都说过以某种形式或形式使用2014-2015，但这些都是学年，而不是固定日期。

Answer 1

您可以直接使用学年作为绘图的x值。只要<=是一个字符或有序因子，您就可以使用比较运算符（如year）进行子集化（但如果year是非有序因子则不行）。作为字符变量，排序将按字母顺序排列。我更喜欢有序因子，以便我可以指定顺序：

data$year = factor(data$year, levels=sort(unique(data$year)), ordered=TRUE)

ggplot(data, aes(x = year, y = value, color = group, group=group)) +
  geom_point() + 
  geom_line(linetype = "dotted") + 
  geom_line(data= data %>% filter(year <= "2014-2015")) + 
  theme_bw()

虽然我更喜欢使用year的顺序进行子集化，但您也可以明确指定要包含的年份：

ggplot(data, aes(x = year, y = value, color = group, group=group)) +
  geom_point() + 
  geom_line(linetype = "dotted") + 
  geom_line(data= data %>% filter(year %in% c("2013-2014","2014-2015"))) + 
  theme_bw()

Answer 2

您可以将日期转换为数字，然后将scale_x_continuous与中断和标签参数一起使用：

library(ggplot2)
library(lubridate)

# calculate the breaks as numeric corresponding to the dates
br <- as.numeric(as.Date(c("2013-01-01", "2014-01-01", "2015-01-01", "2016-01-01")))
# calculate the labels at each break
lb <- c("2013-2014", "2014-2015", "2015-2016", "2016-2017")

ggplot(data, aes(x = as.numeric(plot_year), y = value, color = group)) +
          geom_point() + 
          geom_line(linetype = "dotted") + 
          geom_line(data= data %>% filter(year(plot_year) < 2015), 
                aes(x = as.numeric(plot_year), y = value, color = group)) + 
          theme_bw() + 
          scale_x_continuous(breaks = br, labels = lb) + xlab("year")