Question

我很抱歉这个显而易见的基本问题，但我努力尝试，在网上搜索，但仍然坚持。这些是数据：

NULL

这是在“mydata”上构建3个探索图的循环

temp <- data.frame(mean=seq(1, 200, by=2), 
                 sd=seq(1, 200, by=2))


normv <- function( n , mean , sd ){
  out <- rnorm( n*length(mean) , mean = mean , sd = sd )
  return( matrix( out , , ncol = n , byrow = FALSE ) )
}


set.seed(1)
normv( 5 , temp$mean , temp$sd ) # 5 variables, from  V1 to V5
mydata <- as.data.frame(normv( 5 , temp$mean , temp$sd ))

我想得到的最终影像的模拟如下：请注意，如果我在循环外运行geom_histogram它工作正常，当我排除GGPLOT并使用基本R进行直方图时，它也可以正常工作。但是，当我运行循环时，我仍然收到错误：

require(ggplot2)
require(car)
pdf(paste("Explore",1,".pdf",sep=""))
layout(matrix(c(1,2,3,3), 2, 2, byrow = FALSE))
lst1<- lapply(names(mydata),function(i) 
{
  print (
    ggplot(mydata, aes(i)) +
      geom_histogram(aes(y = ..density..),
                     fill = 'yellow',
                     alpha = 0.7,
                     col = 'black') +
      geom_density(colour="blue", lwd = 1, fill="lightyellow", alpha=0.5) +
      stat_function(fun = dnorm, 
                    args = list(mean = mean(mydata[,i], na.rm=T), sd = sd(mydata[,i], na.rm=T)), 
                    lwd = 1, 
                    col = 'red') +
      geom_vline(xintercept = mean(mydata[,i], na.rm=TRUE),col="lightblue", lty=1, lwd = 1) +
      geom_vline(xintercept = median(mydata[,i], na.rm=TRUE),col="purple", lty=2, lwd = 1) +
      theme_bw() +
      labs(title="Blue Line: Mean, Purple Line: Median") +
      theme(axis.text.x=element_text(size=14), axis.title.x=element_text(size=16),
            axis.text.y=element_text(size=14), axis.title.y=element_text(size=16))
        )


  qqnorm(mydata[,i], axes=FALSE)
  Boxplot(mydata[,i], 
          labels=rownames(mydata), id.n=Inf,
          col="royalblue",
          axes=TRUE,
          ylab=i,
          horizontal=FALSE)
})

另请注意，直方图和条形图之间的差异对我来说非常清楚，在这种情况下，数据显然是连续的而不是离散的，事实上我需要直方图。出于学术目的，我也试图切换到geom_bar：我摆脱了错误，但结果图（如预期的那样）没有意义。

非常感谢任何帮助

Answer 1

这里有很多 - 我会根据你的代码假设这是你想要的图形类型。在这里，我收集变量，以便我们可以沿着可怕的“变量”列进行分析。通常，如果某些事情很难，并且您开始使用循环，那么通常有更好的方法。

library(tidyverse)
library(car)
temp <- data.frame(mean=seq(1, 200, by=2), 
                   sd=seq(1, 200, by=2))


normv <- function( n , mean , sd ){
  out <- rnorm( n*length(mean) , mean = mean , sd = sd )
  return( matrix( out , , ncol = n , byrow = FALSE ) )
}

set.seed(1)
normv( 5 , temp$mean , temp$sd ) # 5 variables, from  V1 to V5

mydata <- as.data.frame(normv( 5 , temp$mean , temp$sd )) %>% 
  gather("variable", "value", V1:V5)


ggplot(mydata, aes(value)) +
  geom_histogram(aes(y = ..density..),
                 fill = 'yellow',
                 alpha = 0.7,
                 col = 'black') +
  geom_density(colour="blue", lwd = 1, fill="lightyellow", alpha=0.5) +
  facet_grid(~variable) +
  geom_vline(aes(xintercept = summarised_value, color = stat), 
             size = 1,
             data = mydata %>% 
               group_by(variable) %>% 
               summarise(mean = mean(value), median = median(value)) %>% 
               gather("stat", "summarised_value", mean:median)) +
  theme_bw() +
  theme(axis.text.x=element_text(size=14), axis.title.x=element_text(size=16),
        axis.text.y=element_text(size=14), axis.title.y=element_text(size=16))

修改

对于整个问题，这应该足以让你开始：

我仍然收集变量，因为这样可以更容易地绘制。在绘图之前，我只使用我关心的值来获取数据帧的子集。

library(tidyverse)
library(car)
library(cowplot)
temp <- data.frame(mean=seq(1, 200, by=2), 
                   sd=seq(1, 200, by=2))


normv <- function( n , mean , sd ){
  out <- rnorm( n*length(mean) , mean = mean , sd = sd )
  return( matrix( out , , ncol = n , byrow = FALSE ) )
}

set.seed(1)
normv( 5 , temp$mean , temp$sd ) # 5 variables, from  V1 to V5

mydata <- as.data.frame(normv( 5 , temp$mean , temp$sd )) %>% 
  gather("variable", "value", V1:V5)


make_plot <- function(variable_name){

  data_subset <- mydata %>% 
    filter(variable == variable_name)

  hist_g <- data_subset %>% 
    ggplot(., aes(value)) +
    geom_histogram(aes(y = ..density..),
                   binwidth = 50,
                   fill = 'yellow',
                   alpha = 0.7,
                   col = 'black') +
    geom_density(colour="#00000040", lwd = 1, fill="lightyellow", alpha=0.5) +
    geom_vline(aes(xintercept = summarised_value, color = stat), 
               size = 1,
               data = . %>% 
                 summarise(mean = mean(value), median = median(value)) %>% 
                 gather("stat", "summarised_value", mean:median)) +
    scale_color_manual(values = c("blue", "red")) +
    theme_bw() +
    theme(axis.text.x=element_text(size=14), axis.title.x=element_text(size=16),
          axis.text.y=element_text(size=14), axis.title.y=element_text(size=16),
          legend.position = c(.95, .95),
          legend.justification = c(1,1),
          legend.background = element_rect(color = "black"))

  qq <- ggplot(data_subset, aes(sample = value)) +
    stat_qq()

  bp <- ggplot(data_subset, aes(x = variable_name, y = value)) +
    geom_boxplot()

  # arrange three in a grid
  plot_grid(
    plot_grid(hist_g, qq, nrow = 2),
    bp,
    ncol = 2
    )
}

figures_list <- map(unique(mydata$variable), make_plot)
all_figures <- plot_grid(plotlist = figures_list, nrow = 1, ncol = 5)
save_plot("out.png", all_figures, ncol = 5, base_aspect_ratio = 0.9, base_height = 7)

我将all_figures <- plot_grid(plotlist = figures_list, ...排成一行，但您可以单独保存，将列表映射到ggsave等。

使用GGPLOT2构建HISTOGRAM：StatBin需要连续的x变量x变量是离散的

1 个答案:

修改