Question

我最近更新了ggplot2软件包并遇到了一些主要问题，使用facets为每个组的平均值绘制水平线。我相信this帖子不再有效？

我正在使用以下代码创建时间序列图：

ggplot(p2p_dt_SKILL_A,aes(x=Date,y=Prod_DL)) +
    geom_line(aes(colour="red"),lwd=1.3) +
    geom_smooth() +
    geom_line(stat = "hline", yintercept = "mean")+
    scale_x_date(labels=date_format("%b-%y"),breaks ="2 month")+
    geom_vline(xintercept = as.numeric(p2p_dt_SKILL_A$Date[p2p_dt_SKILL_A$Date=="2015-09-18"]))+

     geom_vline(xintercept = as.numeric(p2p_dt_SKILL_A$Date[p2p_dt_SKILL_A$Date=="2015-10-02"]))+
     geom_vline(xintercept = as.numeric(p2p_dt_SKILL_A$Date[p2p_dt_SKILL_A$Date=="2015-10-23"]))+
    ylab("DL Prod for All Skills")+
    ggtitle("BVG1 DL Prod for All Skills 2014-2015")+
    theme(axis.title.y = element_text(size = 15,face="bold",color="red"),
          plot.title = element_text(size = 15,lineheight = .8,face="bold",color="red"),
          axis.title.x = element_blank(),
          legend.position="none")+
    facet_wrap(~Patch)

问题1是我无法再使用stat = "hline"中的geom_line(stat = "hline", yintercept = "mean")，因为它会出现以下错误：Error: No stat called StatHline。所以我把它改成了：

ggplot(p2p_dt_SKILL_A,aes(x=Date,y=Prod_DL)) +
    geom_line(aes(colour="red"),lwd=1.3) +
    geom_smooth() +
    geom_hline(yintercept = mean(p2p_dt_SKILL_A$Prod_DL))+
    scale_x_date(labels=date_format("%b-%y"),date_breaks ="2 month")+
    geom_vline(xintercept = as.numeric(p2p_dt_SKILL_A$Date[p2p_dt_SKILL_A$Date=="2015-09-18"]))+

     geom_vline(xintercept = as.numeric(p2p_dt_SKILL_A$Date[p2p_dt_SKILL_A$Date=="2015-10-02"]))+
     geom_vline(xintercept = as.numeric(p2p_dt_SKILL_A$Date[p2p_dt_SKILL_A$Date=="2015-10-23"]))+
    ylab("DL Prod for All Skills")+
    ggtitle("BVG1 DL Prod for All Skills 2014-2015")+
    theme(axis.title.y = element_text(size = 15,face="bold",color="red"),
          plot.title = element_text(size = 15,lineheight = .8,face="bold",color="red"),
          axis.title.x = element_blank(),
          legend.position="none")+
    facet_wrap(~Patch)

但是这并没有在每个Patch的平均值上绘制水平线。它只需Prod_DL的整体均值见下文：

现在有什么新的方法可以计算每组的平均值并绘制水平线吗？

由于

更新

这是我做的：

#first create a dataframe which holds patch and mean values for prod dl, this will then be used in geom_hline()
mean_Prod_DL <- p2p_dt_SKILL_A%>%
                                group_by(Patch)%>%
                                summarise(mean_Prod_DL_per_patch = mean(Prod_DL))


ggplot(p2p_dt_SKILL_A,aes(x=Date,y=Prod_DL)) +
        scale_x_date(labels=date_format("%b-%y"),date_breaks ="2 months")+
        geom_line(aes(colour="red"),lwd=1.3) +
        geom_smooth() +
        geom_hline(data = mean_Prod_DL,aes(yintercept = mean_Prod_DL_per_patch),lty=2)+
        geom_vline(xintercept = as.numeric(p2p_dt_SKILL_A$Date[p2p_dt_SKILL_A$Date=="2015-09-18"]))+
         geom_vline(xintercept = as.numeric(p2p_dt_SKILL_A$Date[p2p_dt_SKILL_A$Date=="2015-10-02"]))+
         geom_vline(xintercept = as.numeric(p2p_dt_SKILL_A$Date[p2p_dt_SKILL_A$Date=="2015-10-23"]))+
        geom_vline(xintercept = as.numeric(p2p_dt_SKILL_A$Date[p2p_dt_SKILL_A$Date=="2015-12-04"]))+
        ylab("DL Prod for All Skills")+
        ggtitle("BVG1 DL Prod for All Skills 2014-2016")+
        theme(axis.title.y = element_text(size = 15,face="bold",color="red"),
              plot.title = element_text(size = 15,lineheight = .8,face="bold",color="red"),
              axis.title.x = element_blank(),
              legend.position="none")+
        facet_wrap(~Patch)

Answer 1

我同意@MLavoie的看法，只计算感兴趣的数量是最简单的解决方案。不确定以什么方式寻找更好的东西＆＃39;。

示例：

# sample data
my_df <- data.frame(x=rep(1:100, 4),
                    y=cumsum(rnorm(400)),
                    category=rep(letters[1:4], each=100))

# calculate the hline data in one line with data.table
library(data.table)
setDT(my_df)[, cat_mean := mean(y), by=category]

# plot
ggplot(my_df, aes(x=x, y=y, group=category)) +
  geom_line(color='red') +
  geom_smooth(color='blue') +
  geom_hline(aes(yintercept=cat_mean)) +
  facet_wrap(~category)

结果：

ggplot2：为每组平均添加行（错误：没有名为StatHline的统计信息。）

1 个答案: