26

我正在使用包中的模型拟合模型gam并将mgcv结果存储在model其中，到目前为止，我一直在使用plot(model). 我最近开始使用 ggplot2 并喜欢它的输出。所以我想知道，是否可以使用 ggplot2 绘制这些图？

这是一个例子：

x1 = rnorm(1000)
x2 = rnorm(1000)
n = rpois(1000, exp(x1) + x2^2)

model = gam(n ~ s(x1, k=10) + s(x2, k=20), family="poisson")
plot(model, rug=FALSE, select=1)
plot(model, rug=FALSE, select=2)

我对合身感兴趣s(x1, k=10)而s(x2, k=20)不是合身。

部分答案：

我深入挖掘plot.gam并mgcv:::plot.mgcv.smooth构建了自己的函数，该函数从平滑分量中提取预测效果和标准误差。它不能处理所有选项和案例，plot.gam所以我只认为它是部分解决方案，但它对我来说效果很好。

EvaluateSmooths = function(model, select=NULL, x=NULL, n=100) {
  if (is.null(select)) {
    select = 1:length(model$smooth)
  }
  do.call(rbind, lapply(select, function(i) {
    smooth = model$smooth[[i]]
    data = model$model

    if (is.null(x)) {
      min = min(data[smooth$term])
      max = max(data[smooth$term])
      x = seq(min, max, length=n)
    }
    if (smooth$by == "NA") {
      by.level = "NA"
    } else {
      by.level = smooth$by.level
    }
    range = data.frame(x=x, by=by.level)
    names(range) = c(smooth$term, smooth$by)

    mat = PredictMat(smooth, range)
    par = smooth$first.para:smooth$last.para

    y = mat %*% model$coefficients[par]

    se = sqrt(rowSums(
      (mat %*% model$Vp[par, par, drop = FALSE]) * mat
    ))

    return(data.frame(
      label=smooth$label
      , x.var=smooth$term
      , x.val=x
      , by.var=smooth$by
      , by.val=by.level
      , value = y
      , se = se
    ))
  }))
}

这将返回一个带有平滑组件的“熔化”数据框，因此现在可以ggplot与上面的示例一起使用：

smooths = EvaluateSmooths(model)

ggplot(smooths, aes(x.val, value)) + 
  geom_line() + 
  geom_line(aes(y=value + 2*se), linetype="dashed") + 
  geom_line(aes(y=value - 2*se), linetype="dashed") + 
  facet_grid(. ~ x.var)

如果有人知道在一般情况下允许这样做的软件包，我将不胜感激。

4

3 回答 3

21

您可以将 visreg 包与 plyr 包结合使用。visreg 基本上绘制任何可以使用 predict() 的模型。

library(mgcv)
library(visreg)
library(plyr)
library(ggplot2)

# Estimating gam model:
x1 = rnorm(1000)
x2 = rnorm(1000)
n = rpois(1000, exp(x1) + x2^2)
model = gam(n ~ s(x1, k=10) + s(x2, k=20), family="poisson")

# use plot = FALSE to get plot data from visreg without plotting
plotdata <- visreg(model, type = "contrast", plot = FALSE)

# The output from visreg is a list of the same length as the number of 'x' variables,
#   so we use ldply to pick the objects we want from the each list part and make a dataframe: 
smooths <- ldply(plotdata, function(part)   
  data.frame(Variable = part$meta$x, 
             x=part$fit[[part$meta$x]], 
             smooth=part$fit$visregFit, 
             lower=part$fit$visregLwr, 
             upper=part$fit$visregUpr))

# The ggplot:
ggplot(smooths, aes(x, smooth)) + geom_line() +
  geom_line(aes(y=lower), linetype="dashed") + 
  geom_line(aes(y=upper), linetype="dashed") + 
  facet_grid(. ~ Variable, scales = "free_x")

我们可以将整个东西放入一个函数中，并添加一个选项来显示模型的残差（res = TRUE）：

ggplot.model <- function(model, type="conditional", res=FALSE, 
                       col.line="#7fc97f", col.point="#beaed4", size.line=1, size.point=1) {
  require(visreg)
  require(plyr)
  plotdata <- visreg(model, type = type, plot = FALSE)
  smooths <- ldply(plotdata, function(part)   
    data.frame(Variable = part$meta$x, 
             x=part$fit[[part$meta$x]], 
             smooth=part$fit$visregFit, 
             lower=part$fit$visregLwr, 
             upper=part$fit$visregUpr))
  residuals <- ldply(plotdata, function(part)
    data.frame(Variable = part$meta$x, 
               x=part$res[[part$meta$x]], 
               y=part$res$visregRes))
  if (res)
    ggplot(smooths, aes(x, smooth)) + geom_line(col=col.line, size=size.line) +
      geom_line(aes(y=lower), linetype="dashed", col=col.line, size=size.line) +
      geom_line(aes(y=upper), linetype="dashed", col=col.line, size=size.line) +
      geom_point(data = residuals, aes(x, y), col=col.point, size=size.point) +
      facet_grid(. ~ Variable, scales = "free_x")
  else
    ggplot(smooths, aes(x, smooth)) + geom_line(col=col.line, size=size.line) +
      geom_line(aes(y=lower), linetype="dashed", col=col.line, size=size.line) +
      geom_line(aes(y=upper), linetype="dashed", col=col.line, size=size.line) +
      facet_grid(. ~ Variable, scales = "free_x")
  }

ggplot.model(model)
ggplot.model(model, res=TRUE)

没有残差的ggplot 带有残差的ggplot 颜色选自http://colorbrewer2.org/。

于 2014-01-17T09:59:32.363 回答
5

仅供参考，visreg可以直接输出一个gg对象：

visreg(model, "x1", gg=TRUE)

在此处输入图像描述

于 2017-06-20T16:44:28.923 回答
0

更新以允许用户选择绘制哪些变量。将“残差”术语更改为“res_data”以避免与residuals功能冲突。

ggplot.model <- function(model, type="conditional", res=FALSE, 
                       col.line="#7fc97f", col.point="#beaed4", size.line=1, size.point=1, no_col = NULL,
                       what = "all") {
  require(visreg)
  require(plyr)
  
  plotdata <- visreg(model, type = type, plot = FALSE)
  smooths <- ldply(plotdata, function(part)   
    data.frame(Variable = part$meta$x, 
             x=part$fit[[part$meta$x]], 
             smooth=part$fit$visregFit, 
             lower=part$fit$visregLwr, 
             upper=part$fit$visregUpr))
  res_data <- ldply(plotdata, function(part)
    data.frame(Variable = part$meta$x, 
               x=part$res[[part$meta$x]], 
               y=part$res$visregRes))
  
   if (what != "all") {
    smooths <- smooths %>%
      filter(lapply(Variable,as.character)%in% what)
    res_data <- res_data%>%
      filter(lapply(Variable,as.character)%in% what)
   }
  
  
  if (res)
    ggplot(smooths, aes(x, smooth)) + geom_line(col=col.line, size=size.line) +
      geom_line(aes(y=lower), linetype="dashed", col=col.line, size=size.line) +
      geom_line(aes(y=upper), linetype="dashed", col=col.line, size=size.line) +
      geom_point(data = res_data, aes(x, y), col=col.point, size=size.point) +
      facet_wrap(. ~ Variable, scales = "free_x", ncol = no_col) + theme_bw()
  else
    ggplot(smooths, aes(x, smooth)) + geom_line(col=col.line, size=size.line) +
      geom_line(aes(y=lower), linetype="dashed", col=col.line, size=size.line) +
      geom_line(aes(y=upper), linetype="dashed", col=col.line, size=size.line) +
      facet_wrap(. ~ Variable, scales = "free_x", ncol=no_col)
}
于 2020-08-18T06:09:02.543 回答