Question

我正在尝试在带有正则表达式的某些列上使用ddply，但我无法使用它。我在下面准备了一个小例子。有没有办法在几个变量上使用ddply，或者我只是错过了手册中的内容？

df <- data.frame(low_1=rnorm(5),low_2=rnorm(5),high_1=rnorm(5),high_2=rnorm(5),N=c(1,2,3,4,5))
ddply(df,.(N), summarise, low=mean("low.."), high=mean("high.."))

Answer 1

您可以使用colwise计算多列上的相同统计信息，例如：

ddply(df, .(N), colwise(mean))

  N      low_1      low_2     high_1      high_2
1 1 -1.3105923 -0.5507862  0.6304232 -0.04553457
2 2 -0.1586676  0.6820199 -0.8220206  0.93301381
3 3  0.4434761  0.4337073 -1.2988521  0.84412693
4 4  0.2522467 -0.1393690  0.2361361  1.64288051
5 5  0.4118032  0.4358705 -0.3529169  0.98916518

要在列名上使用正则表达式，您可以执行以下操作：

使用包含grep()的正则表达式来标识您感兴趣的所有列。
提取分组变量的列号
将数据的子集传递给ddply，其中子集仅包含步骤1和2中标识的列。

试试这个：

idx <- grep("low", names(df))
idk <- which(names(df) == "N")
ddply(df[, c(idx, idk)], .(N), colwise(mean))

  N      low_1      low_2
1 1 -1.3105923 -0.5507862
2 2 -0.1586676  0.6820199
3 3  0.4434761  0.4337073
4 4  0.2522467 -0.1393690
5 5  0.4118032  0.4358705

Answer 2

就目前而言，您需要为您正在计算的每个统计信息传递不同的参数。

ddply(
  df,
  .(N), 
  summarise, 
  low_1  = mean(low_1), 
  low_2  = mean(low_2), 
  high_1 = mean(high_1), 
  high_2 = mean(high_2)
)

计算这个的惯用方法是在计算统计数据之前将数据重新整形为长格式。

library(plyr)
library(reshape2)
library(stringr)
df_long <- melt(df, id.vars = "N")
matches <- str_match(df_long$variable, "(low|high)_([[:digit:]])")
df_long <- within(
  df_long,
  {
    height <- matches[, 2]
    group <- as.integer(matches[, 3])
  }
)
ddply(
  df_long,
  .(N, height, group), 
  summarize, 
  mean_value = mean(value)
)

如果您愿意，可以使用mutate而不是within，并且可以使用现代ddply语法替换对dplyr的来电。

df_long %>%
  group_by(N, height, group) %>%
  summarize(mean_value = mean(value))

Answer 3

您可以执行以下操作：

ddply(df,.(N), summarise, 
      low=mean(sapply(grep("low",colnames(df),value=T),function(x){get(x)})), 
      high=mean(sapply(grep("high",colnames(df),value=T),function(x){get(x)})))

给出了这个输出：

  N         low        high
1 1  0.94613752  1.47197645
2 2 -0.68887596 -0.05779876
3 3 -0.28589753 -0.55694341
4 4 -0.01378869  0.28204629
5 5 -0.08681600  0.88544497

数据：

> dput(df)
structure(list(low_1 = c(0.885675347945903, -1.30343272566325, -2.44201300062675, -1.27709377574332, -0.794159839824383), 
               low_2 = c(1.00659968581264,-0.0743191876393787, 1.87021794472605, 1.24951638739919, 0.620527846366092), 
               high_1 = c(0.630374573470948, 0.169009703225843, -0.573629421621814, 0.340752780334754, 0.417022085050569), 
               high_2 = c(2.31357832822303,-0.284607218026423, -0.540257400090053, 0.223339795927736, 1.35386785598766), 
               N = c(1, 2, 3, 4, 5)), 
               .Names = c("low_1", "low_2", "high_1", "high_2", "N"), 
               row.names = c(NA, -5L), class = "data.frame")

Answer 4

这是dplyr和tidyr的一种方法，我认为会产生所需的输出：

require(dplyr) # if not yet installed, first run: install.packages("dplyr")
require(tidyr) # if not yet installed, first run: install.packages("tidyr")

gather(df, group, val, -N) %>%     # reshape the data to long format
  mutate(group = gsub("*_\\d+$", "", group)) %>%   # delete the numbers from low_x and high_x in the "group" column
  group_by(N, group) %>%           # group the data based on N and group (low/high)
  summarise(val = mean(val)) %>%   # apply the mean
  ungroup() %>%                    # ungroup the data
  spread(group, val)               # reshape to wide format so that low and high are separate columns

#Source: local data frame [5 x 3]
#
#  N        high         low
#1 1  0.29702057  0.15541153
#2 2 -1.02057669  1.09399446
#3 3  0.20745563  0.11582517
#4 4 -0.05573833 -0.22570064
#5 5  0.61697307 -0.06831203

它适用于任意数量的low_X和high_X列。

注意：请确保在 plyr之后加载dplyr 以避免函数名称冲突。

数据

set.seed(4711) df <- data.frame(low_1=rnorm(5),low_2=rnorm(5),high_1=rnorm(5),high_2=rnorm(5),N=c(1,2,3,4,5))

在ddply变量中使用正则表达式

4 个答案:

数据