1. 向量循环移位
library("magic")
x <- 1:10
magic::shift(x,1)
# [1] 10 1 2 3 4 5 6 7 8 9
magic::shift(x,1)
# [1] 10 1 2 3 4 5 6 7 8 9
magic::shift(x,2)
# [1] 9 10 1 2 3 4 5 6 7 8
magic::shift(x,3)
# [1] 8 9 10 1 2 3 4 5 6 7
magic::shift(x,4)
# [1] 7 8 9 10 1 2 3 4 5 6
2. 绘制平行坐标图
使用lattice包：
library("lattice")
parallel(~iris[1:4] | Species, iris)
使用ggplot2包：
D <- data.frame(Gain = rnorm(20), Trader= factor(LETTERS[1:4]), Day = factor(rep(1:5, each = 4)))
ggplot(D) + geom_line(aes(x = Trader, y =Gain, group = Day, color = Day))
3. 绘制表格
library("gridExtra")
cmSmall = 5
cmMed = 7
cmBig = 15
df =matrix(ncol=4,nrow=2)
df[1,] =c('Size',"small","medium","large")
df[2,] =c('cm',cmSmall, cmMed, cmBig)
df =as.data.frame(df)
grid.table(`rownames<-`(df[-1],df[[1]]),gpar.rowtext = gpar(fontface = "bold"),
gpar.rowfill = gpar(fill ="grey95", col = "white"), show.colnames=FALSE)
4. 开发工具包devtools介绍
devtools包是为开发人员提供各种开发工具的包，可以使开发过程变得更轻松。
例如;
get_path()
set_path(path)
以上函数，可以用来在Windows系统中，获取/设置PATH环境变量的值。
install_github函数可以用来直接从github上安装开源包。
clean_source函数可以在一个干净的环境中执行R语言脚本，不受当前环境的影响，帮助进行调试。
更多工具请查看该包的帮助文档。
5. 在函数内部加载包
以下列方式在函数内部调用require函数加载包，无法成功：
p.f <-function(x) (require(x))
p.f('base')
#Loading requiredpackage: x
#[1] FALSE
#Warning message:
#Inlibrary(package, lib.loc = lib.loc, character.only = TRUE, logical.return =TRUE, :
# there is no package called ‘x’
这是因为在全局域中，’base’会被eval成base对象，然后传给require函数，而在函数内部则不会自动执行这个过程，以下方式可以绕过这个限制，告诉require函数传入的是字符串，让其在内部进行处理。
p.f <-function(x) (require(x,character.only = TRUE))
p.f('base')
6. 在进度条上绘制图标
将img <- readPNG("C:/data/Rlogo.png")这一句中的png图片改成你的机器上的一张png图片的地址即可运行：
library(ggplot2)
library(png)
fill_images <-function()
{
l <- list()
for (i in 1:nrow(df3))
{
for (j in 1:floor(df3$units[i]))
{
#seems redundant, but does not workif moved outside of the loop (why?)
img <-readPNG("C:/data/Rlogo.png")
g <- rasterGrob(img,interpolate=TRUE)
l <- c(l, annotation_custom(g,xmin = i-1/2, xmax = i+1/2, ymin = j-1, ymax = j))
}
}
l
}
p <- ggplot(df3,aes(what, units)) +
geom_bar(fill="white",colour="darkgreen", alpha=0.5, stat="identity") +
coord_flip() +
scale_y_continuous(breaks=seq(0, 20, 2)) +
scale_x_discrete() +
theme_bw() +
theme(axis.title.x = element_blank(), axis.title.y = element_blank()) +
fill_images()
p
7. 用transform函数改造数据框
transform函数可以用于对数据框内容进行改造，比如增加新列，对某一列做某种计算等等，返回的是一个新的数据框。
比如，对Ozone这一列数据取反：
transform(airquality,Ozone = -Ozone)
# Ozone Solar.R Wind Temp Month Day
#1 -41 190 7.4 67 5 1
#2 -36 118 8.0 72 5 2
#3 -12 149 12.6 74 5 3
#4 -18 313 11.5 62 5 4
#5 NA NA 14.3 56 5 5
增加新的一列new，对Temp这一列计算Temp – 32 / 1.8，并覆盖Temp这一列的值
transform(airquality,new = -Ozone, Temp = (Temp-32)/1.8)
# Ozone Solar.R Wind Temp Month Day new
#1 41 190 7.4 19.44444 5 1 -41
#2 36 118 8.0 22.22222 5 2 -36
#3 12 149 12.6 23.33333 5 3 -12
#4 18 313 11.5 16.66667 5 4 -18
#5 NA NA 14.3 13.33333 5 5 NA
#6 28 NA 14.9 18.88889 5 6 -28
8. 展开完整的文件路径
文件路径经常可以用一些符号来代替，比如~代替当前工作目录，不在源代码里面使用绝对路径，可以使程序更加有通用性。但是，怎样通过~得到具体的路径呢？示例如下：
#展开当前工作路径
path.expand("~")
#[1]"C:/Users/liuning/Documents"
path.expand('~/data')
#[1]"C:/Users/liuning/Documents/data"
9. 用packageDescription函数查看包的信息
使用R包的时候，经常需要了解包的一些信息，比如包的作用、包依赖的R语言版本和其他包等等。
>packageDescription('zoo')
Package: zoo
Version: 1.7-11
Date: 2014-02-27
Title: S3Infrastructure for Regular and Irregular Time Series
(Z's ordered observations)
Authors@R:c(person(given = "Achim", family = "Zeileis", role
= c("aut", "cre"),email =
"Achim.Zeileis@R-project.org"), person(given ="Gabor",
family = "Grothendieck", role ="aut", email =
"ggrothendieck@gmail.com"),person(given = c("Jeffrey",
"A."), family ="Ryan", role = "aut", email =
"jeff.a.ryan@gmail.com"),person(given = "Felix",
family = "Andrews", role ="ctb", email =
"felix@nfrac.org"))
Description: An S3class with methods for totally ordered
indexed observations. It is particularlyaimed at
irregular time series of numericvectors/matrices and
factors. zoo's key design goals areindependence of a
particular index/date/time class andconsistency with
ts and base R by providing methods toextend standard
generics.
Depends: R (>=2.10.0), stats
Suggests: coda,chron, DAAG, fts, its, ggplot2, mondate,
scales, strucchange, timeDate, timeSeries,tis,
tseries, xts
Imports: utils,graphics, grDevices, lattice (>= 0.20-27)
License: GPL-2 |GPL-3
URL:http://zoo.R-Forge.R-project.org/
Packaged:2014-02-27 08:32:43 UTC; zeileis
Author: AchimZeileis [aut, cre], Gabor Grothendieck [aut],
Jeffrey A. Ryan [aut], Felix Andrews[ctb]
Maintainer: AchimZeileis <Achim.Zeileis@R-project.org>
NeedsCompilation:yes
Repository: CRAN
Date/Publication:2014-02-27 11:46:02
Built: R 3.1.3;x86_64-w64-mingw32; 2015-03-12 00:01:07 UTC;
windows
-- File:C:/Program Files/R/R-3.1.3/library/zoo/Meta/package.rds
10. 读写二进制文件示例
saveMatrixList<- function(baseName, mtxList) {
idxName <- paste(baseName,".idx", sep="")
idxCon <- file(idxName, 'wb')
on.exit(close(idxCon))
dataName <- paste(baseName,".bin", sep="")
con <- file(dataName, 'wb')
on.exit(close(con))
writeBin(0L, idxCon)
for (m in mtxList) {
writeBin(dim(m), con)
writeBin(typeof(m), con)
writeBin(c(m), con)
flush(con)
offset <- as.integer(seek(con))
cat('offset', offset)
writeBin(offset, idxCon)
}
flush(idxCon)
}
loadMatrix <-function(baseName = "data", index) {
idxName <- paste(baseName,".idx", sep="")
idxCon <- file(idxName, 'rb')
on.exit(close(idxCon))
dataName <- paste(baseName,".bin", sep="")
con <- file(dataName, 'rb')
on.exit(close(con))
seek(idxCon, (index-1)*4)
offset <- readBin(idxCon, 'integer')
seek(con, offset)
d <- readBin(con, 'integer', 2)
type <- readBin(con, 'character', 1)
structure(readBin(con, type, prod(d)),dim=d)
}
mtx <-list(matrix(1:12,4), matrix(sin(1:12),4))
saveMatrixList("c:/foo",mtx)
loadMatrix("c:/foo",1)
loadMatrix("c:/foo",2)
11. 利用rbind.fill函数合并列数不同的数据框
rbind.fill函数会合并列名相同的列，缺失列会用NA补足。
library("plyr")
df1 <-data.frame(A = c('A1','A2','A3'),B = c('B1','B2','B3'),C = c('C1','C2','C3'))
df2 <-data.frame(A = c('A4','A5','A6'),C = c('C4','C5','C6'))
rbind.fill(df1,df2)
# A B C
#1 A1 B1 C1
#2 A2 B2 C2
#3 A3 B3 C3
#4 A4 <NA>C4
#5 A5 <NA>C5
#6 A6 <NA>C6
rbind.fill(df2,df1)
# A C B
#1 A4 C4<NA>
#2 A5 C5<NA>
#3 A6 C6<NA>
#4 A1 C1 B1
#5 A2 C2 B2
#6 A3 C3 B3
12. 匹配中文字符示例
library("stringr")
x <-c('abcdefg','I am Chinese!我是中文字符!')
#判断是否含有中文字符,[\u4e00-\u9fa5]是中文字符编码的范围
grepl('[\u4e00-\u9fa5]',x)
#[1] FALSE TRUE
#查找所有的中文字符
str_extract_all(x,'[\u4e00-\u9fa5]')
#[[1]]
#character(0)
#[[2]]
#[1] "我" "是" "中" "文" "字" "符"
#查找连续的中文字符
str_extract_all(x,'[\u4e00-\u9fa5]+')
#[[1]]
#character(0)
#[[2]]
#[1] "我是中文字符"
13. 时间分段划分示例
#将时间按照5分钟划分
time <- seq(as.POSIXct("2014-06-28"), as.POSIXct("2014-07-10"), by = "5 mins")
head(time)
#[1]"2014-06-28 00:00:00 CST" "2014-06-28 00:05:00 CST"
#[3]"2014-06-28 00:10:00 CST" "2014-06-28 00:15:00 CST"
#[5] "2014-06-2800:20:00 CST" "2014-06-28 00:25:00 CST"
#划分成5小时一段
time <-seq(as.POSIXct("2014-06-28"), as.POSIXct("2014-07-10"), by= "5 hours")
head(time)
#[1]"2014-06-28 00:00:00 CST" "2014-06-28 05:00:00 CST"
#[3]"2014-06-28 10:00:00 CST" "2014-06-28 15:00:00 CST"
#[5]"2014-06-28 20:00:00 CST" "2014-06-29 01:00:00 CST"
#划分成2天一段
time <-seq(as.POSIXct("2014-06-28"), as.POSIXct("2014-07-10"), by= "2 days")
time
#[1]"2014-06-28 CST" "2014-06-30 CST" "2014-07-02CST"
#[4]"2014-07-04 CST" "2014-07-06 CST" "2014-07-08CST"
#[7]"2014-07-10 CST"
14. ` `（重音符）和' '（单引号）的区别
这两个符号乍一看都是单引号，其实是有区别的：
`mtcars`
mpg cyl disp hp drat wt qsec vs am gear carb
Mazda RX4 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4
Mazda RX4 Wag 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4
Datsun 710 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1
Hornet 4Drive 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1
HornetSportabout 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2
Valiant 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1
Duster 360 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4
'mtcars'
[1]"mtcars"
可以看出，重音符会把其中的字符转化是实际的对象，而单引号中仅仅只是一个普通字符串而已。
扫一扫
1736
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
