R语言 | 第一部分：数据预处理

#数据框：将字段以列合并在一起。
leadership <- data.frame(manager, date ,country, gender, age, q1,q2,q3,q4,q5, stringsAsFactors=F)

#矩阵：通过调整参数，控制矩阵样式。
m1 <- matrix(c(1:6),nrow=2,ncol=3,dimnames=list(c("r1","r2"),c("c1","c2","c3")))
m2 <- matrix(1:6,nrow=2) #共6个元素，分2行，每行3个元素，未指定行名和列名
m3 <- matrix(1:6,ncol=3) #共6个元素，结果与创建形式2相同
m4 <- matrix(nr=2,nc=3) #未指定元素数据，默认为NA，2行3列，nr是nrow的简写，nc是ncol的简写，R能识别

#数组
mydata <- array(1:12,c(2,3,2),dimnames=list(c("r1","r2"),c("c1","c2","c3"),c("h1","h2"))  #myarray <- array(vector, dimensions, dimnames)

#factor和list
#factor是numeric数值类型
factor(x = character(), levels, labels = levels,exclude = NA, ordered = is.ordered(x), nmax = NA)
#注意：levels与labels的对应关系，其中levels发挥角标作用，与labels位置对应
例如：x <- c("Man", "Male", "Man", "Lady", "Female")
xf <- factor(x, levels = c("Male", "Man" , "Lady",   "Female"),labels = c("Male", "Male", "Female", "Female"))

#数据列表：可用于合并多个不同类型数据字段，例如：
pts <- list(x = cars[,1], y = cars[,2])

方法一：leadership <- transform(leadership,meanx= (q1+q2+q3+q4+q5)/5)
方法二：leadership$x <- c(1,1,1,1,1)
方法三：cbind（leadership，x）
方法四：merge 
student1<-data.frame(ID,name)
student2<-data.frame(ID,score)
total_student<-merge(student1,student2,by="ID") 

方法一：leadership[6,] <- c(6,"5/1/09","US","M",25,1,1,1,1,1,1,1,1,1) #需注意变量个数相等
方法二：rbind
ID<-c(1,2,3)
name<-c("Jame","Kevin","Sunny")
student1<-data.frame(ID,name)

ID<-c(4,5,6)
name<-c("Sun","Frame","Eric")
student2<-data.frame(ID,name)
total<-rbind(student1,student2)

leadership$age[leadership$age==99] <- NA
leadership$agecat2 <- NA
leadership <- within(leadership,{ 
agecat2[age>75] <- "Elder"
  agecat2[age>=55 & age<=75] <- "Middle Aged"
  agecat2[age<55] <- "Young"}
)

library(plyr)
leadership <- rename(leadership,c(manager="managerID", date="testDate"))

leadership[order(age),]
leadership[order(gender,age),]
leadership[order(gender,-age),]

#leadership <- data.frame(manager, date ,country, gender, age, q1,q2,q3,q4,q5, stringsAsFactors=F)

#筛选指定字段
leadership[,c(6:10)]
等同：leadership[c("q1","q2","q3","q4","q5")]
等同：myvars <- paste("q",1:5,sep="")

#条件筛选（和、且）
leadership[gender=='M' & age>30,]
#且
subset(leadership, age>=35 | age<24, select=gender:q4) #or条件筛选+列筛选

leadership[sample(1:nrow(leadership),3,replace=F),]   #replace=T说明不可以重复抽样

options(digits=3)

install.packages("dplyr") 
library(dplyr)】

dplyr包最常使用的函数主要包括以下几个：
变量筛选函数：select
数据筛选函数：filter
排序函数：arrange
变形函数：mutate
汇总函数：summarize
分组函数：group_by
管道连接符：%>%
随机抽样函数：sample_n, sample_frac