R 基本函数操作
aggregate 整合:
aggdata<-aggregate(mtcars[,c('mpg','qsec')],by=list(mtcars$cyl,mtcars$gear),FUN=mean,na.rm=TRUE)
SRE实战 互联网时代守护先锋，助力企业售后服务体系运筹帷幄！一键直达领取阿里云限量特价优惠。na值处理:
library(mice)
data(sleep,package="VIM")
对列：
sleep$NonD[which(is.na(sleep$NonD))]<-0
对整个数据框
sleep[is.na(sleep)]<-0
subset 筛选:
manager <- c(1, 2, 3, 4, 5)
date <- c("10/24/08", "10/28/08", "10/1/08", "10/12/08", "5/1/09")
country <- c("US", "US", "UK", "UK", "UK")
gender <- c("M", "F", "F", "M", "F")
age <- c(32, 45, 25, 39, 99)
q1 <- c(5, 3, 3, 3, 2)
q2 <- c(4, 5, 5, 3, 2)
q3 <- c(5, 2, 5, 4, 1)
q4 <- c(5, 5, 5, NA, 2)
q5 <- c(5, 5, 2, NA, 1)
leadership <- data.frame(manager, date, country, gender, age,
q1, q2, q3, q4, q5, stringsAsFactors=FALSE)
newdata <- subset(leadership, age >= 35 | age < 24,
select=c(q1, q2, q3, q4))
newdata <- subset(leadership, gender=="M" & age > 25,
select=gender:q4)
