- grep
# load data
alldata <- read.table("household_power_consumption.txt",stringsAsFactors = F,header = T,sep = ";")
# change format of Date
alldata$fulltime <- strptime(paste(alldata$Date, alldata$Time, sep=" "),"%d/%m/%Y %H:%M:%S")
# select specified rows
newd1<-alldata[grep(pattern = "2007-02-01",alldata[,10]),]
# alldata: 數(shù)據(jù)框
# pattern: 包含的字段（字符串）
# alldata[,10]: 該字符串位于數(shù)據(jù)框的位置隧期，也可以用$來取
- which
# load data
SCC <- readRDS("Source_Classification_Code.rds")
sumSCC <- readRDS("summarySCC_PM25.rds")
# select specified data
v1 <- SCC[grep(pattern="Coal",SCC$EI.Sector),]
v1 <- as.character(v1$SCC)
data_coal <- sumSCC[which(sumSCC$SCC %in% v1),]
total_coal <- aggregate(Emissions ~ year , data_coal, sum)
- subset
# load data
SCC <- readRDS("Source_Classification_Code.rds")
sumSCC <- readRDS("summarySCC_PM25.rds")
# select specified data
v2 <- SCC[grep(pattern="Vehicles",SCC$EI.Sector),]
v2 <- as.character(v2$SCC)
data_Bal <- sumSCC[which(sumSCC$SCC %in% v2),]
data_Bal <- subset(data_Bal,fips == “24510”)
# data_Bal: 數(shù)據(jù)框
# fips: 選擇fips這一列中值為24150的
total_Bal <- aggregate(Emissions ~ year , data_Bal, sum)
# 或者
new_d3 <- scan("g3.txt")
# subset函數(shù)選擇相應(yīng)的行
freq_d3 <- subset(allData, name %in% new_d3)
最后編輯于 ：
?著作權(quán)歸作者所有,轉(zhuǎn)載或內(nèi)容合作請(qǐng)聯(lián)系作者
