Coursera代码笔记：Getting and cleanin

1. Subsetting and Sorting

set.seed(13435)

X<data.frame("var1"=sample(1:5),"var2"=sample(6:10),"var3"=sample(11:15))

X<-X[sample(1:5),];X$var2[c(1,3)]=NA ＃更改X

X

X[,1]

X[,"var1"]

X[1:2,"var2"]

Logicals ands and ors  （选择）

X[(X$var1<=3&X$var3>11),]

X[(X$var1<=3|X$var3>15),]

Dealing with missing values

X[which(X$var2>8),]

Sorting

sort(X$var1)

sort(X$var1,decreasing=TRUE)

sort(X$var2,na.last=TRUE)

Ordering

X[order(X$var1),]

X[order(X$var1,X$var3),]

Ordering with plyr

library(plyr)

arrange(X,var1)

arrange(X,desc(var1))

Adding rows and columns

X$var4<-rnorm(5)  ＃将var4加入

X

Y<-cbind(X,rnorm(5))

Y

2.Summarizing Data

Getting the data from the web

if(!file.exists("./data")){dir.create("./data")}

fileUrl<-"https://data.baltimorecity.gov/api/views/k5ry-ef3g/rows.csv?accessType=DOWNLOAD"

download.file(fileUrl,destfile="./data/restaurants.csv",method="curl")

restData<-read.csv("./data/restaurants.csv")

Look a bit at the data

head(restData,n=3)  #查看前三行数据

tail(restData,n=3)  ＃查看后三行数据

Make summary

summary(restData)

str(restData)  ＃看更深的数据

quantile(restData$councilDistrict,na.rm=TRUE) ＃看分位数

quantile(restData$councilDistrict,probs=c(0.5,0.75,0.9))

Make table

table(restData$zipCode,useNA="ifany")

table(restData$councilDistrict,restData$zipCode)

Check for missing values

sum(is.na(restData$councilDistrict))

any(is.na(restData$councilDistrict))

all(restData$zipCode>0)

Row and column sums

colSums(is.na(restData))

all(colSums(is.na(restData))==0)  ＃返回TRUE／FALSE

Values with specific characteristics

table(restData$zipCode%in%c("21212"))

table(restData$zipCode%in%c("21212","21213"))

Values with specific characteristics

restData[restData$zipCode%in%c("21212","21213"),]

Cross tabs  ＃把数据根据变量分组查看 

data(UCBAdmissions)

DF=as.data.frame(UCBAdmissions)

summary(DF)

xt<-xtabs(Freq~Gender+Admit,data=DF)

xt

Admit

Gender  Admitted Rejected

Male      1198    1493

Female      557    1278

Flat tables

warpbreaks$replicate<-rep(1:9,len=54)

xt=xtabs(breaks~.,data=warpbreaks)

xt

Flat tables

Size of a data set

fakeData=rnorm(1e5)

object.size(fakeData)

print(object.size(fakeData),units="Mb")

3. Creating New Variables

Getting data from the web

if(!file.exists("./data")){dir.create("./data")}

fileUrl<-"https://data.baltimorecity.gov/api/views/k5ry-ef3g/rows.csv?accessType=DOWNLOAD"

download.file(fileUrl,destfile="./data/restaurants.csv",method="curl")

restData<-read.csv("./data/restaurants.csv")

Creating sequences

Sometimes you need an index for your data set

s1<-seq(1,10,by=2) ;s1

[1] 1 3 5 7 9

s2<-seq(1,10,length=3);s2

[1]  1.0  5.5 10.0

x<-c(1,3,8,25,100); seq(along=x)

[1] 1 2 3 4 5

Subsetting variables

restData$nearMe=restData$neighborhood%in%c("Roland Park","Homeland")

table(restData$nearMe)

    FALSE  TRUE

    1314    13

Creating binary variables

restData$zipWrong=ifelse(restData$zipCode<0,TRUE,FALSE)

table(restData$zipWrong,restData$zipCode<0)

          FALSE TRUE

FALSE  1326    0

TRUE      0       1

Creating categorical variables

restData$zipGroups=cut(restData$zipCode,breaks=quantile(restData$zipCode))

table(restData$zipGroups)

table(restData$zipGroups,restData$zipCode)

Easier cutting

library(Hmisc)

restData$zipGroups=cut2(restData$zipCode,g=4)

table(restData$zipGroups)

Creating factor variables

restData$zcf<-factor(restData$zipCode)

restData$zcf[1:10]

class(restData$zcf)

[1] "factor"

Levels of factor variables

yesno<-sample(c("yes","no"),size=10,replace=TRUE)

yesnofac=factor(yesno,levels=c("yes","no"))

relevel(yesnofac,ref="no")

[1] yes yes yes yes no  yes yes yes no  no

Levels: no yes

as.numeric(yesnofac)

[1] 1 1 1 1 2 1 1 1 2 2

Cutting produces factor variables

library(Hmisc)

restData$zipGroups=cut2(restData$zipCode,g=4)

table(restData$zipGroups)

[-21226,21205) [ 21205,21220) [ 21220,21227) [ 21227,21287]

338            375            300            314

Using the mutate function

library(Hmisc); library(plyr)

restData2=mutate(restData,zipGroups=cut2(zipCode,g=4))

table(restData2$zipGroups)

[-21226,21205) [ 21205,21220) [ 21220,21227) [ 21227,21287]

338            375            300            314

Common transforms

abs(x)  absolute value

sqrt(x)  square root

ceiling(x)  ceiling(3.475) is 4

floor(x)  floor(3.475) is 3

round(x,digits=n)  round(3.475,digits=2) is 3.48

signif(x,digits=n)  signif(3.475,digits=2) is 3.5

cos(x), sin(x) etc.

log(x) natural logarithm

log2(x),log10(x)other common logs

exp(x) exponentiating x

4. Reshaping Data

Start with reshaping

library(reshape2)

head(mtcars)    ＃返回一组以车辆型号为obs的序列，var有各型号的马力数据