R-Retrieve Data (step 1)

深藏阁楼爱情的钟 2022-02-13 02:07 196阅读 0赞

## \[I\]Data Structure ##

### 1.vector ###

*  numeric

> a<-c(1,2,3)  
    > a
    [1] 1 2 3

*  character

> a<-c("1","2","3")   
    > a
    [1] "1" "2" "3"

*  logicals

> a<-c(FALSE,TRUE)
    > a
    [1] FALSE  TRUE

*  scalar

> a<-FALSE
    > a
    [1] FALSE

### 2.matrix ###

*  create

#base
    > mymatrix<-matrix(1:9,nrow=3,ncol=3)
    > mymatrix
         [,1] [,2] [,3]
    [1,]    1    4    7
    [2,]    2    5    8
    [3,]    3    6    9

#labeling rows/cols
    > cells<-c(1:9)
    > rnames<-c("R1","R2","R3")
    > cnames<-c("C1","C2","C3")
    > mymatrix<-matrix(cells,nrow=3,ncol=3,byrow=TRUE,dimnames=list(rnames,cnames))    #fill according to row
    > mymatrix
       C1 C2 C3
    R1  1  2  3
    R2  4  5  6
    R3  7  8  9
    > mymatrix<-matrix(cells,nrow=3,ncol=3,byrow=FALSE,dimnames=list(rnames,cnames))    #fill according to column
    > mymatrix
       C1 C2 C3
    R1  1  4  7
    R2  2  5  8
    R3  3  6  9

*  index

> mymatrix[2,]
    C1 C2 C3 
     2  5  8 
    > mymatrix[,2]
    R1 R2 R3 
     4  5  6 
    > mymatrix[2,2]
    [1] 5
    > mymatrix[2,c(1,2)]
    C1 C2 
     2  5

### 3.array ###

> dim1<-c("A1","A2","A3")
    > dim2<-c("B1","B2","B3")
    > dim3<-c("C1","C2","C3")
    > myarry<-array(1:27,c(3,3,3),dimnames=list(dim1,dim2,dim3))
    > myarray
    , , C1
    
       B1 B2 B3
    A1  1  4  7
    A2  2  5  8
    A3  3  6  9
    
    , , C2
    
       B1 B2 B3
    A1 10 13 16
    A2 11 14 17
    A3 12 15 18
    
    , , C3
    
       B1 B2 B3
    A1 19 22 25
    A2 20 23 26
    A3 21 24 27

### 4.data frame ###

*  create

> ID<-c(1,2,3,4)
    > age<-c(27,26,32,54)
    > sex<-c("Male","Female","Female","Female")
    > music<-c("Type2","Type1","Type1","Type1")
    > status<-c("Excellent","Improved","Poor","Excellent")
    > singerdata<-data.frame(ID,age,sex,music,status)
    > singerdata
      ID age    sex music    status
    1  1  27   Male Type1 Excellent
    2  2  26 Female Type2  Improved
    3  3  32 Female Type1      Poor
    4  4  54 Female Type1 Excellent

*  select

#base
    > singerdata[1:2]
      ID age
    1  1  27
    2  2  26
    3  3  32
    4  4  54
    > singerdata[c("music","status")]
      music    status
    1 Type2 Excellent
    2 Type1  Improved
    3 Type1      Poor
    4 Type1 Excellent
    > table(singerdata$music,singerdata$status)
           
            Excellent Improved Poor
      Type1         1        1    1
      Type2         1        0    0

#external data:e.g.mtcars
    > attach(mtcars)    #No object of the same name 
    > summary(mpg)
       Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
      10.40   15.43   19.20   20.09   22.80   33.90 
    > plot(mpg,disp)
    > detach(mtcars)
    > with(mtcars,{     #object of the same name
    +  nokeepstats<-summary(mpg)
    +  keepstats<<-summary(mpg)
    + })
    > nokeepstats    #internal call
    Error: object 'nokeepstats' not found
    > keepstats    #external call
       Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
      10.40   15.43   19.20   20.09   22.80   33.90

### 5.factor ###

> ID<-c(1,2,3,4)
    > age<-c(27,26,32,54)
    > sex<-c(1,2,2,2)
    > music<-c("Type1","Type2","Type1","Type1")
    > status<-c("Excellent","Improved","Poor","Excellent")
    > sex<-factor(sex,levels=c(1,2),labels=c("Male","Female"))    #label replace
    > music<-factor(music)    #default order:A-Z
    > status<-factor(status,order=TRUE,levels=c("Poor","Improved","Excellent"))    #customize order
    > singerdata<-data.frame(ID,age,sex,music,status)
    > str(singerdata)
    'data.frame':   4 obs. of  5 variables:
     $ ID    : num  1 2 3 4
     $ age   : num  27 26 32 54
     $ sex   : Factor w/ 2 levels "Male","Female": 1 2 2 2
     $ music : Factor w/ 2 levels "Type1","Type2": 1 2 1 1
     $ status: Ord.factor w/ 3 levels "Poor"<"Improved"<..: 3 2 1 3
    > summary(singerdata)
           ID            age            sex      music         status 
     Min.   :1.00   Min.   :26.00   Male  :1   Type1:3   Poor     :1  
     1st Qu.:1.75   1st Qu.:26.75   Female:3   Type2:1   Improved :1  
     Median :2.50   Median :29.50                        Excellent:2  
     Mean   :2.50   Mean   :34.75                                     
     3rd Qu.:3.25   3rd Qu.:37.50                                     
     Max.   :4.00   Max.   :54.00

### 6.list ###

*  create

> tit<-"singer list"
    > name<-c("Hua","Deng","Ga","Wang")
    > age<-c(27,26,32,54)
    > position<-matrix(1:9,nrow=3)
    > mylist<-list(title=tit,name,ages=age,position)
    > mylist
    $title
    [1] "singer list"
    
    [[2]]
    [1] "Hua"  "Deng" "Ga"   "Wang"
    
    $ages
    [1] 27 26 32 54
    
    [[4]]
         [,1] [,2] [,3]
    [1,]    1    4    7
    [2,]    2    5    8
    [3,]    3    6    9

*  index

> mylist[[2]]
    [1] "Hua"  "Deng" "Ga"   "Wang"
    > mylist[["ages"]]
    [1] 27 26 32 54

--------------------

## \[II\]Import Data ##

### 1.keyboard ###

*  text editor

> mydata<-data.frame(age=numeric(0),sex=character(0),order=numeric(0))
    > mydata<-edit(mydata)    #reopen：> mydata<-edit(mydata)

result:  
![importdata\_keyborad][importdata_keyborad]

*  embedded

> mydatatxt<-"
    + age sex order
    + 27 Male 1
    + 26 Female 2
    + 32 Female 3
    + 54 Female 4
    + "
    > mydata<-read.table(header=TRUE,text=mydatatxt)
    > mydata
      age    sex order
    1  27   Male     1
    2  26 Female     2
    3  32 Female     3
    4  54 Female     4

### 2.delimited text file ###

singerdata.csv  
![singerdata][]

> music<-read.table("singerdata.csv",header=TRUE,row.names="ID",sep=",",colClasses=c("character","character","numeric","character","numeric"))
    > music
      name age    sex music
    1  Hua  27   Male   100
    2 Deng  26 Female    95
    3   Ga  32 Female    NA
    4 Wang  54 Female    93
    > str(music)
    'data.frame':   4 obs. of  4 variables:
     $ name : chr  "Hua" "Deng" "Ga" "Wang"
     $ age  : num  27 26 32 54
     $ sex  : chr  "Male" "Female" "Female" "Female"
     $ music: num  100 95 NA 93

### 3.Excel ###

> install.packages("xlsx")
    > install.packages("xlsxjars")
    > install.packages("rJava") 
    > library(xlsx)
    > workbook<-"c:/myworkbook.xlsx"
    > mydatdaframe<-read.xls(workbook,1)

### 4.XML ###

RSXML

### 5.web page ###

[Webscraping using readLines and RCurl][]

### 6.SPSS ###

> install.packages("Hmisc")
    > library(Hmisc)
    > mydataframe<-spss.get("mydata.sav",use.value.labels=TRUE)

### 7.SAS ###

#installed SAS
    > install.packages("Hmisc")  
    > library(Hmisc)
    > datadir<-"C/data"
    > sasexe<-"C/Program Files/SASHome/SASFoundation/9.4/sas.exe"
    > mydata<-sas.get(libraryName=datadir,member="clients",sasprog=sasexe)

#not installed SAS
    > install.packages("sas7bdat")  
    > library(sas7bdat)
    > mydata<-read.sas7bdat("C:/mydata/clients.sas7bdat")

### 8.Stata ###

> install.packages("foreign")
    > library(foreign)
    > mydataframe<-read.dta("mydata.dta")

### 9.NetCDF ###

> install.packages("ncdf4")
    > library(ncdf4)
    > myarray<-ncatt_get(nc,varid)

### 10.HDF5 ###

> source("http://bioconductor.org/biocLite.R")
    > biocLite("rhdf5")
    > library(rhdf5)
    > h5ls("C:/mydata")

### 11.data management system ###

*  ODBC API

> install.packages("RODBC")
    > library(RODBC)
    > myconn<-odbcConnect("mydsn",uid="xw",pwd="xinwenfan")
    > crimedat<-sqlFetch(mymonn,Crime)
    > pundat<-sqlQuery(myconn,"select* from Punishment")
    > close(myconn)

*  DBI  
    [The Comprehensive R Archive Network][]

### 12.Stat/Transfer ###

![stattransfer][]

--------------------

## \[III\]Object Function ##

> length(object)    #the number of elements/ingredients in the object
    > dim(object)    #dimension of object
    > str(object)    #structure of object
    > class(object)    #type of object
    > mode(object)    #type of object
    > names(object)    #name of ingredients
    > c(object,object,...)    #binding objects into one vector
    > cbind(object,object,...)    #binding objects by column
    > rbind(object,)    #binding objects by row
    > object    #printing object
    > head(object)    #listing the beginning part
    > tail(object)    #listing the ending part
    > ls()    #show current list

\----

## \[IV\]Generate dynamic reports by R and LaTex ##

### 1.install LeTex ###

Linux:[TeXLive][]  
Windows:[MikTex][]  
Mac:[MacTeX][]

### 2.install knitr ###

> install.packages("knitr")

### 3.install data package ###

#e.g.multcomp
    > install.packages("multcomp")

### 4.Creat File.Rnw ###

#e.g. drugs.Rnw

### 5.process data ###

> library(knitr)
    > knit("drugs.Rnw")    #drugs.tex
    > knit2pdf("drugs.Rnw")    #drugs.pdf

**END!**

[importdata_keyborad]: /images/20220213/d55ae98aabf74fdc9d424751ea9a579d.png
[singerdata]: /images/20220213/1cc984123a36454387494024a2119901.png
[Webscraping using readLines and RCurl]: http://www.programmingr.com/content/webscraping-using-readlines-and-rcurl/
[The Comprehensive R Archive Network]: https://cran.r-project.org
[stattransfer]: /images/20220213/ebd7670e90194a838d5ae72f94811f86.png
[TeXLive]: http://tug.org/texlive/
[MikTex]: http://miktex.org/
[MacTeX]: http://tug.org/mactex/