R语言学习笔记4-列表篇

- List operations
    - j<-list(name="Joe",salary=55000,union=T)
    - j$sal    # only prefix can be recognized
    - j[["salary"]]    # same as above
    - j[[2]]    # same as above
    - z<-vector(mode="list")
    - z[["abc"]]<-3
    - j[1:2]    # Joe 55000
    - j2<-j[2]
    - class(j2)    # "list"
    - j[[1:2]]    # ERROR [[]] is only for one element
    - j2a<-j[[2]]
    - class(j2a)    # "numeric"
    - names(j)    # "name" "salary" "union"
    - ulj<-unlist(j)    # vector of string, "Joe" "55000" "T"
    - y<-unlist(list(a=5,b=12,c=13))    # class(y)="numeric"
    - names(wu)<-NULL    # same as unname(wu)
    - lapply(list(1:3,25:29),median)    # list apply
        - [[1]] 2
        - [[2]] 27
    - sapply(list(1:3,25:29),median)    # simplified apply
        - 2 27
    - x<-c(12,5,13,8)
    - order(x)    # 2 4 1 3
    - b<-list(u=5,v=12)
    - c<-list(w=13)
    - a<-list(b,c)
    - a
        - [[1]]
        - [[1]]$u
        - 5
        - [[1]]$v
        - 12
    - length(a)    # 2
    - c(list(a=1,b=2,c=list(d=5,e=9)))
        - $a
        - 1
        - $b
        - 2
        - $c
        - $c$d
        - 5
        - $c$e
        - 9 
    - c(list(a=1,b=2,c=list(d=5,e=9)),recursive=T)    # Non recursive list, T is abbr of TRUE, default is FALSE
        - a b c.d c.e
        - 1 2 5 9

- add & remove
    - z<-list(a="abc",b=12)
    - z$c<-"sailing"    # add by key
    - z[[4]]<-28    # add by index
    - z[5:7]<-c(FALSE,TRUE,TRUE)    #add vector
    - z$b<-NULL    # remove both key and value and all index after b substract 1
    - z[[4]]    # FALSE not 28
    - c(list("Joe",55000,T),list(5))    # merge list
    - length(j)    # 3

- example
    findwords<-function(tf) {
        txt<-scan(tf,"")
        wl<-list()
        for (i in 1:length(txt)) {
            wrd<-txt[i]    # ith word in txt
            wl[[wrd]]<-c(wl[[wrd]],i)    # append wrd and its index to wl with key=wrd
        }
        return(wrd)
    }
    findwords("....txt")

    alphawl<-function(wrdlist) {
        nms<-names(wrdlst)
        sn<-sort(nms)    # sort by alphabet
        return(wrdlst[sn])
    }

    freqwl<-function(wrdlst) {
        freqs<-sapply(wrdlst,length)
        return(wrdlst[order(freqs)])    # after sorted original-index list
    }

    nyt<-findwords("nyt.txt")
    snyt<-freqwl(nyt)
    nwords<-length(snyt)
    freqs9<-sapply(snyt[round(0.9*nwords):nwords],length)    # top 10% words hist
    barplot(freqs9)

    g<-c("M","F","F","I","M","M","F")
    lapply(c("M","F","I"),function(gender) which(g==gender))    # [[1]] 1 5 6 [[2]] 2 3 7 [[3]] 4, anonymous function