3

テーブルを使用するデータ フレームのリストがあります。リストは次のようになります。

pronouns <- data.frame(pronounciation = c("juː","juː","juː","ju","ju","jə","jə","hɪm","hɪm","hɪm", "həm","ðɛm"), words = c("you","you","you","you","you","you","you","him","him","him","him","them"))
articles <- data.frame(pronounciation = c("ðiː","ði","ði","ðə","ðə","ði","ðə","eɪ","eɪ","æɪ","æɪ","eɪ","eɪ","eɪ","e"), words = c("the","the","the","the","the","the","the","a","a","a","a","a","a","a","a"))
numbers <- data.frame(pronounciation = c("wʌn","wʌn","wʌn","wʌn","wan","wa:n","tuː","tuː","tuː","tuː","tu","tu","tuː","tuː","θɹiː"), words = c("one","one","one","one","one","one","two","two","two","two","two","two","two","two","three"))
ls <- list(pronouns, articles, numbers)

ls[[1]]
   pronounciation words
1             juː   you
2             juː   you
3             juː   you
4              ju   you
5              ju   you
6              jə   you
7              jə   you
8             hɪm   him
9             hɪm   him
10            hɪm   him
11            həm   him
12            ðɛm  them

このデータフレームのリストから、table() を使用して $words の分割表を抽出しますが、同時に各単語の最も一般的な発音も選択します。必要な結果は ls_out にあります。

pronouns_out <- data.frame(pronounciation = c("juː","hɪm","ðɛm"), words = c("you","him","them"), occurence = c(7,4,1))
articles_out <- data.frame(pronounciation = c("ði","eɪ"), words = c("the","a"), occurence = c(7,8))
numbers_out <- data.frame(pronounciation = c("wʌn","tuː","θɹiː"), words = c("one","two","three"), occurence = c(6,8,1))
ls_out <- list(pronouns_out, articles_out, numbers_out)

ls_out[[1]]
  pronounciation words occurence
1            juː   you         7
2            hɪm   him         4
3            ðɛm  them         1

2 つ以上の発音の頻度が同じ場合 (ls[[2]] の ði と ðə のように)、1 つの発音をランダムに選択する必要があります。

これについてのアドバイスは大歓迎です。

4

3 に答える 3

1

table(および) の使用lapply:

ff = function(pronounce, word) 
{
    tab = table(word, pronounce)
    data.frame(pronounciation = colnames(tab)[max.col(tab, "random")], 
               words = rownames(tab),
               occurences = unname(rowSums(tab)))
}

lapply(ls, function(x) ff(x$pronounciation, x$words))

#[[1]]
#     pronounciation words occurences
#1        h<U+026A>m   him          4
#2 <U+00F0><U+025B>m  them          1
#3        ju<U+02D0>   you          7
#
#[[2]]
#  pronounciation words occurences
#1      e<U+026A>     a          8
#2      <U+00F0>i   the          7
#
#[[3]]
#      pronounciation words occurences
#1         w<U+028C>n   one          6
#2 θ<U+0279>i<U+02D0> three          1
#3         tu<U+02D0>   two          8
于 2013-10-24T11:40:41.833 に答える
0

data.tableライブラリの使用-

library(data.table)

dtlist<-list(pronouns,articles,numbers)
lapply(dtlist,setDT)

# for each data.table in the dtlist, calculate frequency by pron, words
dtlistfreq1 <- 
  lapply(dtlist, function(x) x[,.(freq = .N), by = .(pronunciation,words)])
# for each data.table in the dtlistfreq, pick the highest freq by words
dtlistfreq2 <- 
  lapply(dtlistfreq1, function(x) x[,.SD[which.max(freq)], by = .(words)])

出力

> dtlistfreq2 
[[1]]
   words pronounciation freq
1:   you            ju?    3
2:   him            h?m    4
3:  them            ð?m    1

[[2]]
   words pronounciation freq
1:   the             ði    3
2:     a             e?    5

[[3]]
   words pronounciation freq
1:   one            w?n    4
2:   two            tu?    6
3: three           ??i?    1
于 2013-10-24T11:27:08.083 に答える
0

data.tableこれは、( , ) ペアの数ではなく、occurrence各 の合計出現回数です。wordwordpronunciation

dtlist<-list(pronouns,articles,numbers)
lapply(dtlist,setDT)

common_r<-function(x){
  t<-sort(table(x),decreasing=T)
  n<-length(t[t==max(t)])
  c<-if (n>1)names(t)[ceiling(n*runif(1))] else names(t)[1]
  c
}
lapply(dtlist,function(x)setcolorder(x[,.(occurrence=.N,
                                       pronunciation=common_r(pronunciation)),
                                       by=words]),
                                     c("pronunciation","words","occurrence")))

出力：

[[1]]
   pronunciation words occurrence
1:           juː   you          7
2:           hɪm   him          4
3:           ðɛm  them          1

[[2]]
   pronunciation words occurrence
1:            ði   the          7
2:            eɪ     a          8

[[3]]
   pronunciation words occurrence
1:           wʌn   one          6
2:           tuː   two          8
3:          θɹiː three          1

最も一般的な発音が一意でない場合は、ランダム化するように注意してください。常に一意である場合 (または、この場合、どの発音が選択されてもかまわない場合)、これは単純化できます。

common_r<-function(x){names(sort(table(x),decreasing=T))[1]}

lapplyでラップすることにより、異なる単語カテゴリの3つの個別のリストを持ち歩きたくない場合は、出力をさらに簡素化できますrbindlist。

   pronunciation words occurrence
1:           juː   you          7
2:           hɪm   him          4
3:           ðɛm  them          1
4:            ði   the          7
5:            eɪ     a          8
6:           wʌn   one          6
7:           tuː   two          8
8:          θɹiː three          1

categoryまた、この新しいことわざにフィールドを追加して、data.tableそれぞれがどの単語カテゴリに由来するかを説明することもできます。

于 2015-07-20T21:05:30.180 に答える