Hi我有以下数据结构
> class(iso.table.2)
[1] "list"
> class(iso.table.2[1])
[1] "list"
即嵌套列表。
我可以使用以下选项选择嵌套列表元素：
> head(iso.table.2[[2]][1:2])
V4 V11
1 <NA> <NA>
2 <NA> <NA>
3 <NA> <NA>
4 <NA> <NA>
5 <NA> <NA>
6 <NA> <NA>
其中的情况是，在每个列表元素中，每个表都有许多行，其中每个单元格都是NA。我想看看
iso.表2[[i]][2]
在每个嵌套列表中，并且只选择此列中的值为非NA的子集。所以如果我有：
V4 V11
12 <NA> <NA>
13 mrna <NA>
14 XP_005268469.1 <NA>
15 <NA> <NA>
16 dbSNP rs#cluster id Function
17 rs369314432 synonymous
18 contig reference
我只想检索
V4 V11
16 dbSNP rs#cluster id Function
17 rs369314432 synonymous
18 contig reference
我尝试过以下几种：
iso.table.2[!is.na(iso.table.2)]
就像我习惯于处理数据帧一样。然而，这只是返回整个嵌套列表元素，显然忽略了`！is.na.
我能做的是使用lapply(iso.table.2,'is.na')测试NA值。但这只是一次考验。
有人能帮忙吗。
这里是我的dput（）供参考
> dput(iso.table.2[[1]])
structure(list(V4 = structure(c(NA, NA, NA, NA, NA, NA, 5L, 5L,
5L, 5L, 5L, NA, 3L, 4L, NA, 2L, 18L, 1L, 36L, 1L, 13L, 1L, 29L,
1L, 71L, 1L, 45L, 1L, 32L, 1L, 63L, 1L, 27L, 1L, 12L, 1L, 46L,
1L, 72L, 1L, 9L, 1L, 55L, 1L, 19L, 1L, 21L, 1L, 68L, 1L, 11L,
1L, 74L, 1L, 20L, 1L, 77L, 1L, 33L, 1L, 22L, 1L, 76L, 1L, 38L,
1L, 28L, 1L, 69L, 1L, 25L, 1L, 47L, 1L, 58L, 1L, 30L, 1L, 1L,
10L, 1L, 42L, 1L, 49L, 1L, 6L, 1L, 75L, 1L, 64L, 1L, 44L, 1L,
62L, 1L, 17L, 1L, 70L, 1L, 51L, 1L, 56L, 1L, 8L, 1L, 41L, 1L,
53L, 1L, 60L, 1L, 16L, 1L, 54L, 1L, 7L, 1L, 59L, 1L, 43L, 1L,
61L, 1L, 48L, 1L, 34L, 1L, 65L, 1L, 31L, 1L, 23L, 1L, 15L, 1L,
40L, 1L, 26L, 1L, 24L, 1L, 67L, 1L, 37L, 1L, 35L, 1L, 50L, 1L,
66L, 1L, 14L, 1L, 52L, 1L, 73L, 1L, 39L, 1L, 57L, 1L), .Label = c("",
"dbSNP rs#cluster id", "mrna", "NP_001139512.1", "reverse", "rs112560122",
"rs112970419", "rs114046477", "rs138173310", "rs139058916", "rs139213838",
"rs140420721", "rs141039714", "rs141704405", "rs142888296", "rs143377552",
"rs146034962", "rs146481873", "rs146911085", "rs147156518", "rs147471585",
"rs148221542", "rs148952106", "rs149023945", "rs150716717", "rs151029950",
"rs151276682", "rs17112272", "rs182383995", "rs192326771", "rs199547699",
"rs199561280", "rs199618583", "rs199639315", "rs199910297", "rs200130685",
"rs200171902", "rs200218897", "rs200604203", "rs200606738", "rs201280023",
"rs201471742", "rs202233543", "rs2229962", "rs367564392", "rs368049933",
"rs369314432", "rs369500388", "rs369800907", "rs369873008", "rs370809444",
"rs370920306", "rs371331129", "rs371496582", "rs372342365", "rs372452903",
"rs373114110", "rs373120024", "rs374319634", "rs374834686", "rs374949730",
"rs374982085", "rs375152105", "rs375819582", "rs375840161", "rs376426309",
"rs376610236", "rs377129430", "rs377190917", "rs377524694", "rs62636580",
"rs62636581", "rs74542605", "rs75463357", "rs76872663", "rs77451630",
"rs78363193"), class = "factor"), V11 = structure(c(NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 2L, 3L, 1L, 3L,
1L, 3L, 1L, 3L, 1L, 5L, 1L, 3L, 1L, 3L, 1L, 4L, 1L, 3L, 1L, 3L,
1L, 5L, 1L, 3L, 1L, 3L, 1L, 3L, 1L, 3L, 1L, 3L, 1L, 5L, 1L, 3L,
1L, 5L, 1L, 3L, 1L, 5L, 1L, 3L, 1L, 3L, 1L, 3L, 1L, 3L, 1L, 5L,
1L, 5L, 1L, 5L, 1L, 5L, 1L, 3L, 1L, 5L, 5L, 1L, 3L, 1L, 3L, 1L,
3L, 1L, 5L, 1L, 5L, 1L, 3L, 1L, 3L, 1L, 5L, 1L, 5L, 1L, 5L, 1L,
5L, 1L, 3L, 1L, 5L, 1L, 5L, 1L, 3L, 1L, 3L, 1L, 5L, 1L, 5L, 1L,
5L, 1L, 5L, 1L, 3L, 1L, 3L, 1L, 5L, 1L, 3L, 1L, 5L, 1L, 3L, 1L,
5L, 1L, 3L, 1L, 5L, 1L, 3L, 1L, 5L, 1L, 5L, 1L, 3L, 1L, 3L, 1L,
3L, 1L, 3L, 1L, 3L, 1L, 3L, 1L, 3L, 1L, 5L, 1L, 3L, 1L), .Label = c("contig reference",
"Function", "missense", "nonsense", "synonymous"), class = "factor"),
V12 = structure(c(NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, 3L, 1L, 2L, 1L, 4L, 5L, 4L, 5L, 2L, 5L,
2L, 1L, 5L, 1L, 4L, 5L, 2L, 5L, 1L, 4L, 2L, 2L, 5L, 5L, 2L,
2L, 1L, 1L, 2L, 4L, 5L, 1L, 4L, 4L, 1L, 1L, 4L, 1L, 4L, 2L,
4L, 4L, 1L, 1L, 4L, 2L, 5L, 4L, 1L, 2L, 4L, 5L, 2L, 2L, 5L,
1L, 4L, 5L, 1L, 5L, 4L, 1L, 5L, 2L, 5L, 2L, 2L, 5L, 4L, 1L,
1L, 4L, 2L, 4L, 1L, 4L, 1L, 4L, 4L, 1L, 4L, 1L, 1L, 4L, 5L,
2L, 5L, 2L, 5L, 2L, 5L, 2L, 2L, 5L, 5L, 2L, 1L, 4L, 2L, 5L,
5L, 2L, 1L, 4L, 2L, 5L, 4L, 1L, 5L, 2L, 1L, 2L, 5L, 2L, 5L,
2L, 2L, 5L, 1L, 4L, 5L, 2L, 1L, 4L, 2L, 4L, 5L, 2L, 5L, 2L,
1L, 4L, 1L, 2L, 2L, 5L, 2L, 4L, 4L, 2L, 2L, 4L, 1L, 5L, 1L,
5L), .Label = c("A", "C", "dbSNPallele", "G", "T"), class = "factor"),
V13 = structure(c(NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, 17L, 4L, 10L, 10L, 3L, 11L, 14L, 6L,
3L, 15L, 15L, 11L, 15L, 7L, 3L, 1L, 3L, 12L, 14L, 6L, 18L,
16L, 16L, 12L, 16L, 19L, 4L, 5L, 2L, 2L, 18L, 10L, 3L, 9L,
9L, 7L, 3L, 3L, 3L, 19L, 3L, 3L, 3L, 7L, 3L, 16L, 12L, 9L,
8L, 7L, 8L, 2L, 2L, 2L, 2L, 22L, 22L, 2L, 2L, 22L, 9L, 18L,
18L, 18L, 6L, 3L, 12L, 15L, 22L, 11L, 12L, 12L, 3L, 3L, 7L,
3L, 5L, 9L, 19L, 19L, 8L, 8L, 12L, 12L, 11L, 11L, 11L, 19L,
16L, 16L, 12L, 12L, 19L, 11L, 20L, 3L, 12L, 12L, 12L, 12L,
4L, 4L, 12L, 12L, 16L, 12L, 5L, 4L, 16L, 16L, 8L, 5L, 4L,
4L, 20L, 3L, 21L, 21L, 14L, 22L, 4L, 4L, 13L, 3L, 18L, 18L,
18L, 18L, 15L, 18L, 10L, 3L, 18L, 3L, 18L, 15L, 5L, 8L, 22L,
12L, 16L, 3L, 19L, 19L, 13L, 4L), .Label = c("", "Ala [A]",
"Arg [R]", "Asn [N]", "Asp [D]", "Cys [C]", "Gln [Q]", "Glu [E]",
"Gly [G]", "His [H]", "Ile [I]", "Leu [L]", "Lys [K]", "Met [M]",
"Phe [F]", "Pro [P]", "Proteinresidue", "Ser [S]", "Thr [T]",
"Trp [W]", "Tyr [Y]", "Val [V]"), class = "factor"), V14 = structure(c(NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 4L,
1L, 1L, 2L, 2L, 3L, 3L, 1L, 1L, 3L, 3L, 1L, 1L, 2L, 2L, 1L,
1L, 1L, 1L, 2L, 2L, 3L, 3L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L,
2L, 2L, 3L, 3L, 2L, 2L, 3L, 3L, 2L, 2L, 3L, 3L, 2L, 2L, 2L,
2L, 2L, 2L, 1L, 1L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 2L, 2L,
3L, 3L, 3L, 1L, 1L, 1L, 1L, 1L, 1L, 3L, 3L, 3L, 3L, 2L, 2L,
2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 2L, 2L, 3L, 3L, 1L,
1L, 2L, 2L, 1L, 1L, 3L, 3L, 1L, 1L, 3L, 3L, 3L, 3L, 2L, 2L,
1L, 1L, 3L, 3L, 3L, 3L, 3L, 3L, 1L, 1L, 3L, 3L, 1L, 1L, 3L,
3L, 2L, 2L, 3L, 3L, 3L, 3L, 2L, 2L, 2L, 2L, 1L, 1L, 2L, 2L,
3L, 3L, 1L, 1L, 2L, 2L, 3L, 3L, 3L, 3L), .Label = c("1",
"2", "3", "Codonpos"), class = "factor"), V15 = structure(c(NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 63L,
50L, 50L, 49L, 49L, 48L, 48L, 47L, 47L, 46L, 46L, 46L, 46L,
45L, 45L, 45L, 45L, 44L, 44L, 43L, 43L, 42L, 42L, 41L, 41L,
40L, 40L, 38L, 38L, 37L, 37L, 36L, 36L, 35L, 35L, 34L, 34L,
33L, 33L, 33L, 33L, 32L, 32L, 32L, 32L, 31L, 31L, 30L, 30L,
30L, 30L, 29L, 29L, 28L, 28L, 26L, 26L, 25L, 25L, 23L, 23L,
22L, 22L, 22L, 21L, 21L, 20L, 20L, 19L, 19L, 18L, 18L, 17L,
17L, 17L, 17L, 16L, 16L, 15L, 15L, 14L, 14L, 13L, 13L, 12L,
12L, 11L, 11L, 10L, 10L, 8L, 8L, 7L, 7L, 6L, 6L, 5L, 5L,
5L, 5L, 4L, 4L, 2L, 2L, 2L, 2L, 1L, 1L, 62L, 62L, 61L, 61L,
60L, 60L, 59L, 59L, 57L, 57L, 55L, 55L, 54L, 54L, 51L, 51L,
39L, 39L, 27L, 27L, 27L, 27L, 24L, 24L, 24L, 24L, 9L, 9L,
3L, 3L, 58L, 58L, 56L, 56L, 53L, 53L, 52L, 52L), .Label = c("104",
"113", "13", "130", "145", "150", "158", "164", "17", "174",
"179", "195", "212", "219", "232", "233", "241", "244", "262",
"270", "280", "296", "297", "30", "300", "305", "31", "330",
"331", "341", "343", "344", "347", "349", "366", "369", "373",
"374", "39", "397", "402", "403", "406", "412", "413", "416",
"428", "440", "450", "455", "48", "5", "6", "66", "67", "8",
"86", "9", "93", "97", "98", "99", "Amino acidpos"), class = "factor"),
V16 = structure(c(NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L), .Label = c("", "PubMed"), class = "factor")), .Names = c("V4",
"V11", "V12", "V13", "V14", "V15", "V16"), row.names = c(NA,
-161L), class = "data.frame")
因此，如果您有样本数据
iso.table.2 <- list(
data.frame(a=1:5, b=c(7,NA,9,6,8)),
data.frame(a=6:10, b=c(NA,3,2,NA,1))
)
如果你想要每个数据帧的第二列中的所有值都不是NA，你可以进行
lapply(iso.table.2, function(x) Filter(Negate(is.na), x[[2]]))
获取
[[1]]
[1] 7 9 6 8
[[2]]
[1] 3 2 1