r - 通过逻辑索引向量对列表进行子集化

Question

我有一个 复杂列表并且需要根据 bool 元素的值从中选择一个子集(我需要 hidden 值等于 FALSE 的记录)。我已经基于索引向量尝试了以下代码，但它失败了(如该输出的末尾所示):

startups <- data$startups[data$startups$hidden == FALSE]

或者，或者:

startups <- data$startups[!as.logical(data$startups$hidden)]

交互式 R session 证明数据在那里:

Browse[1]> str(data$startups, list.len=3)
List of 50
 $ :List of 23
  ..$ id               : num 357496
  ..$ hidden           : logi FALSE
  ..$ community_profile: logi FALSE
  .. [list output truncated]
 $ :List of 2
  ..$ id    : num 352159
  ..$ hidden: logi TRUE
 $ :List of 2
  ..$ id    : num 352157
  ..$ hidden: logi TRUE
  [list output truncated]

Browse[1]> data$startups[data$startups$hidden == FALSE]
list()

Browse[1]> data$startups[!as.logical(data$startups$hidden)]
list()

我的代码有什么问题？

更新(希望包括可重现的示例，对复杂的结构感到抱歉)
aa <- dput(head(data$startups, n=3))
产生以下输出:

list(structure(list(id = 386938, hidden = FALSE, community_profile = FALSE, 
    name = "Pritunl", angellist_url = "https://angel.co/pritunl", 
    logo_url = "https://s3.amazonaws.com/photos.angel.co/startups/i/386938-fac0b8cba76c7e9252eee6646ec5b681-medium_jpg.jpg?buster=1398401450", 
    thumb_url = "https://s3.amazonaws.com/photos.angel.co/startups/i/386938-fac0b8cba76c7e9252eee6646ec5b681-thumb_jpg.jpg?buster=1398401450", 
    quality = 0, product_desc = "Enterprise VPN/cloud networking server", 
    high_concept = "Enterprise cloud networking", follower_count = 1, 
    company_url = "http://pritunl.com", created_at = "2014-04-25T04:50:57Z", 
    updated_at = "2014-04-25T06:02:05Z", crunchbase_url = NULL, 
    twitter_url = "http://twitter.com/pritunl", blog_url = "", 
    video_url = "", markets = list(structure(list(id = 12, tag_type = "MarketTag", 
        name = "enterprise software", display_name = "Enterprise Software", 
        angellist_url = "https://angel.co/enterprise-software"), .Names = c("id", 
    "tag_type", "name", "display_name", "angellist_url")), structure(list(
        id = 59, tag_type = "MarketTag", name = "open source", 
        display_name = "Open Source", angellist_url = "https://angel.co/open-source"), .Names = c("id", 
    "tag_type", "name", "display_name", "angellist_url")), structure(list(
        id = 123, tag_type = "MarketTag", name = "internet infrastructure", 
        display_name = "Internet Infrastructure", angellist_url = "https://angel.co/internet-infrastructure"), .Names = c("id", 
    "tag_type", "name", "display_name", "angellist_url")), structure(list(
        id = 306, tag_type = "MarketTag", name = "cloud management", 
        display_name = "Cloud Management", angellist_url = "https://angel.co/cloud-management"), .Names = c("id", 
    "tag_type", "name", "display_name", "angellist_url"))), locations = list(
        structure(list(id = 2071, tag_type = "LocationTag", name = "new york", 
            display_name = "New York", angellist_url = "https://angel.co/new-york"), .Names = c("id", 
        "tag_type", "name", "display_name", "angellist_url"))), 
    company_size = "1-10", company_type = list(structure(list(
        id = 94212, tag_type = "CompanyTypeTag", name = "startup", 
        display_name = "Startup", angellist_url = "https://angel.co/startup"), .Names = c("id", 
    "tag_type", "name", "display_name", "angellist_url"))), status = NULL, 
    screenshots = list(structure(list(thumb = "https://s3.amazonaws.com/screenshots.angel.co/ae/386938/5f7410543201d583eaba1975b931f3fd-thumb_jpg.jpg", 
        original = "https://s3.amazonaws.com/screenshots.angel.co/ae/386938/5f7410543201d583eaba1975b931f3fd-original.png"), .Names = c("thumb", 
    "original")), structure(list(thumb = "https://s3.amazonaws.com/screenshots.angel.co/ae/386938/006c4fb50d4b10df7caf7800ee482c6b-thumb_jpg.jpg", 
        original = "https://s3.amazonaws.com/screenshots.angel.co/ae/386938/006c4fb50d4b10df7caf7800ee482c6b-original.png"), .Names = c("thumb", 
    "original")), structure(list(thumb = "https://s3.amazonaws.com/screenshots.angel.co/ae/386938/741225c3de5021399c0cfc33cecb8830-thumb_jpg.jpg", 
        original = "https://s3.amazonaws.com/screenshots.angel.co/ae/386938/741225c3de5021399c0cfc33cecb8830-original.png"), .Names = c("thumb", 
    "original")), structure(list(thumb = "https://s3.amazonaws.com/screenshots.angel.co/ae/386938/969b60b6ccda577e77b7c9a5c169b2fd-thumb_jpg.jpg", 
        original = "https://s3.amazonaws.com/screenshots.angel.co/ae/386938/969b60b6ccda577e77b7c9a5c169b2fd-original.png"), .Names = c("thumb", 
    "original")), structure(list(thumb = "https://s3.amazonaws.com/screenshots.angel.co/ae/386938/2b2cc3a046c5a4d20b328045ca7f0254-thumb_jpg.jpg", 
        original = "https://s3.amazonaws.com/screenshots.angel.co/ae/386938/2b2cc3a046c5a4d20b328045ca7f0254-original.png"), .Names = c("thumb", 
    "original")), structure(list(thumb = "https://s3.amazonaws.com/screenshots.angel.co/ae/386938/053c3a1c74fc7f39de1117770f9debef-thumb_jpg.jpg", 
        original = "https://s3.amazonaws.com/screenshots.angel.co/ae/386938/053c3a1c74fc7f39de1117770f9debef-original.png"), .Names = c("thumb", 
    "original")), structure(list(thumb = "https://s3.amazonaws.com/screenshots.angel.co/ae/386938/8adcf2d6a6cafc9c6b810f8359a3fedf-thumb_jpg.jpg", 
        original = "https://s3.amazonaws.com/screenshots.angel.co/ae/386938/8adcf2d6a6cafc9c6b810f8359a3fedf-original.png"), .Names = c("thumb", 
    "original")))), .Names = c("id", "hidden", "community_profile", 
"name", "angellist_url", "logo_url", "thumb_url", "quality", 
"product_desc", "high_concept", "follower_count", "company_url", 
"created_at", "updated_at", "crunchbase_url", "twitter_url", 
"blog_url", "video_url", "markets", "locations", "company_size", 
"company_type", "status", "screenshots")), structure(list(id = 385596, 
    hidden = FALSE, community_profile = TRUE, name = "Lariat ", 
    angellist_url = "https://angel.co/lariat-1", logo_url = "https://s3.amazonaws.com/photos.angel.co/startups/i/385596-29de05d584176c3972da411aed5485f0-medium_jpg.jpg?buster=1398260121", 
    thumb_url = "https://s3.amazonaws.com/photos.angel.co/startups/i/385596-29de05d584176c3972da411aed5485f0-thumb_jpg.jpg?buster=1398260121", 
    quality = 0, product_desc = "Thus far, the internet has gone from discovery to search discovery, and then social discovery, but with little focus on recall. Remembering your digital footprint is difficult. We aim to solve that problem. Lariat is a cloud-based recall engine to securely recall information from any page in your search history instantly through intuitive keyword search, not just from page titles, but from the contents and context of the underlying pages.\r\n\r\nWrangle in the information you want, easier and faster.", 
    high_concept = "Recall your digital footprint on the web instantly", 
    follower_count = 1, company_url = "http://www.lariattech.com", 
    created_at = "2014-04-23T13:17:47Z", updated_at = "2014-04-23T13:48:38Z", 
    crunchbase_url = NULL, twitter_url = "", blog_url = "", video_url = NULL, 
    markets = list(structure(list(id = 4, tag_type = "MarketTag", 
        name = "digital media", display_name = "Digital Media", 
        angellist_url = "https://angel.co/digital-media"), .Names = c("id", 
    "tag_type", "name", "display_name", "angellist_url")), structure(list(
        id = 12, tag_type = "MarketTag", name = "enterprise software", 
        display_name = "Enterprise Software", angellist_url = "https://angel.co/enterprise-software"), .Names = c("id", 
    "tag_type", "name", "display_name", "angellist_url")), structure(list(
        id = 59, tag_type = "MarketTag", name = "open source", 
        display_name = "Open Source", angellist_url = "https://angel.co/open-source"), .Names = c("id", 
    "tag_type", "name", "display_name", "angellist_url")), structure(list(
        id = 282, tag_type = "MarketTag", name = "semantic search", 
        display_name = "Semantic Search", angellist_url = "https://angel.co/semantic-search"), .Names = c("id", 
    "tag_type", "name", "display_name", "angellist_url"))), locations = list(
        structure(list(id = 1620, tag_type = "LocationTag", name = "boston", 
            display_name = "Boston", angellist_url = "https://angel.co/boston"), .Names = c("id", 
        "tag_type", "name", "display_name", "angellist_url"))), 
    company_size = "1-10", company_type = structure(list(), class = "AsIs"), 
    status = NULL, screenshots = structure(list(), class = "AsIs")), .Names = c("id", 
"hidden", "community_profile", "name", "angellist_url", "logo_url", 
"thumb_url", "quality", "product_desc", "high_concept", "follower_count", 
"company_url", "created_at", "updated_at", "crunchbase_url", 
"twitter_url", "blog_url", "video_url", "markets", "locations", 
"company_size", "company_type", "status", "screenshots")), structure(list(
    id = 385595, hidden = TRUE), .Names = c("id", "hidden")))

以更易读的格式( aa )相同:

[[1]]
[[1]]$id
[1] 386938

[[1]]$hidden
[1] FALSE

[[1]]$community_profile
[1] FALSE

[[1]]$name
[1] "Pritunl"

[[1]]$angellist_url
[1] "https://angel.co/pritunl"

[[1]]$logo_url
[1] "https://s3.amazonaws.com/photos.angel.co/startups/i/386938-fac0b8cba76c7e9252eee6646ec5b681-medium_jpg.jpg?buster=1398401450"

[[1]]$thumb_url
[1] "https://s3.amazonaws.com/photos.angel.co/startups/i/386938-fac0b8cba76c7e9252eee6646ec5b681-thumb_jpg.jpg?buster=1398401450"

[[1]]$quality
[1] 0

[[1]]$product_desc
[1] "Enterprise VPN/cloud networking server"

[[1]]$high_concept
[1] "Enterprise cloud networking"

[[1]]$follower_count
[1] 1

[[1]]$company_url
[1] "http://pritunl.com"

[[1]]$created_at
[1] "2014-04-25T04:50:57Z"

[[1]]$updated_at
[1] "2014-04-25T06:02:05Z"

[[1]]$crunchbase_url
NULL

[[1]]$twitter_url
[1] "http://twitter.com/pritunl"

[[1]]$blog_url
[1] ""

[[1]]$video_url
[1] ""

[[1]]$markets
[[1]]$markets[[1]]
[[1]]$markets[[1]]$id
[1] 12

[[1]]$markets[[1]]$tag_type
[1] "MarketTag"

[[1]]$markets[[1]]$name
[1] "enterprise software"

[[1]]$markets[[1]]$display_name
[1] "Enterprise Software"

[[1]]$markets[[1]]$angellist_url
[1] "https://angel.co/enterprise-software"


[[1]]$markets[[2]]
[[1]]$markets[[2]]$id
[1] 59

[[1]]$markets[[2]]$tag_type
[1] "MarketTag"

[[1]]$markets[[2]]$name
[1] "open source"

[[1]]$markets[[2]]$display_name
[1] "Open Source"

[[1]]$markets[[2]]$angellist_url
[1] "https://angel.co/open-source"


[[1]]$markets[[3]]
[[1]]$markets[[3]]$id
[1] 123

[[1]]$markets[[3]]$tag_type
[1] "MarketTag"

[[1]]$markets[[3]]$name
[1] "internet infrastructure"

[[1]]$markets[[3]]$display_name
[1] "Internet Infrastructure"

[[1]]$markets[[3]]$angellist_url
[1] "https://angel.co/internet-infrastructure"


[[1]]$markets[[4]]
[[1]]$markets[[4]]$id
[1] 306

[[1]]$markets[[4]]$tag_type
[1] "MarketTag"

[[1]]$markets[[4]]$name
[1] "cloud management"

[[1]]$markets[[4]]$display_name
[1] "Cloud Management"

[[1]]$markets[[4]]$angellist_url
[1] "https://angel.co/cloud-management"



[[1]]$locations
[[1]]$locations[[1]]
[[1]]$locations[[1]]$id
[1] 2071

[[1]]$locations[[1]]$tag_type
[1] "LocationTag"

[[1]]$locations[[1]]$name
[1] "new york"

[[1]]$locations[[1]]$display_name
[1] "New York"

[[1]]$locations[[1]]$angellist_url
[1] "https://angel.co/new-york"



[[1]]$company_size
[1] "1-10"

[[1]]$company_type
[[1]]$company_type[[1]]
[[1]]$company_type[[1]]$id
[1] 94212

[[1]]$company_type[[1]]$tag_type
[1] "CompanyTypeTag"

[[1]]$company_type[[1]]$name
[1] "startup"

[[1]]$company_type[[1]]$display_name
[1] "Startup"

[[1]]$company_type[[1]]$angellist_url
[1] "https://angel.co/startup"



[[1]]$status
NULL

[[1]]$screenshots
[[1]]$screenshots[[1]]
[[1]]$screenshots[[1]]$thumb
[1] "https://s3.amazonaws.com/screenshots.angel.co/ae/386938/5f7410543201d583eaba1975b931f3fd-thumb_jpg.jpg"

[[1]]$screenshots[[1]]$original
[1] "https://s3.amazonaws.com/screenshots.angel.co/ae/386938/5f7410543201d583eaba1975b931f3fd-original.png"


[[1]]$screenshots[[2]]
[[1]]$screenshots[[2]]$thumb
[1] "https://s3.amazonaws.com/screenshots.angel.co/ae/386938/006c4fb50d4b10df7caf7800ee482c6b-thumb_jpg.jpg"

[[1]]$screenshots[[2]]$original
[1] "https://s3.amazonaws.com/screenshots.angel.co/ae/386938/006c4fb50d4b10df7caf7800ee482c6b-original.png"


[[1]]$screenshots[[3]]
[[1]]$screenshots[[3]]$thumb
[1] "https://s3.amazonaws.com/screenshots.angel.co/ae/386938/741225c3de5021399c0cfc33cecb8830-thumb_jpg.jpg"

[[1]]$screenshots[[3]]$original
[1] "https://s3.amazonaws.com/screenshots.angel.co/ae/386938/741225c3de5021399c0cfc33cecb8830-original.png"


[[1]]$screenshots[[4]]
[[1]]$screenshots[[4]]$thumb
[1] "https://s3.amazonaws.com/screenshots.angel.co/ae/386938/969b60b6ccda577e77b7c9a5c169b2fd-thumb_jpg.jpg"

[[1]]$screenshots[[4]]$original
[1] "https://s3.amazonaws.com/screenshots.angel.co/ae/386938/969b60b6ccda577e77b7c9a5c169b2fd-original.png"


[[1]]$screenshots[[5]]
[[1]]$screenshots[[5]]$thumb
[1] "https://s3.amazonaws.com/screenshots.angel.co/ae/386938/2b2cc3a046c5a4d20b328045ca7f0254-thumb_jpg.jpg"

[[1]]$screenshots[[5]]$original
[1] "https://s3.amazonaws.com/screenshots.angel.co/ae/386938/2b2cc3a046c5a4d20b328045ca7f0254-original.png"


[[1]]$screenshots[[6]]
[[1]]$screenshots[[6]]$thumb
[1] "https://s3.amazonaws.com/screenshots.angel.co/ae/386938/053c3a1c74fc7f39de1117770f9debef-thumb_jpg.jpg"

[[1]]$screenshots[[6]]$original
[1] "https://s3.amazonaws.com/screenshots.angel.co/ae/386938/053c3a1c74fc7f39de1117770f9debef-original.png"


[[1]]$screenshots[[7]]
[[1]]$screenshots[[7]]$thumb
[1] "https://s3.amazonaws.com/screenshots.angel.co/ae/386938/8adcf2d6a6cafc9c6b810f8359a3fedf-thumb_jpg.jpg"

[[1]]$screenshots[[7]]$original
[1] "https://s3.amazonaws.com/screenshots.angel.co/ae/386938/8adcf2d6a6cafc9c6b810f8359a3fedf-original.png"




[[2]]
[[2]]$id
[1] 385596

[[2]]$hidden
[1] FALSE

[[2]]$community_profile
[1] TRUE

[[2]]$name
[1] "Lariat "

[[2]]$angellist_url
[1] "https://angel.co/lariat-1"

[[2]]$logo_url
[1] "https://s3.amazonaws.com/photos.angel.co/startups/i/385596-29de05d584176c3972da411aed5485f0-medium_jpg.jpg?buster=1398260121"

[[2]]$thumb_url
[1] "https://s3.amazonaws.com/photos.angel.co/startups/i/385596-29de05d584176c3972da411aed5485f0-thumb_jpg.jpg?buster=1398260121"

[[2]]$quality
[1] 0

[[2]]$product_desc
[1] "Thus far, the internet has gone from discovery to search discovery, and then social discovery, but with little focus on recall. Remembering your digital footprint is difficult. We aim to solve that problem. Lariat is a cloud-based recall engine to securely recall information from any page in your search history instantly through intuitive keyword search, not just from page titles, but from the contents and context of the underlying pages.\r\n\r\nWrangle in the information you want, easier and faster."

[[2]]$high_concept
[1] "Recall your digital footprint on the web instantly"

[[2]]$follower_count
[1] 1

[[2]]$company_url
[1] "http://www.lariattech.com"

[[2]]$created_at
[1] "2014-04-23T13:17:47Z"

[[2]]$updated_at
[1] "2014-04-23T13:48:38Z"

[[2]]$crunchbase_url
NULL

[[2]]$twitter_url
[1] ""

[[2]]$blog_url
[1] ""

[[2]]$video_url
NULL

[[2]]$markets
[[2]]$markets[[1]]
[[2]]$markets[[1]]$id
[1] 4

[[2]]$markets[[1]]$tag_type
[1] "MarketTag"

[[2]]$markets[[1]]$name
[1] "digital media"

[[2]]$markets[[1]]$display_name
[1] "Digital Media"

[[2]]$markets[[1]]$angellist_url
[1] "https://angel.co/digital-media"


[[2]]$markets[[2]]
[[2]]$markets[[2]]$id
[1] 12

[[2]]$markets[[2]]$tag_type
[1] "MarketTag"

[[2]]$markets[[2]]$name
[1] "enterprise software"

[[2]]$markets[[2]]$display_name
[1] "Enterprise Software"

[[2]]$markets[[2]]$angellist_url
[1] "https://angel.co/enterprise-software"


[[2]]$markets[[3]]
[[2]]$markets[[3]]$id
[1] 59

[[2]]$markets[[3]]$tag_type
[1] "MarketTag"

[[2]]$markets[[3]]$name
[1] "open source"

[[2]]$markets[[3]]$display_name
[1] "Open Source"

[[2]]$markets[[3]]$angellist_url
[1] "https://angel.co/open-source"


[[2]]$markets[[4]]
[[2]]$markets[[4]]$id
[1] 282

[[2]]$markets[[4]]$tag_type
[1] "MarketTag"

[[2]]$markets[[4]]$name
[1] "semantic search"

[[2]]$markets[[4]]$display_name
[1] "Semantic Search"

[[2]]$markets[[4]]$angellist_url
[1] "https://angel.co/semantic-search"



[[2]]$locations
[[2]]$locations[[1]]
[[2]]$locations[[1]]$id
[1] 1620

[[2]]$locations[[1]]$tag_type
[1] "LocationTag"

[[2]]$locations[[1]]$name
[1] "boston"

[[2]]$locations[[1]]$display_name
[1] "Boston"

[[2]]$locations[[1]]$angellist_url
[1] "https://angel.co/boston"



[[2]]$company_size
[1] "1-10"

[[2]]$company_type
list()

[[2]]$status
NULL

[[2]]$screenshots
list()


[[3]]
[[3]]$id
[1] 385595

[[3]]$hidden
[1] TRUE

最后，通过逻辑索引向量应用子集操作:

aa[data$startups$hidden == FALSE]

结果是一个空列表(尽管 hidden = FALSE 用于第一个和第二个元素):

list()

再次对输出的大小感到抱歉，但我必须保留列表的结构。

注意事项:

根据 R 项目的“R 简介”( http://cran.r-project.org/doc/manuals/R-intro.html#Index-vectors)，

"Subsets of the elements of a vector may be selected by appending to the name of the vector an index vector in square brackets. More generally any expression that evaluates to a vector may have subsets of its elements similarly selected by appending an index vector in square brackets immediately after the expression".

同时，根据 Hadley Wickham 的“高级 R” ( http://adv-r.had.co.nz/Subsetting.html)，

"subsetting a list works in exactly the same way as subsetting an atomic vector".

Answer 1

问题中的示例数据是一个长度为 3 的列表，我们将其称为 L .它的每个组件本身就是一个列表，每个子列表的一个组件是 hidden .我们可以提取hidden将子列表的组件转换为名为 hidden 的逻辑向量.使用该逻辑向量，我们可以对原始列表进行子集 L给出一个新列表，只包含那些带有 hidden 的子列表TRUE 的组件.

hidden <- sapply(L, "[[", "hidden") # create logical vector hidden
L[hidden]

对于提供的数据，我们得到一个包含一个组件的列表:

> length(L[hidden])
[1] 1

如果我们知道只有一个组件，那么 L[hidden][[1]]或 L[[which(hidden)]]会给那个单一的组件。