将一列数组转换为 R 中的单个值列 [英] Transforming a column of arrays to column of single values in R
问题描述
我有两列数组，我想将它们分配给各个单元格.例如，我的列目前看起来像这样:
I have two columns of arrays that I would like to give individuals cells to. For example, my columns currently look like this:
| NDVI | 日期 |
|---|---|
| [0.1,0.5,0.7] | [1.54E12, 1.54E12, 1.54E12] |
我如何才能将其重新格式化为:
How can I take this and reformat it to:
| NDVI | 日期 |
|---|---|
| 0.1 | 1.54E12 |
| 0.5 | 1.54E12 |
| 0.7 | 1.54E12 |
以下是一些示例数据:
<代码> DF< - 结构(列表(NDVIs = C(" [0.0048532285033119] QUOT;，" [0.031866426092985685，0.0346768172783618，0.05690584716758292，0.05963840093735323，0.049984507125651834，0.05225985971236913，0.05248901349444936，0.05518163825042716，-0.010183523082805207，-0.001665440442765531，0.03987908018516375，0.04187215406831169，0.08414429526637883，0.08715243094329189，-0.005957091678983289，-0.009527640910524507，0.010492166097587687，0.026020594673257052，0.002104522074938855，0.003507257657688491，0.06828452153139898，0.07606416388481754，0.06883156241096627，0.07718980197474816，0.06544808609317253，0.07474777221051583，0.10378917503028039，0.11123383912244203，0.05613527636023197，0.06331642130827059，0.06924611219668912，0.07666941206343858，0.06120038033501253，0.07040186289113536，0.0641993427579592，0.07613137403151546，0.02045492869437104，0.0331589149611709，0.07758880477807421，0.08753787069131283，0.07957631716729259，0.08952965234407557，0.0885082162194797，00.09848859431952328，-0.0020876210575472842，0.00246885618171861，0.10852078141016781，0.11765974025773，-0.026210051068679536，-0.017421882870782675，0.10807407562845053，0.11710267730586506，0.11281567251547685，0.12184561048692327，0.07186643839535878，0.07790008153091242，0.022632037271678205，0.0365365472967711] QUOT ;," [0.03529428376870003，0.009603157045076827，0.010105041611001576，0.022109721139215967，0.04320847194846547，0.06382705400539401，0.01733482969659961] QUOT ;," [0.05067307147600608，0.04650335539685854，0.04230580325409252，0.019941600277439516，0.03878433876933318，0.027594882066713636，0.032576179777168805，0.006187539680589851，0.0018615082099339225，0.042639901745788876，0.04555515255591705，0.05557934077121789，0.03141074118001885，-0.024594166196115066，0.06226281017212869，0.02775252318220509] QUOT ;," [0.22694578827413947，0.30629362044983743，0.26378399913683515，0.2582198975762179，0.25641849395215666，0.23752142045041516，0.23781654568851535，0.14139758147170572，0.2541489741719387，0.2419639056967162，0.2275033844898179，0.24470134691705184，0.22140420350534376，0.22465304694290103，0.21744809821978436，0.20724760985497206，0.19287780410696884] QUOT ;," [0.02437980239793386，0.046501630291612854，0.03515690678492754，0.03996495641681273，0.02565338402629212，0.02522057544087444，0.016355304453160305，0.010076012002045382，0.024906389352811975，0.040025952670788865，0.05043572220046672，0.0676703068532929，0.08040324690810197，0.011653761506917892，0.07901386245569544，0.14084622762340893，0.13315404483239526，0.14297013211925677] QUOT ;," [0.0696531704758789，0.06968717739514622，0.060495302532228894，0.060465281863641605，0.050631820224526766，0.05069794600355197，0.04996845148127263，0.050053255940312645，0.052401506092804355，0.0524735297646711，0.040763890820717345，0.04078582273414091，0.04106548840491197，0.04103821234740117，0.003195298620254946，-0.005673033858736476，-0.0018119432210428274，0.0015232350000433797，0.04386980266596469，0.044086120151773434，0.046401011127926925，0.04647825535002269，0.03833234785505313，0.03824161507110303，0.06037120877605433，0.06055975876554486，0.0592133770889435，0.05950182701095346，0.05530416996051339，0.05463335706292855，0.033097906541426636，0.02467463272473935，0.0580151510674638，0.05815851281926995，0.05560044632496825，0.05621848408403043] QUOT ;," [0.40218207770330455，0.3833707257903159，0.3498789365559936，0.3415851169240495，0.11857246658703605，0.09110434200774196，0.02929675584172094，0.13218157545304937，0.00568591277213531，0.2312335955409189，0.06118283356210741，0.23127376963601848，0.07698393284205111，0.05667080989824748，0.11169816100135183，0.018740255299188605，0.07543980191846927] QUOT ;," [0.04179551280868712，0.0383419807710962，0.0504998226331591，0.0011002529304645489，0.031002814569137，0.022506919207544558，0.03933692454785477，0.029375815795034198，0.04674437953418841，0.04864569790993668，0.036774224525189025，0.002999267453586999，0.03965538865956306，0.04553202255868567，0.012738284285019974，0.05355605970787331，0.03678091244450905] QUOT ;," [0.023817638054132135，0.02855430777145022，0.08243891605296151，0.014681590484211679，0.14321736621086276，0.07733703130141825，0.015297125457766068，0.10985901950753231，0.12587086535155378，0.13064566485984275，0.1297667968282656] QUOT;)，日期= C(" [1.527502095E12] QUOT;，" [1.544955875E12，1.544955875E12，1.545126378E12，1.545126378E12，1.545394367E12，1.545394367E12，1.545561339E12，1.545561339E12，1.545820928E12，1.545820928E12，1.545993046E12，1.545993046E12，1.546250253E12，1.546250253E12，1.546425701E12，1.546425701E12，1.546684843E12，1.546684843E12，1.546854495E12，1.546854495E12，1.547112218E12，1.547112218E12，1.547288454E12，1.547288454E12，1.547546364E12，1.547546364E12，1.547718166E12，1.547718166E12，1.547980939E12，1.547980939E12，1.548153141E12，1.548153141E12，1.548413046E12，1.548413046E12，1.548585114E12，1.548585114E12，1.548842378E12，1.548842378E12，1.549019277E12，1.549019277E12，1.549276707E12，1.549276707E12，1.549447219E12，1.549447219E12，1.549708493E12，1.549708493E12，1.549880513E12，1.549880513E12，1.550138768E12，1.550138768E12，1.550312936E12，1.550312936E12，1.55057479E12，1.55057479E12，1.550745218E12，1.550745218E12，1.551007067E12，1.551007067E12] QUOT ;,"[1.544868896E12, 1.545732881E12, 1.546164507E12, 1.546599228E12, 1.547030531E12, 1.547460976E12],8152E12" [1.562323826E12，1.562755476E12，1.563185103E12，1.563624031E12，1.56405523E12，1.564483439E12，1.564915837E12，1.565347309E12，1.565777661E12，1.566215882E12，1.566643642E12，1.567097272E12，1.567507638E12，1.568369457E12，1.56880789E12，1.569668195E12]"," [1.552392943E12，1.552819566E12，1.553251718E12，1.553682704E12，1.554112987E12，1.55454323E12，1.554975918E12，1.555408185E12，1.555841425E12，1.556271571E12，1.55670391E12，1.557135402E12，1.557568058E12，1.557998903E12，1.558863212E12，1.55929586E12, 1.559728791E12]"," [1.561454836E12，1.561888229E12，1.562320207E12，1.562751856E12，1.563181463E12，1.563618614E12，1.564046906E12，1.564480274E12，1.564912267E12，1.565343999E12，1.565773615E12，1.566210466E12，1.566639283E12，1.567072243E12，1.567504618E12，1.567936832E12, 1.568366042E12, 1.568802771E12]"," [1.561028124E12，1.561028124E12，1.561460566E12，1.561460566E12，1.561887116E12，1.561887116E12，1.562321887E12，1.562321887E12，1.562750997E12，1.562750997E12，1.563188512E12，1.563188512E12，1.563622208E12，1.563622208E12，1.564052361E12，1.564052361E12，1.564478817E12，1.564478817E12，1.564913968E12，1.564913968E12，1.565342227E12，1.565342227E12，1.565780829E12，1.565780829E12，1.566212692E12，1.566212692E12，1.566646344E12，1.566646344E12，1.567071334E12，1.567071334E12，1.567508507E12，1.567508507E12，1.567935649E12, 1.567935649E12, 1.568374212E12, 1.568374212E12]"," [1.558863212E12，1.55929586E12，1.559728791E12，1.5601599E12，1.560589582E12，1.561026607E12，1.561454836E12，1.561888229E12，1.562320207E12，1.562751856E12，1.563181463E12，1.563618614E12，1.564047988E12，1.564480274E12，1.564912267E12，1.565343999E12, 1.565773615E12]"," [1.568719125E12，1.569150328E12，1.569583549E12，1.570013418E12，1.570451296E12，1.570878011E12，1.571311086E12，1.571742422E12，1.572172948E12，1.572604827E12，1.573038304E12，1.573470317E12，1.573899161E12，1.574334225E12，1.575196752E12，1.57562775E12, 1.5760617E12]"," [1.545124633E12，1.545561224E12，1.545990899E12，1.546423114E12，1.546853425E12，1.547287051E12，1.547718865E12，1.548155787E12，1.548586075E12，1.549015326E12，1.549447719E12] QUOT;)), row.names = c(NA, -10L), class = "data.frame")
推荐答案
我们可以使用 str_extract_all 提取不是在 ，它返回一个 [ 之后的 ] 的字符list，然后 unnest 列，并在 , 后跟一个或多个空格处拆分列值(\\s+) 与 separate_rows
We could extract the characters that are not a ] that succeeds the [ with str_extract_all, which returns a list, then unnest the columns, and split the column values at the , followed by one or more spaces (\\s+) with separate_rows
library(dplyr)
library(stringr)
library(tidyr)
df %>%
mutate(across(everything(), str_extract_all, "(?<=\\[)[^]]+")) %>%
unnest(c(NDVIs, dates)) %>%
separate_rows(c(NDVIs, dates), sep=",\\s+", convert = TRUE)
-输出
# A tibble: 198 x 2
# NDVIs dates
# <dbl> <dbl>
# 1 0.00485 1527502095000
# 2 0.0319 1544955875000
# 3 0.0347 1544955875000
# 4 0.0569 1545126378000
# 5 0.0596 1545126378000
# 6 0.0500 1545394367000
# 7 0.0523 1545394367000
# 8 0.0525 1545561339000
# 9 0.0552 1545561339000
#10 -0.0102 1545820928000
# … with 188 more rows
或者使用 [] 不是在每个元素中，然后使用 str_remove_all 删除已经存在的元素并使用 separate_rows
Or with the [] is not in every element, then remove the already existing one with str_remove_all and use separate_rows
df %>%
mutate(across(everything(), str_remove_all, "\\[|\\]")) %>%
separate_rows(c(NDVIs, dates), sep=",\\s+", convert = TRUE)
# A tibble: 198 x 2
# NDVIs dates
# <dbl> <dbl>
# 1 0.00485 1527502095000
# 2 0.0319 1544955875000
# 3 0.0347 1544955875000
# 4 0.0569 1545126378000
# 5 0.0596 1545126378000
# 6 0.0500 1545394367000
# 7 0.0523 1545394367000
# 8 0.0525 1545561339000
# 9 0.0552 1545561339000
#10 -0.0102 1545820928000
# … with 188 more rows
这篇关于将一列数组转换为 R 中的单个值列的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
