R在提迪尔传播与聚集
[英]R spread vs gather in tidyr
问题描述
I have a dataframe in the following form: 
我有以下形式的数据框：
person currentTest beforeValue afterValue
1 1 A 1.284297055 2.671763513
2 2 A -0.618359548 -2.354926905
3 3 A 0.039457430 -0.091709968
4 4 A -0.448608324 -0.362851832
5 5 A -0.961777124 -1.416284339
6 6 A 0.702471895 2.052181444
7 7 A -0.455222045 -2.125684279
8 8 A -1.231549132 -2.777425148
9 9 A -0.797234990 -0.558306183
10 10 A -0.709734963 -1.244159550
11 1 B -0.472799377 -0.869472343
12 2 B 0.059720737 1.444855389
13 3 B 0.924201532 2.731049485
14 4 B 0.658884183 1.017542475
15 5 B -1.989807256 -4.712671740
16 6 B 0.660241305 1.971232718
17 7 B 0.089636952 -0.564457911
18 8 B -0.828399941 0.507659171
19 9 B -0.838074237 -0.316996942
20 10 B -1.659197101 -3.317623686
...
What I'd like is to get a data frame of: 我想要的是获取以下数据框：
person A_Before A_After B_Before, B_After, ...
1 1.284297055 2.671763513 -0.472799377 -0.869472343
2 -0.618359548 -2.354926905 0.059720737 1.444855389
...
I've tried gather and spread but that's not quite what I need as there's the creation of new columns. 我已经尝试过收集和传播，但这并不是我所需要的，因为要创建新的列。 Any suggestions? 有什么建议么？
The dput version for easy access is below: 易于使用的dput版本如下：
resultsData <- dput(resultsData)
structure(list(person = c(1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L,
10L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 1L, 2L, 3L, 4L,
5L, 6L, 7L, 8L, 9L, 10L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L,
10L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 1L, 2L, 3L, 4L,
5L, 6L, 7L, 8L, 9L, 10L), currentTest = structure(c(1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L,
4L, 4L, 4L, 4L, 4L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 6L,
6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L), .Label = c("A", "B", "C",
"D", "E", "F"), class = "factor"), beforeValue = c(1.28429705541541,
-0.618359548370402, 0.039457429902531, -0.448608324038257, -0.961777123997687,
0.702471895259405, -0.455222044740939, -1.23154913153736, -0.797234989892673,
-0.709734963076803, -0.47279937661921, 0.0597207367403981, 0.924201531911827,
0.658884182599422, -1.98980725637449, 0.660241304554785, 0.0896369516528346,
-0.828399941497236, -0.838074236572976, -1.65919710134782, 0.577469369909437,
1.92748171699512, -0.245593641496638, 0.126104785456265, -0.559338325961641,
1.29802115505785, 0.719406692531958, 0.969414499181256, -0.814697072724845,
0.86465983690719, -0.709539159817187, 1.02775240926492, -0.50490096148732,
0.40769259465753, -0.868531009656408, 0.949518511358715, 2.32458579520932,
-0.257578702370506, -0.789761851618986, 0.0979274657020477, -0.00803566278013502,
1.42984177159549, 1.45485678109231, -0.956556613290905, 0.443323691839299,
-0.261951072972966, -1.30990441429799, 0.0921741874883992, -1.02612779569131,
0.81550719514697, -0.403037731404182, -0.384422139459082, 0.417074857491798,
-1.37128032791855, -0.0796160137501127, 1.35302483988882, -0.752751140138746,
0.812453275384099, -1.32443072805549, -1.66986584340583), afterValue = c(2.67176351335094,
-2.35492690509713, -0.0917099675669388, -0.362851831626841, -1.4162843393352,
2.05218144382074, -2.12568427901904, -2.77742514848958, -0.558306182843248,
-1.24415954975022, -0.869472343362331, 1.44485538931333, 2.73104948477609,
1.01754247530805, -4.71267174035743, 1.9712327179732, -0.564457911016569,
0.507659170771878, -0.31699694238194, -3.31762368638082, 1.09068172988414,
4.37537723545199, -0.116850493406969, 1.9533832597394, -1.69003563933244,
2.62250581307257, -0.00837379068728961, 1.84192937988371, -0.675899868505659,
2.08506660046288, -0.583526785879512, 0.699298693972492, -1.26172199141024,
1.23589313451783, -1.56008919968504, 0.436686458587792, 0.11699090169902,
-1.07206510594109, 1.21204947218164, -0.812406581646911, 0.50373332256566,
-0.084945367568491, -0.236015748624917, -0.479606239480476, -0.596799139055039,
-0.562575023441403, -0.339935276865152, -0.213813544612318, -0.265296303857373,
-1.12545083569158, 0.0105156062602101, 0.635695183644557, 0.767433440961415,
0.16648012185356, 0.544633089427927, -0.904001384160196, -0.429299134808951,
0.764224744168297, -0.166062348771635, -0.101892580202475)), class = c("tbl_df",
"tbl", "data.frame"), row.names = c(NA, -60L), .Names = c("person",
"currentTest", "beforeValue", "afterValue"))
3 个解决方案
解决方案1
2 2017-10-14 05:54:58
We can use dcast from reshape2 我们可以使用dcast从reshape2
library(reshape2)
meltdf <- melt(resultsData, id.vars=1:2)
dcast(meltdf, person ~ currentTest + variable)
> dcast(meltdf, person ~ currentTest + variable)
person A_beforeValue A_afterValue B_beforeValue B_afterValue C_beforeValue C_afterValue D_beforeValue D_afterValue E_beforeValue
1 1 1.28429706 2.67176351 -0.47279938 -0.8694723 0.5774694 1.090681730 -0.70953916 -0.5835268 -0.008035663
2 2 -0.61835955 -2.35492691 0.05972074 1.4448554 1.9274817 4.375377235 1.02775241 0.6992987 1.429841772
3 3 0.03945743 -0.09170997 0.92420153 2.7310495 -0.2455936 -0.116850493 -0.50490096 -1.2617220 1.454856781
4 4 -0.44860832 -0.36285183 0.65888418 1.0175425 0.1261048 1.953383260 0.40769259 1.2358931 -0.956556613
5 5 -0.96177712 -1.41628434 -1.98980726 -4.7126717 -0.5593383 -1.690035639 -0.86853101 -1.5600892 0.443323692
6 6 0.70247190 2.05218144 0.66024130 1.9712327 1.2980212 2.622505813 0.94951851 0.4366865 -0.261951073
7 7 -0.45522204 -2.12568428 0.08963695 -0.5644579 0.7194067 -0.008373791 2.32458580 0.1169909 -1.309904414
8 8 -1.23154913 -2.77742515 -0.82839994 0.5076592 0.9694145 1.841929380 -0.25757870 -1.0720651 0.092174187
9 9 -0.79723499 -0.55830618 -0.83807424 -0.3169969 -0.8146971 -0.675899869 -0.78976185 1.2120495 -1.026127796
10 10 -0.70973496 -1.24415955 -1.65919710 -3.3176237 0.8646598 2.085066600 0.09792747 -0.8124066 0.815507195
E_afterValue F_beforeValue F_afterValue
1 0.50373332 -0.40303773 0.01051561
2 -0.08494537 -0.38442214 0.63569518
3 -0.23601575 0.41707486 0.76743344
4 -0.47960624 -1.37128033 0.16648012
5 -0.59679914 -0.07961601 0.54463309
6 -0.56257502 1.35302484 -0.90400138
7 -0.33993528 -0.75275114 -0.42929913
8 -0.21381354 0.81245328 0.76422474
9 -0.26529630 -1.32443073 -0.16606235
10 -1.12545084 -1.66986584 -0.10189258
解决方案2
1 已采纳 2017-10-14 05:47:57
You can use a combined gather + spread approach; 您可以使用gather + spread相结合的方法； Gather the *Values columns and combine with currentTest to form the new header, then spread to wide format: 收集* Values列，并与currentTest组合以形成新的标头，然后扩展为宽格式：
resultsData %>%
gather(key, value, -person, -currentTest) %>%
unite(header, c('currentTest', 'key'), sep = "_") %>%
spread(header, value)
# A tibble: 10 x 13
# person A_afterValue A_beforeValue B_afterValue B_beforeValue C_afterValue C_beforeValue
# * <int> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
# 1 1 2.67176351 1.28429706 -0.8694723 -0.47279938 1.090681730 0.5774694
# 2 2 -2.35492691 -0.61835955 1.4448554 0.05972074 4.375377235 1.9274817
# 3 3 -0.09170997 0.03945743 2.7310495 0.92420153 -0.116850493 -0.2455936
# 4 4 -0.36285183 -0.44860832 1.0175425 0.65888418 1.953383260 0.1261048
# 5 5 -1.41628434 -0.96177712 -4.7126717 -1.98980726 -1.690035639 -0.5593383
# 6 6 2.05218144 0.70247190 1.9712327 0.66024130 2.622505813 1.2980212
# 7 7 -2.12568428 -0.45522204 -0.5644579 0.08963695 -0.008373791 0.7194067
# 8 8 -2.77742515 -1.23154913 0.5076592 -0.82839994 1.841929380 0.9694145
# 9 9 -0.55830618 -0.79723499 -0.3169969 -0.83807424 -0.675899869 -0.8146971
#10 10 -1.24415955 -0.70973496 -3.3176237 -1.65919710 2.085066600 0.8646598
# ... with 6 more variables: D_afterValue <dbl>, D_beforeValue <dbl>, E_afterValue <dbl>,
# E_beforeValue <dbl>, F_afterValue <dbl>, F_beforeValue <dbl>
If you need to rename the columns: 如果需要重命名列：
resultsData %>%
gather(key, value, -person, -currentTest) %>%
unite(header, c('currentTest', 'key'), sep = "_") %>%
spread(header, value) %>%
rename_at(vars(matches("Value$")), funs(gsub("Value$", "", .)))
解决方案3
1 2017-10-14 05:59:39
We could do this in a single line using recast 我们可以使用recast在一行中完成此操作
reshape2::recast(resultsData, person ~currentTest + variable, id.var = 1:2)
#person A_beforeValue A_afterValue B_beforeValue B_afterValue C_beforeValue C_afterValue D_beforeValue D_afterValue
#1 1 1.28429706 2.67176351 -0.47279938 -0.8694723 0.5774694 1.090681730 -0.70953916 -0.5835268
#2 2 -0.61835955 -2.35492691 0.05972074 1.4448554 1.9274817 4.375377235 1.02775241 0.6992987
#3 3 0.03945743 -0.09170997 0.92420153 2.7310495 -0.2455936 -0.116850493 -0.50490096 -1.2617220
#4 4 -0.44860832 -0.36285183 0.65888418 1.0175425 0.1261048 1.953383260 0.40769259 1.2358931
#5 5 -0.96177712 -1.41628434 -1.98980726 -4.7126717 -0.5593383 -1.690035639 -0.86853101 -1.5600892
#6 6 0.70247190 2.05218144 0.66024130 1.9712327 1.2980212 2.622505813 0.94951851 0.4366865
#7 7 -0.45522204 -2.12568428 0.08963695 -0.5644579 0.7194067 -0.008373791 2.32458580 0.1169909
#8 8 -1.23154913 -2.77742515 -0.82839994 0.5076592 0.9694145 1.841929380 -0.25757870 -1.0720651
#9 9 -0.79723499 -0.55830618 -0.83807424 -0.3169969 -0.8146971 -0.675899869 -0.78976185 1.2120495
#10 10 -0.70973496 -1.24415955 -1.65919710 -3.3176237 0.8646598 2.085066600 0.09792747 -0.8124066
# E_beforeValue E_afterValue F_beforeValue F_afterValue
#1 -0.008035663 0.50373332 -0.40303773 0.01051561
#2 1.429841772 -0.08494537 -0.38442214 0.63569518
#3 1.454856781 -0.23601575 0.41707486 0.76743344
#4 -0.956556613 -0.47960624 -1.37128033 0.16648012
#5 0.443323692 -0.59679914 -0.07961601 0.54463309
#6 -0.261951073 -0.56257502 1.35302484 -0.90400138
#7 -1.309904414 -0.33993528 -0.75275114 -0.42929913
#8 0.092174187 -0.21381354 0.81245328 0.76422474
#9 -1.026127796 -0.26529630 -1.32443073 -0.16606235
#10 0.815507195 -1.12545084 -1.66986584 -0.10189258
声明:本站的技术帖子网页，遵循CC BY-SA 4.0协议，如果您需要转载，请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.
相关问题
tidyr 在 shiny 中传播和聚集的问题 - Issue with tidyr spread and gather in shiny
如何使用聚集和传播来解决问题？ (提迪尔) - How to use gather and spread to solve problem? (Tidyr)
R：tidyr :: spread的程序化替代方案？ - R: programmatic alternative for tidyr::spread?
tidyr :: gather（）％>％mutate（）％>％spread（）意外返回NA - tidyr::gather() %>% mutate() %>% spread() returns NA's unexpectedly
评估对象内的聚集函数，tidy，R - evaluating objects inside gather function, tidyr, R
R-tidyr-spread（）-将NA作为列名处理 - R - tidyr - spread() - dealing with NA as column name
将列名传递给R tidyr spread - Passing a column name to R tidyr spread
R tidyr 传播不适用于数据框 - R tidyr spread does not work on a data frame
在R tidyr的spread_上使用NSE - using NSE on spread_ in R tidyr
R-tidyr-变异并分散多列 - R - tidyr - mutate and spread multiple columns
相关标签