时间戳

首页 > 解决方案 > dplyr 根据字符列汇总数字列

r - dplyr 根据字符列汇总数字列

问题描述

我有以下数据框。我想获得颜色和样本的每种组合的平均值。

mm <-
structure(list(color = structure(c(2L, 2L, 1L, 2L, 2L, 2L, 1L, 
2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 1L, 1L, 
1L, 2L, 2L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 
2L, 2L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 2L, 2L, 2L, 1L, 
2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 1L, 1L, 
1L, 2L, 2L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 
2L, 2L, 2L, 1L, 2L, 1L, 1L, 1L, 1L), .Label = c("red", "blue"
), class = "factor"), variable = structure(c(1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 5L, 5L, 5L, 5L, 
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 
6L, 6L, 6L, 6L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 
8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L), .Label = c("SAMPLE_8", 
"SAMPLE_1", "SAMPLE_2", "SAMPLE_3", "SAMPLE_4", "SAMPLE_5", "SAMPLE_6", 
"SAMPLE_7"), class = "factor"), value = c(5204975.22195835, 5921431.37016771, 
4483287.22007228, 9334512.14362206, 8290545.0546112, 5511308.78905786, 
4535669.79559233, 6084482.4859888, 4552670.23553827, 6617188.31470945, 
4465820.654524, 4671357.33199838, 311300.931942485, 302632.345972663, 
282997.351878223, 537463.470193835, 750993.852296993, 310145.485558992, 
318414.131512382, 302279.607384422, 326870.420217549, 337456.764928226, 
281702.352478868, 305075.341449454, 1142089.96619646, 1381523.19977651, 
1478102.43751732, 2313422.4839489, 1165360.86570532, 1371146.64341499, 
1168538.40843253, 1140498.10246773, 3846417.77575045, 3439179.29840624, 
5779121.02860911, 3948012.39935442, 5309451.60747925, 6042469.64246727, 
4502373.03854667, 9777607.60721765, 8373484.97756233, 5694750.45922109, 
4596450.3240182, 6267456.44789408, 4634116.88423172, 6896467.35967418, 
4517202.4683853, 4710615.3886163, 324516.034016253, 291133.601851379, 
547686.545230872, 343315.425877443, 301950.787630643, 407330.982240814, 
1622559.39237951, 293733.354868293, 3402268.54959027, 6405624.51540237, 
747380.853508684, 6291676.05179056, 4976273.57530081, 5788712.60586859, 
4356126.64775492, 9078023.65858526, 8172714.31466804, 5308793.61183594, 
4397207.70605689, 5858088.51971103, 4392449.83869719, 6299277.85075423, 
4344945.38910177, 4490871.86656671, 355542.3811289, 315932.775514382, 
458535.380638158, 365431.666781714, 357061.223400342, 445932.523728128, 
2061248.39168834, 306376.953744205, 3145802.11824005, 7766554.53327765, 
397953.420734522, 7536514.52523919, 5204975.22195835, 5921431.37016771, 
4483287.22007228, 9334512.14362206, 8290545.0546112, 5511308.78905786, 
4535669.79559233, 6084482.4859888, 4552670.23553827, 6617188.31470945, 
4465820.654524, 4671357.33199838)), class = "data.frame", row.names = c(NA, 
-96L))

看起来像这样（前几行）

   color variable     value
1   blue SAMPLE_8 5204975.2
2   blue SAMPLE_8 5921431.4
3    red SAMPLE_8 4483287.2
4   blue SAMPLE_8 9334512.1
5   blue SAMPLE_8 8290545.1
6   blue SAMPLE_8 5511308.8
7    red SAMPLE_8 4535669.8
8   blue SAMPLE_8 6084482.5
9    red SAMPLE_8 4552670.2
10   red SAMPLE_8 6617188.3
11   red SAMPLE_8 4465820.7
12   red SAMPLE_8 4671357.3
13  blue SAMPLE_1  311300.9
14  blue SAMPLE_1  302632.3
15   red SAMPLE_1  282997.4
16  blue SAMPLE_1  537463.5
17  blue SAMPLE_1  750993.9
18  blue SAMPLE_1  310145.5
19   red SAMPLE_1  318414.1
20  blue SAMPLE_1  302279.6
21   red SAMPLE_1  326870.4
22   red SAMPLE_1  337456.8
23   red SAMPLE_1  281702.4
24   red SAMPLE_1  305075.3

我想要这样的东西。

   color variable value
    red SAMPLE_8   xxxxxxx(x being the mean value for red SAMPLE_8( values)
    blue SAMPLE_8   xxxxxxx(x being the mean value for blue SAMPLE_8( values)
    red SAMPLE_1   xxxxxxx(x being the mean value for red SAMPLE_1( values)
    blue SAMPLE_1   xxxxxxx(x being the mean value for blue SAMPLE_1( values)
    ...

我认为 dplyr 可能有助于解决这个问题，但我希望得到您的建议。知道如何获得请求的输出。

标签： rdplyraggregate

解决方案

我找到了 dplyr 的解决方案。

columns <- c("color","variable")
mm %>% 
  #group_by(Odor,variable) %>% 
  group_by_at(vars(one_of(columns))) %>%
  summarise(mean = mean(value))

推荐阅读