Question

我有一个包含多个列的数据

df<- structure(list(X1 = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), X2 = structure(c(1L, 2L, 3L, 
4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L, 
18L, 19L, 20L, 21L, 22L, 23L, 24L, 7L, 8L, 1L, 2L, 3L, 4L, 5L, 
6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L, 18L, 
19L, 20L, 21L, 22L, 23L, 24L), .Label = c("B02", "B03", "B04", 
"B05", "B06", "B07", "C02", "C03", "C04", "C05", "C06", "C07", 
"D02", "D03", "D04", "D05", "D06", "D07", "G02", "G03", "G04", 
"G05", "G06", "G07"), class = "factor"), X3 = c(0.005648642, 
0.005876389, 0.00592532, 0.006244456, 0.005987075, 0.006075874, 
0.006198667, 0.006003758, 0.006041885, 0.006186987, 0.006041323, 
0.006071594, 0.005902391, 0.005976096, 0.00593805, 0.005866524, 
0.0059831, 0.005902586, 0.005914309, 0.005887304, 0.006054509, 
0.005931266, 0.005936195, 0.005895191, 0.005840959, 0.005849247, 
0.005808851, 0.005833586, 0.005825153, 0.00584873, 0.005983976, 
0.00598669, 0.006011548, 0.005997747, 0.005851022, 0.005919044, 
0.005854566, 0.0058226, 0.00578052, 0.005784874, 0.005933198, 
0.005996407, 0.005898848, 0.00595775, 0.005918857, 0.005882898, 
0.005877808, 0.005803604, 0.006235161, 0.005808725), X4 = c(0.024054157, 
0.025850824, 0.023122678, 0.042337945, 0.030468744, 0.026481616, 
0.017430149, 0.024019931, 0.025572552, 0.024869532, 0.024148692, 
0.025228634, 0.030078166, 0.025860944, 0.023530696, 0.029244585, 
0.026599876, 0.023578245, 0.024014744, 0.023963795, 0.025466639, 
0.02969377, 0.02307532, 0.022739164, 0.02860112, 0.022800416, 
0.022287748, 0.022491258, 0.023340693, 0.024576665, 0.024378624, 
0.030037462, 0.024904579, 0.025901291, 0.02912765, 0.024926085, 
0.024044815, 0.023799791, 0.023147189, 0.021253484, 0.023979501, 
0.029659496, 0.029393487, 0.02470603, 0.024562731, 0.023819856, 
0.025065129, 0.023228642, 0.023919905, 0.024781896), X5 = c(0.00535592, 
0.00555428, 0.00555428, 0.00572213, 0.00573739, 0.00575265, 0.00576791, 
0.00572213, 0.00573739, 0.00572213, 0.00575265, 0.00576791, 0.0056611, 
0.0056611, 0.00567636, 0.00563058, 0.0056611, 0.00564584, 0.00563058, 
0.00561532, 0.00575265, 0.00569162, 0.00567636, 0.00564584, 0.00561532, 
0.00560006, 0.00556954, 0.0055848, 0.00555428, 0.00556954, 0.00569162, 
0.00573739, 0.00572213, 0.00567636, 0.00561532, 0.00561532, 0.0055848, 
0.00553903, 0.00552377, 0.00549325, 0.0056611, 0.00572213, 0.0056611, 
0.0056611, 0.00563058, 0.00561532, 0.0055848, 0.00553903, 0.00553903, 
0.00550851)), .Names = c("X1", "X2", "X3", "X4", "X5"), class = "data.frame", row.names = c(NA, 
-50L))

基本上，我试图根据几个值的平均值来修正每个值

我想取G02，G03，G04和G05的平均值，然后如果X1为1或2或其他数字

，则从该列的每个值中减去它例如，让我们看看X3

取平均值

0.005914309
0.005887304
0.006054509
0.005931266

平均值为0.005946847。然后我将X1从第一个值中减去，将X1作为1.它变为0.005648642 -0.005946847 = -0.000298205

然后从该列中X1为1的每个值中减去

当X1为2时，取G02，G03，G04，G05的平均值，当X1为2等时，从该列的每个值中减去

Answer 1

以下是使用data.table加入

的选项

library(data.table)
nm1 <- paste0("X", 3:5)
nm2 <- paste0("G0", 2:5)
dfN <- copy(df)
setDT(dfN)[dfN[X2 %in% nm2, lapply(.SD, function(x) mean(x)), 
         by = .(X1), .SDcols = X3:X5], (nm1) := Map(`-`, mget(nm1), mget(paste0("i.", nm1))),
                  on = .(X1)] 

head(dfN, 10)
#    X1  X2           X3           X4            X5
# 1:  1 B02 -0.000298205 -0.001730580 -0.0003166225
# 2:  1 B03 -0.000070458  0.000066087 -0.0001182625
# 3:  1 B04 -0.000021527 -0.002662059 -0.0001182625
# 4:  1 B05  0.000297609  0.016553208  0.0000495875
# 5:  1 B06  0.000040228  0.004684007  0.0000648475
# 6:  1 B07  0.000129027  0.000696879  0.0000801075
# 7:  1 C02  0.000251820 -0.008354588  0.0000953675
# 8:  1 C03  0.000056911 -0.001764806  0.0000495875
# 9:  1 C04  0.000095038 -0.000212185  0.0000648475
#10:  1 C05  0.000240140 -0.000915205  0.0000495875

Answer 2

使用dplyr的解决方案。 df2是从G02到G05的平均值。 df3是最终输出。

library(dplyr)

df2 <- df %>%
  filter(X2 %in% paste0("G0", 2:5)) %>%
  group_by(X1) %>%
  summarise_at(vars(-X2), funs(mean(.))) %>%
  gather(Col, Value, -X1)

df3 <- df %>%
  group_by(X1) %>%
  mutate(ID = 1:n()) %>%
  gather(Col, Value, -ID, -X1, -X2) %>%
  left_join(df2, by = c("X1", "Col")) %>%
  mutate(Value = Value.x - Value.y) %>%
  select(ID, X1, X2, Col, Value) %>%
  spread(Col, Value) %>%
  arrange(X1, ID) %>%
  select(-ID) %>%
  ungroup()
df3
# A tibble: 50 x 5
      X1     X2           X3           X4            X5
   <int> <fctr>        <dbl>        <dbl>         <dbl>
 1     1    B02 -0.000298205 -0.001730580 -0.0003166225
 2     1    B03 -0.000070458  0.000066087 -0.0001182625
 3     1    B04 -0.000021527 -0.002662059 -0.0001182625
 4     1    B05  0.000297609  0.016553208  0.0000495875
 5     1    B06  0.000040228  0.004684007  0.0000648475
 6     1    B07  0.000129027  0.000696879  0.0000801075
 7     1    C02  0.000251820 -0.008354588  0.0000953675
 8     1    C03  0.000056911 -0.001764806  0.0000495875
 9     1    C04  0.000095038 -0.000212185  0.0000648475
10     1    C05  0.000240140 -0.000915205  0.0000495875
# ... with 40 more rows

如何从每个块中减去特定区域

2 个答案: