Question

我有大量数据如下

    structure(list(chr = structure(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, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("1", 
"10", "11", "12", "13", "14", "15", "16", "17", "18", "19", "2", 
"20", "21", "22", "3", "4", "5", "6", "7", "8", "9", "X", "Y"
), class = "factor"), leftPos = c(1L, 15001L, 30001L, 45001L, 
60001L, 75001L, 90001L, 105001L, 120001L, 135001L, 150001L, 165001L, 
180001L, 195001L, 210001L, 225001L, 240001L, 255001L, 270001L, 
285001L, 300001L, 315001L, 330001L, 345001L, 360001L, 375001L, 
390001L, 405001L, 420001L, 435001L, 450001L, 465001L, 480001L, 
495001L, 510001L, 525001L, 540001L, 555001L, 570001L, 585001L, 
600001L, 615001L, 630001L, 645001L, 660001L, 675001L, 690001L, 
705001L, 720001L, 735001L, 750001L, 765001L, 780001L, 795001L, 
810001L, 825001L, 840001L, 855001L, 870001L, 885001L, 900001L, 
915001L, 930001L, 945001L, 960001L, 975001L, 990001L, 1005001L, 
1020001L, 1035001L), Means = c(NA, NA, NA, NA, NA, NA, NA, NA, 
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 
0.057, 0.162, -0.088, -0.271, 0.038, 0.089, -0.091, -0.223, 0.091, 
-0.023, -0.008, NA, -0.152, -0.228)), .Names = c("chr", "leftPos", 
"Means"), row.names = c(NA, 70L), class = "data.frame")

我想对数据进行分组，以便获得名为Means的列的平均值，以便将leftPos分组为1000000。

所以我使用了这段代码：

NadSWGSv <- NadSWGSv %>%
  group_by(chr, binnum = (leftPos) %/% 1500000) %>%
  summarise(Means = mean(Means)) %>%
  mutate(leftPos = (binnum+1) * 120000) %>%
  select(leftPos, Means)

但它给了我许多我期待的手段。我不知道为什么。

structure(list(chr = structure(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, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("1", 
"10", "11", "12", "13", "14", "15", "16", "17", "18", "19", "2", 
"20", "21", "22", "3", "4", "5", "6", "7", "8", "9", "X", "Y"
), class = "factor"), leftPos = c(120000, 240000, 360000, 480000, 
6e+05, 720000, 840000, 960000, 1080000, 1200000, 1320000, 1440000, 
1560000, 1680000, 1800000, 1920000, 2040000, 2160000, 2280000, 
2400000, 2520000, 2640000, 2760000, 2880000, 3e+06, 3120000, 
3240000, 3360000, 3480000, 3600000, 3720000, 3840000, 3960000, 
4080000, 4200000, 4320000, 4440000, 4560000, 4680000, 4800000, 
4920000, 5040000, 5160000, 5280000, 5400000, 5520000, 5640000, 
5760000, 5880000, 6e+06, 6120000, 6240000, 6360000, 6480000, 
6600000, 6720000, 6840000, 6960000, 7080000, 7200000, 7320000, 
7440000, 7560000, 7680000, 7800000, 7920000, 8040000, 8160000, 
8280000, 8400000), Means = c(NA, NA, NA, NA, NA, NA, -0.07272, 
NA, NA, NA, NA, NA, -0.000940000000000001, NA, NA, NA, NA, NA, 
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 
0.00673, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 
NA, -0.11982, NA, NA, -0.10338, -0.17146, NA, NA, NA, NA, NA, 
NA, NA, NA, NA, NA, NA, -0.09175, NA, NA, NA, NA)), .Names = c("chr", 
"leftPos", "Means"), class = c("grouped_df", "tbl_df", "tbl", 
"data.frame"), row.names = c(NA, -70L), vars = list(chr), drop = TRUE, indices = list(
    0:69), group_sizes = 70L, biggest_group_size = 70L, labels = structure(list(
    chr = structure(1L, .Label = c("1", "10", "11", "12", "13", 
    "14", "15", "16", "17", "18", "19", "2", "20", "21", "22", 
    "3", "4", "5", "6", "7", "8", "9", "X", "Y"), class = "factor")), class = "data.frame", row.names = c(NA, 
-1L), .Names = "chr", vars = list(chr)))

Answer 1

您需要在Means = mean(Means, na.rm = TRUE)来电中使用summarise。

具有NA的任何向量的平均值默认为NA。我们可以通过将参数na.rm = TRUE传递给平均值来取非NA的平均值：

mean(c(1, 2, NA))
[1] NA
mean(c(1, 2, NA), na.rm = TRUE)
[1] 1.5

在您的情况下，列Means具有NA，因此您的NA。

dplyr没有按照预期在R中分组

1 个答案: