Table1:
ST crp pln 2000 2001 2002 2003 yr_count
AL 11 01 13.0 4.9 264 19 5
AL 11 90 NA NA 54 20 11
AL 11 21 NA NA NA NA 0
仅当yr_count> 0时,我才想按2000、2001、2002、2003列计算每一行的平均值和SD。
sel_cols <- c("2000","2001","2002","2003")
Table1[Prm_yr_count > 0,`:=`(Avg_LR = round(rowMeans(.SD, na.rm = TRUE),0L),
Std_LR = round(sd(.SD, na.rm = TRUE),0L)),
by=list(ST,crp,pln), .SDcols=sel_cols]
当我使用列名时,出现以下错误。
Error in `[.data.table`(Avg_CAT_CRP_PLN, Prm_yr_count > 0, `:=`(Avg_LR = round(rowMeans(.SD, :
Some items of .SDcols are not column names (or are NA)
感谢您提供任何帮助以data.table方法解决此问题。
答案 0 :(得分:1)
我们可以使用rowMeans
(来自base R
)和rowSds
(来自matrixStats
)来完成此操作。可以将“ Std_LR”更改为
library(matrixStats)
library(data.table)
Table1[yr_count > 0, `:=`(Avg_LR = round(rowMeans(.SD, na.rm = TRUE),0L),
Std_LR = round(rowSds(as.matrix(.SD), na.rm = TRUE),0L)),
by=list(ST,crp,pln), .SDcols=sel_cols]
Table1
# ST crp pln 2000 2001 2002 2003 yr_count Avg_LR Std_LR
#1: AL 11 1 13 4.9 264 19 5 75 126
#2: AL 11 90 NA NA 54 20 11 37 24
#3: AL 11 21 NA NA NA NA 0 NA NA
注意:假设“表1”是data.table
注意2:“ Table1”具有Prm_yr_count
作为列之一,而不是yr_count
在“ Table2”上使用相同的命令
Table2[yr_count > 0, `:=`(Avg_LR = round(rowMeans(.SD, na.rm = TRUE),0L),
Std_LR = round(rowSds(as.matrix(.SD), na.rm = TRUE),0L)),
by=list(ST,crp,pln), .SDcols=sel_cols]
Table2
# ST crp pln 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2018 yr_count Avg_LR
#1: AL 11 01 NA NA NA NA NA NA NA NA NA NA NA 0.0 0.0 1.5 0 0 5 NaN
#2: AL 11 90 13 4.9 0 267.7 10.0 49.7 0.0 159.7 0 19.1 16.2 NA NA NA NA NA 11 71
#3: AL 15 01 NA NA NA NA NA NA NA NA NA NA NA NaN NaN NaN NaN NaN 0 NA
#4: AL 15 90 NA NA NA NA NA NA NA NA NA NaN NaN NA NA NA NA NA 0 NA
#5: AL 16 90 0 0.0 0 0.0 38.5 0.0 52.9 0.0 0 297.8 46.3 183.5 714.8 487.9 0 NaN 15 0
#6: AL 20 41 NA NA NA NA NA NA 20.0 11.2 0 49.0 117.2 0.0 0.0 39.7 0 NaN 9 NaN
# Std_LR
#1: NA
#2: 131
#3: NA
#4: NA
#5: 0
#6: NA
Table1 <- structure(list(ST = c("AL", "AL", "AL"), crp = c(11L, 11L, 11L
), pln = c(1L, 90L, 21L), `2000` = c(13, NA, NA), `2001` = c(4.9,
NA, NA), `2002` = c(264L, 54L, NA), `2003` = c(19L, 20L, NA),
yr_count = c(5L, 11L, 0L)), class = c("data.table", "data.frame"
), row.names = c(NA, -3L))
Table2 <- structure(list(ST = c("AL", "AL", "AL", "AL", "AL", "AL"
), crp = c(11, 11, 15, 15, 16, 20), pln = c("01", "90", "01",
"90", "90", "41"), `2000` = c(NA, 13, NA, NA, 0, NA), `2001` = c(NA,
4.9, NA, NA, 0, NA), `2002` = c(NA, 0, NA, NA, 0, NA), `2003` = c(NA,
267.7, NA, NA, 0, NA), `2004` = c(NA, 10, NA, NA, 38.5, NA),
`2005` = c(NA, 49.7, NA, NA, 0, NA), `2006` = c(NA, 0, NA,
NA, 52.9, 20), `2007` = c(NA, 159.7, NA, NA, 0, 11.2), `2008` = c(NA,
0, NA, NA, 0, 0), `2009` = c(NA, 19.1, NA, NaN, 297.8, 49
), `2010` = c(NA, 16.2, NA, NaN, 46.3, 117.2), `2011` = c(0,
NA, NaN, NA, 183.5, 0), `2012` = c(0, NA, NaN, NA, 714.8,
0), `2013` = c(1.5, NA, NaN, NA, 487.9, 39.7), `2014` = c(0,
NA, NaN, NA, 0, 0), `2018` = c(0, NA, NaN, NA, NaN, NaN),
yr_count = c(5, 11, 0, 0, 15, 9)), sorted = c("ST",
"crp", "pln"), class = c("data.table", "data.frame"), row.names = c(NA,
-6L))
答案 1 :(得分:1)
这是一种dplyr
方法。然后,您可以cbind
,join
回到旧数据框。该解决方案可能很慢:
library(dplyr)
df %>%
select(contains("X"),yr_count) %>%
mutate(Mean=ifelse(yr_count>0,
rowMeans(.[,-ncol(.)],na.rm=T),
"No"),sd=ifelse(yr_count>0,
apply(.[,-ncol(.)],1,function(x) sd(x,na.rm = T)),
"No"))
X2000 X2001 X2002 X2003 yr_count Mean sd
1 13 4.9 264 19 5 75.225 125.982548394609
2 NA NA 54 20 11 37 24.0416305603426
3 NA NA NA NA 0 No No
如@akrun所建议,我们可以通过使用apply
中的pmap_dbl
来避免purrr
:
df %>%
select(contains("X"),yr_count) %>%
mutate(Mean = rowMeans(.[,-ncol(.)], na.rm = TRUE),
sd = purrr::pmap_dbl(.[,-ncol(.)], ~ sd(c(...), na.rm = TRUE)))
数据:
df<-read.table(text="ST crp pln 2000 2001 2002 2003 yr_count
AL 11 01 13.0 4.9 264 19 5
AL 11 90 NA NA 54 20 11
AL 11 21 NA NA NA NA 0 ",header=T)