如何创建具有不同行数的 RData data.frame
How to create data.frame with different number of rows RData
我有一个文件（格式为 RData）。https://stepik.org/media/attachments/course/724/all_data.Rdata 这个文件包含 7 个列表，其中包含患者的 ID 和体温。
我需要从这些列表中创建一个 data.frame，然后删除所有带有 NA
的行
id temp i.temp i.temp.1 i.temp.2 i.temp.3 i.temp.4 i.temp.5
1: 1 36.70378 36.73161 36.22944 36.05907 35.66014 37.32798 35.88121
2: 2 36.43545 35.96814 36.86782 37.20890 36.45172 36.82727 36.83450
3: 3 36.87599 36.38842 36.70508 37.44710 36.73362 37.09359 35.92993
4: 4 36.17120 35.95853 36.33405 36.45134 37.17186 36.87482 35.45489
5: 5 37.20341 37.04881 36.53252 36.22922 36.78106 36.89219 37.13207
6: 6 36.12201 36.53433 37.29784 35.96451 36.70838 36.58684 36.60122
7: 7 36.92314 36.16220 36.48154 37.05324 36.57829 36.24955 37.23835
8: 8 35.71390 37.26879 37.01673 36.65364 36.89143 36.46331 37.15398
9: 9 36.63558 37.03452 36.40129 37.53705 36.03568 36.78083 36.71873
10: 10 36.77329 36.07161 36.42992 36.20715 36.78880 36.79875 36.15004
11: 11 36.66199 36.74958 36.28661 36.72539 36.17700 37.47495 35.60980
12: 12 NA 36.97689 36.00473 36.64292 35.96789 36.73904 36.93957
13: 13 NA NA NA NA NA 36.63760 36.83916
14: 14 37.40307 35.89668 36.30619 36.64382 37.21882 35.87420 35.45550
15: 15 NA NA NA 37.03758 36.72512 36.45281 37.54388
16: 16 NA 36.44912 36.57126 36.20703 36.83076 36.48287 35.99391
17: 17 NA NA NA 36.39900 36.54043 36.75989 36.47079
18: 18 36.51696 37.09903 37.31166 36.51000 36.42414 36.87976 36.45736
19: 19 37.05117 37.42526 36.15820 36.11824 37.07024 36.60699 36.80168
20: 20 NA NA NA NA NA NA 36.74118
我写了：
load("https://stepik.org/media/attachments/course/724/all_data.Rdata")
library(data.table)
day1<-as.data.table(all_data[1])
day2<-as.data.table(all_data[2])
day3<-as.data.table(all_data[3])
day4<-as.data.table(all_data[4])
day5<-as.data.table(all_data[5])
day6<-as.data.table(all_data[6])
day7<-as.data.table(all_data[7])
setkey(day1, id)
setkey(day2, id)
setkey(day3, id)
setkey(day4, id)
setkey(day5, id)
setkey(day6, id)
setkey(day7, id)
all_day<-day1[day2,][day3, ][day4,][day5,][day6,][day7,]
all_day<-na.omit(all_day)
但是时间太长了。我怎样才能让它更快？
这里有一个data.table解决方案
library( data.table )
#set names for all_data
names( all_data ) <- paste0( "day", 1:length(all_data))
#bind lists to data.table
DT <- data.table::rbindlist( all_data, use.names = TRUE, fill = TRUE, idcol = "day" )
#cast to wide
ans <- dcast( DT, id ~ day, value.var = "temp" )
#only keep complete rows and present output (using [] at the end)
ans[ complete.cases( ans ), ][]
# id day1 day2 day3 day4 day5 day6 day7
# 1: 1 36.70378 36.73161 36.22944 36.05907 35.66014 37.32798 35.88121
# 2: 2 36.43545 35.96814 36.86782 37.20890 36.45172 36.82727 36.83450
# 3: 3 36.87599 36.38842 36.70508 37.44710 36.73362 37.09359 35.92993
# 4: 4 36.17120 35.95853 36.33405 36.45134 37.17186 36.87482 35.45489
# 5: 5 37.20341 37.04881 36.53252 36.22922 36.78106 36.89219 37.13207
# 6: 6 36.12201 36.53433 37.29784 35.96451 36.70838 36.58684 36.60122
# 7: 7 36.92314 36.16220 36.48154 37.05324 36.57829 36.24955 37.23835
# 8: 8 35.71390 37.26879 37.01673 36.65364 36.89143 36.46331 37.15398
# 9: 9 36.63558 37.03452 36.40129 37.53705 36.03568 36.78083 36.71873
# 10:10 36.77329 36.07161 36.42992 36.20715 36.78880 36.79875 36.15004
# 11:11 36.66199 36.74958 36.28661 36.72539 36.17700 37.47495 35.60980
# 12:14 37.40307 35.89668 36.30619 36.64382 37.21882 35.87420 35.45550
# 13:18 36.51696 37.09903 37.31166 36.51000 36.42414 36.87976 36.45736
# 14:19 37.05117 37.42526 36.15820 36.11824 37.07024 36.60699 36.80168
我有一个文件（格式为 RData）。https://stepik.org/media/attachments/course/724/all_data.Rdata 这个文件包含 7 个列表，其中包含患者的 ID 和体温。 我需要从这些列表中创建一个 data.frame，然后删除所有带有 NA
的行 id temp i.temp i.temp.1 i.temp.2 i.temp.3 i.temp.4 i.temp.5
1: 1 36.70378 36.73161 36.22944 36.05907 35.66014 37.32798 35.88121
2: 2 36.43545 35.96814 36.86782 37.20890 36.45172 36.82727 36.83450
3: 3 36.87599 36.38842 36.70508 37.44710 36.73362 37.09359 35.92993
4: 4 36.17120 35.95853 36.33405 36.45134 37.17186 36.87482 35.45489
5: 5 37.20341 37.04881 36.53252 36.22922 36.78106 36.89219 37.13207
6: 6 36.12201 36.53433 37.29784 35.96451 36.70838 36.58684 36.60122
7: 7 36.92314 36.16220 36.48154 37.05324 36.57829 36.24955 37.23835
8: 8 35.71390 37.26879 37.01673 36.65364 36.89143 36.46331 37.15398
9: 9 36.63558 37.03452 36.40129 37.53705 36.03568 36.78083 36.71873
10: 10 36.77329 36.07161 36.42992 36.20715 36.78880 36.79875 36.15004
11: 11 36.66199 36.74958 36.28661 36.72539 36.17700 37.47495 35.60980
12: 12 NA 36.97689 36.00473 36.64292 35.96789 36.73904 36.93957
13: 13 NA NA NA NA NA 36.63760 36.83916
14: 14 37.40307 35.89668 36.30619 36.64382 37.21882 35.87420 35.45550
15: 15 NA NA NA 37.03758 36.72512 36.45281 37.54388
16: 16 NA 36.44912 36.57126 36.20703 36.83076 36.48287 35.99391
17: 17 NA NA NA 36.39900 36.54043 36.75989 36.47079
18: 18 36.51696 37.09903 37.31166 36.51000 36.42414 36.87976 36.45736
19: 19 37.05117 37.42526 36.15820 36.11824 37.07024 36.60699 36.80168
20: 20 NA NA NA NA NA NA 36.74118
我写了：
load("https://stepik.org/media/attachments/course/724/all_data.Rdata")
library(data.table)
day1<-as.data.table(all_data[1])
day2<-as.data.table(all_data[2])
day3<-as.data.table(all_data[3])
day4<-as.data.table(all_data[4])
day5<-as.data.table(all_data[5])
day6<-as.data.table(all_data[6])
day7<-as.data.table(all_data[7])
setkey(day1, id)
setkey(day2, id)
setkey(day3, id)
setkey(day4, id)
setkey(day5, id)
setkey(day6, id)
setkey(day7, id)
all_day<-day1[day2,][day3, ][day4,][day5,][day6,][day7,]
all_day<-na.omit(all_day)
但是时间太长了。我怎样才能让它更快？
这里有一个data.table解决方案
library( data.table )
#set names for all_data
names( all_data ) <- paste0( "day", 1:length(all_data))
#bind lists to data.table
DT <- data.table::rbindlist( all_data, use.names = TRUE, fill = TRUE, idcol = "day" )
#cast to wide
ans <- dcast( DT, id ~ day, value.var = "temp" )
#only keep complete rows and present output (using [] at the end)
ans[ complete.cases( ans ), ][]
# id day1 day2 day3 day4 day5 day6 day7
# 1: 1 36.70378 36.73161 36.22944 36.05907 35.66014 37.32798 35.88121
# 2: 2 36.43545 35.96814 36.86782 37.20890 36.45172 36.82727 36.83450
# 3: 3 36.87599 36.38842 36.70508 37.44710 36.73362 37.09359 35.92993
# 4: 4 36.17120 35.95853 36.33405 36.45134 37.17186 36.87482 35.45489
# 5: 5 37.20341 37.04881 36.53252 36.22922 36.78106 36.89219 37.13207
# 6: 6 36.12201 36.53433 37.29784 35.96451 36.70838 36.58684 36.60122
# 7: 7 36.92314 36.16220 36.48154 37.05324 36.57829 36.24955 37.23835
# 8: 8 35.71390 37.26879 37.01673 36.65364 36.89143 36.46331 37.15398
# 9: 9 36.63558 37.03452 36.40129 37.53705 36.03568 36.78083 36.71873
# 10:10 36.77329 36.07161 36.42992 36.20715 36.78880 36.79875 36.15004
# 11:11 36.66199 36.74958 36.28661 36.72539 36.17700 37.47495 35.60980
# 12:14 37.40307 35.89668 36.30619 36.64382 37.21882 35.87420 35.45550
# 13:18 36.51696 37.09903 37.31166 36.51000 36.42414 36.87976 36.45736
# 14:19 37.05117 37.42526 36.15820 36.11824 37.07024 36.60699 36.80168