R 配置数据 Data.Table
R Configure Data With Data.Table
data=data.frame("Student"=c(1,1,1,2,2,2,3,3,3,4,4,4,5,5,5),
"Grade"=c(5,6,7,3,4,5,4,5,6,8,9,10,2,3,4),
"Pass"=c(NA,0,1,0,1,1,0,1,0,0,NA,NA,0,0,0),
"NEWPass"=c(0,0,1,0,1,1,0,1,1,0,0,0,0,0,0),
"GradeNEWPass"=c(7,7,7,4,4,4,5,5,5,10,10,10,4,4,4),
"GradeBeforeNEWPass"=c(6,6,6,3,3,3,4,4,4,10,10,10,4,4,4))
我有一个data.frame叫数据。它有列名 Student、Grade 和 Pass。我想这样做:
NEWPass:通过并为每个学生填写 NA 值和以前的值。如果第一个值是 'NA' 则输入零。那么这应该是 运行 最大值。
GradeNEWPass:取学生在 NEWPass 中获得的最低等级值。如果一个学生没有在 NEWPass 中获得一个,这等于最高等级。
GradeBeforeNEWPass:在学生获得 NEWPass 之前获取 Grade 的值。如果一个学生没有在 NEWPass 中获得一个,这等于最高等级。
__
尝试次数:
setDT(data)[, NEWPassTry := cummax(Pass), by = Student]
data$GradeNEWPass = data$NEWPassTry * data$Grade
data[, GradeNEWPass := min(GradeNEWPass), by = Student]
诚然,这并不漂亮,但您的逻辑包含 "if any ... for a student" 之类的词,因此它是分组条件,而不是行条件。
library(magrittr) # just for %>% for breakout, not required
mydata %>%
.[, NEWPass2 :=
cummax(fifelse(seq_len(.N) == 1 & is.na(Pass), 0,
zoo::na.locf(Pass, na.rm = FALSE))), by = .(Student) ] %>%
.[, GradeNEWPass2 :=
if (any(NEWPass2 > 0)) min(Grade[ NEWPass2 > 0 ]) else max(Grade),
by = .(Student) ] %>%
.[, GradeBeforeNEWPass2 :=
if (NEWPass2[1] == 0 && any(NEWPass2 > 0)) Grade[ which(NEWPass2 > 0)[1] - 1 ] else max(Grade),
by = .(Student) ]
# Student Grade Pass NEWPass GradeNEWPass GradeBeforeNEWPass NEWPass2 GradeNEWPass2 GradeBeforeNEWPass2
# 1: 1 5 NA 0 7 6 0 7 6
# 2: 1 6 0 0 7 6 0 7 6
# 3: 1 7 1 1 7 6 1 7 6
# 4: 2 3 0 0 4 3 0 4 3
# 5: 2 4 1 1 4 3 1 4 3
# 6: 2 5 1 1 4 3 1 4 3
# 7: 3 4 0 0 5 4 0 5 4
# 8: 3 5 1 1 5 4 1 5 4
# 9: 3 6 0 1 5 4 1 5 4
# 10: 4 8 0 0 10 10 0 10 10
# 11: 4 9 NA 0 10 10 0 10 10
# 12: 4 10 NA 0 10 10 0 10 10
# 13: 5 2 0 0 4 4 0 4 4
# 14: 5 3 0 0 4 4 0 4 4
# 15: 5 4 0 0 4 4 0 4 4
我使用 magrittr::%>%
只是为了将其分解为多个计算阶段,这不是必需的。
我们可以使用data.table
方法。按 'Student' 分组,创建索引 ('i1'),其中 'Pass' 为 1 而不是 NA,然后使用 which
和 [=13= 获取 1 的第一个位置] ('i2'),同时计算'Grade' ('mx')的max
,然后根据索引创建三列('v1' - 得到累计二进制的最大值,'v2' - if
有 any
1,然后用索引 'i2' 或 else
[=33] 对 'Grade' 进行子集化=] 'mx',同理'v3'-索引减1得到'Grade'值
library(data.table)
setDT(data)[, c('NEWPass1', 'GradeNEWPass1', 'GradeBeforeNEWPass1') :={
i1 <- Pass == 1 & !is.na(Pass)
i2 <- head(which(i1), 1)
mx <- max(Grade, na.rm = TRUE)
v1 <- cummax(+(i1))
v2 <- if(any(i1)) Grade[i2] else mx
v3 <- if(any(i1)) Grade[max(1, i2-1)] else mx
.(v1, v2, v3)}, Student]
data
# Student Grade Pass NEWPass GradeNEWPass GradeBeforeNEWPass NEWPass1 GradeNEWPass1 GradeBeforeNEWPass1
# 1: 1 5 NA 0 7 6 0 7 6
# 2: 1 6 0 0 7 6 0 7 6
# 3: 1 7 1 1 7 6 1 7 6
# 4: 2 3 0 0 4 3 0 4 3
# 5: 2 4 1 1 4 3 1 4 3
# 6: 2 5 1 1 4 3 1 4 3
# 7: 3 4 0 0 5 4 0 5 4
# 8: 3 5 1 1 5 4 1 5 4
# 9: 3 6 0 1 5 4 1 5 4
#10: 4 8 0 0 10 10 0 10 10
#11: 4 9 NA 0 10 10 0 10 10
#12: 4 10 NA 0 10 10 0 10 10
#13: 5 2 0 0 4 4 0 4 4
#14: 5 3 0 0 4 4 0 4 4
#15: 5 4 0 0 4 4 0 4 4
data=data.frame("Student"=c(1,1,1,2,2,2,3,3,3,4,4,4,5,5,5),
"Grade"=c(5,6,7,3,4,5,4,5,6,8,9,10,2,3,4),
"Pass"=c(NA,0,1,0,1,1,0,1,0,0,NA,NA,0,0,0),
"NEWPass"=c(0,0,1,0,1,1,0,1,1,0,0,0,0,0,0),
"GradeNEWPass"=c(7,7,7,4,4,4,5,5,5,10,10,10,4,4,4),
"GradeBeforeNEWPass"=c(6,6,6,3,3,3,4,4,4,10,10,10,4,4,4))
我有一个data.frame叫数据。它有列名 Student、Grade 和 Pass。我想这样做:
NEWPass:通过并为每个学生填写 NA 值和以前的值。如果第一个值是 'NA' 则输入零。那么这应该是 运行 最大值。
GradeNEWPass:取学生在 NEWPass 中获得的最低等级值。如果一个学生没有在 NEWPass 中获得一个,这等于最高等级。
GradeBeforeNEWPass:在学生获得 NEWPass 之前获取 Grade 的值。如果一个学生没有在 NEWPass 中获得一个,这等于最高等级。
__ 尝试次数:
setDT(data)[, NEWPassTry := cummax(Pass), by = Student]
data$GradeNEWPass = data$NEWPassTry * data$Grade
data[, GradeNEWPass := min(GradeNEWPass), by = Student]
诚然,这并不漂亮,但您的逻辑包含 "if any ... for a student" 之类的词,因此它是分组条件,而不是行条件。
library(magrittr) # just for %>% for breakout, not required
mydata %>%
.[, NEWPass2 :=
cummax(fifelse(seq_len(.N) == 1 & is.na(Pass), 0,
zoo::na.locf(Pass, na.rm = FALSE))), by = .(Student) ] %>%
.[, GradeNEWPass2 :=
if (any(NEWPass2 > 0)) min(Grade[ NEWPass2 > 0 ]) else max(Grade),
by = .(Student) ] %>%
.[, GradeBeforeNEWPass2 :=
if (NEWPass2[1] == 0 && any(NEWPass2 > 0)) Grade[ which(NEWPass2 > 0)[1] - 1 ] else max(Grade),
by = .(Student) ]
# Student Grade Pass NEWPass GradeNEWPass GradeBeforeNEWPass NEWPass2 GradeNEWPass2 GradeBeforeNEWPass2
# 1: 1 5 NA 0 7 6 0 7 6
# 2: 1 6 0 0 7 6 0 7 6
# 3: 1 7 1 1 7 6 1 7 6
# 4: 2 3 0 0 4 3 0 4 3
# 5: 2 4 1 1 4 3 1 4 3
# 6: 2 5 1 1 4 3 1 4 3
# 7: 3 4 0 0 5 4 0 5 4
# 8: 3 5 1 1 5 4 1 5 4
# 9: 3 6 0 1 5 4 1 5 4
# 10: 4 8 0 0 10 10 0 10 10
# 11: 4 9 NA 0 10 10 0 10 10
# 12: 4 10 NA 0 10 10 0 10 10
# 13: 5 2 0 0 4 4 0 4 4
# 14: 5 3 0 0 4 4 0 4 4
# 15: 5 4 0 0 4 4 0 4 4
我使用 magrittr::%>%
只是为了将其分解为多个计算阶段,这不是必需的。
我们可以使用data.table
方法。按 'Student' 分组,创建索引 ('i1'),其中 'Pass' 为 1 而不是 NA,然后使用 which
和 [=13= 获取 1 的第一个位置] ('i2'),同时计算'Grade' ('mx')的max
,然后根据索引创建三列('v1' - 得到累计二进制的最大值,'v2' - if
有 any
1,然后用索引 'i2' 或 else
[=33] 对 'Grade' 进行子集化=] 'mx',同理'v3'-索引减1得到'Grade'值
library(data.table)
setDT(data)[, c('NEWPass1', 'GradeNEWPass1', 'GradeBeforeNEWPass1') :={
i1 <- Pass == 1 & !is.na(Pass)
i2 <- head(which(i1), 1)
mx <- max(Grade, na.rm = TRUE)
v1 <- cummax(+(i1))
v2 <- if(any(i1)) Grade[i2] else mx
v3 <- if(any(i1)) Grade[max(1, i2-1)] else mx
.(v1, v2, v3)}, Student]
data
# Student Grade Pass NEWPass GradeNEWPass GradeBeforeNEWPass NEWPass1 GradeNEWPass1 GradeBeforeNEWPass1
# 1: 1 5 NA 0 7 6 0 7 6
# 2: 1 6 0 0 7 6 0 7 6
# 3: 1 7 1 1 7 6 1 7 6
# 4: 2 3 0 0 4 3 0 4 3
# 5: 2 4 1 1 4 3 1 4 3
# 6: 2 5 1 1 4 3 1 4 3
# 7: 3 4 0 0 5 4 0 5 4
# 8: 3 5 1 1 5 4 1 5 4
# 9: 3 6 0 1 5 4 1 5 4
#10: 4 8 0 0 10 10 0 10 10
#11: 4 9 NA 0 10 10 0 10 10
#12: 4 10 NA 0 10 10 0 10 10
#13: 5 2 0 0 4 4 0 4 4
#14: 5 3 0 0 4 4 0 4 4
#15: 5 4 0 0 4 4 0 4 4