R 如何基于多种条件将数据从一个数据帧复制到另一个数据帧
在我的R 如何基于多种条件将数据从一个数据帧复制到另一个数据帧,r,dataframe,datetime,R,Dataframe,Datetime,在我的df1（包括df1$id，df1$datetime\u interval，df1$datetime\u事件和df1$event）中，我想根据以下条件放置df2（包括df2$id，df2$datetime\u事件）中的数据： 如果df1$id和df2$id匹配 和如果df2$datetime\u事件在df1$datetime\u间隔内 比我想把df2$datetime_事件的数据复制到df1$datetime_事件的df1中相应行的df2$datetime_事件的列中，和df1$event中
df1df1$iddf1$datetime\u intervaldf1$datetime\u事件df1$eventdf2df2$iddf2$datetime\u事件df1$iddf2$iddf2$datetime\u事件df1$datetime\u间隔内df2$datetime_事件的数据df1$datetime_事件df1df2$datetime_事件的列中，和df1$event
中的字符串（例如“yes”）
如果不满足条件，我不希望有结果（NA）
因此：
我试过一些方法，但效果并不理想。我仍然错过了一些步骤，我不知道如何继续前进。这就是我到目前为止所做的：
for(i in seq_along(df1$id)){
for(j in seq_along(df2$id)){
ifelse(df2$id[j] == df1$id[i]) {
ifelse(df2$datetime_event[j] %within% df1$datetime_interval[i] == TRUE){
df1$datetime_event <- df2$datetime_ic_corr[j]
}
}
}
}
提前感谢您的所有新输入！因为我被卡住了
dput(df1)
structure(list(ID = c(1, 1, 2, 3, 3, 6), datetime_interval = c("2019-04-19 21:50:00 UTC--2019-04-20 21:31:00 UTC",
"2019-07-02 04:23:00 UTC--2019-07-02 08:51:00 UTC", "2019-07-04 19:45:00 UTC--2019-07-05 00:30:00 UTC",
"2019-06-07 08:55:00 UTC--2019-06-07 14:43:00 UTC", "2019-05-06 17:18:00 UTC--2019-05-06 23:18:00 UTC",
"2019-08-02 22:00:00 UTC--2019-08-04 03:10:00 UTC"), datetime_event = c("NA",
"NA", "NA", "NA", "NA", "NA"), event = c("NA", "NA", "NA", "NA",
"NA", "NA")), row.names = c(NA, -6L), class = c("tbl_df", "tbl",
"data.frame"))
dput(df2)
structure(list(ID = c(1, 3, 5, 6, 6), datetime_event = c("2019-04-19 21:55:00 UTC",
"2019-05-06 21:23:00 UTC", "2019-07-04 19:45:00 UTC", "2019-05-06 17:18:00 UTC",
"2019-08-03 10:10:00 UTC")), row.names = c(NA, -5L), class = c("tbl_df",
"tbl", "data.frame"))
棘手的问题。我认为这是可行的：
library(dplyr)
library(tidyr)
# convert datetime_interval to datetime class start and end columns
# and add row IDs
df1 = df1 %>%
separate(datetime_interval, into = c("start", "end"), sep = "--") %>%
mutate_at(vars(start, end), as.POSIXct) %>%
select(-datetime_event, -event) %>%
mutate(row_id = row_number())
# convert datetime event to datetime class
df2 = df2 %>%
mutate(datetime_event = as.POSIXct(datetime_event))
# join and filter
df1 %>% left_join(df2, by = "ID") %>%
mutate(
datetime_event = ifelse(datetime_event >= start & datetime_event <= end, datetime_event, NA),
event = ifelse(is.na(datetime_event), NA, "yes")
) %>%
arrange(row_id, datetime_event) %>%
group_by(row_id) %>%
slice(1)
# # A tibble: 6 x 6
# # Groups: row_id [6]
# ID start end row_id datetime_event event
# <dbl> <dttm> <dttm> <int> <dbl> <chr>
# 1 1 2019-04-19 21:50:00 2019-04-20 21:31:00 1 1555725300 yes
# 2 1 2019-07-02 04:23:00 2019-07-02 08:51:00 2 NA NA
# 3 2 2019-07-04 19:45:00 2019-07-05 00:30:00 3 NA NA
# 4 3 2019-06-07 08:55:00 2019-06-07 14:43:00 4 NA NA
# 5 3 2019-05-06 17:18:00 2019-05-06 23:18:00 5 1557192180 yes
# 6 6 2019-08-02 22:00:00 2019-08-04 03:10:00 6 1564841400 yes
库（dplyr）
图书馆（tidyr）
#将datetime\u interval转换为datetime类的开始列和结束列
#并添加行ID
df1=df1%>%
分开（日期时间间隔，分为=c（“开始”、“结束”）、sep=“-->%）
在（变量（开始，结束），如.POSIXct）%>%
选择（-datetime_event，-event）%>%
变异（行id=行编号（））
#将datetime事件转换为datetime类
df2=df2%>%
mutate（datetime_事件=as.POSIXct（datetime_事件））
#加入并筛选
df1%>%左联合（df2，by=“ID”）%>%
变异(
datetime\u event=ifelse（datetime\u event>=start&datetime\u event%
排列（行id，日期时间事件）%>%
分组依据（行id）%>%
切片（1）
##tibble:6 x 6
##组：行id[6]
#ID开始结束行\u ID日期时间\u事件
#
#1199-04-19 21:50:00 2019-04-20 21:31:00 1155725300是
#2019-07-02 04:23:00 2019-07-02 08:51:00 2不适用
#3 2 2019-07-04 19:45:00 2019-07-05 00:30:00 3北美
#2019-06-07 08:55:00 2019-06-07 14:43:00 4 NA
#5 3 2019-05-06 17:18:00 2019-05-06 23:18:00 5 1557192180是
#6 2019-08-02 22:00:00 2019-08-04 03:10:00 6 1564841400是
棘手的问题。我认为这是可行的：
library(dplyr)
library(tidyr)
# convert datetime_interval to datetime class start and end columns
# and add row IDs
df1 = df1 %>%
separate(datetime_interval, into = c("start", "end"), sep = "--") %>%
mutate_at(vars(start, end), as.POSIXct) %>%
select(-datetime_event, -event) %>%
mutate(row_id = row_number())
# convert datetime event to datetime class
df2 = df2 %>%
mutate(datetime_event = as.POSIXct(datetime_event))
# join and filter
df1 %>% left_join(df2, by = "ID") %>%
mutate(
datetime_event = ifelse(datetime_event >= start & datetime_event <= end, datetime_event, NA),
event = ifelse(is.na(datetime_event), NA, "yes")
) %>%
arrange(row_id, datetime_event) %>%
group_by(row_id) %>%
slice(1)
# # A tibble: 6 x 6
# # Groups: row_id [6]
# ID start end row_id datetime_event event
# <dbl> <dttm> <dttm> <int> <dbl> <chr>
# 1 1 2019-04-19 21:50:00 2019-04-20 21:31:00 1 1555725300 yes
# 2 1 2019-07-02 04:23:00 2019-07-02 08:51:00 2 NA NA
# 3 2 2019-07-04 19:45:00 2019-07-05 00:30:00 3 NA NA
# 4 3 2019-06-07 08:55:00 2019-06-07 14:43:00 4 NA NA
# 5 3 2019-05-06 17:18:00 2019-05-06 23:18:00 5 1557192180 yes
# 6 6 2019-08-02 22:00:00 2019-08-04 03:10:00 6 1564841400 yes
库（dplyr）
图书馆（tidyr）
#将datetime\u interval转换为datetime类的开始列和结束列
#并添加行ID
df1=df1%>%
分开（日期时间间隔，分为=c（“开始”、“结束”）、sep=“-->%）
在（变量（开始，结束），如.POSIXct）%>%
选择（-datetime_event，-event）%>%
变异（行id=行编号（））
#将datetime事件转换为datetime类
df2=df2%>%
mutate（datetime_事件=as.POSIXct（datetime_事件））
#加入并筛选
df1%>%左联合（df2，by=“ID”）%>%
变异(
datetime\u event=ifelse（datetime\u event>=start&datetime\u event%
排列（行id，日期时间事件）%>%
分组依据（行id）%>%
切片（1）
##tibble:6 x 6
##组：行id[6]
#ID开始结束行\u ID日期时间\u事件
#
#1199-04-19 21:50:00 2019-04-20 21:31:00 1155725300是
#2019-07-02 04:23:00 2019-07-02 08:51:00 2不适用
#3 2 2019-07-04 19:45:00 2019-07-05 00:30:00 3北美
#2019-06-07 08:55:00 2019-06-07 14:43:00 4 NA
#5 3 2019-05-06 17:18:00 2019-05-06 23:18:00 5 1557192180是
#6 2019-08-02 22:00:00 2019-08-04 03:10:00 6 1564841400是
您能否与dput
共享输入df1
和df2
？这将使它们可以复制/粘贴，并使人们更容易演示解决方案。如果您的实际数据大于您显示的数据，请将dput（df1）
的输出放入dput（head（df1））
进入你的问题。@GregorThomas谢谢！我已经把它们放入我的问题中了！你能将输入df1
和df2
与dput
共享吗？这将使它们可以复制/粘贴，并使人们更容易演示解决方案。将dput（df1）
的输出（或者dput（head（df1））
，如果您的实际数据比您显示的数据大），请输入您的问题。@GregorThomas谢谢！我已经将它们输入到我的问题中了！
dput(df1)
structure(list(ID = c(1, 1, 2, 3, 3, 6), datetime_interval = c("2019-04-19 21:50:00 UTC--2019-04-20 21:31:00 UTC",
"2019-07-02 04:23:00 UTC--2019-07-02 08:51:00 UTC", "2019-07-04 19:45:00 UTC--2019-07-05 00:30:00 UTC",
"2019-06-07 08:55:00 UTC--2019-06-07 14:43:00 UTC", "2019-05-06 17:18:00 UTC--2019-05-06 23:18:00 UTC",
"2019-08-02 22:00:00 UTC--2019-08-04 03:10:00 UTC"), datetime_event = c("NA",
"NA", "NA", "NA", "NA", "NA"), event = c("NA", "NA", "NA", "NA",
"NA", "NA")), row.names = c(NA, -6L), class = c("tbl_df", "tbl",
"data.frame"))
dput(df2)
structure(list(ID = c(1, 3, 5, 6, 6), datetime_event = c("2019-04-19 21:55:00 UTC",
"2019-05-06 21:23:00 UTC", "2019-07-04 19:45:00 UTC", "2019-05-06 17:18:00 UTC",
"2019-08-03 10:10:00 UTC")), row.names = c(NA, -5L), class = c("tbl_df",
"tbl", "data.frame"))
library(dplyr)
library(tidyr)
# convert datetime_interval to datetime class start and end columns
# and add row IDs
df1 = df1 %>%
separate(datetime_interval, into = c("start", "end"), sep = "--") %>%
mutate_at(vars(start, end), as.POSIXct) %>%
select(-datetime_event, -event) %>%
mutate(row_id = row_number())
# convert datetime event to datetime class
df2 = df2 %>%
mutate(datetime_event = as.POSIXct(datetime_event))
# join and filter
df1 %>% left_join(df2, by = "ID") %>%
mutate(
datetime_event = ifelse(datetime_event >= start & datetime_event <= end, datetime_event, NA),
event = ifelse(is.na(datetime_event), NA, "yes")
) %>%
arrange(row_id, datetime_event) %>%
group_by(row_id) %>%
slice(1)
# # A tibble: 6 x 6
# # Groups: row_id [6]
# ID start end row_id datetime_event event
# <dbl> <dttm> <dttm> <int> <dbl> <chr>
# 1 1 2019-04-19 21:50:00 2019-04-20 21:31:00 1 1555725300 yes
# 2 1 2019-07-02 04:23:00 2019-07-02 08:51:00 2 NA NA
# 3 2 2019-07-04 19:45:00 2019-07-05 00:30:00 3 NA NA
# 4 3 2019-06-07 08:55:00 2019-06-07 14:43:00 4 NA NA
# 5 3 2019-05-06 17:18:00 2019-05-06 23:18:00 5 1557192180 yes
# 6 6 2019-08-02 22:00:00 2019-08-04 03:10:00 6 1564841400 yes