blocks|key|2521528|text|我只是使用了一个data.table，它也提供了一个year函数，并且忽略了as.POSIXct中可能很慢的日期转换逻辑。|type|unstyled|depth|inlineStyleRanges|offset|length|style|CODE|entityRanges|data|2521529|我还假设to_date和from_date可能只相差一年(不超过一年！)。|2521530|library(data.table)++#+also+provides+a+"year"+function

setDT(test)

#+Create+additional+rows+for+the+new+year
additional_rows+<-+test[year(from_date)+<+year(to_date),+]
additional_rows[,+from_date+:=+as.POSIXct(paste0(year(to_date),"-01-01"))]

#+Shorten+the+"from_date"+of+the+affected+original+rows
test[year(from_date)+<+year(to_date),+to_date+:=+as.POSIXct(paste0(year(from_date),"-12-31"))]

#+Create+a+combined+data+table+as+result
result+<-+rbind(test,+additional_rows)
setkey(result,+ID,+Payment,+from_date)++#+just+to+sort+the+data+like+the+"test_desired"+sort+order|code-block|syntax|javascript|2521531|这导致了|2521532|>+result
+++ID+Disease+Pass+Payment++from_date++++to_date
1:+10+++++++P+++US+++++110+2008-01-09+2008-12-31
2:+10+++++++P+++US+++++110+2009-01-01+2009-01-08
3:+10+++++++P+++US+++++110+2009-01-09+2009-12-31
4:+10+++++++P+++US+++++110+2010-01-01+2010-01-08
5:+10+++++++P+++US+++++115+2010-01-09+2010-12-31
6:+10+++++++P+++US+++++115+2011-01-01+2011-01-08
7:+12+++++++D+++EN+++++240+2008-01-01+2008-12-31
8:+12+++++++P+++EN+++++255+2013-12-31+2013-12-31
9:+12+++++++P+++EN+++++255+2014-01-01+2014-12-30|2521533|entityMap^0|8|A|Q|4|12|A|0|4|7|C|9|0|0|0|0^^$0|@$1|2|3|4|5|6|7|S|8|@$9|T|A|U|B|C]|$9|V|A|W|B|C]|$9|X|A|Y|B|C]]|D|@]|E|$]]|$1|F|3|G|5|6|7|Z|8|@$9|10|A|11|B|C]|$9|12|A|13|B|C]]|D|@]|E|$]]|$1|H|3|I|5|J|7|14|8|@]|D|@]|E|$K|L]]|$1|M|3|N|5|6|7|15|8|@]|D|@]|E|$]]|$1|O|3|P|5|J|7|16|8|@]|D|@]|E|$K|L]]|$1|Q|3|-4|5|6|7|17|8|@]|D|@]|E|$]]]|R|$]]

I am just using a <code>data.table</code> which also provides a <code>year</code>function
and ignore the possibly slow date conversion logic with <code>as.POSIXct</code>.

I am also assuming that the <code>to_date</code> and <code>from_date</code> may differ by one year only (not more than one year!).

<pre><code>library(data.table) # also provides a "year" function

setDT(test)

# Create additional rows for the new year
additional_rows &lt;- test[year(from_date) &lt; year(to_date), ]
additional_rows[, from_date := as.POSIXct(paste0(year(to_date),"-01-01"))]

# Shorten the "from_date" of the affected original rows
test[year(from_date) &lt; year(to_date), to_date := as.POSIXct(paste0(year(from_date),"-12-31"))]

# Create a combined data table as result
result &lt;- rbind(test, additional_rows)
setkey(result, ID, Payment, from_date) # just to sort the data like the "test_desired" sort order
</code></pre>

which results in

<pre><code>&gt; result
 ID Disease Pass Payment from_date to_date
1: 10 P US 110 2008-01-09 2008-12-31
2: 10 P US 110 2009-01-01 2009-01-08
3: 10 P US 110 2009-01-09 2009-12-31
4: 10 P US 110 2010-01-01 2010-01-08
5: 10 P US 115 2010-01-09 2010-12-31
6: 10 P US 115 2011-01-01 2011-01-08
7: 12 D EN 240 2008-01-01 2008-12-31
8: 12 P EN 255 2013-12-31 2013-12-31
9: 12 P EN 255 2014-01-01 2014-12-30
</code></pre>

blocks|key|2521548|text|使用from_date和to_date，我们可以使用seq.Date创建日期序列，然后将该序列按年拆分，最后选择每年的最小和最大值。然后使用apply、separate_rows和separate得到最终结果。|type|unstyled|depth|inlineStyleRanges|offset|length|style|CODE|entityRanges|data|2521549|cr_date+<-+function(d1,+d2){
++++#browser()
++++sequence_date+<-+seq.Date(as.Date(d1),+as.Date(d2),+by='day')+
++++lst_dates+<-+lapply(split(sequence_date,+lubridate::year(sequence_date)),
++++++++++++++++++++++++function(x)+paste0(min(x),+'%7C',+max(x)))
++++result+<-+paste0(lst_dates,+collapse+=+';')
++++return(result)
++}

#Test
#cr_date(as.Date('2008-01-09'),as.Date('2009-01-08'))
test$flag+<-+apply(test,+1,+function(x)+cr_date(x['from_date'],+x['to_date']))

library(tidyr)
separate_rows(test,+flag,+sep=';')+%25>%25+
++separate(flag,+into+=+c('from_date_new','to_date_new'),+'\\%7C')+%25>%25+
++mutate_at(vars('from_date_new','to_date_new'),+list(~as.Date(.)))


++++ID+Disease+Pass+Payment++from_date++++to_date+from_date_new+to_date_new
++1+10+++++++P+++US+++++110+2008-01-09+2009-01-08++++2008-01-09++2008-12-31
++2+10+++++++P+++US+++++110+2008-01-09+2009-01-08++++2009-01-01++2009-01-08
++3+10+++++++P+++US+++++110+2009-01-09+2010-01-08++++2009-01-09++2009-12-31
++4+10+++++++P+++US+++++110+2009-01-09+2010-01-08++++2010-01-01++2010-01-08
++5+10+++++++P+++US+++++115+2010-01-09+2011-01-08++++2010-01-09++2010-12-31
++6+10+++++++P+++US+++++115+2010-01-09+2011-01-08++++2011-01-01++2011-01-08
++7+12+++++++D+++EN+++++240+2008-01-01+2008-12-31++++2008-01-01++2008-12-31
++8+12+++++++P+++EN+++++255+2013-12-31+2014-12-30++++2013-12-31++2013-12-31
++9+12+++++++P+++EN+++++255+2013-12-31+2014-12-30++++2014-01-01++2014-12-30|code-block|syntax|javascript|2521550|entityMap^0|Q|8|1Y|5|24|D|2I|8|0|0^^$0|@$1|2|3|4|5|6|7|M|8|@$9|N|A|O|B|C]|$9|P|A|Q|B|C]|$9|R|A|S|B|C]|$9|T|A|U|B|C]]|D|@]|E|$]]|$1|F|3|G|5|H|7|V|8|@]|D|@]|E|$I|J]]|$1|K|3|-4|5|6|7|W|8|@]|D|@]|E|$]]]|L|$]]

Using from_date and to_date we can create a date sequence using <code>seq.Date</code> then split this sequence by year, finally select min and max of each year. Then use <code>apply</code>, <code>separate_rows</code> and <code>separate</code> to get the final result. 

<pre><code>cr_date &lt;- function(d1, d2){
 #browser()
 sequence_date &lt;- seq.Date(as.Date(d1), as.Date(d2), by='day') 
 lst_dates &lt;- lapply(split(sequence_date, lubridate::year(sequence_date)),
 function(x) paste0(min(x), '|', max(x)))
 result &lt;- paste0(lst_dates, collapse = ';')
 return(result)
 }

#Test
#cr_date(as.Date('2008-01-09'),as.Date('2009-01-08'))
test$flag &lt;- apply(test, 1, function(x) cr_date(x['from_date'], x['to_date']))

library(tidyr)
separate_rows(test, flag, sep=';') %&gt;% 
 separate(flag, into = c('from_date_new','to_date_new'), '\\|') %&gt;% 
 mutate_at(vars('from_date_new','to_date_new'), list(~as.Date(.)))


 ID Disease Pass Payment from_date to_date from_date_new to_date_new
 1 10 P US 110 2008-01-09 2009-01-08 2008-01-09 2008-12-31
 2 10 P US 110 2008-01-09 2009-01-08 2009-01-01 2009-01-08
 3 10 P US 110 2009-01-09 2010-01-08 2009-01-09 2009-12-31
 4 10 P US 110 2009-01-09 2010-01-08 2010-01-01 2010-01-08
 5 10 P US 115 2010-01-09 2011-01-08 2010-01-09 2010-12-31
 6 10 P US 115 2010-01-09 2011-01-08 2011-01-01 2011-01-08
 7 12 D EN 240 2008-01-01 2008-12-31 2008-01-01 2008-12-31
 8 12 P EN 255 2013-12-31 2014-12-30 2013-12-31 2013-12-31
 9 12 P EN 255 2013-12-31 2014-12-30 2014-01-01 2014-12-30
</code></pre>

blocks|key|2521561|text|您也可以使用dplyr和lubridate尝试如下所示的内容。其原理如下:+1.使用rbind复制数据帧。2.首先在ID上排列，然后在from_date上排列，最后在test中按行的顺序排列。3.在偶数行中，将from_date更改为新年的第一天。4.在奇数行中，将to_date更改为前一年的最后一天。5.最后，排除from_date和to_date相差仅1秒的行。|type|unstyled|depth|inlineStyleRanges|offset|length|style|CODE|entityRanges|data|2521562|test+%25>%25+
++rbind(test)+%25>%25+
++arrange(ID,+from_date)+%25>%25+
++mutate(from_date+=+if_else(row_number()+%25%25+2+==+0,+ceiling_date(from_date,+"year")+%2B+1,+from_date),
+++++++++to_date+=+if_else(row_number()+%25%25+2+==+1,+floor_date(to_date,+"year")+-+1,+to_date))+%25>%25+
++filter(from_date+-+to_date+!=+1)

++ID+Disease+Pass+Payment+++++++++++from_date+++++++++++++to_date
1+10+++++++P+++US+++++110+2008-01-09+00:00:00+2008-12-31+23:59:59
2+10+++++++P+++US+++++110+2009-01-01+00:00:01+2009-01-08+00:00:00
3+10+++++++P+++US+++++110+2009-01-09+00:00:00+2009-12-31+23:59:59
4+10+++++++P+++US+++++110+2010-01-01+00:00:01+2010-01-08+00:00:00
5+10+++++++P+++US+++++115+2010-01-09+00:00:00+2010-12-31+23:59:59
6+10+++++++P+++US+++++115+2011-01-01+00:00:01+2011-01-08+00:00:00
7+12+++++++D+++EN+++++240+2008-01-01+00:00:01+2008-12-31+00:00:00
8+12+++++++P+++EN+++++255+2013-12-31+00:00:00+2013-12-31+23:59:59
9+12+++++++P+++EN+++++255+2014-01-01+00:00:01+2014-12-30+00:00:00|code-block|syntax|javascript|2521563|唯一的缺点可能是添加了时间，但您当然可以删除这些时间。如果一个周期可能持续到第三年，您可以使用相同的逻辑，但使用第二个rbind和row_number()+%25%25+3+==+0|2521564|entityMap^0|6|5|C|9|16|5|1M|2|1V|9|2B|4|2X|9|3P|7|4F|9|4P|7|0|0|1N|5|1T|M|0^^$0|@$1|2|3|4|5|6|7|O|8|@$9|P|A|Q|B|C]|$9|R|A|S|B|C]|$9|T|A|U|B|C]|$9|V|A|W|B|C]|$9|X|A|Y|B|C]|$9|Z|A|10|B|C]|$9|11|A|12|B|C]|$9|13|A|14|B|C]|$9|15|A|16|B|C]|$9|17|A|18|B|C]]|D|@]|E|$]]|$1|F|3|G|5|H|7|19|8|@]|D|@]|E|$I|J]]|$1|K|3|L|5|6|7|1A|8|@$9|1B|A|1C|B|C]|$9|1D|A|1E|B|C]]|D|@]|E|$]]|$1|M|3|-4|5|6|7|1F|8|@]|D|@]|E|$]]]|N|$]]

You could as well try something like below using <code>dplyr</code> and <code>lubridate</code>. It works as following: 1. Duplicate the dataframe using <code>rbind</code>. 2. Arrange at first on <code>ID</code>, secondly on <code>from_date</code> and third on the order of rows given in <code>test</code>. 3. in the even rows, change <code>from_date</code> to the first day of the new year. 4. In the odd rows, change <code>to_date</code> to the last day of the previous year. 5. Finally, exclude the rows in which the difference between <code>from_date</code> and <code>to_date</code> is only 1 second.

<pre><code>test %&gt;% 
 rbind(test) %&gt;% 
 arrange(ID, from_date) %&gt;% 
 mutate(from_date = if_else(row_number() %% 2 == 0, ceiling_date(from_date, "year") + 1, from_date),
 to_date = if_else(row_number() %% 2 == 1, floor_date(to_date, "year") - 1, to_date)) %&gt;% 
 filter(from_date - to_date != 1)

 ID Disease Pass Payment from_date to_date
1 10 P US 110 2008-01-09 00:00:00 2008-12-31 23:59:59
2 10 P US 110 2009-01-01 00:00:01 2009-01-08 00:00:00
3 10 P US 110 2009-01-09 00:00:00 2009-12-31 23:59:59
4 10 P US 110 2010-01-01 00:00:01 2010-01-08 00:00:00
5 10 P US 115 2010-01-09 00:00:00 2010-12-31 23:59:59
6 10 P US 115 2011-01-01 00:00:01 2011-01-08 00:00:00
7 12 D EN 240 2008-01-01 00:00:01 2008-12-31 00:00:00
8 12 P EN 255 2013-12-31 00:00:00 2013-12-31 23:59:59
9 12 P EN 255 2014-01-01 00:00:01 2014-12-30 00:00:00
</code></pre>

Only downside might be that times are added, but you could of course delete those. And in case a period might continue in a third year, you could use the same logic but with a second <code>rbind</code> and <code>row_number() %% 3 == 0</code>

blocks|key|2521570|text|这是一个基于tidyverse的解决方案。它类似于Lennyy，但条件检查更少，添加时间也没有问题(它们可能会显示在tibble中，但会显示为00:00:00)。我添加了ungroup()，因为它听起来像是在某个地方有一个分组变量(在Lennyy的解决方案下进行注释)。如果您不这样做，则可以将其删除：|type|unstyled|depth|inlineStyleRanges|offset|length|style|CODE|entityRanges|data|2521571|library(dplyr)
library(lubridate)
library(purrr)

test+%25>%25+
++++ungroup()+%25>%25+#+This+isn't+necessary+if+there+are+no+groupings.
++++split(rownames(test))+%25>%25+
++++map_dfr(function(df){
++++++++if+(year(df$from_date)+==+year(df$to_date))+return(df)
++++++++bind_rows(mutate(df,+to_date+=+rollback(floor_date(to_date,+"y"))),
++++++++++++++++++mutate(df,+from_date+=+floor_date(to_date,+"y"))
++++++++++++++++++)
++++}
++++)

####+OUTPUT+####

++ID+Disease+Pass+Payment++from_date++++to_date
1+10+++++++P+++US+++++110+2008-01-09+2008-12-31
2+10+++++++P+++US+++++110+2009-01-01+2009-01-08
3+10+++++++P+++US+++++110+2009-01-09+2009-12-31
4+10+++++++P+++US+++++110+2010-01-01+2010-01-08
5+10+++++++P+++US+++++115+2010-01-09+2010-12-31
6+10+++++++P+++US+++++115+2011-01-01+2011-01-08
7+12+++++++D+++EN+++++240+2008-01-01+2008-12-31
8+12+++++++P+++EN+++++255+2013-12-31+2013-12-31
9+12+++++++P+++EN+++++255+2014-01-01+2014-12-30|code-block|syntax|javascript|2521572|解释:数据帧被分成一个行列表。然后，我使用map_dfr在from_date和to_date包含不同年份的每个数据帧上运行函数。map_dfr还将结果数据帧绑定在一起。在匿名函数中，我按年填写to_date，然后针对第一行中的新to_date将其回滚到上个月的最后一天，或者将其保留为第二行中新from_date的原样。|2521573|entityMap^0|1Z|8|2D|9|0|0|L|7|T|9|13|7|1S|7|2O|7|36|7|43|9|0^^$0|@$1|2|3|4|5|6|7|O|8|@$9|P|A|Q|B|C]|$9|R|A|S|B|C]]|D|@]|E|$]]|$1|F|3|G|5|H|7|T|8|@]|D|@]|E|$I|J]]|$1|K|3|L|5|6|7|U|8|@$9|V|A|W|B|C]|$9|X|A|Y|B|C]|$9|Z|A|10|B|C]|$9|11|A|12|B|C]|$9|13|A|14|B|C]|$9|15|A|16|B|C]|$9|17|A|18|B|C]]|D|@]|E|$]]|$1|M|3|-4|5|6|7|19|8|@]|D|@]|E|$]]]|N|$]]

Here's a tidyverse based solution. It's similar to Lennyy's, but with fewer condition checks, and there's no issue with times being added (they might show up in a tibble, but as <code>00:00:00</code>). I've added <code>ungroup()</code> because it sounds like you have a grouping variable somewhere (comment under Lennyy's solution). It can be removed if you don't:

<pre class="lang-r prettyprint-override"><code>library(dplyr)
library(lubridate)
library(purrr)

test %&gt;% 
 ungroup() %&gt;% # This isn't necessary if there are no groupings.
 split(rownames(test)) %&gt;% 
 map_dfr(function(df){
 if (year(df$from_date) == year(df$to_date)) return(df)
 bind_rows(mutate(df, to_date = rollback(floor_date(to_date, "y"))),
 mutate(df, from_date = floor_date(to_date, "y"))
 )
 }
 )

#### OUTPUT ####

 ID Disease Pass Payment from_date to_date
1 10 P US 110 2008-01-09 2008-12-31
2 10 P US 110 2009-01-01 2009-01-08
3 10 P US 110 2009-01-09 2009-12-31
4 10 P US 110 2010-01-01 2010-01-08
5 10 P US 115 2010-01-09 2010-12-31
6 10 P US 115 2011-01-01 2011-01-08
7 12 D EN 240 2008-01-01 2008-12-31
8 12 P EN 255 2013-12-31 2013-12-31
9 12 P EN 255 2014-01-01 2014-12-30
</code></pre>

To explain: The dataframe is split into a list of rows. I then use <code>map_dfr</code> to run the function on each dataframe where <code>from_date</code> and <code>to_date</code> contain different years. <code>map_dfr</code> also binds the resulting dataframes together. Within the anonymous function I floor <code>to_date</code> by year, and then I either roll it back to the last day of the previous month for the new <code>to_date</code> in the first row, or leave it as it is for the new <code>from_date</code> in the second row.

blocks|key|2521595|text|这只使用了基数R。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|2521596|首先请注意，只使用不带时间的日期，所以我们应该使用Date类，而不是POSIXct。后者可能会引入不必要的时区错误，除非您非常小心，因此在末尾的说明中，我们假设我们从包含Date类数据的test2开始。注释中的代码还显示了如何将其转换为Date类(如果它已经POSIXct+)。|offset|length|style|CODE|2521597|在给定test2的情况下，我们添加from_year、to_year和eoy+(年底日期)列，以提供test3。然后我们迭代各行，如果年份相同，则返回行，如果不相同，则返回拆分的行。这给出了我们rbind在一起的单行和双行数据帧的列表。|2521598|test3+<-+transform(test2,+
++from_year+=+format(from_date,+"%25Y"),
++to_year+=+format(to_date,+"%25Y"),
++eoy+=+as.Date(sub("-.*",+"-12-31",+from_date)))

nr+<-+nrow(test2)
do.call("rbind",+lapply(1:nr,+function(i)+with(test3[i,+],
++if+(from_year+==+to_year)+test2[i,+]
++else+data.frame(ID,+Disease,+Pass,+Payment,+
++++++from_date+=+c(from_date,+eoy%2B1),
++++++to_date+=+c(eoy,+to_date)))
))|code-block|syntax|javascript|2521599|备注|2521600|假设输入为可重现的形式。如上所述，它使用Date类。|2521601|test2+<-+transform(test,+
++from_date+=+as.Date(from_date),
++to_date+=+as.Date(to_date))|2521602|entityMap^0|0|P|4|Y|7|2D|4|2L|5|3A|4|3L|7|0|3|5|H|9|R|7|Z|3|1E|5|2P|5|0|0|0|K|4|0|0^^$0|@$1|2|3|4|5|6|7|W|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|X|8|@$D|Y|E|Z|F|G]|$D|10|E|11|F|G]|$D|12|E|13|F|G]|$D|14|E|15|F|G]|$D|16|E|17|F|G]|$D|18|E|19|F|G]]|9|@]|A|$]]|$1|H|3|I|5|6|7|1A|8|@$D|1B|E|1C|F|G]|$D|1D|E|1E|F|G]|$D|1F|E|1G|F|G]|$D|1H|E|1I|F|G]|$D|1J|E|1K|F|G]|$D|1L|E|1M|F|G]]|9|@]|A|$]]|$1|J|3|K|5|L|7|1N|8|@]|9|@]|A|$M|N]]|$1|O|3|P|5|6|7|1O|8|@]|9|@]|A|$]]|$1|Q|3|R|5|6|7|1P|8|@$D|1Q|E|1R|F|G]]|9|@]|A|$]]|$1|S|3|T|5|L|7|1S|8|@]|9|@]|A|$M|N]]|$1|U|3|-4|5|6|7|1T|8|@]|9|@]|A|$]]]|V|$]]

This uses only base R.

First note that only dates with no times are used so we should be using <code>Date</code> class, not <code>POSIXct</code>. The latter can needlessly introduce timezone errors unless you are very careful so in the Note at the end which shows the input used we assume that we are starting out with <code>test2</code> which contains <code>Date</code> class data. The code in the Note also shows how to convert it to <code>Date</code> class if it it already <code>POSIXct</code>.

Given <code>test2</code> we add <code>from_year</code>, <code>to_year</code> and <code>eoy</code> (date at the end of the year) columns giving <code>test3</code>. Then we iterate over the rows and if the years are the same return the row and if not return the split rows. This gives a list of one and two row data frames which we <code>rbind</code> together.

<pre><code>test3 &lt;- transform(test2, 
 from_year = format(from_date, "%Y"),
 to_year = format(to_date, "%Y"),
 eoy = as.Date(sub("-.*", "-12-31", from_date)))

nr &lt;- nrow(test2)
do.call("rbind", lapply(1:nr, function(i) with(test3[i, ],
 if (from_year == to_year) test2[i, ]
 else data.frame(ID, Disease, Pass, Payment, 
 from_date = c(from_date, eoy+1),
 to_date = c(eoy, to_date)))
))
</code></pre>

<h2>Note</h2>

Assumed input in reproducible form. As noted above it uses <code>Date</code> class.

<pre><code>test2 &lt;- transform(test, 
 from_date = as.Date(from_date),
 to_date = as.Date(to_date))
</code></pre>

I have data from a hospital with many variables, and also from and to dates for each row, which tells us when each row is "valid". Each row can maximum be valid for a year.

<pre><code>test = data.frame(ID=c(10,10,10,12,12), Disease=c("P","P","P","D","P"), Pass=c("US","US","US","EN","EN"),
 Payment=c(110,110,115,240,255), 
 from_date=as.POSIXct(c("2008-01-09","2009-01-09","2010-01-09","2008-01-01","2013-12-31")),
 to_date=as.POSIXct(c("2009-01-08","2010-01-08","2011-01-08","2008-12-31","2014-12-30"))
 )
</code></pre>

For the rows that pass from one year to another, I want to split up the rows, such that I end up with two rows instead of the original row, and also manipulate the from_date and to_date, such that I end up with a new dataset looking like this:

<pre><code> test_desired = data.frame(ID=c(10,10,10,10,10,10,12,12,12), Disease=c("P","P","P","P","P","P","D","P","P"), Pass=c("US","US","US","US","US","US","EN","EN","EN"),
 Payment=c(110,110,110,110,115,115,240,255,255), 
 from_date=as.POSIXct(c("2008-01-09","2009-01-01","2009-01-09","2009-01-01","2010-01-09","2011-01-01","2008-01-01","2013-12-31","2014-01-01")),
 to_date=as.POSIXct(c("2008-12-31","2009-01-08","2009-12-31","2010-01-08","2010-12-31","2011-01-08","2008-12-31","2013-12-31","2014-12-30"))
 ) 
</code></pre>

Attempt:

<pre><code>library(lubridate) #for function "year" below
test_desired=test
row=c()
tmp=c()
for(i in 1:nrow(test_desired)){
 if(year(test_desired$from_date)[i]&lt;year(test_desired$to_date)[i]){
 test_desired$to_date[i] = as.POSIXct(paste0(year(test_desired$from_date[i]),"-12-31"))
 row = test_desired[i,]
 row$from_date = as.POSIXct(paste0(year(test$to_date[i]),"-01-01"))
 row$to_date = test$to_date[i]
 tmp=rbind(tmp,row)

 } else next
}
test_desired=rbind(test_desired,tmp)
library(dplyr)
test_desired=arrange(test_desired,ID,from_date)
</code></pre>

Is there a more elegant way of doing this, for example with dplyr?

Split date rows by new year

我有一家医院的数据，有很多变量，还有每一行的from和to data，这告诉我们每一行什么时候是“有效的”。每一行的有效期最长为一年。test = data.frame(ID=c(10,10,10,12,12), Disease=c("P","P","P","D","P"), Pass=c("US","US","US"...

问按新年份拆分日期行
EN

社区

活动

资源

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问按新年份拆分日期行EN

社区

活动

资源

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问按新年份拆分日期行
EN