在这种情况下，我有点坚持使用R.我每天都有一行数据表，如下所示：
Date = c(as.Date("2015-12-31"), as.Date("2016-01-01"));
Month1 = c("DEC", "JAN");
Year1 = c("15", "16");
Price1 = c(100, 110);
Month2 = c(NA_character_, NA_character_);
Year2 = c(NA_character_, NA_character_);
Price2 = c(NA_integer_, NA_integer_);
Month3 = c(NA_character_, NA_character_);
Year3 = c(NA_character_, NA_character_);
Price3 = c(NA_integer_, NA_integer_);
Month4 = c(NA_character_, NA_character_);
Year4 = c(NA_character_, NA_character_);
Price4 = c(NA_integer_, NA_integer_);
dataSample = data.frame(Date, Month1, Year1, Price1, Month2, Year2, Price2, Month3, Year3, Price3, Month4, Year4, Price4);
给出了这样一个表格：
Date Month1 Year1 Price1 Month2 Year2 Price2 Month3 Year3 Price3 Month4 Year4 Price4
1 2015-12-31 DEC 15 100 <NA> <NA> NA <NA> <NA> NA <NA> <NA> NA
2 2016-01-01 JAN 16 110 <NA> <NA> NA <NA> <NA> NA <NA> <NA> NA
现在我需要计算每个月的所有月份和价格。为此，我有2个其他数据框：
Date = c(as.Date("2015-12-31"), as.Date("2015-12-31"), as.Date("2015-12-31"), as.Date("2016-01-01"), as.Date("2016-01-01"), as.Date("2016-01-01"));
Month.Start = c("DEC", "JAN", "FEB", "JAN", "FEB", "MAR");
Year.Start = c("15", "16", "16", "16", "16", "16")
Month.End = c("JAN", "FEB", "MAR", "FEB", "MAR", "APR");
Year.End = c("16", "16", "16", "16", "16", "16")
Diff = c(10, 15, -15, 19, -20, -5);
diffsOneMonth = data.frame(Date, Month.Start, Year.Start, Month.End, Year.End, Diff)
Date = c(as.Date("2015-12-31"), as.Date("2016-01-01"));
Month.Start = c("DEC", "MAR");
Year.Start = c("15", "16")
Month.End = c("MAR", "JUN");
Year.End = c("16", "16")
Diff = c(11, 25);
diffsThreeMonth = data.frame(Date, Month.Start, Year.Start, Month.End, Year.End, Diff)
这给了我这些表格：
One month price differences
Date Month.Start Year.Start Month.End Year.End Diff
1 2015-12-31 DEC 15 JAN 16 10
2 2015-12-31 JAN 16 FEB 16 15
3 2015-12-31 FEB 16 MAR 16 -15
4 2016-01-01 JAN 16 FEB 16 19
5 2016-01-01 FEB 16 MAR 16 -20
6 2016-01-01 MAR 16 APR 16 -5
Three month price differences
Date Month.Start Year.Start Month.End Year.End Diff
1 2015-12-31 DEC 15 MAR 16 20
2 2016-01-01 MAR 16 JUN 16 25
现在，我必须使用差异表中的数据填充 dataSample 数据框。我检查那里有哪些开始/结束月/年，并且必须在 dataSample 中填写这些月/年。然后在 dataSample 中获取价格差异并设置计算价格。所以例如在 dataSample 中我们从DEC 15开始，然后在 diffsOneMonth 中我们有条目DEC 15 - JAN 16，差异为10所以我们将它添加到DEC 15价格并获得JAN 16价格110：
Date Month1 Year1 Price1 Month2 Year2 Price2 Month3 Year3 Price3 Month4 Year4 Price4
1 2015-12-31 DEC 15 100 JAN 16 110 <NA> <NA> NA <NA> <NA> NA
2 2016-01-01 JAN 16 110 <NA> <NA> NA <NA> <NA> NA <NA> <NA> NA
现在可以在下个月再做下一个等等。如果我们只使用 diffsOneMonth ，我们会得到这样的理想结果：
Date Month1 Year1 Price1 Month2 Year2 Price2 Month3 Year3 Price3 Month4 Year4 Price4
1 2015-12-31 DEC 15 100 JAN 16 110 FEB 16 125 MAR 16 110
2 2016-01-01 JAN 16 110 FEB 16 129 MAR 16 109 APR 16 104
然而，如果可能的话，我还必须使用更宽的月份差价来计算价格。因此，对于2015-12-31，从DEC 15到MAR 16存在三个月的差价，这应该超过一个月差价的价格。所以DEC 15的价格是110而DEC 15 - MAR 16的差价是11，这使得MAR 16的价格不是110而是111：
Date Month1 Year1 Price1 Month2 Year2 Price2 Month3 Year3 Price3 Month4 Year4 Price4
1 2015-12-31 DEC 15 100 JAN 16 110 FEB 16 125 MAR 16 111
2 2016-01-01 JAN 16 110 FEB 16 129 MAR 16 109 APR 16 104
因此，对于这个样本，它将是我最终的理想输出。 实际数据要复杂得多，每个日期有6个月和12个月的差异，前进64个月。也可能缺少几个月。我尝试用循环来做但它很慢，但是我不知道如何在没有循环的情况下解决这样的问题。我已经创建了一些辅助方法来计算明年/月：
nextContract = function(currentMonth, currentYear, length = 1,
years = c("10", "11", "12", "13", "14", "15", "16", "17", "18"),
months = c("JAN", "FEB", "MAR", "APR", "MAY", "JUN", "JUL", "AUG", "SEP", "OCT", "NOV", "DEC")) {
mIdx <- match(currentMonth, months)+length;
yDiff = ifelse(length(months) < mIdx, mIdx / length(months) - ifelse(mIdx %% length(months) == 0, 1, 0), 0);
return(data.frame(nextMonth(currentMonth, length, months), nextYear(currentYear, length = yDiff)))
}
nextYear = function(currentYear, length = 1, years = c("10", "11", "12", "13", "14", "15", "16", "17", "18")) {
return(years[match(currentYear, years)+length]);
}
nextMonth = function(currentMonth, length = 1, months = c("JAN", "FEB", "MAR", "APR", "MAY", "JUN", "JUL", "AUG", "SEP", "OCT", "NOV", "DEC")) {
mIdx <- match(currentMonth, months)+length;
return(months[ifelse(length(months) < mIdx, ifelse(mIdx %% length(months) != 0, mIdx %% length(months), length(months)), mIdx)]);
}
使用示例可以是：
> nextContract("DEC", "15")
nextMonth.currentMonth..length..months. nextYear.currentYear..length...yDiff.
1 JAN 16
或：
> nextContract("DEC", "15", length = 3)
nextMonth.currentMonth..length..months. nextYear.currentYear..length...yDiff.
1 MAR 16
这是一个很长的问题，但我希望有人会花时间来审查它：）
提前致谢！
修改 对提议的解决方案有一点改进，我得到了我需要的东西：
outrightAndForwardRows <- list("1" = diffsOneMonth, "3" = diffsThreeMonth) %>%
bind_rows(.id = "time_step") %>%
left_join(dataSample %>%
select(Date, Price1, Month1, Year1) ) %>%
mutate(Day.Start = 1) %>%
mutate(Day.End = 1) %>%
mutate(Outright.Day = 1) %>%
unite("Contract.Start", Day.Start, Month.Start, Year.Start) %>%
unite("Contract.End", Day.End, Month.End, Year.End) %>%
unite("Contract.Outright", Outright.Day, Month1, Year1) %>%
mutate(time_step = as.numeric(time_step),
Contract.Start =
Contract.Start %>%
parse_date_time("%d_%b_%y")) %>%
mutate(Contract.End =
Contract.End %>%
parse_date_time("%d_%b_%y")) %>%
mutate(Contract.Outright =
Contract.Outright %>%
parse_date_time("%d_%b_%y")) %>%
group_by(time_step, Date) %>%
arrange(Contract.End) %>%
mutate(Price = cumsum(Diff) + Price1) %>%
group_by(Date, Contract.End) %>%
slice(time_step %>% which.max) %>%
ungroup() %>%
select(-time_step, -Diff, -Contract.Start)
#### add outright and forward months to the same columns
outright <- outrightAndForwardRows %>% select(Date, Price=Price1, Contract=Contract.Outright) %>% unique
forwardMonths <- outrightAndForwardRows %>% select(Date, Contract=Contract.End, Price)
# join and sort rows
joined <- rbind(outright, forwardMonths) %>% arrange(Date, Contract)
# add contract sequence
joined = data.table(joined)
joined = joined[, Contract.seq:=seq(.N), by=Date];
dcast(joined, Date ~ Contract.seq, value.var=c("Price", "Contract"))
答案 0 :(得分：1)
这样的事情：
library(dplyr)
library(tidyr)
library(lubridate)
list(`1` = diffsOneMonth,
`3` = diffsThreeMonth) %>%
bind_rows(.id = "time_step") %>%
left_join(dataSample %>%
select(Date, Price1, Month1, Year1) ) %>%
mutate(Day.Start = 1) %>%
unite("Date.Start", Day.Start, Month.Start, Year.Start) %>%
mutate(time_step = as.numeric(time_step),
Date.Start =
Date.Start %>%
parse_date_time("%d_%b_%y")) %>%
group_by(time_step, Date) %>%
arrange(Date.Start) %>%
mutate(Price = cumsum(Diff) + Price1) %>%
group_by(Date, Date.Start) %>%
slice(time_step %>% which.max)