【发布时间】：2019-07-08 03:50:16
【问题描述】：
以下两个数据帧是我目前正在处理的数据的一个 sn-p。 df1 包含投资者的历史记录（以 id 分隔）以及他们拥有的不同产品的股份数量。每次股份数量发生变化时，都会创建一个新条目。 df2 包含与产品对应的价格。
我正在尝试计算所有客户在其投资期间的每月投资组合价值。
这是 df1 和 df2 的可重现示例：
library(dplyr)
library(lubridate)
library(timeDate)
#create df1 customer portfolio history
id <- c("1","1","1","1","2","2","2","3","3","3","3","3")
df1 <- data.frame(id)
df1$start <- as.Date(c("2012-03-11", "2012-04-17","2012-05-09", "2012-05-11", "2012-11-17","2012-12-09",
"2013-01-21", "2011-06-27","2012-07-02", "2012-07-21", "2012-09-03","2012-09-16"))
df1$end <- as.Date(c("2012-05-08", "2012-05-21","2012-06-11", "2012-11-16", "2012-12-08","2013-01-20",
"2013-02-03", "2011-07-01","2012-09-15", "2012-09-02", "2012-09-20","2012-09-16"))
df1$product <- c("a","b","a","b","b","b","b","c","c","a","a","c")
df1$amount <- as.numeric(c("5","12","7","11","3","8","6","4","1","16","17","9"))
#create df2 with corresponding Prices
date <- seq.Date(from = as.Date("2011-05-01"), to = as.Date("2013-02-01"), by = "month")
df2 <- data.frame(date)
df2$product <- "a"
date <- seq.Date(from = as.Date("2012-04-01"), to = as.Date("2013-02-01"), by = "month")
date <- data.frame(date)
date$product <- "b"
df2 <- rbind(df2,date)
date <- seq.Date(from = as.Date("2011-06-01"), to = as.Date("2012-09-01"), by = "month")
date <- data.frame(date)
date$product <- "c"
df2 <- rbind(df2,date)
df2$price <- as.numeric(sample(100, size = nrow(df2), replace = TRUE))
df2$date <- as.Date(timeLastDayInMonth(df2$date))
我最终做的是将我的投资者数据分散到一个广泛的格式中，并在每个月底人为地添加一行日期。然后我继续对我的价格数据做同样的事情，将两者结合起来，最终用 rowSums 计算投资组合值。
这是我上面数据框的代码：
#convert to wide data
df1 <- df1 %>%
spread(product, amount, fill = NA, convert = FALSE)
colnames(df1)[4:6] <- paste("xxx", colnames(df1[,c(4:6)]), sep = "_")
#add end of month observations to data frame
seq <- df1 %>%
group_by(id) %>%
summarize(start= floor_date(AddMonths(min(start),-1), "month"),end=max(end)) %>%
group_by(rn=row_number()) %>%
do(data.frame(id=.$id, datum=seq(.$start,.$end,by="1 month"))) %>%
ungroup() %>%
select(-rn)
seq <- seq %>%
group_by(id) %>%
mutate(start = as.Date(timeLastDayInMonth(datum))) %>%
ungroup() %>%
select(-2)
df1 <- full_join(df1,seq, by = c("id","start"))
df1 <- df1[with(df1, order(id, start)),]
#create grouping variable and filter all end of month data
df1<- df1 %>%
group_by(id) %>%
mutate(grp = as.numeric(as.Date(start)- as.Date(timeLastDayInMonth(start))))
df1 <- df1 %>%
group_by(id) %>%
fill(4:6, .direction = "down")
df1 <- filter(df1, grp == 0)
na_sub <- function(x) { x[is.na(x)] <- 0; x }
df1 <- df1 %>%
select(-end, -grp) %>%
na_sub()
#Join both wide dataframes and calculate monthly portfoliovalues
df2 <- df2 %>%
spread(product, price, fill = NA, convert = FALSE)
colnames(df2)[2:4] <- paste("yyy", colnames(df2[,c(2:4)]), sep = "_")
names(df2)[names(df2) == "date"] <- "start"
df1 <- left_join(df1, df2, by = "start")
df1$portfoliovalue <- rowSums(select(df1, starts_with("xxx_")) * select(df1, starts_with("yyy_")), na.rm = TRUE)
代码通过每个投资者的每月投资组合价值得出预期结果。正如我所提到的，这是整个数据的 sn-p。不幸的是，我遇到了麻烦，尤其是宽数据框的大小（由于产品数量的增加，它们获得了大量的列）。这使得无法使用更大的数据集运行代码。是否可以将数据保留为长格式以进行计算？是否有提供此类计算程序的软件包？
【问题讨论】：