使用 lapply 和 split 执行先前的刻度聚合

Question

在过去的 3 个月里，我一直在努力解决这个问题。请帮忙。

我有属于一个交易所的许多股票的报价数据（价格和交易量）。每只股票在硬盘上都有自己的.rds 文件。我有兴趣清理它：

1. 通过取中位数合并多个相同的时间戳

2. 仅限交换时间的子集数据

3. 按之前的刻度聚合在 20 分钟内聚合它

我知道

高频包中的函数聚合

可以执行之前的tick聚合操作。但是，该函数只取一只股票一天的数据。

为了演示这个问题，我使用单个股票的原始分时数据（命名交易）。

    dput(head(trade,50))
structure(c(54.7, 54.7, 54.5, 54.5, 54.5, 54.6, 54.6, 54.65, 
54.65, 54.6, 54.65, 54.65, 54.65, 54.65, 54.7, 54.7, 54.8, 54.8, 
54.85, 54.85, 54.85, 54.85, 54.8, 54.8, 54.8, 54.8, 54.65, 54.65, 
54.8, 54.8, 54.8, 54.8, 54.65, 54.65, 54.65, 54.75, 54.65, 54.7, 
54.7, 54.7, 54.75, 54.75, 54.75, 54.75, 54.75, 54.7, 54.7, 54.7, 
54.65, 54.65, 8, 542, 110, 600, 88, 200, 150, 100, 700, 250, 
75, 100, 25, 200, 100, 600, 1546, 940, 100, 6250, 89, 6911, 89, 
211, 100, 50, 1410, 1090, 913, 4737, 50, 300, 2486, 400, 25, 
85, 250, 168, 50, 100, 40, 40, 60, 50, 40, 10, 91, 6072, 229, 
1000), class = c("xts", "zoo"), .indexCLASS = c("POSIXct", "POSIXt"
), tclass = c("POSIXct", "POSIXt"), .indexTZ = "Asia/Calcutta", tzone = "Asia/Calcutta", index = structure(c(1459481853, 
1459481853, 1459482302, 1459482302, 1459482305, 1459482306, 1459482306, 
1459482307, 1459482307, 1459482308, 1459482312, 1459482314, 1459482314, 
1459482315, 1459482317, 1459482317, 1459482318, 1459482318, 1459482319, 
1459482319, 1459482320, 1459482320, 1459482322, 1459482322, 1459482330, 
1459482330, 1459482331, 1459482331, 1459482336, 1459482336, 1459482337, 
1459482337, 1459482338, 1459482338, 1459482339, 1459482340, 1459482344, 
1459482348, 1459482351, 1459482351, 1459482356, 1459482357, 1459482357, 
1459482361, 1459482362, 1459482364, 1459482367, 1459482367, 1459482369, 
1459482369), tzone = "Asia/Calcutta", tclass = c("POSIXct", "POSIXt"
)), .Dim = c(50L, 2L), .Dimnames = list(NULL, c("value", "size"
)))

我使用以下代码将先前的刻度聚合到 20 分钟间隔：

require(xts)
require(highfrequency)
trade<-xts(trade[,-1], order.by = trade[,1])
trade2<-do.call(rbind, lapply(split(trade,"days"), mergeTradesSameTimestamp))
colnames(trade)[c(1,2)]<-c("PRICE", "SIZE")
trade2<-trade2["T09:30:00/T15:30:00"]
trade2<-trade2[,1]
fundo=function(x) aggregatets(FUN = previoustick,on="minutes",k=20, dropna =F)

由于 aggregatets() 只需要 1 天的数据，我将 trade2 分成几天并将其应用于它们

trade3<-do.call(rbind, lapply(split(trade2, "days"), fundo))

但我收到函数 aggregatets 的错误：

    trade3<-do.call(rbind, lapply(split(trade2, "days"), fundo))
Error in FUN != "previoustick" : 
  comparison (2) is possible only for atomic and list types
Called from: aggregatets(FUN = previoustick, on = "minutes", k = 20, dropna = F)

请建议如何解决此错误。

Answer 1

根据您提供的有限数据，此代码有效。您的错误是由于没有将对象传递给参数ts。 （同样在您的示例数据中，没有任何滴答声在上午 9:30 之前发生，因此为了重现此答案，我将其更改为上午 8.30。即trade2<-trade2["T08:30:00/T15:30:00"]）：

trade <- structure(c(54.7, 54.7, 54.5, 54.5, 54.5, 54.6, 54.6, 54.65, 
    54.65, 54.6, 54.65, 54.65, 54.65, 54.65, 54.7, 54.7, 54.8, 54.8, 
    54.85, 54.85, 54.85, 54.85, 54.8, 54.8, 54.8, 54.8, 54.65, 54.65, 
    54.8, 54.8, 54.8, 54.8, 54.65, 54.65, 54.65, 54.75, 54.65, 54.7, 
    54.7, 54.7, 54.75, 54.75, 54.75, 54.75, 54.75, 54.7, 54.7, 54.7, 
    54.65, 54.65, 8, 542, 110, 600, 88, 200, 150, 100, 700, 250, 
    75, 100, 25, 200, 100, 600, 1546, 940, 100, 6250, 89, 6911, 89, 
    211, 100, 50, 1410, 1090, 913, 4737, 50, 300, 2486, 400, 25, 
    85, 250, 168, 50, 100, 40, 40, 60, 50, 40, 10, 91, 6072, 229, 
    1000), class = c("xts", "zoo"), .indexCLASS = c("POSIXct", "POSIXt"
    ), tclass = c("POSIXct", "POSIXt"), .indexTZ = "Asia/Calcutta", tzone = "Asia/Calcutta", index = structure(c(1459481853, 
    1459481853, 1459482302, 1459482302, 1459482305, 1459482306, 1459482306, 
    1459482307, 1459482307, 1459482308, 1459482312, 1459482314, 1459482314, 
    1459482315, 1459482317, 1459482317, 1459482318, 1459482318, 1459482319, 
    1459482319, 1459482320, 1459482320, 1459482322, 1459482322, 1459482330, 
    1459482330, 1459482331, 1459482331, 1459482336, 1459482336, 1459482337, 
    1459482337, 1459482338, 1459482338, 1459482339, 1459482340, 1459482344, 
    1459482348, 1459482351, 1459482351, 1459482356, 1459482357, 1459482357, 
    1459482361, 1459482362, 1459482364, 1459482367, 1459482367, 1459482369, 
    1459482369), tzone = "Asia/Calcutta", tclass = c("POSIXct", "POSIXt"
    )), .Dim = c(50L, 2L), .Dimnames = list(NULL, c("value", "size"
    )))

# mergeTradesSameTimestamp wants "PRICE" column, so rename now:
colnames(trade) <- c("PRICE", "SIZE")

trade2<-do.call(rbind, lapply(split(trade,"days"), mergeTradesSameTimestamp))
trade2<-trade2["T08:30:00/T15:30:00"]
# Your error was from not passing through x to argument ts:
fundo=function(x) aggregatets(ts = x, FUN = "previoustick",on="minutes",k=20, dropna =F)
trade3<-do.call(rbind, lapply(split(trade2, "days"), fundo))