r - 使用 "dimnames"= List of 2 格式化动物园对象

Question

我正在使用 eventstudies package .我正在使用 phys2eventtime(..)设置我的数据。但是我得到

Error in `colnames<-`(`*tmp*`, value = integer(0)) : 
  attempt to set 'colnames' on an object with less than two dimensions

我的猜测是，我的数据格式错误。当我查看使用示例中的函数的示例数据时:

    > es <- phys2eventtime(z=StockPriceReturns, events=SplitDates, width=10)
    > (str(StockPriceReturns))
'zoo' series from 2000-04-03 to 2013-03-28
  Data: num [1:3246, 1:30] NA NA NA NA NA NA NA NA NA NA ...
 - attr(*, "dimnames")=List of 2
  ..$ : NULL
  ..$ : chr [1:30] "Bajaj.Auto" "BHEL" "Bharti.Airtel" "Cipla" ...
  Index:  Date[1:3246], format: "2000-04-03" "2000-04-04" "2000-04-05" "2000-04-06" ...
NULL

与此相比，我的数据如下所示:

> (str(zoo_Data))
'zoo' series from 2002-01-01 to 2013-08-20
  Data: num [1:3036] 183 183 186 191 191 ...
  Index:  Date[1:3036], format: "2002-01-01" "2002-01-02" "2002-01-03" "2002-01-04" ...
NULL    

这是不同的:

样本数据使用诸如 - attr(*, "dimnames")=List of 2 之类的东西

在查看原始数据时也可以看到这一点:

样本数据:

> (head(StockPriceReturns))
           Bajaj.Auto       BHEL Bharti.Airtel     Cipla Coal.India   Dr.Reddy
2000-04-03         NA  4.9171044            NA  6.810041         NA -3.2541653
2000-04-04         NA -8.3348496            NA -3.368606         NA -8.3353739
2000-04-05         NA  0.3305788            NA  0.836825         NA  0.2616345
2000-04-06         NA -2.7605266            NA -2.466056         NA -1.8941289
2000-04-07         NA  3.2543548            NA  7.690426         NA  7.6961041
2000-04-10         NA  3.3107586            NA  6.154276         NA  6.4769648

我的数据:

> (head(zoo_Data))
2002-01-01 2002-01-02 2002-01-03 2002-01-04 2002-01-07 2002-01-08 
    182.83     182.83     186.40     190.57     191.17     193.25 

df data :

我正在从我的数据中构建动物园对象，如下所示:

> dfToZoo <- function(df) {
    require(zoo)
    date <- as.Date(df[, 1], format = '%d.%m.%Y')
    #TODO have a look if the column are rightly named
    with(df, zoo(TotalReturns, date))
} 


csv_data <- read.csv(..., header = TRUE, sep = ";",stringsAsFactors=FALSE)

totalReturns <- (as.double(gsub(",",".",csv_data$TotalReturn)))


df <- data.frame(csv_data$Date, totalReturns)
names(df) <- c("Date" ,"TotalReturns")


zoo_Data <- dfToZoo(df)

如何添加 attr(*, "dimnames")=List of 2我的数据？

我感谢您的回复!

更新 1

这是 example data code从库包:

library(eventstudies)
library(zoo)

###########################

# Load data

(data(SplitDates))
(data(StockPriceReturns))

data <- StockPriceReturns

(head(StockPriceReturns))



es <- phys2eventtime(z=StockPriceReturns, events=SplitDates, width=10)
es.w <- window(es$z.e, start=-10, end=10)
SplitDates[1:3,]

更新 2

这是我自己的数据的格式:

> (str(s_dates))
'data.frame':   36799 obs. of  2 variables:
 $ unit: chr  "ZAE000006284" "ZAE000006284" "ZAE000006284" "ZAE000006284" ...
 $ when: Date, format: "2003-12-18" "2005-04-06" ...
NULL
> (str(zoo_Data))
'zoo' series from 2002-01-01 to 2013-08-20
  Data: num [1:3036] 183 183 186 191 191 ...
  Index:  Date[1:3036], format: "2002-01-01" "2002-01-02" "2002-01-03" "2002-01-04" ...
NULL

事件研究包中的数据格式如下:

> (str(SplitDates))
'data.frame':   22 obs. of  2 variables:
 $ unit: chr  "BHEL" "Bharti.Airtel" "Cipla" "Coal.India" ...
 $ when: Date, format: "2011-10-03" "2009-07-24" ...
NULL
> (str(StockPriceReturns))
'zoo' series from 2000-04-03 to 2013-03-28
  Data: num [1:3246, 1:30] NA NA NA NA NA NA NA NA NA NA ...
 - attr(*, "dimnames")=List of 2
  ..$ : NULL
  ..$ : chr [1:30] "Bajaj.Auto" "BHEL" "Bharti.Airtel" "Cipla" ...
  Index:  Date[1:3246], format: "2000-04-03" "2000-04-04" "2000-04-05" "2000-04-06" ...
NULL

更新 3

可重现的示例

我最初是通过不同的 csv 文件读取数据。请参阅我的可重现示例:

可重现的例子

library(eventstudies)
library(zoo)

s_dates <- 
  structure(list(unit = c("ZAE000006284", "ZAE000006284", "ZAE000006284", 
                          "ZAE000006284", "ZAE000006284", "XS0430907989", "XS0430907989"
  ), when = structure(c(12404, 12879, 12879, 12880, 12930, 14411, 
                        14411), class = "Date")), .Names = c("unit", "when"), row.names = c(NA, 
                                                                                            7L), class = "data.frame")

zoo_Data <- 
  structure(c(182.83, 182.83, 186.4, 190.57, 191.17, 193.25, 190.57
  ), index = structure(c(11688, 11689, 11690, 11691, 11694, 11695, 
                         11696), class = "Date"), class = "zoo")

es <- phys2eventtime(z=zoo_Data, events=s_dates, width=10)
Error in `colnames<-`(`*tmp*`, value = integer(0)) : 
  attempt to set 'colnames' on an object with less than two dimensions
> es.w <- window(es$z.e, start=-10, end=10)
  Error in window(es$z.e, start = -10, end = 10) : object 'es' not found

更新 4

好的，当我尝试转换我的 zoo_data 时:

> library(eventstudies)
> library(zoo)
> 
> s_dates <- dput(head(s_dates,30))
structure(list(unit = c("ZAE000006284", "ZAE000006284", "ZAE000006284", 
"ZAE000006284", "ZAE000006284", "XS0430907989", "XS0430907989", 
"XS0302626899", "XS0302626899", "XS0302626899", "XS0302626899", 
"XS0302626899", "XS0302626899", "XS0266838746", "XS0187043079", 
"XS0187043079", "XS0187043079", "XF0000TZ7757", "XF0000AK5197", 
"XF0000AK5197", "XF0000AK5197", "XF0000AK5197", "XF0000AK5197", 
"USU02681027", "USU026281027", "USU026281027", "USU026281027", 
"USU026281027", "USU026281027", "USU026281027"), when = structure(c(12404, 
12879, 12879, 12880, 12930, 14411, 14411, 14599, 14600, 15134, 
15139, 15328, 15328, 13913, 14330, 14335, 14593, 13049, 12953, 
12954, 12954, 12954, 12955, 12934, 13537, 13537, 13537, 13648, 
13649, 13649), class = "Date")), .Names = c("unit", "when"), row.names = c(NA, 
30L), class = "data.frame")
> zoo_Data <- dput(head(zoo_Data,30))
structure(c(182.83, 182.83, 186.4, 190.57, 191.17, 193.25, 190.57, 
184.02, 181.34, 172.11, 169.73, 160.2, 175.09, 172.11, 170.92, 
176.58, 171.51, 170.92, 173.9, 168.54, 167.34, 166.75, 166.45, 
167.34, 164.37, 159.01, 158.11, 154.84, 156.63, 161.99), index = structure(c(11688, 
11689, 11690, 11691, 11694, 11695, 11696, 11697, 11698, 11701, 
11702, 11703, 11704, 11705, 11708, 11709, 11710, 11711, 11712, 
11715, 11716, 11717, 11718, 11719, 11722, 11723, 11724, 11725, 
11726, 11729), class = "Date"), class = "zoo")
> 
> n = 20                       ## number of observation
> cn <- unique(s_dates$unit)   ## get response variable 
> 
> as.xts(zoo_Data)
> 
> names(zoo_Data) <- cn
> 
> es <- phys2eventtime(z=zoo_Data), events=s_dates, width=10)
Error in `colnames<-`(`*tmp*`, value = integer(0)) : 
  attempt to set 'colnames' on an object with less than two dimensions
> es.w <- window(es$z.e, start=-3, end=3)
Error in window(es$z.e, start = -3, end = 3) : object 'es' not found

Answer 1

phys2eventtime将实际日期转换为事件日期。

因此，给定动物园时间序列和事件日期，它将实际日期转换为事件日期。这意味着，如果它在 zoo 对象的范围内找到一个事件日期，则该日期将变为 0，所有其他日期也相应地发生变化。

所以给这个事件日期对象:

          unit       when
1 ZAE000006284 2003-12-18
2 ZAE000006284 2005-04-06
3 ZAE000006284 2005-04-06
4 ZAE000006284 2005-04-07
5 ZAE000006284 2005-05-27
6 XS0430907989 2009-06-16
7 XS0430907989 2009-06-16

转换 ts --> 事件日期的条件

您的物理时间序列日期(动物园对象)应满足 2 个条件:

在 中应该至少有一个列名(响应变量)单位值 (COND1)

此响应变量的范围日期应至少包含一个事件日期(when 列)。(COND2)

创建可转换为事件日期的物理时间序列

现在我将创建一个满足这两个条件的时间序列:一个多时间序列(xts 对象)，它的索引落在 s_dates 的范围内并且在 s_dates 单位值内具有列名。

n = 20                       ## number of observation
cn <- unique(s_dates$unit)   ## get response variable 
rr = range(s_dates$when)     ## get date range
## COND2
index = seq(rr[1],rr[2],length.out=n)   
mat = matrix(round(runif(n*2,min=150,max=200),2),ncol=2)
ev.dat = xts(mat,index)
## COND1
names(ev.dat) <- cn

检查我们的时间序列对象:

head(ev.dat)
           ZAE000006284 XS0430907989
2003-12-18       183.27       152.89
2004-04-01       195.23       172.78
2004-07-16       190.18       164.92
2004-10-29       182.24       191.19
2005-02-12       151.78       195.81
2005-05-29       153.78       189.27

毫不奇怪，它工作正常:

(es <- phys2eventtime(z=ev.dat, events=s_dates, width=5))
(es.w <- window(es$z.e, start=-10, end=10))
head(es.w)
        2      3      4      5
-4 197.28 197.28 197.28 197.28
-3 158.54 158.54 158.54 158.54
-2 180.56 180.56 180.56 180.56
-1 194.41 194.41 194.41 194.41
0  157.64 157.64 157.64 157.64
1  151.06 151.06 151.06 151.06

如何测试您的时间序列是否满足这两个条件:

作为奖励，我创建了一个小函数，为您提供 2 个条件:

check.phys2ev <- function(ev.dat,s_dates){
  is.sucess = lapply(s_dates$when,function(when){
    inter = findInterval(when, index(ev.dat))
    inter < nrow(ev.dat) && inter >1 
  })
  sum(unlist(is.sucess)) >0 &
    all(colnames(ev.dat) %in% s_dates$unit)
}

check.phys2ev(ev.dat,s_dates)
[1] TRUE