R:合并两个不规则的时间序列

Question

我有两个多变量时间序列x和y,两者都覆盖了大致相同的时间范围(一个在另一个之前两年开始,但它们在同一天结束).两个系列都以日期列旁边的空列形式缺少观察结果,并且在某种意义上,其中一个系列具有在另一个系列中找不到的几个日期,反之亦然.

我想创建一个数据框(或类似),其中列列出了在x或y中找到的所有日期,没有重复日期.对于每个日期(行),我想在y的观察值旁边水平叠加来自x的观测值,其中NA填充缺失的单元格.例:

>x
"1987-01-01"   7.1    NA   3
"1987-01-02"   5.2    5    2
"1987-01-06"   2.3    NA   9

>y
"1987-01-01"   55.3   66   45
"1987-01-03"   77.3   87   34

# result I would like
"1987-01-01"   7.1    NA   3   55.3   66   45
"1987-01-02"   5.2    5    2   NA     NA   NA
"1987-01-03"   NA     NA   NA  77.3   87   34
"1987-01-06"   2.3    NA   9   NA     NA   NA

我尝试过:使用zoo包,我尝试了merge.zoo方法,但这似乎只是将两个系列相互叠加,并附有日期(作为数字,例如"1987-01-02"显示如每个系列中的6210)出现在两个单独的列中.

我已经坐了几个小时几乎无处可去,所以所有的帮助都表示赞赏.

编辑:根据Soumendra的建议,下面包含一些代码

atcoa <- read.csv(file = "ATCOA_full_adj.csv", header = TRUE)
atcob <- read.csv(file = "ATCOB_full_adj.csv", header = TRUE)
atcoa$date <- as.Date(atcoa$date)
atcob$date <- as.Date(atcob$date)

# only number of observations and the observations themselves differ 
>str(atcoa)
'data.frame':   6151 obs. of  8 variables:
 $ date        :Class 'Date'  num [1:6151] 6210 6213 6215 6216 6217 ...
 $ max         : num  4.31 4.33 4.38 4.18 4.13 4.05 4.08 4.05 4.08 4.1 ...
 $ min         : num  4.28 4.31 4.28 4.13 4.05 3.95 3.97 3.95 4 4.02 ...
 $ close       : num  4.31 4.33 4.31 4.15 4.1 3.97 4 3.97 4.08 4.02 ...
 $ avg         : num  NA NA NA NA NA NA NA NA NA NA ...
 $ tot.vol     : int  877733 89724 889437 1927113 3050611 846525 1782774 1497998 2504466 5636999 ...
 $ turnover    : num  3762300 388900 3835900 8015900 12468100 ...
 $ transactions: int  12 9 24 17 31 26 34 35 37 33 ...

>atcoa[1:1, ]
date a.max a.min a.close a.avg a.tot.vol a.turnover a.transactions
1 1987-01-02  4.31  4.28    4.31    NA    877733    3762300             12

# using timeSeries package
ts.atcoa <- timeSeries::as.timeSeries(atcoa, format = "%Y-%m-%d")
ts.atcob <- timeSeries::as.timeSeries(atcob, format = "%Y-%m-%d")

>str(ts.atcoa)
Time Series:          
 Name:               object
Data Matrix:        
 Dimension:          6151 7
 Column Names:       a.max a.min a.close a.avg a.tot.vol a.turnover a.transactions
 Row Names:          1970-01-01 01:43:30  ...  1970-01-01 04:12:35
Positions:          
 Start:              1970-01-01 01:43:30
 End:                1970-01-01 04:12:35
With:               
 Format:             %Y-%m-%d %H:%M:%S
 FinCenter:          GMT
 Units:              a.max a.min a.close a.avg a.tot.vol a.turnover a.transactions
 Title:              Time Series Object
 Documentation:      Wed Aug 17 13:00:50 2011

>ts.atcoa[1:1, ]
GMT
 a.max a.min a.close a.avg a.tot.vol a.turnover a.transactions
 1970-01-01 01:43:30  4.31  4.28    4.31    NA    877733    3762300             12

# The following will create an object of class "data frame" and mode "list", which contains observations for the days mutual for the two series
>ts.atco <- timeSeries::merge(atcoa, atcob)  # produces same result as base::merge, apparently
>ts.atco[1:1, ]
date a.max a.min a.close a.avg a.tot.vol a.turnover a.transactions b.max b.min b.close b.avg b.tot.vol b.turnover b.transactions
1 1989-08-25  7.92  7.77    7.79    NA    269172    2119400             19  7.69  7.56    7.64    NA  81176693  593858000             12

编辑:问题解决(使用动物园包)

atcoa <- read.zoo(read.csv(file = "ATCOA_full_adj.csv", header = TRUE))
atcob <- read.zoo(read.csv(file = "ATCOB_full_adj.csv", header = TRUE))

names(atcoa) <- c("a.max", "a.min", "a.close",
                   "a.avg", "a.tot.vol", "a.turnover", "a.transactions")
names(atcob) <- c("b.max", "b.min", "b.close",
                   "b.avg", "b.tot.vol", "b.turnover", "b.transactions")

atco <- merge.zoo(atcoa, atcob)

感谢大家的帮助.

Answer 1

试试这个:

Lines.x <- '"1987-01-01"   7.1    NA   3
"1987-01-02"   5.2    5    2
"1987-01-06"   2.3    NA   9'

Lines.y <- '"1987-01-01"   55.3   66   45
"1987-01-03"   77.3   87   34'

library(zoo)
# in reality x might be in a file and might be read via: x <- read.zoo("x.dat")
# ditto for y. See ?read.zoo and the zoo-read vignette if you need other args too
x <- read.zoo(text = Lines.x)
y <- read.zoo(text = Lines.y)
merge(x,  y)

赠送:

           V2.x V3.x V4.x V2.y V3.y V4.y
1987-01-01  7.1   NA    3 55.3   66   45
1987-01-02  5.2    5    2   NA   NA   NA
1987-01-03   NA   NA   NA 77.3   87   34
1987-01-06  2.3   NA    9   NA   NA   NA