在R中多次延迟多个变量

时间:2015-04-06 16:36:58

标签: r lag series

因此,我正在处理一个444天内每日数据的数据框。我有几个变量,我想在回归模型中使用滞后(lm)。我想每次滞后7次。我目前正在产生这样的滞后......

email_data$email_reach1 <- lag(ts(email_data$email_reach, start = 1, end = 444), 1)
email_data$email_reach2 <- lag(ts(email_data$email_reach, start = 1, end = 444), 2)
email_data$email_reach3 <- lag(ts(email_data$email_reach, start = 1, end = 444), 3)
email_data$email_reach4 <- lag(ts(email_data$email_reach, start = 1, end = 444), 4)
email_data$email_reach5 <- lag(ts(email_data$email_reach, start = 1, end = 444), 5)
email_data$email_reach6 <- lag(ts(email_data$email_reach, start = 1, end = 444), 6)
email_data$email_reach7 <- lag(ts(email_data$email_reach, start = 1, end = 444), 7)

然后,我为每个我想要滞后的变量重复这个。

这似乎是实现这一目标的可怕方式。还有更好的东西吗?

我已经考虑过落后整个数据框架了,但是我不知道你如何为结果分配变量名称并将其合并回原始数据框。 / p>

6 个答案:

答案 0 :(得分:7)

您也可以使用data.table。 (HT到@akrun)

set.seed(1)
email_data <- data.frame(dates=1:10, email_reach=rbinom(10, 10, 0.5))

library(data.table)
setDT(email_data)[, paste0('email_reach', 1:3) := shift(email_reach, 1:3)][]

#   dates email_reach email_reach1 email_reach2 email_reach3
# 1:     1           4           NA           NA           NA
# 2:     2           4            4           NA           NA
# 3:     3           5            4            4           NA
# 4:     4           7            5            4            4
# 5:     5           4            7            5            4
# 6:     6           7            4            7            5
# 7:     7           7            7            4            7
# 8:     8           6            7            7            4
# 9:     9           6            6            7            7
#10:    10           3            6            6            7

答案 1 :(得分:3)

另一种方法是使用xts库。接下来是一个小例子,我们从:

开始
x <- ts(matrix(rnorm(100),ncol=2), start=c(2009, 1), frequency=12) 
head(x)
        Series 1   Series 2
[1,] -1.82934747 -0.1234372
[2,]  1.08371836  1.3365919
[3,]  0.95786815  0.0885484
[4,]  0.59301446 -0.6984993
[5,] -0.01094955 -0.3729762
[6,] -0.19256525  0.3137705

将其转换为xts,调用lag(),此处有0,1,2滞后以最小化输出:

library(xts)
head(lag(as.xts(x),0:2))
            Series.1   Series.2  Series.1.1 Series.2.1 Series.1.2 Series.2.2
jan 2009 -1.82934747 -0.1234372          NA         NA         NA         NA
feb 2009  1.08371836  1.3365919 -1.82934747 -0.1234372         NA         NA
mar 2009  0.95786815  0.0885484  1.08371836  1.3365919 -1.8293475 -0.1234372
apr 2009  0.59301446 -0.6984993  0.95786815  0.0885484  1.0837184  1.3365919
maj 2009 -0.01094955 -0.3729762  0.59301446 -0.6984993  0.9578682  0.0885484
jun 2009 -0.19256525  0.3137705 -0.01094955 -0.3729762  0.5930145 -0.6984993

答案 2 :(得分:2)

对于任何给定的n,我认为这与上面的代码相同。

n <- 7
for (i in 1:n) {
  email_data[[paste0("email_reach", i)]] <- lag(ts(email_data$email_reach, start = 1, end = 444), i)  
}

答案 3 :(得分:1)

基于Molx的答案,但是对于任何变量列表都进行了推广,并修补了一下......感谢Molx!

do_lag <- function(the_data, variables, num_periods) {
  num_vars <- length(variables)
  num_rows <- nrow(the_data)

  for (j in 1:num_vars) {
    for (i in 1:num_periods) {
      the_data[[paste0(variables[j], i)]] <- c(rep(NA, i), head(the_data[[variables[j]]], num_rows - i))
    }
  }

  return(the_data)
}

答案 4 :(得分:1)

这不是一个真正的答案,只是使用答案格式作为上述警告的详细说明:

email_data <- data.frame( email_reach=ts(email_data$email_reach, start = 1, end = 444))

然后你的代码就是你得到的:

> head(email_data, 10)
   email_reach email_reach1 email_reach2 email_reach3 email_reach4
1            4            4            4            4            4
2            4            4            4            4            4
3            5            5            5            5            5
4            7            7            7            7            7
5            4            4            4            4            4
6            7            7            7            7            7
7            7            7            7            7            7
8            6            6            6            6            6
9            6            6            6            6            6
10           3            3            3            3            3
   email_reach5 email_reach6 email_reach7
1             4            4            4
2             4            4            4
3             5            5            5
4             7            7            7
5             4            4            4
6             7            7            7
7             7            7            7
8             6            6            6
9             6            6            6
10            3            3            3

答案 5 :(得分:0)

collapse::flag提供了解决此问题的常规且快速(基于C ++)的解决方案:

library(collapse)
# Time-series (also supports xts and others)
head(flag(AirPassengers, -1:2))
##           F1  --  L1  L2
## Jan 1949 118 112  NA  NA
## Feb 1949 132 118 112  NA
## Mar 1949 129 132 118 112
## Apr 1949 121 129 132 118
## May 1949 135 121 129 132
## Jun 1949 148 135 121 129

# Time-series matrix
head(flag(EuStockMarkets, -1:2))
## Time Series:
## Start = c(1991, 130) 
## End = c(1998, 169) 
## Frequency = 260 
##           F1.DAX     DAX  L1.DAX  L2.DAX F1.SMI    SMI L1.SMI L2.SMI F1.CAC    CAC L1.CAC L2.CAC F1.FTSE   FTSE L1.FTSE L2.FTSE
## 1991.496 1613.63 1628.75      NA      NA 1688.5 1678.1     NA     NA 1750.5 1772.8     NA     NA  2460.2 2443.6      NA      NA
## 1991.500 1606.51 1613.63 1628.75      NA 1678.6 1688.5 1678.1     NA 1718.0 1750.5 1772.8     NA  2448.2 2460.2  2443.6      NA
## 1991.504 1621.04 1606.51 1613.63 1628.75 1684.1 1678.6 1688.5 1678.1 1708.1 1718.0 1750.5 1772.8  2470.4 2448.2  2460.2  2443.6
## 1991.508 1618.16 1621.04 1606.51 1613.63 1686.6 1684.1 1678.6 1688.5 1723.1 1708.1 1718.0 1750.5  2484.7 2470.4  2448.2  2460.2
## 1991.512 1610.61 1618.16 1621.04 1606.51 1671.6 1686.6 1684.1 1678.6 1714.3 1723.1 1708.1 1718.0  2466.8 2484.7  2470.4  2448.2
## 1991.515 1630.75 1610.61 1618.16 1621.04 1682.9 1671.6 1686.6 1684.1 1734.5 1714.3 1723.1 1708.1  2487.9 2466.8  2484.7  2470.4

# Data frame
head(flag(airquality[1:3], -1:2))
##   F1.Ozone Ozone L1.Ozone L2.Ozone F1.Solar.R Solar.R L1.Solar.R L2.Solar.R F1.Wind Wind L1.Wind L2.Wind
## 1       36    41       NA       NA        118     190         NA         NA     8.0  7.4      NA      NA
## 2       12    36       41       NA        149     118        190         NA    12.6  8.0     7.4      NA
## 3       18    12       36       41        313     149        118        190    11.5 12.6     8.0     7.4
## 4       NA    18       12       36         NA     313        149        118    14.3 11.5    12.6     8.0
## 5       28    NA       18       12         NA      NA        313        149    14.9 14.3    11.5    12.6
## 6       23    28       NA       18        299      NA         NA        313     8.6 14.9    14.3    11.5

# Panel lag
head(flag(iris[1:2], -1:2, iris$Species))
## Panel-lag computed without timevar: Assuming ordered data
##   F1.Sepal.Length Sepal.Length L1.Sepal.Length L2.Sepal.Length F1.Sepal.Width Sepal.Width L1.Sepal.Width L2.Sepal.Width
## 1             4.9          5.1              NA              NA            3.0         3.5             NA             NA
## 2             4.7          4.9             5.1              NA            3.2         3.0            3.5             NA
## 3             4.6          4.7             4.9             5.1            3.1         3.2            3.0            3.5
## 4             5.0          4.6             4.7             4.9            3.6         3.1            3.2            3.0
## 5             5.4          5.0             4.6             4.7            3.9         3.6            3.1            3.2
## 6             4.6          5.4             5.0             4.6            3.4         3.9            3.6            3.1

类似地,collapse::fdiffcollapse::fgrowth支持在(多元)时间序列和面板上适当地滞后/领先和迭代(准,对数)差异和增长率。