我有一个在很长一段时间内发生的序列。我尝试了 8 种不同的算法来对我的序列进行分类(OM、CHi2、...)。时间从 1 到 123。我有 110 个个人和 8 个事件。
我的结果并不像预期的那样。首先,它非常难以阅读。其次,一个类别包含太多的代表序列(group3)。第三,每组的序列数量确实不平衡。
这可能是因为我的时间变量的范围为 123。我搜索了时间范围过长存在问题的文章。我在 Sabherwal 和 Robey(1993 年)以及 Shi 和 Prescott(2011 年)中读到,您可以通过将所需的转换数量除以较长序列的长度来标准化“每个序列”。我怎么能在 R 中做到这一点?
请在下面找到我的数据描述:
library(TraMineRextras)
head(seq.tse.data)
seq.tse.data <- structure(list(
ID = c(1L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L,
4L, 4L, 4L, 5L, 5L, 5L, 6L, 6L, 6L, 6L, 6L, 6L,
6L, 6L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L),
Year = c(2008L, 2010L, 2012L, 2007L, 2009L, 2010L, 2012L,
2013L, 1996L, 1997L, 1999L, 2003L, 2006L, 2008L,
2012L, 2007L, 2007L, 2008L, 2003L, 2007L, 2007L,
2009L, 2009L, 2011L, 2014L, 2016L, 2006L, 2009L,
2011L, 2013L, 2013L, 2015L, 2015L, 2016L),
Event = c(5L, 4L, 5L, 3L, 1L, 5L, 5L, 5L, 3L,3L,3L,3L,3L,5L, 1L, 5L,
5L,5L,4L,5L, 5L, 5L, 5L, 5L, 5L,5L,5L,5L, 4L, 4L, 1L, 4L, 1L,5L)),
class = "data.frame", row.names = c(NA, -34L)
)
seq.sts <- TSE_to_STS(seq.tse.data,
id = 1, timestamp = 2, event = 3,
stm =NULL, tmin = 1935, tmax = 2018,
firstState = "None")
seq.SPS <- seqformat(seq.sts, 1:84, from = "STS", to = "SPS")
seq.obj <- seqdef(seq.SPS)
> head(seq.tse.data)
ID Year Event
1 1 2008 5
2 2 2010 4
3 2 2012 5
4 3 2007 3
5 3 2009 1
6 3 2010 5
> head(seq.obj)
Sequence
[1] (None,74)-(5,10)-1
[2] (None,76)-(4,2)-(5.4,6)-2
[3] (None,73)-(3,2)-(3.1,1)-(5.3.1,8)-3
[4] (None,62)-(3,12)-(5.3,4)-(5.3.1,6)-3
[5] (None,73)-(5,11)-1
[6] (None,69)-(4,4)-(5.4,11)-2
> head(alphabet(seq.obj),10)
[1] "(1,1)" "(1,10)" "(1,11)" "(1,12)" "(1,14)" "(1,19)" "(1,2)" "(1,21)" "(1,25)" "(1,3)"
...
[145] "(5.4.3.1,5)" "(5.4.3.1,6)" "(5.4.3.1,7)" "(5.4.3.1,8)" "(5.4.3.1.2,9)" "(None,1)" "(None,11)" "(None,20)"
[153] "(None,26)" "(None,30)" "(None,38)" "(None,41)" "(None,42)" "(None,44)" "(None,45)" "(None,49)"
[161] "(None,51)" "(None,53)" "(None,55)" "(None,57)" "(None,58)" "(None,59)" "(None,60)" "(None,61)"
[169] "(None,62)" "(None,64)" "(None,65)" "(None,66)" "(None,67)" "(None,68)" "(None,69)" "(None,7)"
[177] "(None,70)" "(None,71)" "(None,72)" "(None,73)" "(None,74)" "(None,75)" "(None,76)" "(None,77)"
[185] "(None,78)" "(None,79)"
提前致谢,
安东宁