I am running into an error when using GTS to specify two hierarchy groups. The error is:
Error in
colnames<-
(*tmp*
, value = unlist(labels[levels])) :
length of 'dimnames' [2] not equal to array extent
I've recreated the issue with the below code. In this example, there are two hierarchies State/County and Industry/Sub-industry/product. The State/County is constant in this example - this may or may not be true in my actual data set.
y3 <- ts(matrix(rnorm(25),ncol=5,nrow=5))
blnames3 <- paste(rep("CA",5), # State
rep("AL",5), # County
rep("O",5), # Industry
c("P","Q","Q","P","R"), # Sub-industry
c("514","807","514","807","807"), # product
sep="")
colnames(y3) <- blnames3
head(y3)
gy3 <- gts(y3, characters=list(c(2,2),c(1,1,3)))
fc3 <- forecast(gy3, h = 6, method = "comb", fmethod="ets")
If I use a different method such as bu, the forecast function returns successfully but any subsequent operations such as allts fails with the same error.
fc3 <- forecast(gy3, h = 6, method = "bu", fmethod="ets")
allts(fc3)
I have used gts
a few times, but don't claim to know everything about the package. But hopefully this will help.
I think what is happening is that your gts
object is specifying a hierarchy that doesn't exist in your data. The first vector in your list is c(2,2)
which would indicate that State/County is a hierarchy level. However, all of the states and counties are the same in your data, so this isn't really a hierarchy.
Then your second hierarchy consists of c(1,1,3)
but Industry is always constant, leaving you with just Sub-Industry and Product changing.
In summary, this does not look like a hierarchical series. I noticed that the labels in gy3
have many NA
's
gy3$labels
$G1
[1] "G1/CA"
$<NA>
[1] "G1/CAAL"
$<NA>
[1] "G1/O"
$<NA>
[1] "G1/OP" "G1/OQ" "G1/OR"
$<NA>
[1] "G1/OP514" "G1/OQ807" "G1/OQ514" "G1/OP807" "G1/OR807"
$<NA>
[1] "G1/CAO"
$<NA>
[1] "G1/CAOP" "G1/CAOQ" "G1/CAOR"
$<NA>
[1] "G1/CAOP514" "G1/CAOQ807" "G1/CAOQ514" "G1/CAOP807" "G1/CAOR807"
$<NA>
[1] "G1/CAALO"
$<NA>
[1] "G1/CAALOP" "G1/CAALOQ" "G1/CAALOR"
Tracing through the code, this seems to cause an issue with aggts
aggts(gy3)
Error in `colnames<-`(`*tmp*`, value = unlist(labels[levels])) :
length of 'dimnames' [2] not equal to array extent
aggts
is called when you specify a comb
method, which requires a hierarchical series. bu
does not fail, because it is bottoms-up, which does not require a hierarchy.
Long-story short, one way to correct your code would be to specify a vector of c(6, 3)
encompassing the sub-industry in one group and product in the other.
gy3 <- gts(y3, characters=c(6, 3))
fc3 <- forecast(gy3, h = 6, method = "comb", fmethod="ets")
fc3
Grouped Time Series
4 Levels
Number of groups at each level: 1 3 2 5
Total number of series: 11
Number of observations in each historical series: 5
Number of forecasts per series: 6
Top level series of forecasts:
Time Series:
Start = 6
End = 11
Frequency = 1
[1] -0.5835628 -0.5835628 -0.5835628 -0.5835628 -0.5835628 -0.5835628
This works too
fc3 <- forecast(gy3, h = 6, method = "bu", fmethod="ets")
allts(fc3)
Time Series:
Start = 6
End = 11
Frequency = 1
Total G1/CAALOP G1/CAALOQ G1/CAALOR G2/514 G2/807 CAALOP514 CAALOQ807 CAALOQ514 CAALOP807 CAALOR807
6 -0.6227325 0.0344344 -0.8919916 0.2348247 -0.02331766 -0.5994149 0.2459208 -0.6227531 -0.2692384 -0.2114864 0.2348247
7 -0.6227325 0.0344344 -0.8919916 0.2348247 -0.02331766 -0.5994149 0.2459208 -0.6227531 -0.2692384 -0.2114864 0.2348247
8 -0.6227325 0.0344344 -0.8919916 0.2348247 -0.02331766 -0.5994149 0.2459208 -0.6227531 -0.2692384 -0.2114864 0.2348247
9 -0.6227325 0.0344344 -0.8919916 0.2348247 -0.02331766 -0.5994149 0.2459208 -0.6227531 -0.2692384 -0.2114864 0.2348247
10 -0.6227325 0.0344344 -0.8919916 0.2348247 -0.02331766 -0.5994149 0.2459208 -0.6227531 -0.2692384 -0.2114864 0.2348247
11 -0.6227325 0.0344344 -0.8919916 0.2348247 -0.02331766 -0.5994149 0.2459208 -0.6227531 -0.2692384 -0.2114864 0.2348247