Closed niklaag closed 3 years ago
Hello,
It comes from the fact that the function tramoseats
produces a formatted output with a lot of indicators and the extraction of one of them gives you an error. A workaround is to use the jtramoseats
function that only returns a java object and to use the function get_indicators
to get the variables you want. The function get_dictionary
gives you all the parameters that you can export. Below an example to export the irregular component.
library(RJDemetra)
y <- ts(c(93, 92, 91, 87, 91, 93, 94, 99, 103, 106, 111, 112,
110, 108, 111, 111, 112, 114, 110, 95, 100, 103, 100, 99, 98,
100, 101, 103, 104, 104),start = 1990)
mod <- jtramoseats(y)
get_indicators(mod, "i")
#> $i
#> Time Series:
#> Start = 1990
#> End = 2019
#> Frequency = 1
#> [1] 1.0026792 1.0000024 1.0085145 0.9777485 1.0057924 1.0027378 0.9897434
#> [8] 1.0030314 1.0027013 0.9956372 1.0092964 1.0067423 1.0000555 0.9886013
#> [15] 1.0068459 0.9977333 0.9977926 1.0134165 0.9928425 0.8661731 0.9090189
#> [22] 0.9457237 0.9471534 0.9660163 0.9686838 0.9856985 0.9858016 0.9941756
#> [29] 0.9965835 0.9956195
head(get_dictionary(mod), 10)
#> [1] "y" "y_f" "t" "t_f" "sa" "sa_f" "s" "s_f" "i" "i_f"
Created on 2021-03-16 by the reprex package (v1.0.0)
Hello, I have a small issue related to annual data.
In one of my projects I'm interested in using RJDemetra to estimate the irregular component in annual time series. However, when I'm trying to specify the model, I get the following error message:
Error in .jcall(rslt, "Ljava/lang/Object;", "getData", name, rjdemetra_java$clobject) : java.lang.NullPointerException
Here's a short snip of the code preceding the problem. The problem occurs when I try to specify x1 below.
`rm(list = ls())
library(rJava) library(readxl) library(xlsx) library(RJDemetra)
dataset <- read_excel("r_input2.xlsx", col_names = TRUE)
s <- ts(dataset, start=c(2020-dim(dataset)[1]), frequency=1)
myspec <- tramoseats_spec(spec = c("RSA3"), outlier.enabled = TRUE, outlier.ao = TRUE, outlier.ls = FALSE, outlier.tc = FALSE, transform.function = c("Log"), )
x1 <- tramoseats(s[, "x1"], spec = myspec)`
When I tried this in NbDemetra it worked fine. I also reinstalled R and RStudios and tried with the latest devtools version available.
Thanks.