From 3824fbae54203264a2df6183ec27df1ee3c43c91 Mon Sep 17 00:00:00 2001 From: Tanguy BARTHELEMY Date: Mon, 6 May 2024 11:18:48 +0200 Subject: [PATCH 1/4] lint space if --- R/jd3_fractionalairline.R | 2 +- R/print.R | 4 ++-- R/zzz.R | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/R/jd3_fractionalairline.R b/R/jd3_fractionalairline.R index 7ac0351..8b064c9 100644 --- a/R/jd3_fractionalairline.R +++ b/R/jd3_fractionalairline.R @@ -226,7 +226,7 @@ fractionalAirlineEstimation <- function(y, o<-.jevalArray(var_out_names) nO<-length(o) - if(nO>0){ + if (nO>0){ regvar_outliers<-rep(NA,nX-nO) for(j in 1:nX-nO) { regvar_outliers[j]=paste("x-", j)} diff --git a/R/print.R b/R/print.R index e03c4f9..ac08a57 100644 --- a/R/print.R +++ b/R/print.R @@ -129,7 +129,7 @@ print.JDFractionalAirlineEstimation <- function(x, digits = max(3L, getOption("d cat("Number of calendar regressors:", nb_reg_cjo, ", Number of outliers :", nb_outliers) cat("\n\n") - if(nb_reg_cjo > 0) { + if (nb_reg_cjo > 0) { cat("TD regressors coefficients:") cat("\n") print(reg_cjo_coeff, row.names = FALSE) @@ -138,7 +138,7 @@ print.JDFractionalAirlineEstimation <- function(x, digits = max(3L, getOption("d cat("\n") } - if(nb_outliers > 0) { + if (nb_outliers > 0) { cat("Outliers coefficients:") cat("\n") print(outliers_coeff, row.names = FALSE) diff --git a/R/zzz.R b/R/zzz.R index 4f475b0..f9b1c27 100644 --- a/R/zzz.R +++ b/R/zzz.R @@ -2,7 +2,7 @@ #' @import rjd3sts .onLoad <- function(libname, pkgname) { - if (! requireNamespace("rjd3sts", quietly=TRUE)) stop("Loading rjd3 libraries failed") + if (!requireNamespace("rjd3sts", quietly = TRUE)) stop("Loading rjd3 libraries failed") result <- .jpackage(pkgname, lib.loc=libname) if (!result) stop("Loading java packages failed") From 0511d1c73c4b9b9e15ee38abf1592273c489b7c5 Mon Sep 17 00:00:00 2001 From: Tanguy BARTHELEMY Date: Mon, 6 May 2024 11:19:43 +0200 Subject: [PATCH 2/4] update rea --- README.Rmd | 4 ++-- README.md | 7 ++++++- 2 files changed, 8 insertions(+), 3 deletions(-) diff --git a/README.Rmd b/README.Rmd index bfd50ae..95491fd 100644 --- a/README.Rmd +++ b/README.Rmd @@ -25,7 +25,7 @@ High-frequency time series ## Installation -Running rjd3 packages requires Java 17 or higher. How to set up such a configuration in R is explained [here](https://jdemetra-new-documentation.netlify.app/#installing-the-software) +Running rjd3 packages requires Java 17 or higher. How to set up such a configuration in R is explained [here](https://jdemetra-new-documentation.netlify.app/#installing-the-software). You can install the development version of **rjd3highfreq** from [GitHub](https://github.com/) with: @@ -188,4 +188,4 @@ pull requests should include **updated tests** and **updated documentation**. If ## Licensing -The code of this project is licensed under the [European Union Public Licence (EUPL)](https://joinup.ec.europa.eu/page/eupl-text-11-12). +The code of this project is licensed under the [European Union Public Licence (EUPL)](https://joinup.ec.europa.eu/collection/eupl/eupl-text-eupl-12). diff --git a/README.md b/README.md index 6663185..aa2a74b 100644 --- a/README.md +++ b/README.md @@ -10,6 +10,10 @@ High-frequency time series ## Installation +Running rjd3 packages requires Java 17 or higher. How to set up such a +configuration in R is explained +[here](https://jdemetra-new-documentation.netlify.app/#installing-the-software). + You can install the development version of **rjd3highfreq** from [GitHub](https://github.com/) with: @@ -226,4 +230,5 @@ should be added or updated. ## Licensing The code of this project is licensed under the [European Union Public -Licence (EUPL)](https://joinup.ec.europa.eu/page/eupl-text-11-12). +Licence +(EUPL)](https://joinup.ec.europa.eu/collection/eupl/eupl-text-eupl-12). From 225b426da466d3dabbd488b8136e8cfa98358348 Mon Sep 17 00:00:00 2001 From: Tanguy BARTHELEMY Date: Mon, 6 May 2024 14:12:49 +0200 Subject: [PATCH 3/4] change rjdemetra3 --> rjd3workspace and rjdemetra --> rjdverse --- DESCRIPTION | 8 +- NEWS.md | 4 +- README.Rmd | 4 +- README.html | 773 +++++++++++++++++++++++++++++++++++++++++++++++++++ README.md | 4 +- _pkgdown.yml | 2 +- 6 files changed, 784 insertions(+), 11 deletions(-) create mode 100644 README.html diff --git a/DESCRIPTION b/DESCRIPTION index 371490b..9624137 100644 --- a/DESCRIPTION +++ b/DESCRIPTION @@ -16,17 +16,17 @@ Imports: checkmate, methods Remotes: - github::rjdemetra/rjd3toolkit, - github::rjdemetra/rjd3sts + github::rjdverse/rjd3toolkit, + github::rjdverse/rjd3sts SystemRequirements: Java (>= 17) License: EUPL -URL: https://github.com/rjdemetra/rjd3highfreq, https://rjdemetra.github.io/rjd3highfreq/ +URL: https://github.com/rjdverse/rjd3highfreq, https://rjdverse.github.io/rjd3highfreq/ LazyData: TRUE Suggests: knitr, rmarkdown RoxygenNote: 7.3.1 -BugReports: https://github.com/rjdemetra/rjd3highfreq/issues +BugReports: https://github.com/rjdverse/rjd3highfreq/issues Encoding: UTF-8 Collate: 'utils.R' diff --git a/NEWS.md b/NEWS.md index e20f740..9574aa9 100644 --- a/NEWS.md +++ b/NEWS.md @@ -22,5 +22,5 @@ to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). ## [2.0.0] - 2023-12-12 -[Unreleased]: https://github.com/rjdemetra/rjd3highfreq/compare/v2.0.0...HEAD -[2.0.0]: https://github.com/rjdemetra/rjd3highfreq/releases/tag/v2.0.0 +[Unreleased]: https://github.com/rjdverse/rjd3highfreq/compare/v2.0.0...HEAD +[2.0.0]: https://github.com/rjdverse/rjd3highfreq/releases/tag/v2.0.0 diff --git a/README.Rmd b/README.Rmd index bc90040..f24784c 100644 --- a/README.Rmd +++ b/README.Rmd @@ -32,7 +32,7 @@ You can install the development version of **rjd3highfreq** from [GitHub](https: ```{r, eval = FALSE} # Install development version from GitHub # install.packages("remotes") -remotes::install_github("rjdemetra/rjd3highfreq") +remotes::install_github("rjdverse/rjd3highfreq") ``` @@ -177,7 +177,7 @@ plot(amb.multi, main = "2012", ``` -With the package [**rjd3x11plus**](https://github.com/rjdemetra/rjd3x11plus), you can perform an X-11 like decomposition with any (non integer) periodicity. +With the package [**rjd3x11plus**](https://github.com/rjdverse/rjd3x11plus), you can perform an X-11 like decomposition with any (non integer) periodicity. ## Package Maintenance and contributing diff --git a/README.html b/README.html new file mode 100644 index 0000000..65bffdb --- /dev/null +++ b/README.html @@ -0,0 +1,773 @@ + + + + + + + + + + + + + + + + + + + + + +

rjd3highfreq

+ + + + +

rjd3highfreq provides functions for seasonal adjustment of +high-frequency data displaying multiple, non integer periodicities. +Pre-adjustment with extended airline model and Arima Model Based +decomposition.

+

Installation

+

Running rjd3 packages requires Java 17 or higher. +How to set up such a configuration in R is explained here

+

You can install the development version of +rjd3highfreq from GitHub with:

+
# Install development version from GitHub
+# install.packages("remotes")
+remotes::install_github("rjdverse/rjd3highfreq")
+

Demonstration with +the daily french births

+
library("rjd3highfreq")
+
## Import of data
+df_daily <- read.csv2("https://raw.githubusercontent.com/TanguyBarthelemy/Tsace_RJD_Webinar_Dec22/b5fcf6b14ae47393554950547ef4788a0068a0f6/Data/TS_daily_births_franceM_1968_2020.csv")
+
+# Creation of log variables to multiplicative model
+df_daily$log_births <- log(df_daily$births)
+df_daily$date <- as.Date(df_daily$date)
+

Plot of the raw series:

+ + +

Preparation of the calendar with the package +rjd3toolkit:

+
# French calendar
+frenchCalendar <- rjd3toolkit::national_calendar(days = list(
+  rjd3toolkit::fixed_day(7, 14), # Bastille Day
+  rjd3toolkit::fixed_day(5, 8, validity = list(start = "1982-05-08")), # End of 2nd WW
+  rjd3toolkit::special_day('NEWYEAR'),
+  rjd3toolkit::special_day('MAYDAY'), # 1st may
+  rjd3toolkit::special_day('EASTERMONDAY'),
+  rjd3toolkit::special_day('ASCENSION'),
+  rjd3toolkit::special_day('WHITMONDAY'),
+  rjd3toolkit::special_day('ASSUMPTION'),
+  rjd3toolkit::special_day('ALLSAINTSDAY'), # Toussaint
+  rjd3toolkit::special_day('ARMISTICE'), # End of 1st WW
+  rjd3toolkit::special_day('CHRISTMAS'))
+)
+

Creation of the calendar regressor in a matrix with the package +rjd3toolkit:

+
# Calendar regressor matrix
+cal_reg <- rjd3toolkit::holidays(
+    calendar = frenchCalendar,
+    start = "1968-01-01", length = nrow(df_daily),
+    type = "All", nonworking = 7L)
+
+colnames(cal_reg) <- c("14th_july", "8th_may", "1st_jan", "1st_may",
+                       "east_mon", "asc", "pen_mon",
+                       "15th_aug", "1st_nov", "11th_nov", "Xmas")
+

Preprocessing with the function +fractionalAirlineEstimation:

+
pre_pro <- fractionalAirlineEstimation(
+    y = df_daily$births,
+    x = cal_reg,
+    periods = 7, # weekly frequency
+    outliers = c("ao", "wo"), log = TRUE, y_time = df_daily$date)
+
+print(pre_pro)
+#> Number of observations: 19359
+#> Start: 1968-01-01 
+#> End: 2020-12-31 
+#> 
+#> Estimate MA parameters:
+#>       MA_parameter      Coef     Coef_SE    Tstat
+#>           Theta(1) 0.7620698 0.005571472 136.7807
+#>  Theta(period = 7) 0.9731793 0.001413477 688.5002
+#> 
+#> Number of calendar regressors: 11 , Number of outliers : 7
+#> 
+#> TD regressors coefficients:
+#>   Variable    Coef Coef_SE    Tstat
+#>  14th_july -0.1226  0.0047 -26.0615
+#>    8th_may -0.1419  0.0054 -26.3419
+#>    1st_jan -0.2223  0.0047 -47.3511
+#>    1st_may -0.1225  0.0047 -26.2643
+#>   east_mon -0.1891  0.0046 -40.7635
+#>        asc -0.1726  0.0046 -37.1949
+#>    pen_mon -0.1900  0.0046 -40.9429
+#>   15th_aug -0.1181  0.0047 -25.3461
+#>    1st_nov -0.1503  0.0046 -32.5662
+#>   11th_nov -0.1238  0.0046 -26.8142
+#>       Xmas -0.2310  0.0046 -49.7435
+#> 
+#> Outliers coefficients:
+#>       Variable    Coef Coef_SE   Tstat
+#>  WO.1999-12-31 -0.1762  0.0226 -7.7916
+#>  AO.1995-08-15 -0.2224  0.0340 -6.5503
+#>  WO.1999-12-24 -0.1447  0.0226 -6.3981
+#>  AO.2012-01-01  0.2098  0.0340  6.1786
+#>  AO.1998-07-14 -0.2101  0.0340 -6.1880
+#>  AO.1997-07-14 -0.2092  0.0340 -6.1602
+#>  AO.1995-05-01 -0.2042  0.0340 -6.0146
+#> 
+#> Sum of square residuals: 25.17 on 19330 degrees of freedom
+#> Log likelihood = 3.682e+04, 
+#>  aic = -7.361e+04, 
+#>  aicc = -7.361e+04, 
+#>  bic(corrected for length) = -6.635
+#> Hannan–Quinn information criterion = -7.355e+04
+
plot(pre_pro, main = "French births")
+ + +
plot(x = pre_pro,
+     from = as.Date("2000-01-01"), to = as.Date("2000-12-31"),
+     main = "French births in 2000")
+ + +

Decomposition with the AMB (Arima Model Based) algorithm:

+
# Decomposition with weekly pattern
+amb.dow <- rjd3highfreq::fractionalAirlineDecomposition(
+    y = pre_pro$model$linearized, # linearized series from preprocessing
+    period = 7,
+    log = TRUE, y_time = df_daily$date)
+
+# Extract day-of-year pattern from day-of-week-adjusted linearised data
+amb.doy <- rjd3highfreq::fractionalAirlineDecomposition(
+    y = amb.dow$decomposition$sa, # DOW-adjusted linearised data
+    period = 365.2425, # day of year pattern
+    log = TRUE, y_time = df_daily$date)
+

Plot:

+
plot(amb.dow, main = "Weekly pattern")
+

+
plot(amb.dow, main = "Weekly pattern - January 2018",
+     from = as.Date("2018-01-01"),
+     to = as.Date("2018-01-31"))
+

+
plot(amb.doy, main = "Yearly pattern")
+

+
plot(amb.doy, main = "Weekly pattern - 2000 - 2002",
+     from = as.Date("2000-01-01"),
+     to = as.Date("2002-12-31"))
+

+

Perform an Arima Model Based (AMB) decomposition on several +periodcities at once:

+
amb.multi <- rjd3highfreq::multiAirlineDecomposition(
+  y = pre_pro$model$linearized, # input time series
+  periods = c(7, 365.2425), # 2 frequency
+  log = TRUE, y_time = df_daily$date)
+

Plot the comparison between the two AMB methods for the annual +periodicity:

+
plot(amb.multi)
+

+
plot(amb.multi, main = "2012",
+     from = as.Date("2012-01-01"),
+     to = as.Date("2012-12-31"))
+

+

With the package rjd3x11plus, +you can perform an X-11 like decomposition with any (non integer) +periodicity.

+

Package Maintenance and +contributing

+

Any contribution is welcome and should be done through pull requests +and/or issues. pull requests should include updated +tests and updated documentation. If +functionality is changed, docstrings should be added or updated.

+

Licensing

+

The code of this project is licensed under the European +Union Public Licence (EUPL).

+ + + diff --git a/README.md b/README.md index e9192b3..f09bb49 100644 --- a/README.md +++ b/README.md @@ -23,7 +23,7 @@ You can install the development version of **rjd3highfreq** from ``` r # Install development version from GitHub # install.packages("remotes") -remotes::install_github("rjdemetra/rjd3highfreq") +remotes::install_github("rjdverse/rjd3highfreq") ``` ## Demonstration with the daily french births @@ -220,7 +220,7 @@ plot(amb.multi, main = "2012", With the package -[**rjd3x11plus**](https://github.com/rjdemetra/rjd3x11plus), you can +[**rjd3x11plus**](https://github.com/rjdverse/rjd3x11plus), you can perform an X-11 like decomposition with any (non integer) periodicity. ## Package Maintenance and contributing diff --git a/_pkgdown.yml b/_pkgdown.yml index 70a7bc2..ac6f981 100644 --- a/_pkgdown.yml +++ b/_pkgdown.yml @@ -1,4 +1,4 @@ -url: https://rjdemetra.github.io/rjd3highfreq/ +url: https://rjdverse.github.io/rjd3highfreq/ template: bootstrap: 5 From a0178eb289f50c44c04c7c98a8ff9fbd3b3dd2c8 Mon Sep 17 00:00:00 2001 From: Tanguy BARTHELEMY Date: Tue, 7 May 2024 14:21:09 +0200 Subject: [PATCH 4/4] harmonisation of .gitignore and .Rbuildignore --- .Rbuildignore | 28 +- .gitignore | 54 +++- README.html | 773 -------------------------------------------------- 3 files changed, 74 insertions(+), 781 deletions(-) delete mode 100644 README.html diff --git a/.Rbuildignore b/.Rbuildignore index cbad3e9..89416d3 100644 --- a/.Rbuildignore +++ b/.Rbuildignore @@ -1,9 +1,27 @@ ^.*\.Rproj$ ^\.Rproj\.user$ -^README.Rmd$ -^_pkgdown\.yml$ + +^\.git$ +^\.github$ + +^README\.Rmd$ +^README-.*\.png$ + +^Meta$ ^docs$ +^doc$ ^pkgdown$ -^\.github$ -^LICENSE$ -^.lintr$ +^_pkgdown\.yml$ + +^\.lintr$ + +^appveyor\.yml$ +.travis.yml + +cran-comments.md + +^\.DS_Store$ + +^revdep$ +^reconf\.sh$ +^rjd3toolkit-java-deps\.xml$ diff --git a/.gitignore b/.gitignore index f87d9b5..de7c8b2 100644 --- a/.gitignore +++ b/.gitignore @@ -1,7 +1,55 @@ -.Rproj.user +# History files .Rhistory +.Rapp.history + +# Session Data files .RData +.RDataTmp + +# User-specific files .Ruserdata -TO_DO -docs +# Example code in package build process +*-Ex.R + +# Output files from R CMD build +/*.tar.gz + +# Output files from R CMD check +/*.Rcheck/ + +# RStudio files +.Rproj.user/ + +# produced vignettes +vignettes/*.html +vignettes/*.pdf +Meta/ +inst/doc/ +doc/ + +# OAuth2 token, see https://github.com/hadley/httr/releases/tag/v0.3 +.httr-oauth + +# knitr and R markdown default cache directories +*_cache/ +/cache/ + +# Temporary files created by R markdown +*.utf8.md +*.knit.md + +# R Environment Variables +.Renviron + +# pkgdown site +docs/ + +# translation temp files +po/*~ + +# RStudio Connect folder +rsconnect/ + +# Hidden file from mac-os +.DS_Store diff --git a/README.html b/README.html deleted file mode 100644 index 65bffdb..0000000 --- a/README.html +++ /dev/null @@ -1,773 +0,0 @@ - - - - - - - - - - - - - - - - - - - - - -

rjd3highfreq

- - - - -

rjd3highfreq provides functions for seasonal adjustment of -high-frequency data displaying multiple, non integer periodicities. -Pre-adjustment with extended airline model and Arima Model Based -decomposition.

-

Installation

-

Running rjd3 packages requires Java 17 or higher. -How to set up such a configuration in R is explained here

-

You can install the development version of -rjd3highfreq from GitHub with:

-
# Install development version from GitHub
-# install.packages("remotes")
-remotes::install_github("rjdverse/rjd3highfreq")
-

Demonstration with -the daily french births

-
library("rjd3highfreq")
-
## Import of data
-df_daily <- read.csv2("https://raw.githubusercontent.com/TanguyBarthelemy/Tsace_RJD_Webinar_Dec22/b5fcf6b14ae47393554950547ef4788a0068a0f6/Data/TS_daily_births_franceM_1968_2020.csv")
-
-# Creation of log variables to multiplicative model
-df_daily$log_births <- log(df_daily$births)
-df_daily$date <- as.Date(df_daily$date)
-

Plot of the raw series:

- - -

Preparation of the calendar with the package -rjd3toolkit:

-
# French calendar
-frenchCalendar <- rjd3toolkit::national_calendar(days = list(
-  rjd3toolkit::fixed_day(7, 14), # Bastille Day
-  rjd3toolkit::fixed_day(5, 8, validity = list(start = "1982-05-08")), # End of 2nd WW
-  rjd3toolkit::special_day('NEWYEAR'),
-  rjd3toolkit::special_day('MAYDAY'), # 1st may
-  rjd3toolkit::special_day('EASTERMONDAY'),
-  rjd3toolkit::special_day('ASCENSION'),
-  rjd3toolkit::special_day('WHITMONDAY'),
-  rjd3toolkit::special_day('ASSUMPTION'),
-  rjd3toolkit::special_day('ALLSAINTSDAY'), # Toussaint
-  rjd3toolkit::special_day('ARMISTICE'), # End of 1st WW
-  rjd3toolkit::special_day('CHRISTMAS'))
-)
-

Creation of the calendar regressor in a matrix with the package -rjd3toolkit:

-
# Calendar regressor matrix
-cal_reg <- rjd3toolkit::holidays(
-    calendar = frenchCalendar,
-    start = "1968-01-01", length = nrow(df_daily),
-    type = "All", nonworking = 7L)
-
-colnames(cal_reg) <- c("14th_july", "8th_may", "1st_jan", "1st_may",
-                       "east_mon", "asc", "pen_mon",
-                       "15th_aug", "1st_nov", "11th_nov", "Xmas")
-

Preprocessing with the function -fractionalAirlineEstimation:

-
pre_pro <- fractionalAirlineEstimation(
-    y = df_daily$births,
-    x = cal_reg,
-    periods = 7, # weekly frequency
-    outliers = c("ao", "wo"), log = TRUE, y_time = df_daily$date)
-
-print(pre_pro)
-#> Number of observations: 19359
-#> Start: 1968-01-01 
-#> End: 2020-12-31 
-#> 
-#> Estimate MA parameters:
-#>       MA_parameter      Coef     Coef_SE    Tstat
-#>           Theta(1) 0.7620698 0.005571472 136.7807
-#>  Theta(period = 7) 0.9731793 0.001413477 688.5002
-#> 
-#> Number of calendar regressors: 11 , Number of outliers : 7
-#> 
-#> TD regressors coefficients:
-#>   Variable    Coef Coef_SE    Tstat
-#>  14th_july -0.1226  0.0047 -26.0615
-#>    8th_may -0.1419  0.0054 -26.3419
-#>    1st_jan -0.2223  0.0047 -47.3511
-#>    1st_may -0.1225  0.0047 -26.2643
-#>   east_mon -0.1891  0.0046 -40.7635
-#>        asc -0.1726  0.0046 -37.1949
-#>    pen_mon -0.1900  0.0046 -40.9429
-#>   15th_aug -0.1181  0.0047 -25.3461
-#>    1st_nov -0.1503  0.0046 -32.5662
-#>   11th_nov -0.1238  0.0046 -26.8142
-#>       Xmas -0.2310  0.0046 -49.7435
-#> 
-#> Outliers coefficients:
-#>       Variable    Coef Coef_SE   Tstat
-#>  WO.1999-12-31 -0.1762  0.0226 -7.7916
-#>  AO.1995-08-15 -0.2224  0.0340 -6.5503
-#>  WO.1999-12-24 -0.1447  0.0226 -6.3981
-#>  AO.2012-01-01  0.2098  0.0340  6.1786
-#>  AO.1998-07-14 -0.2101  0.0340 -6.1880
-#>  AO.1997-07-14 -0.2092  0.0340 -6.1602
-#>  AO.1995-05-01 -0.2042  0.0340 -6.0146
-#> 
-#> Sum of square residuals: 25.17 on 19330 degrees of freedom
-#> Log likelihood = 3.682e+04, 
-#>  aic = -7.361e+04, 
-#>  aicc = -7.361e+04, 
-#>  bic(corrected for length) = -6.635
-#> Hannan–Quinn information criterion = -7.355e+04
-
plot(pre_pro, main = "French births")
- - -
plot(x = pre_pro,
-     from = as.Date("2000-01-01"), to = as.Date("2000-12-31"),
-     main = "French births in 2000")
- - -

Decomposition with the AMB (Arima Model Based) algorithm:

-
# Decomposition with weekly pattern
-amb.dow <- rjd3highfreq::fractionalAirlineDecomposition(
-    y = pre_pro$model$linearized, # linearized series from preprocessing
-    period = 7,
-    log = TRUE, y_time = df_daily$date)
-
-# Extract day-of-year pattern from day-of-week-adjusted linearised data
-amb.doy <- rjd3highfreq::fractionalAirlineDecomposition(
-    y = amb.dow$decomposition$sa, # DOW-adjusted linearised data
-    period = 365.2425, # day of year pattern
-    log = TRUE, y_time = df_daily$date)
-

Plot:

-
plot(amb.dow, main = "Weekly pattern")
-

-
plot(amb.dow, main = "Weekly pattern - January 2018",
-     from = as.Date("2018-01-01"),
-     to = as.Date("2018-01-31"))
-

-
plot(amb.doy, main = "Yearly pattern")
-

-
plot(amb.doy, main = "Weekly pattern - 2000 - 2002",
-     from = as.Date("2000-01-01"),
-     to = as.Date("2002-12-31"))
-

-

Perform an Arima Model Based (AMB) decomposition on several -periodcities at once:

-
amb.multi <- rjd3highfreq::multiAirlineDecomposition(
-  y = pre_pro$model$linearized, # input time series
-  periods = c(7, 365.2425), # 2 frequency
-  log = TRUE, y_time = df_daily$date)
-

Plot the comparison between the two AMB methods for the annual -periodicity:

-
plot(amb.multi)
-

-
plot(amb.multi, main = "2012",
-     from = as.Date("2012-01-01"),
-     to = as.Date("2012-12-31"))
-

-

With the package rjd3x11plus, -you can perform an X-11 like decomposition with any (non integer) -periodicity.

-

Package Maintenance and -contributing

-

Any contribution is welcome and should be done through pull requests -and/or issues. pull requests should include updated -tests and updated documentation. If -functionality is changed, docstrings should be added or updated.

-

Licensing

-

The code of this project is licensed under the European -Union Public Licence (EUPL).

- - -