Giter VIP home page Giter VIP logo

danigiro / foreco Goto Github PK

View Code? Open in Web Editor NEW
30.0 2.0 5.0 14.27 MB

Forecast Reconciliation - Classical (bottom-up), optimal and heuristic combination forecast reconciliation procedures for cross-sectional, temporal, and cross-temporal linearly constrained time series.

Home Page: https://danigiro.github.io/FoReco/

License: GNU General Public License v3.0

R 96.48% SCSS 0.65% TeX 2.88%
forecasting reconciliation r cran time-series

foreco's Issues

Release FoReco 0.2.6

Prepare for release:

  • git pull
  • Check current CRAN check results
  • Polish NEWS
  • devtools::build_readme()
  • urlchecker::url_check()
  • devtools::check(remote = TRUE, manual = TRUE)
  • devtools::check_win_devel()
  • rhub::check_for_cran()
  • revdepcheck::revdep_check(num_workers = 4)
  • Update cran-comments.md
  • git push

Submit to CRAN:

  • usethis::use_version('patch')
  • devtools::submit_cran()
  • Approve email

Wait for CRAN...

  • Accepted 🎉
  • git push
  • usethis::use_github_release()
  • usethis::use_dev_version()
  • git push

`htsrec` function doesn't work as intended when `nn = TRUE` and `nn_type = "osqp"`

Please see below.

library(hts)
#> Loading required package: forecast
#> Registered S3 method overwritten by 'quantmod':
#>   method            from
#>   as.zoo.data.frame zoo
library(FoReco)
#> Warning: package 'FoReco' was built under R version 4.3.3
#> Loading required package: Matrix
#> Loading required package: osqp
#> Warning: package 'osqp' was built under R version 4.3.3
#> ──────────────────────────────────────────────────────────────── FoReco 0.2.6 ──
set.seed(123)
abc <- ts(0.5 + matrix(sort(rnorm(200)), ncol = 4, nrow = 50))
nodes <- list(2, c(2, 2))
y <- hts(abc, nodes = nodes)
#> Since argument characters are not specified, the default labelling system is used.
h <- 12
ally <- aggts(y)
n <- nrow(ally)
p <- ncol(ally)
allf <- matrix(NA,nrow = h,ncol = ncol(ally))
for(i in 1:p)
{
  fit <- auto.arima(ally[, i])
  allf[, i] <- forecast(fit, h = h)$mean
}
htsrec(allf, comb = "ols", C = smatrix(y)[1:3,], keep = "recf", nn = FALSE)
#>       serie1     serie2   serie3     serie4    serie5    serie6   serie7
#> h1  5.294030 0.28844210 5.005588 -0.1386732 0.4271153 1.0532083 3.952380
#> h2  5.473805 0.26662846 5.207177 -0.1490871 0.4157156 1.0434417 4.163735
#> h3  5.653610 0.24486500 5.408745 -0.1597520 0.4046170 1.0336652 4.375080
#> h4  5.833394 0.22306733 5.610327 -0.1702386 0.3933059 1.0238954 4.586432
#> h5  6.013193 0.20129296 5.811900 -0.1808519 0.3821448 1.0141210 4.797779
#> h6  6.192981 0.17950274 6.013479 -0.1913751 0.3708778 1.0043498 5.009129
#> h7  6.372777 0.15772329 6.215053 -0.2019623 0.3596856 0.9945764 5.220477
#> h8  6.552567 0.13593653 6.416631 -0.2125041 0.3484406 0.9848045 5.431826
#> h9  6.732361 0.11415473 6.618206 -0.2230781 0.3372329 0.9750316 5.643175
#> h10 6.912153 0.09236957 6.819783 -0.2336292 0.3259988 0.9652594 5.854524
#> h11 7.091946 0.07058668 7.021359 -0.2441967 0.3147833 0.9554867 6.065873
#> h12 7.271738 0.04880226 7.222936 -0.2547525 0.3035547 0.9457143 6.277222
combinef(allf, nodes = nodes, nonnegative = FALSE, keep = "all")
#>           [,1]       [,2]     [,3]       [,4]      [,5]      [,6]     [,7]
#>  [1,] 5.294030 0.28844210 5.005588 -0.1386732 0.4271153 1.0532083 3.952380
#>  [2,] 5.473805 0.26662846 5.207177 -0.1490871 0.4157156 1.0434417 4.163735
#>  [3,] 5.653610 0.24486500 5.408745 -0.1597520 0.4046170 1.0336652 4.375080
#>  [4,] 5.833394 0.22306733 5.610327 -0.1702386 0.3933059 1.0238954 4.586432
#>  [5,] 6.013193 0.20129296 5.811900 -0.1808519 0.3821448 1.0141210 4.797779
#>  [6,] 6.192981 0.17950274 6.013479 -0.1913751 0.3708778 1.0043498 5.009129
#>  [7,] 6.372777 0.15772329 6.215053 -0.2019623 0.3596856 0.9945764 5.220477
#>  [8,] 6.552567 0.13593653 6.416631 -0.2125041 0.3484406 0.9848045 5.431826
#>  [9,] 6.732361 0.11415473 6.618206 -0.2230781 0.3372329 0.9750316 5.643175
#> [10,] 6.912153 0.09236957 6.819783 -0.2336292 0.3259988 0.9652594 5.854524
#> [11,] 7.091946 0.07058668 7.021359 -0.2441967 0.3147833 0.9554867 6.065873
#> [12,] 7.271738 0.04880226 7.222936 -0.2547525 0.3035547 0.9457143 6.277222
htsrec(allf, comb = "ols", C = smatrix(y)[1:3,], keep = "recf", nn = TRUE)
#> Warning: OSQP flag -4 OSQP pri_res 1.89503316505579e-06
#> Warning: OSQP flag -4 OSQP pri_res 1.89476372725039e-06
#> Warning: OSQP flag -4 OSQP pri_res 1.89535603567492e-06
#> Warning: OSQP flag -4 OSQP pri_res 1.89519846571784e-06
#> Warning: OSQP flag -4 OSQP pri_res 1.89522438631684e-06
#> Warning: OSQP flag -4 OSQP pri_res 1.89534762284893e-06
#> Warning: OSQP flag -4 OSQP pri_res 1.89524621418968e-06
#> Warning: OSQP flag -4 OSQP pri_res 1.8955886389449e-06
#> Warning: OSQP flag -4 OSQP pri_res 1.89518414117629e-06
#> Warning: OSQP flag -4 OSQP pri_res 1.89527509064646e-06
#> Warning: OSQP flag -4 OSQP pri_res 1.89532261174463e-06
#> Warning: OSQP flag -4 OSQP pri_res 1.89510910786339e-06
#> $recf
#>         serie1     serie2     serie3     serie4     serie5     serie6
#> h1  2143289344 2143289344 2143289344 2143289344 2143289344 2143289344
#> h2  2143289344 2143289344 2143289344 2143289344 2143289344 2143289344
#> h3  2143289344 2143289344 2143289344 2143289344 2143289344 2143289344
#> h4  2143289344 2143289344 2143289344 2143289344 2143289344 2143289344
#> h5  2143289344 2143289344 2143289344 2143289344 2143289344 2143289344
#> h6  2143289344 2143289344 2143289344 2143289344 2143289344 2143289344
#> h7  2143289344 2143289344 2143289344 2143289344 2143289344 2143289344
#> h8  2143289344 2143289344 2143289344 2143289344 2143289344 2143289344
#> h9  2143289344 2143289344 2143289344 2143289344 2143289344 2143289344
#> h10 2143289344 2143289344 2143289344 2143289344 2143289344 2143289344
#> h11 2143289344 2143289344 2143289344 2143289344 2143289344 2143289344
#> h12 2143289344 2143289344 2143289344 2143289344 2143289344 2143289344
#>         serie7
#> h1  2143289344
#> h2  2143289344
#> h3  2143289344
#> h4  2143289344
#> h5  2143289344
#> h6  2143289344
#> h7  2143289344
#> h8  2143289344
#> h9  2143289344
#> h10 2143289344
#> h11 2143289344
#> h12 2143289344
#> 
#> $info
#>    obj_val  run_time iter      pri_res status status_polish
#> 1   -1e+30 0.0000747   25 1.895033e-06     -4             0
#> 2   -1e+30 0.0000504   25 1.894764e-06     -4             0
#> 3   -1e+30 0.0000567   25 1.895356e-06     -4             0
#> 4   -1e+30 0.0000459   25 1.895198e-06     -4             0
#> 5   -1e+30 0.0000467   25 1.895224e-06     -4             0
#> 6   -1e+30 0.0000534   25 1.895348e-06     -4             0
#> 7   -1e+30 0.0000527   25 1.895246e-06     -4             0
#> 8   -1e+30 0.0000487   25 1.895589e-06     -4             0
#> 9   -1e+30 0.0000731   25 1.895184e-06     -4             0
#> 10  -1e+30 0.0000542   25 1.895275e-06     -4             0
#> 11  -1e+30 0.0000339   25 1.895323e-06     -4             0
#> 12  -1e+30 0.0001343   25 1.895109e-06     -4             0
combinef(allf, nodes = nodes, nonnegative = TRUE, keep = "all")
#> Warning in combinef(allf, nodes = nodes, nonnegative = TRUE, keep = "all"):
#> Negative base forecasts are truncated to zero.
#> Time Series:
#> Start = 1 
#> End = 12 
#> Frequency = 1 
#>       Total         A        B AA        AB        BA       BB
#>  1 5.326032 0.3417779 4.984254  0 0.3417779 1.0425411 3.941713
#>  2 5.508210 0.3239697 5.184240  0 0.3239697 1.0319735 4.152267
#>  3 5.690476 0.3063081 5.384168  0 0.3063081 1.0213765 4.362791
#>  4 5.872680 0.2885437 5.584136  0 0.2885437 1.0108002 4.573336
#>  5 6.054928 0.2708514 5.784076  0 0.2708514 1.0002093 4.783867
#>  6 6.237145 0.2531085 5.984036  0 0.2531085 0.9896286 4.994408
#>  7 6.419383 0.2354011 6.183982  0 0.2354011 0.9790409 5.204941
#>  8 6.601607 0.2176689 6.383938  0 0.2176689 0.9684580 5.415480
#>  9 6.783841 0.1999540 6.583887  0 0.1999540 0.9578717 5.626015
#> 10 6.966067 0.1822270 6.783840  0 0.1822270 0.9472879 5.836553
#> 11 7.148299 0.1645085 6.983791  0 0.1645085 0.9367023 6.047088
#> 12 7.330527 0.1467840 7.183743  0 0.1467840 0.9261179 6.257625

Created on 2024-05-23 with reprex v2.1.0

Release FoReco 0.1.0

Prepare for release:

  • Check that description is informative
  • Check licensing of included files
  • devtools::build_readme()
  • usethis::use_cran_comments()
  • devtools::check(remote = TRUE, manual = TRUE)
  • devtools::check_win_devel()
  • rhub::check_for_cran()
  • Update cran-comments.md
  • Review pkgdown reference index for, e.g., missing topics
  • Draft blog post

Submit to CRAN:

  • usethis::use_version('minor')
  • devtools::submit_cran()
  • Approve email

Wait for CRAN...

  • Accepted 🎉
  • usethis::use_github_release()
  • usethis::use_dev_version()
  • Update install instructions in README

Constraints for immutable set

In theory, not any user-specified immutable set is feasible. Here are two examples:

  1. Y = A+B. You can not keep immutable for Y, A, and B, and at the same time, give incoherent base forecasts for Y, A, and B.
  2. Y = X1 + X2, X1 = X11 + X12, X2 = X21 + X22. You can not keep X1, X11, X12 to be immutable simultaneously. You can not also keep Y, X1 and X2 to be immutable simutaneously.

In general, the number of immutable series should not be bigger than the number of bottom-level series (or basis time series in general linear constraints). And the immutable set should satisfy some conditions.

Release FoReco 0.2.4

Prepare for release:

  • git pull
  • Check current CRAN check results
  • Polish NEWS
  • devtools::build_readme()
  • urlchecker::url_check()
  • devtools::check(remote = TRUE, manual = TRUE)
  • devtools::check_win_devel()
  • rhub::check_for_cran()
  • revdepcheck::revdep_check(num_workers = 4)
  • Update cran-comments.md
  • git push

Submit to CRAN:

  • usethis::use_version('patch')
  • devtools::submit_cran()
  • Approve email

Wait for CRAN...

  • Accepted 🎉
  • git push
  • usethis::use_github_release()
  • usethis::use_dev_version()
  • git push

Converting the Package to Python

@danigiro I wanted to convert this package to Python and use it in produciton. But I am not able to find alternatives to the some parts of code. Any info on what will be best way to convert it.. where do I start..

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.