update vignettes

ygeunkim · Sep 16, 2024 · 344b8c7 · 344b8c7
1 parent 81588bc
commit 344b8c7
Show file tree

Hide file tree

Showing 9 changed files with 134 additions and 82 deletions.
diff --git a/.github/workflows/pkgdown.yaml b/.github/workflows/pkgdown.yaml
@@ -49,7 +49,7 @@ jobs:
         shell: Rscript {0}
 
       - name: Deploy to GitHub pages 🚀
-        if: github.event_name != 'pull_request' && "!startsWith(github.ref, 'refs/heads/release/')"
+        if: "github.event_name != 'pull_request' && !startsWith(github.ref, 'refs/heads/release/')"
         uses: JamesIves/[email protected]
         with:
           token: ${{ secrets.YGEUNKIM_PAGE_PAT }}

diff --git a/README.Rmd b/README.Rmd
@@ -49,7 +49,7 @@ install.packages("bvhar")
 
 <!-- dev badges: start -->
 [![dev-r-cmd-check](https://github.com/ygeunkim/bvhar/actions/workflows/R-CMD-check.yaml/badge.svg?branch=develop)](https://github.com/ygeunkim/bvhar/actions/workflows/R-CMD-check.yaml?query=branch%3Adevelop)
-[![dev-codecov](https://codecov.io/github/ygeunkim/bvhar/branch/develop/graph/badge.svg)](https://codecov.io/github/ygeunkim/bvhar)
+[![dev-codecov](https://codecov.io/github/ygeunkim/bvhar/branch/develop/graph/badge.svg)](https://app.codecov.io/gh/ygeunkim/bvhar/tree/develop)
 [![Development version updated](https://img.shields.io/github/last-commit/ygeunkim/bvhar/develop?label=dev%20updated)](https://github.com/ygeunkim/bvhar/tree/develop)
 <!-- dev badges: end -->
 
@@ -60,6 +60,11 @@ You can install the development version from [develop branch](https://github.com
 remotes::install_github("ygeunkim/bvhar@develop")
 ```
 
+We started to develop a Python version in python directory.
+
+- [bvhar for Python](https://ygeunkim.github.io/package/bvhar/python/)
+- [Source code](https://github.com/ygeunkim/bvhar/tree/develop/python)
+
 ## Models
 
 ```{r example, message=FALSE}
@@ -80,6 +85,7 @@ Repeatedly, `bvhar` is a research tool to analyze multivariate time series model
 
 This readme document shows forecasting procedure briefly.
 Details about each function are in vignettes and help documents.
+Note that each `bvar_minnesota()` and `bvhar_minnesota()` will be integrated into `var_bayes()` and `vhar_bayes()` and removed in the next version.
 
 h-step ahead forecasting:
 
@@ -186,16 +192,6 @@ forecast_bvhar_v2 <- predict(mod_bvhar_v2, h)
 (msebvhar_v2 <- mse(forecast_bvhar_v2, etf_te))
 ```
 
-## Plots
-
-```{r predfig}
-autoplot(forecast_var, x_cut = 870, ci_alpha = .7, type = "wrap") +
-  autolayer(forecast_vhar, ci_alpha = .6) +
-  autolayer(forecast_bvar, ci_alpha = .4) +
-  autolayer(forecast_bvhar_v1, ci_alpha = .2) +
-  autolayer(forecast_bvhar_v2, ci_alpha = .1)
-```
-
 ## Citation
 
 Please cite this package with following BibTeX:

diff --git a/README.md b/README.md
@@ -39,7 +39,7 @@ install.packages("bvhar")
 <!-- dev badges: start -->
 
 [![dev-r-cmd-check](https://github.com/ygeunkim/bvhar/actions/workflows/R-CMD-check.yaml/badge.svg?branch=develop)](https://github.com/ygeunkim/bvhar/actions/workflows/R-CMD-check.yaml?query=branch%3Adevelop)
-[![dev-codecov](https://codecov.io/github/ygeunkim/bvhar/branch/develop/graph/badge.svg)](https://codecov.io/github/ygeunkim/bvhar)
+[![dev-codecov](https://codecov.io/github/ygeunkim/bvhar/branch/develop/graph/badge.svg)](https://app.codecov.io/gh/ygeunkim/bvhar/tree/develop)
 [![Development version
 updated](https://img.shields.io/github/last-commit/ygeunkim/bvhar/develop?label=dev%20updated)](https://github.com/ygeunkim/bvhar/tree/develop)
 <!-- dev badges: end -->
@@ -52,6 +52,11 @@ branch](https://github.com/ygeunkim/bvhar/tree/develop).
 remotes::install_github("ygeunkim/bvhar@develop")
 ```
 
+We started to develop a Python version in python directory.
+
+- [bvhar for Python](https://ygeunkim.github.io/package/bvhar/python/)
+- [Source code](https://github.com/ygeunkim/bvhar/tree/develop/python)
+
 ## Models
 
 ``` r
@@ -72,7 +77,9 @@ series model above
 | BVHAR |   `vhar_bayes()`    |   SSVS, Horseshoe, Minnesota, NG, DL    |
 
 This readme document shows forecasting procedure briefly. Details about
-each function are in vignettes and help documents.
+each function are in vignettes and help documents. Note that each
+`bvar_minnesota()` and `bvhar_minnesota()` will be integrated into
+`var_bayes()` and `vhar_bayes()` and removed in the next version.
 
 h-step ahead forecasting:
 
@@ -274,18 +281,6 @@ forecast_bvhar_v2 <- predict(mod_bvhar_v2, h)
 #>     5.54
 ```
 
-## Plots
-
-``` r
-autoplot(forecast_var, x_cut = 870, ci_alpha = .7, type = "wrap") +
-  autolayer(forecast_vhar, ci_alpha = .6) +
-  autolayer(forecast_bvar, ci_alpha = .4) +
-  autolayer(forecast_bvhar_v1, ci_alpha = .2) +
-  autolayer(forecast_bvhar_v2, ci_alpha = .1)
-```
-
-<img src="man/figures/README-predfig-1.png" width="70%" style="display: block; margin: auto;" />
-
 ## Citation
 
 Please cite this package with following BibTeX:
@@ -294,15 +289,19 @@ Please cite this package with following BibTeX:
       title = {{bvhar}: Bayesian Vector Heterogeneous Autoregressive Modeling},
       author = {Young Geun Kim and Changryong Baek},
       year = {2023},
-      note = {R package version 2.0.1.9014},
+      doi = {10.32614/CRAN.package.bvhar},
+      note = {R package version 2.1.0},
       url = {https://cran.r-project.org/package=bvhar},
     }
 
     @Article{,
       title = {Bayesian Vector Heterogeneous Autoregressive Modeling},
       author = {Young Geun Kim and Changryong Baek},
       journal = {Journal of Statistical Computation and Simulation},
-      year = {2023},
+      year = {2024},
+      volume = {94},
+      number = {6},
+      pages = {1139--1157},
       doi = {10.1080/00949655.2023.2281644},
     }
 

diff --git a/_pkgdown.yml b/_pkgdown.yml
@@ -17,7 +17,7 @@ home:
   # see the configuration in .github/workflows/pkgdown.yaml
   - text: VERSION_TEXT
     href: VERSION_REF
-  - text: bvhar in Python
+  - text: bvhar for Python
     href: https://ygeunkim.github.io/package/bvhar/python/
 
 development:
@@ -46,7 +46,6 @@ reference:
     Prior settings for Bayesian models.
   contents:
   - set_bvar
-  - init_ssvs
   - set_ssvs
   - set_lambda
   - set_horseshoe
@@ -70,14 +69,18 @@ reference:
 
 - title: Deprecated
   desc: >
-    Deprecated modeling functions that will be removed soon
+    Deprecated functions that will be removed soon
   contents:
   - bvar_sv
   - bvar_ssvs
   - bvar_horseshoe
   - bvhar_sv
   - bvhar_ssvs
   - bvhar_horseshoe
+  - init_ssvs
+  - choose_ssvs
+  - sim_ssvs_var
+  - sim_horseshoe_var
 
 - title: Forecasting
   desc: ~
@@ -125,7 +128,6 @@ reference:
   - choose_bvhar
   - bound_bvhar
   - choose_bayes
-  - choose_ssvs
 
 - title: Information criteria
   desc: ~
@@ -161,8 +163,6 @@ reference:
   - sim_mniw
   - sim_mvt
   - sim_gig
-  - sim_ssvs_var
-  - sim_horseshoe_var
 
 - title: Data
   desc: ~
@@ -178,13 +178,16 @@ reference:
   - residuals
   - fitted
 
-# destination: '../../myprofile/young-blogdown/static/package/bvhar'
-
 navbar:
   structure:
-    left: [intro, reference, articles, tutorials, news, research, accepted]
+    left: [intro, reference, articles, tutorials, news, publication, research, accepted]
     right: [github, goback]
   components:
+    publication:
+      icon: fa-newspaper
+      href: https://www.tandfonline.com/eprint/ZIRSC2CDJ9JM9FK2E3WD/full?target=10.1080/00949655.2023.2281644
+      aria-label: Published
+      text: Published
     research:
       icon: fa-laptop-code
       href: https://github.com/ygeunkim/paper-bvhar
@@ -204,15 +207,17 @@ news:
     href: https://github.com/ygeunkim/bvhar/releases/tag/v0.12.0
   # - text: "Version 1.0.0"
   #   href: https://github.com/ygeunkim/bvhar/releases/tag/v1.0.0
-  # - text: "Version 1.0.1"
-  #   href: https://github.com/ygeunkim/bvhar/releases/tag/v1.0.1
-  # - text: "Version 1.0.2"
-  #   href: https://github.com/ygeunkim/bvhar/releases/tag/v1.0.2
-  # - text: "Version 1.1.0"
-  #   href: https://github.com/ygeunkim/bvhar/releases/tag/v1.1.0
+  - text: "Version 1.0.1"
+    href: https://github.com/ygeunkim/bvhar/releases/tag/v1.0.1
+  - text: "Version 1.0.2"
+    href: https://github.com/ygeunkim/bvhar/releases/tag/v1.0.2
+  - text: "Version 1.1.0"
+    href: https://github.com/ygeunkim/bvhar/releases/tag/v1.1.0
   - text: "Version 1.2.0"
     href: https://github.com/ygeunkim/bvhar/releases/tag/v1.2.0
-  # - text: "Version 2.0.0"
-  #   href: https://github.com/ygeunkim/bvhar/releases/tag/v2.0.0
+  - text: "Version 2.0.0"
+    href: https://github.com/ygeunkim/bvhar/releases/tag/v2.0.0
   - text: "Version 2.0.1"
     href: https://github.com/ygeunkim/bvhar/releases/tag/v2.0.1
+  - text: "Version 2.1.0"
+    href: https://github.com/ygeunkim/bvhar/releases/tag/v2.1.0
diff --git a/man/figures/README-predfig-1.png b/man/figures/README-predfig-1.png
diff --git a/revdep/README.md b/revdep/README.md
@@ -1,23 +1,41 @@
 # Platform
 
-|field    |value                                         |
-|:--------|:---------------------------------------------|
-|version  |R version 4.3.2 (2023-10-31)                  |
-|os       |macOS Ventura 13.6.4                          |
-|system   |aarch64, darwin20                             |
-|ui       |X11                                           |
-|language |(EN)                                          |
-|collate  |en_US.UTF-8                                   |
-|ctype    |UTF-8                                         |
-|tz       |Asia/Seoul                                    |
-|date     |2024-03-01                                    |
-|pandoc   |3.1.12.1 @ /opt/homebrew/bin/ (via rmarkdown) |
+|field    |value                        |
+|:--------|:----------------------------|
+|version  |R version 4.3.3 (2024-02-29) |
+|os       |macOS Big Sur ... 10.16      |
+|system   |x86_64, darwin20             |
+|ui       |X11                          |
+|language |(EN)                         |
+|collate  |en_US.UTF-8                  |
+|ctype    |en_US.UTF-8                  |
+|tz       |Asia/Seoul                   |
+|date     |2024-09-16                   |
+|pandoc   |3.3 @ /usr/local/bin/pandoc  |
 
 # Dependencies
 
-|package |old   |new   |Δ  |
-|:-------|:-----|:-----|:--|
-|bvhar   |2.0.0 |2.0.1 |*  |
+|package     |old   |new       |Δ  |
+|:-----------|:-----|:---------|:--|
+|bvhar       |2.0.1 |2.1.0     |*  |
+|abind       |NA    |1.4-8     |*  |
+|backports   |NA    |1.5.0     |*  |
+|checkmate   |NA    |2.3.2     |*  |
+|cli         |NA    |3.6.3     |*  |
+|colorspace  |NA    |2.1-1     |*  |
+|cpp11       |NA    |0.4.7     |*  |
+|farver      |NA    |2.1.2     |*  |
+|ggplot2     |NA    |3.5.1     |*  |
+|gtable      |NA    |0.3.5     |*  |
+|matrixStats |NA    |1.4.1     |*  |
+|munsell     |NA    |0.5.1     |*  |
+|posterior   |NA    |1.5.0     |*  |
+|Rcpp        |NA    |1.0.13    |*  |
+|RcppEigen   |NA    |0.3.4.0.2 |*  |
+|rlang       |NA    |1.1.4     |*  |
+|stringi     |NA    |1.8.4     |*  |
+|tidyselect  |NA    |1.2.1     |*  |
+|withr       |NA    |3.0.1     |*  |
 
 # Revdeps
 
diff --git a/vignettes/bvhar.Rmd b/vignettes/bvhar.Rmd
@@ -238,7 +238,8 @@ names(fit_har)
 
 ## BVAR
 
-`bvhar` package provides two prior framework - Minnesota prior and flat prior.
+This page provides deprecated two functions examples.
+Both `bvar_minnesota()` and `bvar_flat()` will be integrated into `var_bayes()` and removed in the next version.
 
 ### Minnesota prior
 
@@ -348,6 +349,7 @@ We call this VAR-type Minnesota prior or BVHAR-S.
 
 `bvhar_minnesota(y, har = c(5, 22), bayes_spec, include_mean = TRUE)` can fit BVHAR with this prior.
 This is the default prior setting.
+Similar to above functions, this function will be also integrated into `vhar_bayes()` and removed in the next version.
 
 ```{r}
 (fit_bvhar_v1 <- bvhar_minnesota(etf_train, num_iter = 10, bayes_spec = bvhar_spec_v1))

diff --git a/vignettes/shrinkage.Rmd b/vignettes/shrinkage.Rmd
@@ -1,8 +1,8 @@
 ---
-title: "Shrinkage Priors"
+title: "Bayesian VAR and VHAR Models"
 output: rmarkdown::html_vignette
 vignette: >
-  %\VignetteIndexEntry{Shrinkage Priors}
+  %\VignetteIndexEntry{Bayesian VAR and VHAR Models}
   %\VignetteEngine{knitr::rmarkdown}
   %\VignetteEncoding{UTF-8}
 ---
@@ -26,36 +26,44 @@ library(bvhar)
 ```
 
 ```{r etfdat}
-etf <- etf_vix[1:100, 1:3]
+etf <- etf_vix[1:55, 1:3]
 # Split-------------------------------
 h <- 5
 etf_eval <- divide_ts(etf, h)
 etf_train <- etf_eval$train
 etf_test <- etf_eval$test
 ```
 
+# Bayesian VAR and VHAR
 
-# Stochastic Search Variable Selection (SSVS) Prior
+`var_bayes()` and `vhar_bayes()` fit BVAR and BVHAR each with various priors.
 
 - `y`: Multivariate time series data. It should be data frame or matrix, which means that every column is numeric. Each column indicates variable, i.e. it sould be wide format.
-- `har`: Order of VHAR
+- `p` or `har`: VAR lag, or order of VHAR
 - `num_chains`: Number of chains
     - If OpenMP is enabled, parallel loop will be run.
 - `num_iter`: Total number of iterations
 - `num_burn`: Number of burn-in
 - `thinning`: Thinning
 - `bayes_spec`: Output of `set_ssvs()`
-    - By default, use a default semi-automatic approach using `choose_ssvs()`.
-<!-- - `init_spec`: Gibbs sampler initialization by `init_ssvs()`. -->
-  <!-- - By default, `init_ssvs(type = "auto")` uses OLS. -->
+    - Minneosta prior
+        - BVAR: `set_bvar()`
+        - BVHAR: `set_bvhar()` and `set_weight_bvhar()`
+        - Can induce prior on $\lambda$ using `lambda = set_lambda()`
+    - SSVS prior: `set_ssvs()`
+    - Horseshoe prior: `set_horseshoe()`
+    - NG prior: `set_ng()`
+    - DL prior: `set_dl()`
 - `cov_spec`: Covariance prior specification. Use `set_ldlt()` for homoskedastic model.
 - `include_mean = TRUE`: By default, you include the constant term in the model.
 - `minnesota = c("no", "short", "longrun")`: Minnesota-type shrinkage.
 - `verbose = FALSE`: Progress bar
 - `num_thread`: Number of thread for OpenMP
-    - Used in both Eigen computation and parallel multi-chain loop
+    - Used in parallel multi-chain loop
     - This option is valid only when OpenMP in user's machine.
 
+## Stochastic Search Variable Selection (SSVS) Prior
+
 ```{r fitssvs}
 (fit_ssvs <- vhar_bayes(etf_train, num_chains = 1, num_iter = 20, bayes_spec = set_ssvs(), cov_spec = set_ldlt(), include_mean = FALSE, minnesota = "longrun"))
 ```
@@ -68,7 +76,7 @@ autoplot(fit_ssvs)
 ```
 
 
-# Horseshoe Prior
+## Horseshoe Prior
 
 `bayes_spec` is the initial specification by `set_horseshoe()`. Others are the same.
 
@@ -80,6 +88,23 @@ autoplot(fit_ssvs)
 autoplot(fit_hs)
 ```
 
+## Minnesota Prior
+
+```{r fitmn}
+(fit_mn <- vhar_bayes(etf_train, num_chains = 2, num_iter = 20, bayes_spec = set_bvhar(lambda = set_lambda()), cov_spec = set_ldlt(), include_mean = FALSE, minnesota = "longrun"))
+```
+
+## Normal-Gamma prior
+
+```{r fitng}
+(fit_ng <- vhar_bayes(etf_train, num_chains = 2, num_iter = 20, bayes_spec = set_ng(), cov_spec = set_ldlt(), include_mean = FALSE, minnesota = "longrun"))
+```
+
+## Dirichlet-Laplace prior
+
+```{r fitdl}
+(fit_dl <- vhar_bayes(etf_train, num_chains = 2, num_iter = 20, bayes_spec = set_dl(), cov_spec = set_ldlt(), include_mean = FALSE, minnesota = "longrun"))
+```
 
 # Bayesian visualization