updated build pipeline

.Rbuildignore

@@ -29,3 +29,11 @@ data/ndvi_AK3000\.rda
 cran-comments\.md
 
 README\.html
+
+# build pipeline
+build.R
+render_vignette.R
+check_pkg.R
+build_pipeline.R
+builds/
+figure/

.gitignore

@@ -15,3 +15,7 @@ data-raw
 /Meta/
 
 README.html
+
+# built versions of the package
+builds/
+figure/

build.R

@@ -0,0 +1,3 @@
+Rcpp::compileAttributes()
+devtools::document()
+devtools::build(path = "builds")

build_pipeline.R

@@ -0,0 +1,3 @@
+source("check_pkg.R")
+source("build.R")
+source("render_vignette.R")

check_pkg.R

@@ -0,0 +1,3 @@
+Rcpp::compileAttributes()
+devtools::document()
+devtools::check()

render_vignette.R

@@ -0,0 +1,4 @@
+rmarkdown::render(input = "vignettes/Alaska.Rmd",
+                  output_format = "html_document",
+                  output_file = "Alaska.html",
+                  output_dir = "docs/")

vignettes/Alaska.Rmd

@@ -253,8 +253,7 @@ this covariance function.
 ```{r visualize_range, fig.asp = 1, fig.width = 4.5, include = FALSE}
 curve(covar_exp(x, r = .1), xlab = "distance", ylab = "covar_exp(d, r)")
 curve(covar_exp(x, r = .2), add = TRUE, col = "red")
-legend("topright", legend = c("0.1", "0.2"), title = "r", 
-       col = c("black", "red"), lty = 1)
+legend("topright", legend = c("0.1", "0.2"), title = "r", col = c("black", "red"), lty = 1)
 ```
 
 `V` represents the correlation among points if all variation is accounted for.
@@ -267,8 +266,7 @@ $I$ is the identity matrix.
 nugget <- .3
 curve(covar_exp(x, r = .1), xlab = "distance", ylab = "covar_exp(d, r)")
 curve((1-nugget)*covar_exp(x, r = .1), add = TRUE, col = "red")
-legend("topright", legend = c(0, .2), title = expression(eta), 
-       col = c("black", "red"), lty = 1)
+legend("topright", legend = c(0, .2), title = expression(eta), col = c("black", "red"), lty = 1)
 ```
 
 If we know the range parameter $r$, we can calculate `V` from `D` with `covar_exp()`:
@@ -381,9 +379,8 @@ at 0.1. For this example, we will also specify `fit.n = 3000`, which ensures
 that all pixels are used to estimate spatial parameters. 
 
 ```{r fit_range_parameter}
-corfit <- fitCor(resids = residuals(ARfit), coords = coords, 
-                covar_FUN = "covar_exp", start = list(range = 0.1), 
-                fit.n = 3000)
+corfit <- fitCor(resids = residuals(ARfit), coords = coords, covar_FUN = "covar_exp", 
+                 start = list(range = 0.1), fit.n = 3000)
 (range.opt = corfit$spcor)
 ```
 
@@ -397,9 +394,8 @@ map:
 
 ```{r fit_range_km, eval = FALSE}
 max.dist <- max(distm_km(coords))
-corfit.km <- fitCor(resids = residuals(ARfit), coords = coords, 
-                   covar_FUN = "covar_exp", start = list(range = max.dist*0.1),
-                   distm_FUN = "distm_km", fit.n = 3000)
+corfit.km <- fitCor(resids = residuals(ARfit), coords = coords, covar_FUN = "covar_exp", 
+                    start = list(range = max.dist*0.1), distm_FUN = "distm_km", fit.n = 3000)
 ```
 
 Note that, depending on the covariance function used, not all parameters will 
@@ -428,8 +424,7 @@ so that F-tests are calculated. For the F-tests, the default reduced model is th
 it is also possible to specify alternative reduced models as a formula in the `formula0` option.
 
 ```{r optimized_nugget}
-GLS.opt <- fitGLS(formula = AR_coef ~ 0 + land, data = ndvi_AK3000, V = V.opt, nugget = NA, 
-                 no.F = FALSE)
+GLS.opt <- fitGLS(formula = AR_coef ~ 0 + land, data = ndvi_AK3000, V = V.opt, nugget = NA, no.F = FALSE)
 (nug.opt = GLS.opt$nugget)
 coefficients(GLS.opt)
 ```
@@ -528,8 +523,7 @@ Finally, to test the hypothesis that "temporal trends in NDVI differ with
 latitude", we can regress the AR coefficient on latitude in our GLS model:
 
 ```{r fit_GLS_latitude}
-(GLS.lat <- fitGLS(AR_coef ~ 1 + lat, data = ndvi_AK3000, V = V.opt, nugget = nug.opt,
-                   no.F = FALSE))
+(GLS.lat <- fitGLS(AR_coef ~ 1 + lat, data = ndvi_AK3000, V = V.opt, nugget = nug.opt, no.F = FALSE))
 ```
 
 The t-tests show that temporal trends in NDVI did not differ with latitude.