version 0.2.0

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: clustra
-Version: 0.1.6
-Date: 2022-01-15
+Version: 0.2.0
+Date: 2023-09-30
 Title: Clustering Longitudinal Trajectories
 Authors@R: c(person("George", "Ostrouchov", role = c("aut", "cre"), email = 
         "ostrouchovg@ornl.gov"),
@@ -15,7 +15,7 @@ Authors@R: c(person("George", "Ostrouchov", role = c("aut", "cre"), email =
 Depends: R (>= 3.5.0)
 Imports: data.table, graphics, grDevices, methods, mgcv, MixSim,
         parallel, stats
-Suggests: ggplot2, knitr, rmarkdown
+Suggests: haven, knitr, rmarkdown
 Description: Clusters longitudinal trajectories over time (can be unequally 
     spaced, unequal length time series and/or partially overlapping series) on
     a common time axis. Performs k-means clustering on a single continuous 
@@ -29,10 +29,12 @@ LazyLoad: yes
 License: BSD 2-clause License + file LICENSE
 Encoding: UTF-8
 Maintainer: George Ostrouchov <ostrouchovg@ornl.gov>
-RoxygenNote: 7.1.2
+RoxygenNote: 7.2.3
 VignetteBuilder: knitr
+LazyData: true
+LazyDataCompression: xz
 NeedsCompilation: no
-Packaged: 2022-01-16 06:17:17 UTC; ost
+Packaged: 2023-10-14 02:36:54 UTC; ost
 Author: George Ostrouchov [aut, cre],
   David Gagnon [aut],
   Hanna Gerlovin [aut],
@@ -42,4 +44,4 @@ Author: George Ostrouchov [aut, cre],
   U.S. Department of Veteran's Affairs [fnd] (Project: Million Veteran
     Program Data Core)
 Repository: CRAN
-Date/Publication: 2022-01-16 06:42:41 UTC
+Date/Publication: 2023-10-14 04:50:02 UTC

MD5

@@ -1,33 +1,45 @@
-ae121f6809579bf05fda0c8c6b771de2 *DESCRIPTION
+bf6bb4c2da96b4aef130bbaa08961d2c *DESCRIPTION
 d77b82eba56279e0051c4ed0aa2d3d14 *LICENSE
-f07e83dd5ecbba2409157731fb119f18 *NAMESPACE
-948199ff0d18147f65ade7d783792867 *NEWS.md
-1fbafabaa8a7849792b161b5f0252624 *R/clustra-package.R
-12792f1999d8d48b88abdad420cb30d1 *R/deltime.R
-ad486d951b8311f77df2bf3067ad186c *R/evaluate.R
-3534dc49b1e832c9ed4a506849b8387d *R/generate.R
-44128efe7b6205859cd88cd0cf7cab30 *R/trajectories.R
-f892964351d35b44e315b7e485409138 *README.md
-a2a47c4ee05a09fac1d105406f210c03 *build/vignette.rds
-a79ae835c09a1f148886243d109e19cc *inst/doc/clustra_vignette.R
-d3f1d4f9581adb344d7377abf0d8cc12 *inst/doc/clustra_vignette.Rmd
-dc47946aecb755214952c762f7bb2a7e *inst/doc/clustra_vignette.html
-d78e251d946302a2e73d1a9a82d437b2 *man/allpair_RandIndex.Rd
+a67570371de37a3c8f08593f14d583ce *NAMESPACE
+30162adb1ed353c1d203859cc523d23c *NEWS.md
+485f56b7aab5249415ff87d4c11785d8 *R/clustra-package.R
+05ab1d058667c2f85eac5de8a9258c94 *R/data.R
+6e76e9734a495c2a70cb1601aee44f88 *R/evaluate.R
+b72e454bd78fbd237a2ac2ad28b7b100 *R/generate.R
+cfa3f1aae5bfe9214be83d4154e48354 *R/graphics.R
+843c1f1e0f9eb5706d4b4dcc54a44faa *R/trajectories.R
+1094de6c85a3e5ba4926087ebfec355c *README.md
+b2318daec94d5cbeee1a0b3668469cfe *build/vignette.rds
+c73a08a398ce2fb7f459a9af27f7dc07 *data/bp10k.rda
+49182df60f0f80bbdfa6bc7ff0589ae3 *inst/doc/clustra_bp_vignette.R
+6103e7b56c9560c3dfa3b307b6a87854 *inst/doc/clustra_bp_vignette.Rmd
+784628d47f98150562f38319061bcf23 *inst/doc/clustra_bp_vignette.html
+ba3c6507e9b05a0f9ebef0bee0a0b380 *inst/doc/clustra_vignette.R
+32bebaa7b43e992247be9ac095896fa1 *inst/doc/clustra_vignette.Rmd
+2436255775a196fde9eb9cbbf9a7801f *inst/doc/clustra_vignette.html
+9a621a0814463bdcd4e84273d306887b *man/allpair_RandIndex.Rd
+e41cf6db975649f7790ca4d52f5e7d53 *man/bp10k.Rd
 11bddacb11edeea0ff4abefa8b87eb78 *man/check_df.Rd
-db5cb195b00920258ca6a8728934da9d *man/clustra-package.Rd
-63ddbad49eb963063df940092b813a8e *man/clustra.Rd
-f040a52147eb8e8739466bb7e815ae29 *man/clustra_rand.Rd
-f41032dde7adc59b0bf5758a64b8c848 *man/clustra_sil.Rd
-e53f041da70c153a81d22241522dc212 *man/deltime.Rd
-87aa255659bca54218a4bd5eb3cef0e6 *man/gen_traj_data.Rd
-8c191ed6fae6f480296c8476d0b4aa49 *man/gendata.Rd
-f8435bedba26420d29e656d945ca270d *man/mse_g.Rd
-abf510cc017f615edf09a99a05723011 *man/oneid.Rd
+c85df281c34b43faca311dcb588ea8d9 *man/clustra-package.Rd
+4d73c629f7b45c0463b7d47d87def60f *man/clustra.Rd
+0954142e2cfe56f0917c00e7c0ed08d4 *man/clustra_rand.Rd
+5fecd414147a086986b5af10c3eb56e8 *man/clustra_sil.Rd
+14e08f58acd7f4f6a56311ca9c77f8c8 *man/deltime.Rd
+f925a1187aa090c6007b8ea1328efbbc *man/gen_traj_data.Rd
+a018bd3229b45ac6d5168beb22b57275 *man/gendata.Rd
+5c00608c226ef6459cb151c6f6a6f697 *man/ic_fun.Rd
+0b4220c7dd63ddfde815583fcefbf0a3 *man/kchoose.Rd
+6c51bf8e160fcac3b51019271056d9bb *man/mse_g.Rd
+913b11585b088045bfb87b7af658f4f2 *man/oneid.Rd
+48b0c57ef49281a57b54981dab41839b *man/plot_sample.Rd
+0bad7f54613a3456ba96a6856ca1fa08 *man/plot_silhouette.Rd
+37ce3f143ec9a4b7264eecf32546689f *man/plot_smooths.Rd
 b66ba2ec5b253d50d3917b897f1a3666 *man/pred_g.Rd
-6d9ea4624be633b222d40a3232fd372d *man/rand_plot.Rd
-a1e7dee9687951730fed122a853581e7 *man/start_groups.Rd
-a92b8f68410dbaaa8c6d748d11e55a21 *man/tps_g.Rd
-b95504dbbbd1027877deacebe23f7a24 *man/traj_rep.Rd
-6d5f50137a1a76dbe65cafcaced178c8 *man/trajectories.Rd
+e0f7e1b3cb8155538b837ff0426f327f *man/rand_plot.Rd
+4c9ca622008540e6f08be6b46ec8b69b *man/start_groups.Rd
+a630b92c92702f317adfc8ae8786232a *man/tps_g.Rd
+8fa349672b5650ad6c853756de3e115a *man/traj_rep.Rd
+9415e9e55b7c46daef2e893a65e1842a *man/trajectories.Rd
 e06416343fabc98d9e050a0c6889edbf *man/xit_report.Rd
-d3f1d4f9581adb344d7377abf0d8cc12 *vignettes/clustra_vignette.Rmd
+6103e7b56c9560c3dfa3b307b6a87854 *vignettes/clustra_bp_vignette.Rmd
+32bebaa7b43e992247be9ac095896fa1 *vignettes/clustra_vignette.Rmd

NAMESPACE

@@ -4,22 +4,35 @@ export(clustra)
 export(clustra_rand)
 export(clustra_sil)
 export(deltime)
+export(deltimeT)
 export(gen_traj_data)
+export(plot_sample)
+export(plot_silhouette)
+export(plot_smooths)
 export(rand_plot)
-export(start_groups)
 export(trajectories)
 importFrom(data.table,":=")
 importFrom(grDevices,colorRampPalette)
 importFrom(grDevices,dev.off)
 importFrom(grDevices,pdf)
 importFrom(graphics,abline)
 importFrom(graphics,axis)
+importFrom(graphics,barplot)
 importFrom(graphics,box)
+importFrom(graphics,close.screen)
 importFrom(graphics,image)
 importFrom(graphics,layout)
+importFrom(graphics,legend)
+importFrom(graphics,lines)
+importFrom(graphics,mtext)
 importFrom(graphics,par)
+importFrom(graphics,points)
+importFrom(graphics,screen)
+importFrom(graphics,split.screen)
+importFrom(graphics,text)
 importFrom(methods,is)
 importFrom(stats,dist)
+importFrom(stats,median)
 importFrom(stats,predict)
 importFrom(stats,rnorm)
 importFrom(stats,rpois)

NEWS.md

@@ -1,3 +1,16 @@
+# clustra v0.2.0
+* Added a 10,000 id data set `bp10k`
+* Added a second vignette to reproduce associated paper graphics and more
+* Reduced vignette dependence to only base graphics
+* New function `plot_sample` built on base graphics
+* New function `plot_smooths` built on base graphics
+* New function `plot_silhouette` built on base graphics
+* Expanded capability of `gen_traj_data` beyond 3 clusters with `type` and `intercept` parameters
+* Modified parameters in `clustra`
+* Added `starts = "distant"` option in function `start_groups`
+* Added parameter `starts` in `clustra_sil` and `clustra_rand`
+* New internal functions `kchoose` and `ic_fun` (not exported)
+
 # clustra v0.1.6
 * Original ids are now included in `clustra` output
 * Added the ability to reuse previous clustra runs by `clustra_sil` for silhouette plots

R/clustra-package.R

@@ -1,18 +1,32 @@
 #' clustra-package
 #' 
-#' Clusters medical trajectories (unequally spaced and unequal lengths) aligned 
-#' by an intervention time. Performs k-means clustering, where each mean is a 
-#' thin plate spline fit to all points in a cluster. Distance is MSE across 
-#' trajectory points to cluster spline. Provides silhouette plots and Adjusted
-#' Rand Index evaluations of the number of clusters. Scales well to large data
-#' with multicore parallelism available to speed computation.
+#' Clusters trajectories (unequally spaced and unequal length time series) on 
+#' a common time axis. Clustering proceeds by an EM algorithm that iterates 
+#' switching between fitting a thin plate spline (TPS) to combined responses 
+#' within each cluster (M-step) and reassigning cluster membership based on the 
+#' nearest fitted TPS (E-step). Initial cluster assignments are random or 
+#' distant trajectories. The fitting is done with the *mgcv* package function 
+#' *bam*, which scales well to very large data sets. Additional parallelism 
+#' available via multicore on unix and mac platforms.
 #' 
 #' @name clustra-package
 #' @docType package
 #' @author George Ostrouchov, David Gagnon, Hanna Gerlovin
 #' @keywords Package
+#' @details
+#' This research is based on data from the Million Veteran Program, Office of 
+#' Research and Development, Veterans Health Administration, and was supported 
+#' by award No.~MVP000. This research used resources from the Knowledge 
+#' Discovery Infrastructure (KDI) at Oak Ridge National Laboratory, which is 
+#' supported by the Office of Science of the US Department of Energy under 
+#' Contract No. DE-AC05-00OR22725.
+#' 
+#' This research used resources of the Compute and Data Environment 
+#' for Science (CADES) at the Oak Ridge National Laboratory, which is supported 
+#' by the Office of Science of the U.S. Department of Energy under Contract No. 
+#' DE-AC05-00OR22725.
 #' 
-#' # Import package operators
 #' @importFrom data.table ":="
 #' 
 NULL
+

R/data.R

@@ -0,0 +1,26 @@
+#' Simulated blood pressure data
+#' 
+#' A sample of 10,000 individuals from the full 80,000 individuals in a dataset
+#' available on GitHub at 
+#' https://github.com/MVP-CHAMPION/clustra-SAS/raw/main/bp_data/simulated_data_27June2023.csv.gz
+#' 
+#' The full data set contains 80,000 individuals, each with an average of about
+#' 17 observations in 5 clusters with scatter. The individuals are generated 
+#' from a 5-cluster thin spline model of actual blood pressures collected from 
+#' roughly the same number of individuals at U.S. Department of Veterans Affairs
+#' facilities in connection with the MVP-CHAMPION project. Each cluster-mean 
+#' generated individual has a random number of observations at random times with
+#' one observation at intervention time 0, and with added standard normal error.
+#' The resulting data has 1,353,910 rows and 4 columns.
+#' 
+#' @format ## `bp10k`
+#' A "data.table" and "data.frame" with 167,277 rows and 4 columns:
+#' \describe{
+#'   \item{id}{An integer in 1:80000.}
+#'   \item{group}{An integer in 1:5.}
+#'   \item{time}{An integer between -365 and 730, giving observation day with
+#'   reference to an intervention at time 0.}
+#'   \item{response}{The systolic blood pressure on that day.}
+#' }
+#' 
+"bp10k"