-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge branch 'master' into swig_1_db
- Loading branch information
Showing
153 changed files
with
20,194 additions
and
172 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Binary file not shown.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,19 +1,19 @@ | ||
| bibentry(bibtype = "Article", | ||
| title = "Nonparametric Machine Learning and Efficient Computation with {B}ayesian Additive Regression Trees: The {BART} {R} Package", | ||
| author = c(person(given = "Rodney", | ||
| family = "Sparapani", | ||
| email = "[email protected]"), | ||
| person(given = "Charles", | ||
| family = "Spanbauer"), | ||
| person(given = "Robert", | ||
| family = "McCulloch")), | ||
| journal = "Journal of Statistical Software", | ||
| year = "2021", | ||
| volume = "97", | ||
| number = "1", | ||
| pages = "1--66", | ||
| doi = "10.18637/jss.v097.i01", | ||
|
|
||
| header = "To cite BART in publications use:" | ||
| ) | ||
|
|
||
| bibentry(bibtype = "Article", | ||
| title = "Nonparametric Machine Learning and Efficient Computation with {B}ayesian Additive Regression Trees: The {BART} {R} Package", | ||
| author = c(person(given = "Rodney", | ||
| family = "Sparapani", | ||
| email = "[email protected]"), | ||
| person(given = "Charles", | ||
| family = "Spanbauer"), | ||
| person(given = "Robert", | ||
| family = "McCulloch")), | ||
| journal = "Journal of Statistical Software", | ||
| year = "2021", | ||
| volume = "97", | ||
| number = "1", | ||
| pages = "1--66", | ||
| doi = "10.18637/jss.v097.i01", | ||
| header = "To cite BART in publications use:" | ||
| ) | ||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,3 +1,10 @@ | ||
| # Databricks notebook source | ||
| # MAGIC %md | ||
| # MAGIC R.home('include') | ||
|
|
||
| # COMMAND ---------- | ||
|
|
||
| # MAGIC %sh | ||
| # MAGIC make wmain.out check | ||
| # MAGIC make clean | ||
| # MAGIC make check | ||
| # MAGIC |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,146 +1,146 @@ | ||
| \name{alligator} | ||
| \alias{alligator} | ||
| \docType{data} | ||
| \title{ American alligator Food Choice } | ||
|
|
||
| \description{ In 1985, American alligators were harvested by hunters | ||
| from August 26 to September 30 in peninsular Florida from lakes Oklawaha | ||
| (Putnam County), George (Putnam and Volusia counties), Hancock (Polk | ||
| County) and Trafford (Collier County). Lake, length and sex were | ||
| recorded for each alligator. Stomachs from a sample of alligators | ||
| 1.09-3.89m long were frozen prior to analysis. After thawing, stomach | ||
| contents were removed and separated and food items were identified and | ||
| tallied. Volumes were determined by water displacement. The stomach | ||
| contents of 219 alligators were classified into five categories of | ||
| primary food choice: Fish | ||
| (the most common primary food choice), Invertebrate (snails, insects, | ||
| crayfish, etc.), Reptile (turtles, alligators), Bird, and Other | ||
| (amphibians, plants, household pets, stones, and other debris). } | ||
|
|
||
| \usage{data(alligator)} | ||
| \format{ | ||
| A data frame with 80 observations on the following 5 variables. | ||
| \describe{ | ||
| \item{\code{lake}}{a factor with levels \code{George} \code{Hancock} \code{Oklawaha} \code{Trafford}} | ||
| \item{\code{sex}}{a factor with levels \code{female} \code{male}} | ||
| \item{\code{size}}{alligator size, a factor with levels \code{large} (>2.3m) \code{small} (<=2.3m)} | ||
| \item{\code{food}}{primary food choice, a factor with levels \code{bird} \code{fish} \code{invert} \code{other} \code{reptile}} | ||
| \item{\code{count}}{cell frequency, a numeric vector} | ||
| } | ||
| } | ||
|
|
||
| \details{ The table contains a fair number of 0 counts. \code{food} is | ||
| the response variable. \code{fish} is the most frequent choice, and | ||
| often taken as a baseline category in multinomial response models. } | ||
|
|
||
| \source{ | ||
| Agresti, A. (2002). | ||
| \emph{Categorical Data Analysis}, | ||
| New York: Wiley, 2nd Ed., Table 7.1 | ||
| } | ||
|
|
||
| \references{ | ||
| Delany MF, Linda SB, Moore CT (1999). | ||
| "Diet and condition of American alligators in 4 Florida lakes." | ||
| In \emph{Proceedings of the Annual Conference of the Southeastern | ||
| Association of Fish and Wildlife Agencies}, \bold{53}, | ||
| 375--389. | ||
| } | ||
|
|
||
| \examples{ | ||
|
|
||
| data(alligator) | ||
|
|
||
| ## nnet::multinom Multinomial logit model fit with neural nets | ||
| fit <- multinom(food ~ lake+size+sex, data=alligator, weights=count) | ||
|
|
||
| summary(fit$fitted.values) | ||
| ## 1=bird, 2=fish, 3=invert, 4=other, 5=reptile | ||
|
|
||
| (L=length(alligator$count)) | ||
| (N=sum(alligator$count)) | ||
| y.train=integer(N) | ||
| x.train=matrix(nrow=N, ncol=3) | ||
| x.test=matrix(nrow=L, ncol=3) | ||
| k=1 | ||
| for(i in 1:L) { | ||
| x.test[i, ]=as.integer( | ||
| c(alligator$lake[i], alligator$size[i], alligator$sex[i])) | ||
| if(alligator$count[i]>0) | ||
| for(j in 1:alligator$count[i]) { | ||
| y.train[k]=as.integer(alligator$food[i]) | ||
| x.train[k, ]=as.integer( | ||
| c(alligator$lake[i], alligator$size[i], alligator$sex[i])) | ||
| k=k+1 | ||
| } | ||
| } | ||
| table(y.train) | ||
| ##test mbart with token run to ensure installation works | ||
| set.seed(99) | ||
| check = mbart(x.train, y.train, nskip=1, ndpost=1) | ||
|
|
||
| \dontrun{ | ||
| set.seed(99) | ||
| check = mbart(x.train, y.train, nskip=1, ndpost=1) | ||
| post=mbart(x.train, y.train, x.test) | ||
|
|
||
| ##post=mc.mbart(x.train, y.train, x.test, mc.cores=8, seed=99) | ||
| ##check=predict(post, x.test, mc.cores=8) | ||
| ##print(cor(post$prob.test.mean, check$prob.test.mean)^2) | ||
|
|
||
| par(mfrow=c(3, 2)) | ||
| K=5 | ||
| for(j in 1:5) { | ||
| h=seq(j, L*K, K) | ||
| print(cor(fit$fitted.values[ , j], post$prob.test.mean[h])^2) | ||
| plot(fit$fitted.values[ , j], post$prob.test.mean[h], | ||
| xlim=0:1, ylim=0:1, | ||
| xlab=paste0('NN: Est. Prob. j=', j), | ||
| ylab=paste0('BART: Est. Prob. j=', j)) | ||
| abline(a=0, b=1) | ||
| } | ||
| par(mfrow=c(1, 1)) | ||
|
|
||
| L=16 | ||
| x.test=matrix(nrow=L, ncol=3) | ||
| k=1 | ||
| for(size in 1:2) | ||
| for(sex in 1:2) | ||
| for(lake in 1:4) { | ||
| x.test[k, ]=c(lake, size, sex) | ||
| k=k+1 | ||
| } | ||
| x.test | ||
|
|
||
| ## two sizes: 1=large: >2.3m, 2=small: <=2.3m | ||
| pred=predict(post, x.test) | ||
| ##pred=predict(post, x.test, mc.cores=8) | ||
| ndpost=nrow(pred$prob.test) | ||
|
|
||
| size.test=matrix(nrow=ndpost, ncol=K*2) | ||
| for(i in 1:K) { | ||
| j=seq(i, L*K/2, K) ## large | ||
| size.test[ , i]=apply(pred$prob.test[ , j], 1, mean) | ||
| j=j+L*K/2 ## small | ||
| size.test[ , i+K]=apply(pred$prob.test[ , j], 1, mean) | ||
| } | ||
| size.test.mean=apply(size.test, 2, mean) | ||
| size.test.025=apply(size.test, 2, quantile, probs=0.025) | ||
| size.test.975=apply(size.test, 2, quantile, probs=0.975) | ||
|
|
||
| plot(factor(1:K, labels=c('bird', 'fish', 'invert', 'other', 'reptile')), | ||
| rep(1, K), col=1:K, type='n', lwd=1, lty=0, | ||
| xlim=c(1, K), ylim=c(0, 0.5), ylab='Prob.', | ||
| sub="Multinomial BART\nFriedman's partial dependence function") | ||
| points(1:K, size.test.mean[1:K+K], col=1) | ||
| lines(1:K, size.test.025[1:K+K], col=1, lty=2) | ||
| lines(1:K, size.test.975[1:K+K], col=1, lty=2) | ||
| points(1:K, size.test.mean[1:K], col=2) | ||
| lines(1:K, size.test.025[1:K], col=2, lty=2) | ||
| lines(1:K, size.test.975[1:K], col=2, lty=2) | ||
| ## legend('topright', legend=c('Small', 'Large'), | ||
| ## pch=1, col=1:2) | ||
|
|
||
| } | ||
| } | ||
| \keyword{datasets} | ||
| \name{alligator} | ||
| \alias{alligator} | ||
| \docType{data} | ||
| \title{ American alligator Food Choice } | ||
|
|
||
| \description{ In 1985, American alligators were harvested by hunters | ||
| from August 26 to September 30 in peninsular Florida from lakes Oklawaha | ||
| (Putnam County), George (Putnam and Volusia counties), Hancock (Polk | ||
| County) and Trafford (Collier County). Lake, length and sex were | ||
| recorded for each alligator. Stomachs from a sample of alligators | ||
| 1.09-3.89m long were frozen prior to analysis. After thawing, stomach | ||
| contents were removed and separated and food items were identified and | ||
| tallied. Volumes were determined by water displacement. The stomach | ||
| contents of 219 alligators were classified into five categories of | ||
| primary food choice: Fish | ||
| (the most common primary food choice), Invertebrate (snails, insects, | ||
| crayfish, etc.), Reptile (turtles, alligators), Bird, and Other | ||
| (amphibians, plants, household pets, stones, and other debris). } | ||
|
|
||
| \usage{data(alligator)} | ||
| \format{ | ||
| A data frame with 80 observations on the following 5 variables. | ||
| \describe{ | ||
| \item{\code{lake}}{a factor with levels \code{George} \code{Hancock} \code{Oklawaha} \code{Trafford}} | ||
| \item{\code{sex}}{a factor with levels \code{female} \code{male}} | ||
| \item{\code{size}}{alligator size, a factor with levels \code{large} (>2.3m) \code{small} (<=2.3m)} | ||
| \item{\code{food}}{primary food choice, a factor with levels \code{bird} \code{fish} \code{invert} \code{other} \code{reptile}} | ||
| \item{\code{count}}{cell frequency, a numeric vector} | ||
| } | ||
| } | ||
|
|
||
| \details{ The table contains a fair number of 0 counts. \code{food} is | ||
| the response variable. \code{fish} is the most frequent choice, and | ||
| often taken as a baseline category in multinomial response models. } | ||
|
|
||
| \source{ | ||
| Agresti, A. (2002). | ||
| \emph{Categorical Data Analysis}, | ||
| New York: Wiley, 2nd Ed., Table 7.1 | ||
| } | ||
|
|
||
| \references{ | ||
| Delany MF, Linda SB, Moore CT (1999). | ||
| "Diet and condition of American alligators in 4 Florida lakes." | ||
| In \emph{Proceedings of the Annual Conference of the Southeastern | ||
| Association of Fish and Wildlife Agencies}, \bold{53}, | ||
| 375--389. | ||
| } | ||
|
|
||
| \examples{ | ||
|
|
||
| data(alligator) | ||
|
|
||
| ## nnet::multinom Multinomial logit model fit with neural nets | ||
| fit <- multinom(food ~ lake+size+sex, data=alligator, weights=count) | ||
|
|
||
| summary(fit$fitted.values) | ||
| ## 1=bird, 2=fish, 3=invert, 4=other, 5=reptile | ||
|
|
||
| (L=length(alligator$count)) | ||
| (N=sum(alligator$count)) | ||
| y.train=integer(N) | ||
| x.train=matrix(nrow=N, ncol=3) | ||
| x.test=matrix(nrow=L, ncol=3) | ||
| k=1 | ||
| for(i in 1:L) { | ||
| x.test[i, ]=as.integer( | ||
| c(alligator$lake[i], alligator$size[i], alligator$sex[i])) | ||
| if(alligator$count[i]>0) | ||
| for(j in 1:alligator$count[i]) { | ||
| y.train[k]=as.integer(alligator$food[i]) | ||
| x.train[k, ]=as.integer( | ||
| c(alligator$lake[i], alligator$size[i], alligator$sex[i])) | ||
| k=k+1 | ||
| } | ||
| } | ||
| table(y.train) | ||
| ##test mbart with token run to ensure installation works | ||
| set.seed(99) | ||
| check = mbart(x.train, y.train, nskip=1, ndpost=1) | ||
|
|
||
| \dontrun{ | ||
| set.seed(99) | ||
| check = mbart(x.train, y.train, nskip=1, ndpost=1) | ||
| post=mbart(x.train, y.train, x.test) | ||
|
|
||
| ##post=mc.mbart(x.train, y.train, x.test, mc.cores=8, seed=99) | ||
| ##check=predict(post, x.test, mc.cores=8) | ||
| ##print(cor(post$prob.test.mean, check$prob.test.mean)^2) | ||
|
|
||
| par(mfrow=c(3, 2)) | ||
| K=5 | ||
| for(j in 1:5) { | ||
| h=seq(j, L*K, K) | ||
| print(cor(fit$fitted.values[ , j], post$prob.test.mean[h])^2) | ||
| plot(fit$fitted.values[ , j], post$prob.test.mean[h], | ||
| xlim=0:1, ylim=0:1, | ||
| xlab=paste0('NN: Est. Prob. j=', j), | ||
| ylab=paste0('BART: Est. Prob. j=', j)) | ||
| abline(a=0, b=1) | ||
| } | ||
| par(mfrow=c(1, 1)) | ||
|
|
||
| L=16 | ||
| x.test=matrix(nrow=L, ncol=3) | ||
| k=1 | ||
| for(size in 1:2) | ||
| for(sex in 1:2) | ||
| for(lake in 1:4) { | ||
| x.test[k, ]=c(lake, size, sex) | ||
| k=k+1 | ||
| } | ||
| x.test | ||
|
|
||
| ## two sizes: 1=large: >2.3m, 2=small: <=2.3m | ||
| pred=predict(post, x.test) | ||
| ##pred=predict(post, x.test, mc.cores=8) | ||
| ndpost=nrow(pred$prob.test) | ||
|
|
||
| size.test=matrix(nrow=ndpost, ncol=K*2) | ||
| for(i in 1:K) { | ||
| j=seq(i, L*K/2, K) ## large | ||
| size.test[ , i]=apply(pred$prob.test[ , j], 1, mean) | ||
| j=j+L*K/2 ## small | ||
| size.test[ , i+K]=apply(pred$prob.test[ , j], 1, mean) | ||
| } | ||
| size.test.mean=apply(size.test, 2, mean) | ||
| size.test.025=apply(size.test, 2, quantile, probs=0.025) | ||
| size.test.975=apply(size.test, 2, quantile, probs=0.975) | ||
|
|
||
| plot(factor(1:K, labels=c('bird', 'fish', 'invert', 'other', 'reptile')), | ||
| rep(1, K), col=1:K, type='n', lwd=1, lty=0, | ||
| xlim=c(1, K), ylim=c(0, 0.5), ylab='Prob.', | ||
| sub="Multinomial BART\nFriedman's partial dependence function") | ||
| points(1:K, size.test.mean[1:K+K], col=1) | ||
| lines(1:K, size.test.025[1:K+K], col=1, lty=2) | ||
| lines(1:K, size.test.975[1:K+K], col=1, lty=2) | ||
| points(1:K, size.test.mean[1:K], col=2) | ||
| lines(1:K, size.test.025[1:K], col=2, lty=2) | ||
| lines(1:K, size.test.975[1:K], col=2, lty=2) | ||
| ## legend('topright', legend=c('Small', 'Large'), | ||
| ## pch=1, col=1:2) | ||
|
|
||
| } | ||
| } | ||
| \keyword{datasets} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.