Merge branch 'master' into summary2

R/h2o-package/demo/h2o.gbm.R

@@ -1,9 +1,9 @@
 # This is a demo of H2O's GBM function
 # It imports a data set, parses it, and prints a summary
 # Then, it runs GBM on a subset of the dataset
-library(h2o)
-localH2O = new("H2OClient", ip="localhost", port=54321)
-h2o.checkClient(localH2O)
+library(h2oWrapper)
+h2oWrapper.installDepPkgs()
+localH2O = h2oWrapper.init(ip = "localhost", port = 54321, startH2O = TRUE, silentUpgrade = TRUE, promptUpgrade = FALSE)
 
 prostate.hex = h2o.importFile(localH2O, system.file("extdata", "prostate.csv", package="h2o"), "prostate.hex")
 summary(prostate.hex)

R/h2o-package/demo/h2o.glm.R

@@ -2,9 +2,9 @@
 # It imports a data set, parses it, and prints a summary
 # Then, it runs GLM with a binomial link function using 10-fold cross-validation
 # Note: This demo runs H2O on localhost:54321
-library(h2o)
-localH2O = new("H2OClient", ip = "localhost", port = 54321)
-h2o.checkClient(localH2O)
+library(h2oWrapper)
+h2oWrapper.installDepPkgs()
+localH2O = h2oWrapper.init(ip = "localhost", port = 54321, startH2O = TRUE, silentUpgrade = TRUE, promptUpgrade = FALSE)
 
 prostate.hex = h2o.importFile(localH2O, path = system.file("extdata", "prostate.csv", package="h2o"), key = "prostate.hex")
 summary(prostate.hex)
@@ -17,4 +17,4 @@ axis(1, at = 1:length(myLabels), labels = myLabels)
 abline(h = 0, col = 2, lty = 2)
 title("Coefficients from Logistic Regression\n of Prostate Cancer Data")
 
-barplot(prostate.glm@model$coefficients, main = "Coefficients from Logistic Regression\n of Prostate Cancer Data")
+barplot(prostate.glm@model$coefficients, main = "Coefficients from Logistic Regression\n of Prostate Cancer Data")

R/h2o-package/demo/h2o.kmeans.R

@@ -2,9 +2,9 @@
 # It imports a data set, parses it, and prints a summary
 # Then, it runs K-Means with k = 5 centers on a subset of characteristics
 # Note: This demo runs H2O on localhost:54321
-library(h2o)
-localH2O = new("H2OClient", ip="localhost", port=54321)
-h2o.checkClient(localH2O)
+library(h2oWrapper)
+h2oWrapper.installDepPkgs()
+localH2O = h2oWrapper.init(ip = "localhost", port = 54321, startH2O = TRUE, silentUpgrade = TRUE, promptUpgrade = FALSE)
 
 prostate.hex = h2o.importFile(localH2O, system.file("extdata", "prostate.csv", package="h2o"), "prostate.hex")
 summary(prostate.hex)
@@ -34,4 +34,4 @@ par(mfrow = c(1,2))
 prostate.ctrs = as.data.frame(prostate.km@model$centers)
 plot(prostate.ctrs[,1:2])
 plot(prostate.ctrs[,3:4])
-title("K-Means Centers for k = 10", outer = TRUE, line = -2.0)
+title("K-Means Centers for k = 10", outer = TRUE, line = -2.0)

R/h2o-package/demo/h2o.prcomp.R

@@ -1,9 +1,9 @@
 # This is a demo of H2O's PCA function
 # It imports a data set, parses it, and prints a summary
 # Then, it runs PCA on a subset of the features
-library(h2o)
-localH2O = new("H2OClient", ip="localhost", port=54321)
-h2o.checkClient(localH2O)
+library(h2oWrapper)
+h2oWrapper.installDepPkgs()
+localH2O = h2oWrapper.init(ip = "localhost", port = 54321, startH2O = TRUE, silentUpgrade = TRUE, promptUpgrade = FALSE)
 
 australia.hex = h2o.importFile(localH2O, system.file("extdata", "australia.csv", package="h2o"), "australia.hex")
 summary(australia.hex)
@@ -13,4 +13,4 @@ print(australia.pca)
 plot(australia.pca)
 
 australia.pca2 = h2o.prcomp(australia.hex, tol = 0.5, standardize = FALSE)
-print(australia.pca2)
+print(australia.pca2)

R/h2o-package/demo/h2o.randomForest.R

@@ -2,9 +2,9 @@
 # It imports a data set, parses it, and prints a summary
 # Then, it runs RF with 50 trees, maximum depth of 100, using the iris class as the response
 # Note: This demo runs H2O on localhost:54321
-library(h2o)
-localH2O = new("H2OClient", ip="localhost", port=54321)
-h2o.checkClient(localH2O)
+library(h2oWrapper)
+h2oWrapper.installDepPkgs()
+localH2O = h2oWrapper.init(ip = "localhost", port = 54321, startH2O = TRUE, silentUpgrade = TRUE, promptUpgrade = FALSE)
 
 iris.hex = h2o.importFile(localH2O, path = system.file("extdata", "iris.csv", package="h2o"), key = "iris.hex")
 summary(iris.hex)
@@ -16,4 +16,4 @@ invisible(readline("Hit <Return> to continue: "))
 covtype.hex = h2o.importFile(localH2O, path = system.file("extdata", "covtype.csv", package="h2o"), key = "covtype.hex")
 summary(covtype.hex)
 covtype.rf = h2o.randomForest(y = "Cover_Type", x = setdiff(colnames(covtype.hex), c("Cover_Type", "Aspect", "Hillshade_9am")), data = covtype.hex, ntree = 50, depth = 150)
-print(covtype.rf)
+print(covtype.rf)

R/h2o-package/man/H2OClient-class.Rd

@@ -49,7 +49,6 @@ Objects can be created by calls of the form \code{new("H2OClient", ...)}
 library(h2oWrapper)
 h2oWrapper.installDepPkgs()
 localH2O = h2oWrapper.init(ip = "localhost", port = 54321, startH2O = TRUE, silentUpgrade = TRUE, promptUpgrade = FALSE)
-library(h2o)
 showClass("H2OClient")
 }
 \keyword{classes}

R/h2o-package/man/h2o.checkClient.Rd

@@ -44,7 +44,6 @@ h2o.checkClient(object)
 library(h2oWrapper)
 h2oWrapper.installDepPkgs()
 localH2O = h2oWrapper.init(ip = "localhost", port = 54321, startH2O = TRUE, silentUpgrade = TRUE, promptUpgrade = FALSE)
-library(h2o)
 h2o.checkClient(localH2O)
 }
 % Add one or more standard keywords, see file 'KEYWORDS' in the

R/h2o-package/man/h2o.gbm.Rd

@@ -0,0 +1,77 @@
+\name{h2o.gbm}
+\alias{h2o.gbm}
+%- Also NEED an '\alias' for EACH other topic documented here.
+\title{
+H2O: GBM
+}
+%%  ~~function to do ... ~~
+
+\description{Builds gradient boosed classification trees on a parsed data set.
+}
+\usage{
+h2o.gbm(y, x, distribution, data, n.trees, interaction.depth, n.minobsinnode, shrinkage)
+}
+\arguments{
+  \item{y}{
+The name or index of the response variable. If the data does not contain a header, this is the column index number starting at 0, and increasing from left to right. (The response must be either an integer or a categorical variable).
+}
+  \item{x}{
+A vector containing the names or indices of the predictor variables to use in building the GBM model.
+}
+  \item{distribution}{
+The type of GBM model to be produced, categorization is "multinomial" (default), "gaussian" used for regression.
+}
+  \item{data}{
+An \code{\linkS4class{H2OParsedData}} object containing the variables in the model.
+}
+  \item{n.trees}{
+Number of trees to grow. Must be a nonnegative integer.
+}
+  \item{interaction.depth}{
+Maximum depth to grow the tree.
+}
+  \item{n.minobsinnode}{
+Minimum number of rows to assign to teminal nodes.
+}
+  \item{shrinkage}{
+A learning-rate parameter defining step size reduction.
+}   
+  }
+\value{
+An object of class \code{\linkS4class{H2OGBM}} with slots key, data, and model, where the last is a list of the following components:
+\item{type }{The type of the tree, which currently must be classification.}
+\item{n.trees }{Number of trees grown.}
+\item{oob_err }{Out of bag error rate.}
+\item{forest }{A matrix giving the minimum, mean, and maximum of the tree depth and number of leaves.}
+\item{confusion }{Confusion matrix of the prediction.}
+}
+\references{
+
+1. Elith, Jane, John R Leathwick, and Trevor Hastie. "A Working Guide to
+Boosted Regression Trees." Journal of Animal Ecology 77.4 (2008): 802-813
+
+2. Friedman, Jerome, Trevor Hastie, Saharon Rosset, Robert Tibshirani,
+and Ji Zhu. "Discussion of Boosting Papers." Ann. Statist 32 (2004): 
+102-107
+
+3. Hastie, Trevor, Robert Tibshirani, and J Jerome H Friedman. The
+Elements of Statistical Learning.
+Vol.1. N.p.: Springer New York, 2001. 
+http://www.stanford.edu/~hastie/local.ftp/Springer/OLD//ESLII_print4.pdf
+}
+
+
+\seealso{
+For more information see: http://docs.0xdata.com
+}
+\examples{
+library(h2oWrapper)
+h2oWrapper.installDepPkgs()
+localH2O = h2oWrapper.init(ip = "localhost", port = 54321, startH2O = TRUE, silentUpgrade = TRUE, promptUpgrade = FALSE)
+# Run classification GBM on CAPSULE ~ AGE + RACE + PSA + DCAPS
+prostate.hex = h2o.importURL(localH2O, path = "https://raw.github.com/0xdata/h2o/master/smalldata/logreg/prostate.csv", key = "prostate.hex")
+h2o.gbm(y = "CAPSULE", x = c("AGE","RACE","PSA","DCAPS"), data = prostate.hex, n.trees = 100, interaction.depth = 8, n.minobsinnode = 10, shrinkage = 0.2)
+# Run regression GBM on CAPSULE ~ AGE + RACE + PSA + DCAPS
+myX = setdiff(colnames(prostate.hex), c("ID", "DPROS", "DCAPS", "VOL"))
+h2o.gbm(y = "VOL", x = myX, data = prostate.hex, n.trees = 10, interaction.depth = 5, shrinkage = 0.1)
+}

R/h2o-package/man/h2o.getTree.Rd

@@ -48,7 +48,6 @@ The particular tree to retrieve. (Must be an integer between 1 and \code{ntree})
 library(h2oWrapper)
 h2oWrapper.installDepPkgs()
 localH2O = h2oWrapper.init(ip = "localhost", port = 54321, startH2O = TRUE, silentUpgrade = TRUE, promptUpgrade = FALSE)
-library(h2o)
 irisPath = system.file("extdata", "iris.csv", package="h2o")
 iris.hex = h2o.importFile(localH2O, path = irisPath, key = "iris.hex")
 iris.rf = h2o.randomForest(y = 4, data = iris.hex, ntree = 50, depth = 100)

R/h2o-package/man/h2o.glm.Rd

@@ -80,7 +80,6 @@ The slot xval is a list of \code{\linkS4class{H2OGLMModel}} objects representing
 library(h2oWrapper)
 h2oWrapper.installDepPkgs()
 localH2O = h2oWrapper.init(ip = "localhost", port = 54321, startH2O = TRUE, silentUpgrade = TRUE, promptUpgrade = FALSE)
-library(h2o)
 # Run GLM of CAPSULE ~ AGE + RACE + PSA + DCAPS
 prostate.hex = h2o.importURL(localH2O, path = "https://raw.github.com/0xdata/h2o/master/smalldata/logreg/prostate.csv", key = "prostate.hex")
 h2o.glm(y = "CAPSULE", x = c("AGE","RACE","PSA","DCAPS"), data = prostate.hex, family = 

R/h2o-package/man/h2o.importFile.Rd

@@ -55,7 +55,6 @@ If \code{parse = TRUE}, the function returns an object of class \code{\linkS4cla
 library(h2oWrapper)
 h2oWrapper.installDepPkgs()
 localH2O = h2oWrapper.init(ip = "localhost", port = 54321, startH2O = TRUE, silentUpgrade = TRUE, promptUpgrade = FALSE)
-library(h2o)
 irisPath = system.file("extdata", "iris.csv", package="h2o")
 iris.hex = h2o.importFile(localH2O, path = irisPath, key = "iris.hex")
 summary(iris.hex)

R/h2o-package/man/h2o.importFolder.Rd

@@ -49,7 +49,6 @@ WARNING: In H2O, import is lazy! Do not modify the data files on hard disk until
 library(h2oWrapper)
 h2oWrapper.installDepPkgs()
 localH2O = h2oWrapper.init(ip = "localhost", port = 54321, startH2O = TRUE, silentUpgrade = TRUE, promptUpgrade = FALSE)
-library(h2o)
 myPath = paste(path.package("h2o"), "extdata", sep="/")
 all_files.hex = h2o.importFolder(localH2O, path = myPath)
 for(i in 1:length(all_files.hex))

R/h2o-package/man/h2o.importHDFS.Rd

@@ -52,7 +52,6 @@ When the path is a directory, if \code{parse = TRUE}, the function returns a lis
 library(h2oWrapper)
 h2oWrapper.installDepPkgs()
 localH2O = h2oWrapper.init(ip = "localhost", port = 54321, startH2O = TRUE, silentUpgrade = TRUE, promptUpgrade = FALSE)
-library(h2o)
 covtype.hex = importHDFS(localH2O, path = "hdfs://192.168.1.173:54321/0xdiag/datasets/standard/covtype.data", parse = TRUE)
 summary(covtype.hex)
 

R/h2o-package/man/h2o.importURL.Rd

@@ -55,7 +55,6 @@ If \code{parse = TRUE}, the function returns an object of class \code{\linkS4cla
 library(h2oWrapper)
 h2oWrapper.installDepPkgs()
 localH2O = h2oWrapper.init(ip = "localhost", port = 54321, startH2O = TRUE, silentUpgrade = TRUE, promptUpgrade = FALSE)
-library(h2o)
 prostate.hex = h2o.importURL(localH2O, path = "https://raw.github.com/0xdata/h2o/master/smalldata/logreg/prostate.csv", key = "prostate.hex")
 summary(prostate.hex)
 }

R/h2o-package/man/h2o.kmeans.Rd

@@ -60,7 +60,6 @@ An object of class \code{\linkS4class{H2OKMeansModel}} with slots key, data, and
 library(h2oWrapper)
 h2oWrapper.installDepPkgs()
 localH2O = h2oWrapper.init(ip = "localhost", port = 54321, startH2O = TRUE, silentUpgrade = TRUE, promptUpgrade = FALSE)
-library(h2o)
 prosPath = system.file("extdata", "prostate.csv", package="h2o")
 prostate.hex = h2o.importFile(localH2O, path = prosPath)
 h2o.kmeans(data = prostate.hex, centers = 10, cols = c("AGE", "RACE", "VOL", "GLEASON"))

R/h2o-package/man/h2o.parseRaw.Rd

@@ -48,7 +48,6 @@ After the raw data file is parsed, it will be automatically deleted from the H2O
 library(h2oWrapper)
 h2oWrapper.installDepPkgs()
 localH2O = h2oWrapper.init(ip = "localhost", port = 54321, startH2O = TRUE, silentUpgrade = TRUE, promptUpgrade = FALSE)
-library(h2o)
 prosPath = system.file("extdata", "prostate.csv", package="h2o")
 prostate.raw = h2o.importFile(localH2O, path = prosPath, parse = FALSE)
 # Do not modify prostate.csv on disk at this point!

R/h2o-package/man/h2o.prcomp.Rd

@@ -50,7 +50,6 @@ The signs of the columns of the rotation matrix are arbitrary, and so may differ
 library(h2oWrapper)
 h2oWrapper.installDepPkgs()
 localH2O = h2oWrapper.init(ip = "localhost", port = 54321, startH2O = TRUE, silentUpgrade = TRUE, promptUpgrade = FALSE)
-library(h2o)
 prosPath = system.file("extdata", "prostate.csv", package="h2o")
 prostate.hex = h2o.importFile(localH2O, path = prosPath)
 prostate.pca = h2o.prcomp(data = prostate.hex, standardize = TRUE)

R/h2o-package/man/h2o.predict.Rd

@@ -44,7 +44,6 @@ A \code{\linkS4class{H2OParsedData}} object containing the predictions.
 library(h2oWrapper)
 h2oWrapper.installDepPkgs()
 localH2O = h2oWrapper.init(ip = "localhost", port = 54321, startH2O = TRUE, silentUpgrade = TRUE, promptUpgrade = FALSE)
-library(h2o)
 # Run GLM of CAPSULE ~ AGE + RACE + PSA + DCAPS
 prostate.hex = h2o.importURL(localH2O, path = "https://raw.github.com/0xdata/h2o/master/smalldata/logreg/prostate.csv", key = "prostate.hex")
 prostate.glm = h2o.glm(y = "CAPSULE", x = c("AGE","RACE","PSA","DCAPS"), data = prostate.hex, family = 

R/h2o-package/man/h2o.randomForest.Rd

@@ -13,7 +13,7 @@ h2o.randomForest(y, x, data, ntree = 50, depth = 2147483647, classwt = as.numeri
 %- maybe also 'usage' for other objects documented here.
 \arguments{
   \item{y}{
-The name or index of the response variable. If the data does not contain a header, this is the column index. (The response must be either an integer or a categorical variable).
+The name or index of the response variable. If the data does not contain a header, this is the column index, designated by increasing numbers from left to right. (The response must be either an integer or a categorical variable).
 }
 \item{x}{
 A vector containing the names or indices of the predictor variables to use in building the random forest model.
@@ -31,7 +31,7 @@ Number of trees to grow. (Must be a nonnegative integer).
   (Optional) Priors of the classes. Need not add up to one. If missing, defaults to all weights set at 1.0.}
 }
 \details{
-Currently, only classification regression trees are supported. Note that indexing begins at zero, so for example, to specify the first column as the response variable, set \code{y = 0}.
+Currently, only classification trees are supported. Note that indexing begins at zero, so for example, to specify the first column as the response variable, set \code{y = 0}.
 }
 \value{
 An object of class \code{\linkS4class{H2ORForestModel}} with slots key, data, and model, where the last is a list of the following components:
@@ -65,7 +65,6 @@ An object of class \code{\linkS4class{H2ORForestModel}} with slots key, data, an
 library(h2oWrapper)
 h2oWrapper.installDepPkgs()
 localH2O = h2oWrapper.init(ip = "localhost", port = 54321, startH2O = TRUE, silentUpgrade = TRUE, promptUpgrade = FALSE)
-library(h2o)
 irisPath = system.file("extdata", "iris.csv", package="h2o")
 iris.hex = h2o.importFile(localH2O, path = irisPath, key = "iris.hex")
 h2o.randomForest(y = 5, x = c(2,3,4), data = iris.hex, ntree = 50, depth = 100, 

R/h2o-package/man/h2o.setColNames.Rd

@@ -46,7 +46,6 @@ This function modifies the \code{data} file directly. It does not create a new c
 library(h2oWrapper)
 h2oWrapper.installDepPkgs()
 localH2O = h2oWrapper.init(ip = "localhost", port = 54321, startH2O = TRUE, silentUpgrade = TRUE, promptUpgrade = FALSE)
-library(h2o)
 irisPath = system.file("extdata", "iris.csv", package="h2o")
 iris.hex = h2o.importFile(localH2O, path = irisPath, key = "iris.hex")
 summary(iris.hex)

R/h2oWrapper-package/R/h2oWrapper.R

@@ -128,7 +128,8 @@ h2oWrapper.checkPackage <- function(myURL, silentUpgrade, promptUpgrade) {
       warning("Mismatched MD5 hash! Check you have downloaded complete R package.")
     install.packages(paste(getwd(), myFile, sep="/"), repos = NULL, type = "source")
     file.remove(paste(getwd(), myFile, sep="/"))
-    cat("\nSuccess\nYou may now type 'library(h2o)' to load the R package\n\n")
+    #cat("\nSuccess\nYou may now type 'library(h2o)' to load the R package\n\n")
+    library(h2o)
   }
 }
 
@@ -153,4 +154,4 @@ h2oWrapper.__formatError <- function(error, prefix="  ") {
   for (i in 1:length(items))
     result = paste(result, prefix, items[i], "\n", sep="")
   result
-}
+}

prj.el

@@ -17,6 +17,6 @@
  '(jde-sourcepath (quote ("./src")))
  '(jde-run-option-hotspot-type (quote server))
  '(jde-compile-option-target (quote ("1.6")))
- '(jde-run-option-heap-size (quote ((1100 . "megabytes") (1100 . "megabytes"))))
+ '(jde-run-option-heap-size (quote ((4000 . "megabytes") (4000 . "megabytes"))))
  '(jde-run-application-class "water.Boot")
  '(jde-compile-option-debug (quote ("all" (t t t)))))