Merge branch 'master' of github.com:h2oai/h2o

R/H2OTestDemo.R

@@ -8,7 +8,7 @@ localH2O = new("H2OClient", ip = "localhost", port = 54321)
 # h2o.checkClient(localH2O)
 
 # Test using prostate cancer data set
-prostate.hex = h2o.importURL(localH2O, path = "https://raw.github.com/0xdata/h2o/master/smalldata/logreg/prostate.csv", key = "prostate.hex")
+prostate.hex = h2o.importURL(localH2O, path = "https://raw.github.com/h2oai/h2o/master/smalldata/logreg/prostate.csv", key = "prostate.hex")
 prostate.sum = summary(prostate.hex)
 print(prostate.sum)
 prostate.glm = h2o.glm(y = "CAPSULE", x = c("AGE","RACE","PSA","DCAPS"), data = prostate.hex, family = "binomial", nfolds = 10, alpha = 0.5)
@@ -38,13 +38,13 @@ for(i in 1:length(glm_test.hex))
 
 
 #Test of GLMGrid using prostate cancer data set
-prostate.hex = h2o.importURL(localH2O, path = "https://raw.github.com/0xdata/h2o/master/smalldata/logreg/prostate.csv", key = "prostate.hex")
+prostate.hex = h2o.importURL(localH2O, path = "https://raw.github.com/h2oai/h2o/master/smalldata/logreg/prostate.csv", key = "prostate.hex")
 prostate.sum = summary(prostate.hex)
 prostate.glmgrid = h2o.glmgrid(y = "CAPSULE", x = c("AGE","RACE","PSA","DCAPS"), data = prostate.hex, family = "binomial", nfolds = 10, alpha = c(0.2,0.5,1),lambda=c(1e-4,1))
 print(prostate.glmgrid)
 
 # Test of PCA using prostate cancer data set
-prostate.hex = h2o.importURL(localH2O, path = "https://raw.github.com/0xdata/h2o/master/smalldata/logreg/prostate.csv", key = "prostate.hex")
+prostate.hex = h2o.importURL(localH2O, path = "https://raw.github.com/h2oai/h2o/master/smalldata/logreg/prostate.csv", key = "prostate.hex")
 prostate.pca = h2o.prcomp(prostate.hex)
 print(prostate.pca)
 summary(prostate.pca)

R/README.txt

@@ -1,108 +1,36 @@
 H2O in R
-------------
-
+--------
 
 These instructions assume you are using R 2.13.0 or later.  
 
-**STEP 1**
-
-The download package can be obtained by clicking on the button "Download H2O" at http://0xdata.com/h2o <http://0xdata.com/h2o.
-
-Unzip the downloaded h2o zip file
-
-
-**STEP 2: Console Users and Studio Users should follow the same steps: **
-
-In the R console install the package by 
-
-1. Visiting http://0xdata.com/downloadtable/
-2. Choosing the version of H2O appropriate for their environment 
-3. Copy and pasting the R command shown below the downloadable zip file on the download page for the version of their choice into their R console. 
-
-
-Correctly following the above steps will return output similar to the following: 
-
-trying URL 'http://s3.amazonaws.com/h2o-release/h2o/master/1247/R/bin/macosx/contrib/3.0/h2o_2.3.0.1247.tgz'
-Content type 'application/x-tar; charset=binary' length 36702378 bytes (35.0 Mb)
-opened URL
-==================================================
-downloaded 35.0 Mb
-
-
-**STEP 3**
-
-Start an instance of H2O. If you have questions about how to do this see the notes provided at the bottom of the page for starting from a zip file.
-
-If users choose to not start an instance of H2O prior to attempting to connect to H2O through R, an instance will be started automatically for them at ip: localhost, port: 54321.
-
-*Users should be aware that in order for H2O to successfully run through R, an instance of H2O must also simultaneously be running. If the instance of H2O is stopped, the R program will no longer run, and work done will be lost.* 
-
-
-**STEP 4** 
-
-call the H2O package in the R environment, start the connection between R and H2O at ip: localhost and port: 54321
-
-
-  >library(h2o)
-
-  >localH2O = h2o.init()
-
-
 
-**STEP 6** 
+**STEP 1: Unzip**
 
-Here is an example of using the above object in an H2O call in R
+If you are reading this, you probably already downloaded an h2o zip file and unzipped it.
+(Note:  Obtain a zip file from the Download button at http://h2o.ai)
 
 
+**STEP 2: Install the H2O R Package**
 
-  >irisPath = system.file("extdata", "iris.csv", package="h2o")
-  >iris.hex = h2o.importFile(localH2O, path = irisPath, key = "iris.hex")
-  >summary(iris.hex)
+In a terminal window, type:
 
+R CMD INSTALL h2o*.gz
 
 
+**STEP 3: Start a connection to H2O**
 
+Load the H2O package in the R environment.  Start the connection between R and H2O (with defaults at ip: localhost and port: 54321).
+Look at the help for h2o.init() for additional information about how to start and connect to H2O.
 
-Getting started from a zip file
--------------------------------
+  > library(h2o)
+  > localH2O = h2o.init()
 
 
-1. Download the latest release of H2O as a .zip file from the H2O website http://0xdata.com/h2O/.
+**STEP 4: Drive H2O from R** 
 
-2. From your terminal change your working directory to the same directory where your .zip file is saved.
-
-3. From your terminal, unzip the .zip file.  For example:
-
-
-  unzip h2o-1.7.0.520.zip
-
-4. At the prompt enter the following commands.  (Choose a unique name (use the -name option) for yourself if other people might be running H2O in your network.)
-
-
-  cd h2o-1.7.0.520 
-  java -Xmx1g -jar h2o.jar -name mystats-cloud
-
-5. Wait a few moments and the output similar to the following will appear in your terminal window:
-
-
-
-  03:05:45.311 main      INFO WATER: ----- H2O started -----
-  03:05:45.312 main      INFO WATER: Build git branch: master
-  03:05:45.312 main      INFO WATER: Build git hash: f253798433c109b19acd14cb973b45f255c59f3f
-  03:05:45.312 main      INFO WATER: Build git describe: f253798
-  03:05:45.312 main      INFO WATER: Build project version: 1.7.0.520
-  03:05:45.313 main      INFO WATER: Built by: 'jenkins'
-  03:05:45.313 main      INFO WATER: Built on: 'Thu Sep 12 00:01:52 PDT 2013'
-  03:05:45.313 main      INFO WATER: Java availableProcessors: 8
-  03:05:45.321 main      INFO WATER: Java heap totalMemory: 0.08 gb
-  03:05:45.321 main      INFO WATER: Java heap maxMemory: 0.99 gb
-  03:05:45.322 main      INFO WATER: ICE root: '/tmp/h2o-tomk'
-  03:05:45.364 main      INFO WATER: Internal communication uses port: 54322
-  +                                  Listening for HTTP and REST traffic on  http://192.168.1.52:54321/
-  03:05:45.409 main      INFO WATER: H2O cloud name: 'mystats-cloud'
-  03:05:45.409 main      INFO WATER: (v1.7.0.520) 'mystats-cloud' on /192.168.1.52:54321, discovery address /236.151.114.91:60567
-  03:05:45.411 main      INFO WATER: Cloud of size 1 formed [/192.168.1.52:54321]
-  03:05:45.543 main      INFO WATER: Log dir: '/tmp/h2o-tomk/h2ologs'
+  > irisPath = system.file("extdata", "iris.csv", package="h2o")
+  > iris.hex = h2o.importFile(localH2O, irisPath)
+  > summary(iris.hex)
 
 
 
@@ -126,16 +54,3 @@ memory).  For best performance, Xmx should be 4x the size of your
 data, but never more than the total amount of memory on your
 computer. For larger data sets, running on a server or service 
 with more memory available for computing is recommended. 
-
-
-
-
-
-
-
-
-
-
-
-
-

R/h2o-DESCRIPTION.template

@@ -2,11 +2,11 @@ Package: h2o
 Type: Package
 Title: H2O R Interface
 Version: SUBST_PROJECT_VERSION
-Date: 2014-05-15
+Date: 2015-02-05
 Author: Anqi Fu, Spencer Aiello, Ariel Rao, Tom Kraljevic and Petr Maj,
-        with contributions from the 0xdata team
+        with contributions from the H2O team
 Maintainer: Tom Kraljevic <[email protected]>
-Description: Run H2O via its REST API from within R.
+Description: Run H2O via its REST interface from within R.
 License: Apache License (== 2.0)
 Depends: R (>= 2.13.0), statmod, survival, stats, graphics, utils, methods
 Imports: RCurl, rjson, tools
@@ -15,4 +15,4 @@ Collate: Wrapper.R Internal.R Classes.R ParseImport.R models.R Algorithms.R
 NeedsCompilation: no
 SystemRequirements: Java (>= 1.6)
 Suggests: plyr
-URL: http://www.0xdata.com
+URL: http://www.h2o.ai

R/h2o-package.template

@@ -13,36 +13,35 @@ This is a package for running H2O via its REST API from within R. To communicate
 Package: \tab h2o\cr
 Type: \tab Package\cr
 Version: \tab SUBST_PROJECT_VERSION\cr
-Date: \tab 2014-05-15\cr
+Date: \tab 2015-02-05\cr
 License: \tab Apache License (== 2.0)\cr
 Depends: \tab R (>= 2.13.0), RCurl, rjson, statmod, tools, methods, utils\cr
 }
 
-This package allows the user to run basic H2O commands using R commands. In order to use it, you must first have H2O running (See \href{http://docs.0xdata.com/newuser/quickstart_jar.html}{How to Start H2O}). To run H2O on your local machine, call \code{h2o.init} without any arguments, and H2O will be automatically launched on \url{http://127.0.0.1:54321}, where the IP is "127.0.0.1" and the port is 54321. If H2O is running on a cluster, you must provide the IP and port of the remote machine as arguments to the h2o.init() call. 
+This package allows the user to run basic H2O commands using R commands. In order to use it, you must first have H2O running (See \href{http://docs.h2o.ai/newuser/quickstart_jar.html}{How to Start H2O}). To run H2O on your local machine, call \code{h2o.init} without any arguments, and H2O will be automatically launched on http://127.0.0.1:54321, where the IP is "127.0.0.1" and the port is 54321. If H2O is running on a cluster, you must provide the IP and port of the remote machine as arguments to the h2o.init() call. 
 
 H2O supports a number of standard statistical models, such as GLM, K-means, and Random Forest classification. For example, to run GLM, call \code{\link{h2o.glm}} with the H2O parsed data and parameters (response variable, error distribution, etc...) as arguments. (The operation will be done on the server associated with the data object where H2O is running, not within the R environment). 
 
 Note that no actual data is stored in the R workspace; and no actual work is carried out by R. R only saves the named objects, which uniquely identify the data set, model, etc on the server. When the user makes a request, R queries the server via the REST API, which returns a JSON file with the relevant information that R then displays in the console.
 }
 \author{
-Anqi Fu, Tom Kraljevic and Petr Maj, with contributions from the 0xdata team
+Anqi Fu, Tom Kraljevic and Petr Maj, with contributions from the H2O team
 
-Maintainer: Ariel Rao <ariel@0xdata.com>
+Maintainer: Tom Kraljevic <tomk@0xdata.com>
 }
 \references{
 \itemize{
-  \item \href{http://www.0xdata.com}{0xdata Homepage}
-  \item \href{http://docs.0xdata.com}{H2O Documentation}
-  \item \href{https://github.com/0xdata/h2o}{H2O on Github}
+  \item \href{http://www.h2o.ai}{H2O Homepage}
+  \item \href{http://docs.h2o.ai}{H2O Documentation}
+  \item \href{https://github.com/h2oai/h2o}{H2O on Github}
   }
 }
 \keyword{ package }
 \examples{
-# Check connection with H2O and ensure local H2O R package matches server version.
-# Optionally, ask for startH2O to start H2O if it's not already running.
-# Note that for startH2O to work, the IP must be 127.0.0.1 or localhost with port 54321.
+# Connect to an instance of H2O (after creating it, if needed).
+# See the help for h2o.init() for more details.
 library(h2o)
-localH2O = h2o.init(ip = "127.0.0.1", port = 54321, startH2O = TRUE)
+localH2O = h2o.init()
 
 # Import iris dataset into H2O and print summary
 irisPath = system.file("extdata", "iris.csv", package = "h2o")

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

@@ -112,10 +112,10 @@ h2o.deeplearning(x = 1:4, y = 5, data = iris.hex, activation = "Tanh",
 \dontrun{
 # DeepLearning variable importance
 # Also see:
-#   https://github.com/0xdata/h2o/blob/master/R/tests/testdir_demos/runit_demo_VI_all_algos.R
+#   https://github.com/h2oai/h2o/blob/master/R/tests/testdir_demos/runit_demo_VI_all_algos.R
 data.hex = h2o.importFile(
   localH2O,
-  path = "https://raw.github.com/0xdata/h2o/master/smalldata/bank-additional-full.csv",
+  path = "https://raw.github.com/h2oai/h2o/master/smalldata/bank-additional-full.csv",
   key = "data.hex")
 myX = 1:20
 myY="y"

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

@@ -112,10 +112,10 @@ h2o.gbm(y = dependent, x = independent, data = australia.hex, n.trees = 3, inter
 
 # GBM variable importance
 # Also see:
-#   https://github.com/0xdata/h2o/blob/master/R/tests/testdir_demos/runit_demo_VI_all_algos.R
+#   https://github.com/h2oai/h2o/blob/master/R/tests/testdir_demos/runit_demo_VI_all_algos.R
 data.hex = h2o.importFile(
   localH2O,
-  path = "https://raw.github.com/0xdata/h2o/master/smalldata/bank-additional-full.csv",
+  path = "https://raw.github.com/h2oai/h2o/master/smalldata/bank-additional-full.csv",
   key = "data.hex")
 myX = 1:20
 myY="y"

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

@@ -153,10 +153,10 @@ h2o.glm(y = "VOL", x = myX, data = prostate.hex, family = "gaussian",
 \dontrun{
 # GLM variable importance
 # Also see:
-#   https://github.com/0xdata/h2o/blob/master/R/tests/testdir_demos/runit_demo_VI_all_algos.R
+#   https://github.com/h2oai/h2o/blob/master/R/tests/testdir_demos/runit_demo_VI_all_algos.R
 data.hex = h2o.importFile(
   localH2O,
-  path = "https://raw.github.com/0xdata/h2o/master/smalldata/bank-additional-full.csv",
+  path = "https://raw.github.com/h2oai/h2o/master/smalldata/bank-additional-full.csv",
   key = "data.hex")
 myX = 1:20
 myY="y"

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

@@ -55,7 +55,7 @@ If \code{parse = TRUE}, the function returns an object of class \code{\linkS4cla
 library(h2o)
 localH2O = h2o.init()
 prostate.hex = h2o.importURL(localH2O, path = paste("https://raw.github.com", 
-  "0xdata/h2o/master/smalldata/logreg/prostate.csv", sep = "/"), key = "prostate.hex")
+  "h2oai/h2o/master/smalldata/logreg/prostate.csv", sep = "/"), key = "prostate.hex")
 class(prostate.hex)
 summary(prostate.hex)
 }

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

@@ -80,7 +80,7 @@ localH2O = h2o.init()
 
 # Run PCR on Prostate Data
 prostate.hex = h2o.importURL(localH2O, path = paste("https://raw.github.com", 
-  "0xdata/h2o/master/smalldata/logreg/prostate.csv", sep = "/"), key = "prostate.hex")
+  "h2oai/h2o/master/smalldata/logreg/prostate.csv", sep = "/"), key = "prostate.hex")
 h2o.pcr(x = c("AGE","RACE","PSA","DCAPS"), y = "CAPSULE", data = prostate.hex, family = "binomial", 
   nfolds = 0, alpha = 0.5, ncomp = 2)
 }

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

@@ -106,10 +106,10 @@ h2o.randomForest(y = 5, x = c(2,3,4), data = iris.hex, ntree = 50, depth = 100)
 \dontrun{
 # RF variable importance
 # Also see:
-#   https://github.com/0xdata/h2o/blob/master/R/tests/testdir_demos/runit_demo_VI_all_algos.R
+#   https://github.com/h2oai/h2o/blob/master/R/tests/testdir_demos/runit_demo_VI_all_algos.R
 data.hex = h2o.importFile(
   localH2O,
-  path = "https://raw.github.com/0xdata/h2o/master/smalldata/bank-additional-full.csv",
+  path = "https://raw.github.com/h2oai/h2o/master/smalldata/bank-additional-full.csv",
   key = "data.hex")
 myX = 1:20
 myY="y"

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

@@ -22,7 +22,7 @@ Returns paths of model objects saved.
 library(h2o)
 localH2O = h2o.init()
 prostate.hex = h2o.importFile(localH2O, path = paste("https://raw.github.com", 
-  "0xdata/h2o/master/smalldata/logreg/prostate.csv", sep = "/"), key = "prostate.hex")
+  "h2oai/h2o/master/smalldata/logreg/prostate.csv", sep = "/"), key = "prostate.hex")
 prostate.glm = h2o.glm(y = "CAPSULE", x = c("AGE","RACE","PSA","DCAPS"), 
   data = prostate.hex, family = "binomial", nfolds = 10, alpha = 0.5)
 prostate.gbm = h2o.gbm(y = "CAPSULE", x = c("AGE","RACE","PSA","DCAPS"), n.trees=3,

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

@@ -23,7 +23,7 @@ Returns path of model object saved.
 library(h2o)
 localH2O = h2o.init()
 prostate.hex = h2o.importFile(localH2O, path = paste("https://raw.github.com", 
-  "0xdata/h2o/master/smalldata/logreg/prostate.csv", sep = "/"), key = "prostate.hex")
+  "h2oai/h2o/master/smalldata/logreg/prostate.csv", sep = "/"), key = "prostate.hex")
 prostate.glm = h2o.glm(y = "CAPSULE", x = c("AGE","RACE","PSA","DCAPS"), 
   data = prostate.hex, family = "binomial", nfolds = 10, alpha = 0.5)
 h2o.saveModel(object = prostate.glm, dir = "/Users/UserName/Desktop", save_cv = TRUE, force = TRUE)

packaging/index.html

@@ -358,6 +358,7 @@ <h2>Run H<sub>2</sub>O on Hadoop in just 3 steps.</h2>
         <div id="documentation">
           <h2>Documentation</h2>
           <ul>
+            <li><a id="ddocrecent" href="https://github.com/h2oai/h2o/blob/master/CHANGES.md">Recent Changes</a></li>
             <li><a id="ddocall" href="docs-website/index.html">Full Documentation</a></li>
             <li><a id="ddochadoop" href="docs-website/deployment/hadoop_tutorial.html">Hadoop Documentation</a></li>
 	    <li><a id="ddocr" href="docs-website/bits/h2o_package.pdf">R User Documentation</a></li>

py/h2o_methods.py

@@ -602,6 +602,7 @@ def create_frame(self, timeoutSecs=120, **kwargs):
         'randomize': None,
         'value': None,
         'real_range': None,
+        'binary_fraction': None,
         'categorical_fraction': None,
         'factors': None,
         'integer_fraction': None,
@@ -610,6 +611,7 @@ def create_frame(self, timeoutSecs=120, **kwargs):
         'binary_ones_fraction': None,
         'missing_fraction': None,
         'response_factors': None,
+        'has_response': None,
     }
     browseAlso = kwargs.pop('browseAlso', False)
     check_params_update_kwargs(params_dict, kwargs, 'create_frame', print_params=True)

py/testdir_multi_jvm/test_KMeans_create_frame_fvec.py

@@ -59,6 +59,7 @@ def test_KMeans_create_frame_fvec(self):
                 'cols': 10
             }
             h2o_util.pickRandParams(cfParamDict, params)
+            b = params.get('binary_fraction', None)
             i = params.get('integer_fraction', None)
             c = params.get('categorical_fraction', None)
             r = params.get('randomize', None)
@@ -67,21 +68,25 @@ def test_KMeans_create_frame_fvec(self):
             # h2o does some strict checking on the combinations of these things
             # fractions have to add up to <= 1 and only be used if randomize
             # h2o default randomize=1?
-            if r:
-                if not i:
-                    i = 0
-                if not c:
-                    c = 0
-                if (i and c) and (i + c) >= 1.0:
-                    c = 1.0 - i
-                params['integer_fraction'] = i
-                params['categorical_fraction'] = c
-                params['value'] = None
-
-            else:
-                params['randomize'] = 0
-                params['integer_fraction'] = 0
-                params['categorical_fraction'] = 0
+            if not b:
+                b = 0
+            if not i:
+                i = 0
+            if not c:
+                c = 0
+
+            # force a good combo, by decreasing t2o a little at a time
+            while (i + b + c) > 1.0:
+                print "Trying to find a good mix of fractional", b, i, c
+                b = max(0, b - 0.13)
+                i = max(0, i - 0.17)
+                # what's left
+                c = 1.0 - (i + b)
+
+            params['binary_fraction'] = b
+            params['integer_fraction'] = i
+            params['categorical_fraction'] = c
+            params['value'] = None
 
 
             kwargs = params.copy()