aboutsummaryrefslogtreecommitdiff
path: root/mllib
Commit message (Collapse)AuthorAgeFilesLines
* Make XORShiftRandom explicit in KMeans and roll it back for RDDMarek Kolodziej2013-11-201-4/+4
|
* Updates to reflect pull request code reviewMarek Kolodziej2013-11-181-2/+3
|
* XORShift RNG with unit tests and benchmarkMarek Kolodziej2013-11-181-1/+1
| | | | | | | | | | | To run unit test, start SBT console and type: compile test-only org.apache.spark.util.XORShiftRandomSuite To run benchmark, type: project core console Once the Scala console starts, type: org.apache.spark.util.XORShiftRandom.benchmark(100000000)
* Merge branch 'master' into implicit-alsNick Pentreath2013-10-071-4/+4
|\
| * Merging build changes in from 0.8Patrick Wendell2013-10-051-4/+4
| |
* | Bumping up test matrix size to eliminate random failuresNick Pentreath2013-10-072-12/+12
| |
* | Style fix using 'if' rather than 'match' on booleanNick Pentreath2013-10-041-14/+13
| |
* | Fixing closing brace indentationNick Pentreath2013-10-041-1/+1
| |
* | Reverting to using comma-delimited splitNick Pentreath2013-10-041-1/+1
| |
* | Merge remote-tracking branch 'upstream/master' into implicit-alsNick Pentreath2013-10-041-1/+1
|\|
| * Update build version in masterPatrick Wendell2013-09-241-1/+1
| |
* | Merge remote-tracking branch 'upstream/master' into implicit-alsNick Pentreath2013-09-233-8/+331
|\|
| * Small tweaks to MLlib docsMatei Zaharia2013-09-082-8/+9
| |
| * respose to PR commentsAmeet Talwalkar2013-09-081-0/+322
| |
* | Adding algorithm for implicit feedback data to ALSNick Pentreath2013-09-063-54/+296
|/
* Add missing license headers found with RATMatei Zaharia2013-09-022-0/+34
|
* Move some classes to more appropriate packages:Matei Zaharia2013-09-0121-26/+43
| | | | | | * RDD, *RDDFunctions -> org.apache.spark.rdd * Utils, ClosureCleaner, SizeEstimator -> org.apache.spark.util * JavaSerializer, KryoSerializer -> org.apache.spark.serializer
* Fix some URLsMatei Zaharia2013-09-011-1/+1
|
* Initial work to rename package to org.apache.sparkMatei Zaharia2013-09-0140-136/+136
|
* Fix broken build by removing addInterceptShivaram Venkataraman2013-08-302-11/+8
|
* Merge pull request #863 from shivaram/etrain-ridgeEvan Sparks2013-08-2912-297/+755
|\ | | | | Adding linear regression and refactoring Ridge regression to use SGD
| * Center & scale variables in Ridge, Lasso.Shivaram Venkataraman2013-08-2510-228/+347
| | | | | | | | | | Also add a unit test that checks if ridge regression lowers cross-validation error.
| * Fixing typos in Java tests, and addressing alignment issues.Evan Sparks2013-08-184-16/+16
| |
| * Centralizing linear data generator and mllib regression tests to use it.Evan Sparks2013-08-189-282/+84
| |
| * Adding Linear Regression, and refactoring Ridge Regression.Evan Sparks2013-08-188-176/+713
| |
* | Merge pull request #819 from shivaram/sgd-cleanupEvan Sparks2013-08-298-48/+160
|\ \ | | | | | | Change SVM to use {0,1} labels
| * | Add an option to turn off data validation, test it.Shivaram Venkataraman2013-08-255-18/+28
| | | | | | | | | | | | | | | Also moves addIntercept to have default true to make it similar to validateData option
| * | Specify label format in LogisticRegression.Shivaram Venkataraman2013-08-131-0/+6
| | |
| * | Fix SVM model and unit test to work with {0,1}.Shivaram Venkataraman2013-08-135-12/+18
| | | | | | | | | | | | Also rename validateFuncs to validators.
| * | Change SVM to use {0,1} labels.Shivaram Venkataraman2013-08-137-26/+116
| |/ | | | | | | | | Also add a data validation check to make sure classification labels are always 0 or 1 and add an appropriate test case.
* | Fix code style and a nondeterministic RDD issue in ALSMatei Zaharia2013-08-221-11/+20
| |
* | Merge pull request #814 from holdenk/masterMatei Zaharia2013-08-221-7/+14
|\ \ | | | | | | Create less instances of the random class during ALS initialization.
| * | FixHolden Karau2013-08-151-2/+2
| | |
| * | Code review feedback :)Holden Karau2013-08-121-7/+7
| | |
| * | Use less instances of the random class during ALS setupHolden Karau2013-08-121-7/+14
| |/
* | Remove redundant dependencies from POMsJey Kottalam2013-08-181-4/+0
| |
* | Maven build now also works with YARNJey Kottalam2013-08-161-40/+0
| |
* | Don't mark hadoop-client as 'provided'Jey Kottalam2013-08-161-1/+0
| |
* | Maven build now works with CDH hadoop-2.0.0-mr1Jey Kottalam2013-08-161-27/+0
| |
* | Initial changes to make Maven build agnostic of hadoop versionJey Kottalam2013-08-161-33/+10
|/
* Merge pull request #812 from shivaram/maven-mllib-testsMatei Zaharia2013-08-126-7/+32
|\ | | | | Create SparkContext in beforeAll for MLLib tests
| * Create SparkContext in beforeAll for MLLib testsShivaram Venkataraman2013-08-116-7/+32
| | | | | | | | This overcomes test failures that occur using Maven
* | Clean up scaladoc in ML Lib.Shivaram Venkataraman2013-08-1117-60/+171
|/ | | | | Also build and copy ML Lib scaladoc in Spark docs build. Some more minor cleanup with respect to naming, test locations etc.
* Merge pull request #762 from shivaram/sgd-cleanupEvan Sparks2013-08-1121-417/+816
|\ | | | | Refactor SGD options into a new class.
| * Fix GLM code review comments and move java testsShivaram Venkataraman2013-08-104-6/+2
| |
| * Add setters for optimizer, gradient in SGD.Shivaram Venkataraman2013-08-082-8/+19
| | | | | | | | Also remove java-specific constructor for LabeledPoint.
| * Merge branch 'master' of git://github.com/mesos/spark into sgd-cleanupShivaram Venkataraman2013-08-066-6/+366
| |\ | | | | | | | | | | | | Conflicts: mllib/src/main/scala/spark/mllib/util/MLUtils.scala
| * | Refactor GLM algorithms and add Java testsShivaram Venkataraman2013-08-0620-169/+540
| | | | | | | | | | | | | | | | | | | | | | | | | | | This change adds Java examples and unit tests for all GLM algorithms to make sure the MLLib interface works from Java. Changes include - Introduce LabeledPoint and avoid using Doubles in train arguments - Rename train to run in class methods - Make the optimizer a member variable of GLM to make sure the builder pattern works
| * | Move implicit arg to constructor for Java access.Shivaram Venkataraman2013-08-031-4/+7
| | |
| * | Refactor optimizers and create GLMsShivaram Venkataraman2013-08-0210-286/+320
| | | | | | | | | | | | | | | | | | | | | This change refactors the structure of GLMs to use mixins which maintain a similar interface to other ML lib algorithms. This change also creates an Optimizer trait which allows GLMs to be extended to use other optimization techniques.