Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

SPARK-4156 [MLLIB] EM algorithm for GMMs #3022

Closed
wants to merge 31 commits into from
Closed

SPARK-4156 [MLLIB] EM algorithm for GMMs #3022

wants to merge 31 commits into from

Commits on Oct 30, 2014

  1. SPARK-4156

    Travis Galoppo committed Oct 30, 2014
    Configuration menu
    Copy the full SHA
    c15405c View commit details
    Browse the repository at this point in the history

Commits on Nov 11, 2014

  1. Merge remote-tracking branch 'upstream/master'

    Travis Galoppo committed Nov 11, 2014
    Configuration menu
    Copy the full SHA
    5c96c57 View commit details
    Browse the repository at this point in the history

  2. Made GaussianMixtureModel class serializable 

    Modified sum function for better performance
    Travis Galoppo committed Nov 11, 2014
    Configuration menu
    Copy the full SHA
    c1a8e16 View commit details
    Browse the repository at this point in the history

Commits on Nov 13, 2014

  1. Added scala test suite with basic test

    @tgaloppo
    tgaloppo committed Nov 13, 2014
    Configuration menu
    Copy the full SHA
    719d8cc View commit details
    Browse the repository at this point in the history

Commits on Nov 17, 2014

  1. Merge remote-tracking branch 'upstream/master'

    @tgaloppo
    tgaloppo committed Nov 17, 2014
    Configuration menu
    Copy the full SHA
    86fb382 View commit details
    Browse the repository at this point in the history

Commits on Nov 18, 2014

  1. Merged with master branch; update test suite with latest context chan… 

    …ges.

Improved cluster initialization strategy.
    @tgaloppo
    tgaloppo committed Nov 18, 2014
    Configuration menu
    Copy the full SHA
    e6ea805 View commit details
    Browse the repository at this point in the history

Commits on Dec 3, 2014

  1. Fixed to no longer ignore delta value provided on command line

    @tgaloppo
    tgaloppo committed Dec 3, 2014
    Configuration menu
    Copy the full SHA
    676e523 View commit details
    Browse the repository at this point in the history

  2. Added additional train() method to companion object for cluster count… 

    … and tolerance parameters.

Modified cluster initialization strategy to use an initial covariance matrix derived from the sample points used to initialize the mean.
    @tgaloppo
    tgaloppo committed Dec 3, 2014
    Configuration menu
    Copy the full SHA
    8aaa17d View commit details
    Browse the repository at this point in the history

Commits on Dec 12, 2014

  1. Corrected a variety of style and naming issues.

    @tgaloppo
    tgaloppo committed Dec 12, 2014
    Configuration menu
    Copy the full SHA
    9770261 View commit details
    Browse the repository at this point in the history

  2. Moved multivariate Gaussian utility class to mllib/stat/impl 

    Improved comments
    @tgaloppo
    tgaloppo committed Dec 12, 2014
    Configuration menu
    Copy the full SHA
    e7d413b View commit details
    Browse the repository at this point in the history

  3. Moved MultivariateGaussian utility class

    @tgaloppo
    tgaloppo committed Dec 12, 2014
    Configuration menu
    Copy the full SHA
    dc9c742 View commit details
    Browse the repository at this point in the history

Commits on Dec 16, 2014

  1. Fixed style issues

    @tgaloppo
    tgaloppo committed Dec 16, 2014
    Configuration menu
    Copy the full SHA
    97044cf View commit details
    Browse the repository at this point in the history

  2. Added predict() to return the cluster labels and membership values

    @FlytxtRnD
    FlytxtRnD committed Dec 16, 2014
    Configuration menu
    Copy the full SHA
    f407b4c View commit details
    Browse the repository at this point in the history

  3. Merge pull request #1 from FlytxtRnD/predictBranch 

    Added predict() to return the cluster labels and membership values
    @tgaloppo
    tgaloppo committed Dec 16, 2014
    Configuration menu
    Copy the full SHA
    b99ecc4 View commit details
    Browse the repository at this point in the history

  4. Fixed style issue

    @tgaloppo
    tgaloppo committed Dec 16, 2014
    Configuration menu
    Copy the full SHA
    2df336b View commit details
    Browse the repository at this point in the history

  5. Merge branch 'master' of https://github.com/tgaloppo/spark 

      Adds predict() method
    @tgaloppo
    tgaloppo committed Dec 16, 2014
    Configuration menu
    Copy the full SHA
    c3b8ce0 View commit details
    Browse the repository at this point in the history

  6. Fixed style issues

    @tgaloppo
    tgaloppo committed Dec 16, 2014
    Configuration menu
    Copy the full SHA
    d695034 View commit details
    Browse the repository at this point in the history

  7. Style issue

    @tgaloppo
    tgaloppo committed Dec 16, 2014
    Configuration menu
    Copy the full SHA
    9be2534 View commit details
    Browse the repository at this point in the history

  8. Style issue

    @tgaloppo
    tgaloppo committed Dec 16, 2014
    Configuration menu
    Copy the full SHA
    8b633f3 View commit details
    Browse the repository at this point in the history

Commits on Dec 17, 2014

  1. Added functionality to allow setting of GMM starting point. 

    Added two cluster test to testing suite.
    @tgaloppo
    tgaloppo committed Dec 17, 2014
    Configuration menu
    Copy the full SHA
    42b2142 View commit details
    Browse the repository at this point in the history

  2. Removed unusued code

    @tgaloppo
    tgaloppo committed Dec 17, 2014
    Configuration menu
    Copy the full SHA
    20ebca1 View commit details
    Browse the repository at this point in the history

  3. Replaced accumulators with RDD.aggregate

    @tgaloppo
    tgaloppo committed Dec 17, 2014
    Configuration menu
    Copy the full SHA
    cff73e0 View commit details
    Browse the repository at this point in the history

Commits on Dec 18, 2014

  1. Numerous changes to improve code

    @tgaloppo
    tgaloppo committed Dec 18, 2014
    Configuration menu
    Copy the full SHA
    308c8ad View commit details
    Browse the repository at this point in the history

  2. Moved prediction methods into model class.

    @tgaloppo
    tgaloppo committed Dec 18, 2014
    Configuration menu
    Copy the full SHA
    227ad66 View commit details
    Browse the repository at this point in the history

  3. Removed unused import

    @tgaloppo
    tgaloppo committed Dec 18, 2014
    Configuration menu
    Copy the full SHA
    578c2d1 View commit details
    Browse the repository at this point in the history

  4. Removed redundant array from array creation

    @tgaloppo
    tgaloppo committed Dec 18, 2014
    Configuration menu
    Copy the full SHA
    1de73f3 View commit details
    Browse the repository at this point in the history

Commits on Dec 19, 2014

  1. Minor fixes and tweaks.

    @tgaloppo
    tgaloppo committed Dec 19, 2014
    Configuration menu
    Copy the full SHA
    b97fe00 View commit details
    Browse the repository at this point in the history

Commits on Dec 20, 2014

  1. Style improvements 

    Changed ExpectationSum to a private class
    @tgaloppo
    tgaloppo committed Dec 20, 2014
    Configuration menu
    Copy the full SHA
    9b2fc2a View commit details
    Browse the repository at this point in the history

Commits on Dec 22, 2014

  1. Fixed parameter comment in GaussianMixtureModel 

    Made maximum iterations an optional parameter to DenseGmmEM
    @tgaloppo
    tgaloppo committed Dec 22, 2014
    Configuration menu
    Copy the full SHA
    acf1fba View commit details
    Browse the repository at this point in the history

  2. fixed usage line to include optional maxIterations parameter

    @tgaloppo
    tgaloppo committed Dec 22, 2014
    Configuration menu
    Copy the full SHA
    709e4bf View commit details
    Browse the repository at this point in the history

  3. MLUtils: changed privacy of EPSILON from [util] to [mllib] 

    GaussianMixtureEM: Renamed from GaussianMixtureModelEM; corrected formatting issues

GaussianMixtureModel: Renamed predictLabels() to predict()

Others: Modifications based on rename of GaussianMixtureEM
    @tgaloppo
    tgaloppo committed Dec 22, 2014
    Configuration menu
    Copy the full SHA
    aaa8f25 View commit details
    Browse the repository at this point in the history