Skip to content

Hivemall v0.4.1-alpha.3 (Alpha release)

@myui myui released this · 1 commit to master since this release

This is the third alpha release for v0.4.1. We DO NOT recommend to use this version in production yet.

Major enhancement of this release is the support for mini batch gradient descent.
Find the usage in this page.

Note that the usage/behavior of RandomForest has been changed in this release.
You can find changes in this page.


Changes since v0.4.1-alpha.2 are summarized as follows:

  • Major Enhancement

    • Supported mini batch gradient descent for logistic regression #252
  • Minor Enhancement

    • Supported min_samples_leaf option in RandomForest #253
    • Added inflate/deflate UDF [4f2747c]
    • Added base91/unbase91 UDFs [8c70d8d]
    • Add scritps to start/stop MIX servers #241
    • Supported classification_error for the SplitRule of RandomForest classification [19ae202]
  • Major Change

    • Supported various mode types for the output prediction model of RandomForest. Due to that, the behavior of RandomForest has been changed. #249
      • Refined tree_predict UDF [57bae25]
      • Changed the default output model type [10f0ea2]
  • Minor Changes

    • Fixed the default numbers of used threads for smile for non-TD env [5c8bea3]
    • Changed/enlarged buffer size for iterative training of Factorization Machine [dcf0dbc]
    • Changed formula for calculating the number of random selected features [13c3917]
  • Bug Fixes

    • Fixed mf_predict logic for unkown examples [a43f793]
    • Fixed a bug that maxDepth is not set in DecisionTree [df21aba]

Downloads

Hivemall v0.4.1-alpha.2 (Alpha release)

@myui myui released this · 83 commits to master since this release

This is the 2nd alpha release for v0.4.1. We DO NOT recommend to use this version in production yet.

Changes since v0.4.1-alpha.1 are summarized as follows:

  • Bug Fixes
    • Fix bugs in MixServer PartialResult#diffClock and add tests [0c7672d]
    • Changed the implementation of fm_predict to GenericUDAF and fixed a bug [2906b38]
    • Applied a workaround for KryoException/java.util.ConcurrentModificationException in tokenize_ja [06b3762]

Downloads

Hivemall v0.4.1-alpha.1 (Alpha release)

@myui myui released this · 99 commits to master since this release

This is a alpha release for v0.4.1. We DO NOT recommend to use this version in production yet.

For the usage of tokenize_ja, please refer this wiki page.

Changes since v0.4.0-2 are summarized as follows:

  • Major Enhancement

    • Supported Japanese tokenizer UDF tokenize_ja [#227]
  • Major Changes

    • Separated maven module into core and mixserv [#225]
    • Changed the default max_depth of gradient tree boosting classifier [c4ade19]
  • Bug Fixes

    • Fixed fm_predict not to use Custom class for the result of terminatePartial [#230]

Downloads

Hivemall v0.4.0-2 (maintenance release)

@myui myui released this · 133 commits to master since this release

This is a maintenance release of Hivemall v0.4.0. The following bug fixes have been applied.

Changes since v0.4.0-1 are summarized as follows:

  • Minor Changes
    • Changed behaviors of categorical_features|indexed_features|quantitative_features|vectorize_features for empty string [24e77f4]
    • Changed behaviors of convert_label [9f611e6]

Downloads

Hivemall v0.4.0-1 (maintenance release)

@myui myui released this · 138 commits to master since this release

This is a maintenance release of Hivemall v0.4.0. The following bug fixes have been applied.

Changes since v0.4.0 are summarized as follows:

  • Minor Changes

    • Applied a fix to mf_predict for Treasure Data [c53de81]
  • Bugfix

    • Fixed a corner case bug in fm_predict [c53de81]

Downloads

The release version of Hivemall v0.4.0

@myui myui released this · 142 commits to master since this release

This is the stable release of Hivemall v0.4.0.

This version makes major development leaps and includes lots of changes. Major enhancements in this release includes supports for Factorization Machine (usage 1) and RandomForest (usage 1, 2).

Last but not least, I would like to thank contributors who made contributions to this release.

Changes since v0.3.2-3 are summarized as follows:

  • Major Enhancement

    • Introduced RandomForest classifier/regressor using Smile #219
    • Introduced Factorization Machine classifier/regressor #207
  • Minor Enhancement

  • Major Changes

    • Changed behavior of categorical_features UDF to always makes categorial features [d6f84f2]
    • Changed behavior of vectorize_features to parse numbers as double instead of float [982e079]
    • Fixed to include Netty jars to hivemall-fat.jar [6685d75]
  • Minor Changes

    • Added "-help" option to UDTF that shows an usage of the function [9603460]
    • Added -workers option to MixServer #212
    • Added dependency to log4j to hivemall-fat.jar [4b98bae]
    • Removed ant build file. Use Maven instead. [568ef5d]
  • Bugfix

    • Fixed a bug in tf UDAF [224057b]
    • Fixed a bug in diffclock computation logic in MixServer #220
    • Fixed a bug for sigmoid(null). Treasure Data PLT-4718. [ffe213a]
    • Fixed a bug in normalization functions that results becomes NaN when divided by zero [624e375]

Downloads

Hivemall v0.3.2-3 (maintenance release)

@myui myui released this · 310 commits to master since this release

This is just a maintenance release of Hivemall v0.3.2.
Only minor changes have been applied. A support for efficient Top-K query processing is the main update in this release.


  • Major Enhancement

  • Minor Enhancement

    • Added x_rank() function [333d3a6]
    • Added euclid_similarity UDF [10d6e23]
    • Added manhattan_distance/minkowski_distance UDFs and distance2similarity UDF [821060a]
  • Minor Changes

    • Added no_bias option to Matrix Factorization [c94f993]
    • Modified distance/similarity UDF to subclasses of GenericUDF for a better performance [29f1102]

Downloads

Hivemall v0.3.2-2 (maintenance release)

@myui myui released this · 330 commits to master since this release

This is just a maintenance release of Hivemall v0.3.2.
Only minor changes have been applied.


  • Minor Changes
    • Supported -no_bias option in Matrix Factorization [d6d2ac2]
    • Fixed to accept BigInt type for label in Multi-class classification [0c79c82]
    • Changed categorical_features() behavior [00cc200]

Downloads

Hivemall v0.3.2-1 (maintenance release)

@myui myui released this · 335 commits to master since this release

This is just a maintenance release of Hivemall v0.3.2.

Only minor changes have been applied since the last release as follows:

  • Minor Enhancement

    • Added feature(name, value) UDF [ea5e089]
    • Added jaccard_distance UDF [adcf2f8]
    • Added categorical_feature UDF [86d3011]
  • Minor Changes

    • Updated jaccard to accept arrays as the inputs [ea5e089]
    • Fixed to_string_array to accept ANY primitive types [1860636]

Downloads

The release version of Hivemall v0.3.2

@myui myui released this · 351 commits to master since this release

This is the stable release version of Hivemall v0.3.2.

A major enhancement in this release is support for anomaly detection using LOF and polynomial features that is useful for non-linear regression/classification.

Changes since v0.3.1 are summarized as follows:

  • Major Enhancement

  • Minor Enhancement

  • Minor Changes

    • Added alias cosine_similarity to cosine_sim [3f615e5]
    • Modified to return null instead of throwing UDFArgumentException for a null argument in mhash [181b369]
    • Moved the package of similarity UDFs from hivemall.knn.distance to hivemall.knn.similarity and changed the function signature of consine_similarity function. [2a0f1e7]
    • Changed argument signatures from INT to DOUBLE in TF-IDF macro [61eeca2]
  • Bugfix

    • Fixed a bug in java_min [a48c367]

Downloads

Something went wrong with that request. Please try again.