Skip to content

HTTPS clone URL

Subversion checkout URL

You can clone with HTTPS or Subversion.

Download ZIP

release-0.5.3

BLD New release: 0.5.3
Full ChangeLog:
    * Fix MDS for non-array inputs
    * Fix MDS bug
    * Add return_* arguments to kmeans
    * Extend zscore() to work on non-ndarrays
    * Add frac_precluster_learner
    * Work with older C++ compilers

release-0.5.2

BLD Release 0.5.2
Fix building, which is important on its own

release-0.5.1

BLD New release: 0.5.1
Most important new "feature" is bundling of Eigen with source.

Full ChangeLog:
    - Add subspace projection kNN
    - Export ``pdist`` in milk namespace
    - Add Eigen to source distribution
    - Add measures.curves.roc
    - Add ``mds_dists`` function
    - Add ``verbose`` argument to milk.tests.run

release-0.5

BLD New release: 0.5
Full ChangeLog:
    * Add coordinate-descent based LASSO
    * Add unsupervised.center function
    * Make zscore work with NaNs (by ignoring them)
    * Propagate apply_many calls through transformers
    * Much faster SVM classification with means a much faster defaultlearner()
    [measured 2.5x speedup on yeast dataset!]

release-0.4.3

BLD: New release: 0.4.3
ChangeLog:
    * Add select_n_best & rank_corr to featureselection
    * Add Euclidean MDS
    * Add tree multi-class strategy
    * Fix adaboost with boolean weak learners (issue #6, reported by audy
    (Austin Richardson))
    * Add ``axis`` arguments to zscore()

release-0.4.2

BLD New version: 0.4.2
It has been too long since last release. Many improvements and bugfixes
lingering.

ChangeLog:

* Make defaultlearner able to take extra arguments
* Make ctransforms_model a supervised_model (adds apply_many)
* Add expanded argument to defaultlearner
* Fix corner case in SDA
* Fix repeated_kmeans
* Fix parallel gridminimise on Windows
* Add multi_label argument to normaliselabels
* Add multi_label argument to nfoldcrossvalidation.foldgenerator
* Do not fork a process in gridminimise if nprocs == 1 (makes for easier
  debugging, at the cost of slightly more complex code).
* Add milk.supervised.multi_label
* Fix ext.jugparallel when features is a Task
* Add milk.measures.bayesian_significance

release-0.4.1

NEW RELEASE
Fix an important bug in gridsearch!

release-0.4.0

NEW VERSION: 0.4.0
- Use multiprocessing to take advantage of multi core machines (off by
  default).
- Add perceptron learner
- Set random seed in random forest learner
- Add warning to milk/__init__.py if import fails
- Add return value to ``gridminimise``
- Set random seed in ``precluster_learner``
- Implemented Error-Correcting Output Codes for reduction of multi-class
  to binary (including probability estimation)
- Add ``multi_strategy`` argument to ``defaultlearner()``
- Make the dot kernel in svm much, much, faster
- Make sigmoidal fitting for SVM probability estimates faster
- Fix bug in randomforest (patch by Wei on milk-users mailing list)

release-0.3.10

New release 0.3.10
Many small changes.

release-0.3.8

New release
This is very minor, but it fixes compilation problems, so it's critical.

release-0.3.7

BLD New release
Changes:
- Logistic regression
- Source demos included (in source and documentation)
- Add cluster agreement metrics
- Fix nfoldcrossvalidation bug when using origins

release-0.3.6

Release 0.3.6: Fixes and Adaboost

release-0.3.4

New release
New Features
------------
Random forest learners
Decision trees sped up 20x
Much faster gridsearch  (finds optimum without computing all folds)

release-0.3.2

New release
kmeans() for distance=mahalanobis
minimise dependency on scipy
self-organising maps
important bug fix in repeated_kmeans
faster feature selection

release-0.3.1

Release 0.3.1
Version 0.3.1 2010-09-25
	* fix sparse non-negative matrix factorisation
	* mean grouped classifier
	* update multi classifier to newer interface

release-0.3

Version 0.3
Features
	* no scipy.weave dependency
	* flatter namespace
	* faster kmeans
	* affinity propagation (borrowed from scikits-learn & slightly improved)
	* pdist()

release-0.2.1

New version: 0.2.1
Bugfixes, speedups and other minor things.
Something went wrong with that request. Please try again.