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

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!]

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 luispedro#6, reported by audy
    (Austin Richardson))
    * Add ``axis`` arguments to zscore()

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

NEW RELEASE

Fix an important bug in gridsearch!

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)

New release 0.3.10

Many small changes.

New release

New release

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

BLD New release

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