Makes Weka algorithms available in scikit-learn, by using python-weka-wrapper3 under the hood.
GPL-3.0 License
Bot releases are visible (Hide)
scikit-learn
instead of deprecated sklearn
dependency for scikit-learn (https://github.com/fracpete/sklearn-weka-plugin/pull/10)Published by fracpete over 1 year ago
WekaEstimator
(module sklweka.classifiers
) now has a custom score
method that distinguishes between classification and regression to return the correct score.data
to X
and targets
to y
, since some sklearn schemes use named argumentssample_weight=None
to fit
, score
and fit_predict
methodsto_instance
(module: sklweka.dataset
) now performs correct missing value checkto_nominal_labels
(module: sklweka.dataset
) generates nicer labels nowPublished by fracpete over 2 years ago
WekaEstimator
(module sklweka.classifiers
) and WekaCluster
(module sklweka.clusters
) now allow specifying how many labels a particular nominal attribute or class attribute has (to avoid error message like Cannot handle unary class attribute!
if there is only one label present in a particular split)Published by fracpete over 2 years ago
to_nominal_attributes
method in the sklearn.dataset
module requires now the indices
parameter (incorrectly declared as optional); can parse a range string now as wellfit
, set_params
and __str__
methods fo the MakeNominal
transformer (module sklweka.preprocessing
)WekaEstimator
(module sklweka.classifiers
) and WekaCluster
(module sklweka.clusters
) now allow specifying which attributes to turn into nominal ones, which avoids having to manually convert the data (either as list with 0-based indices or range string with 1-based indices)set_params
methods now ignore empty dictionariesPublished by fracpete almost 3 years ago
to_instances
method in module sklweka.dataset
X
when no class present in load_arff
method (module sklweka.dataset
)load_dataset
method in module sklweka.dataset
that uses Weka to load the data before converting it into sklearn data structures (slower, but more flexible)Published by fracpete almost 3 years ago
Published by fracpete over 3 years ago
Published by fracpete over 3 years ago