This repository has been archived by the owner on Apr 2, 2020. It is now read-only.
Releases: fracpete/python-weka-wrapper
Releases · fracpete/python-weka-wrapper
Release v0.3.16
- added console scripts:
pww-associator
,pww-attsel
,pww-classifier
,pww-clusterer
,pww-datagenerator
,pww-filter
- added
serialize
,deserialize
methods toweka.classifiers.Classifier
to simplify loading/saving model - added
serialize
,deserialize
methods toweka.clusterers.Clusterer
to simplify loading/saving model - added
serialize
,deserialize
methods toweka.filters.Filter
to simplify loading/saving filter - added methods
plot_rocs
andplot_prcs
toweka.plot.classifiers
module to plot ROC/PRC curve on same dataset
for multiple classifiers - method
plot_classifier_errors
ofweka.plot.classifiers
module now allows plotting predictions of multiple
classifiers by providing a dictionary - method
create_instances_from_matrices
from moduleweka.core.dataset
now allows string and bytes as well - method
create_instances_from_lists
from moduleweka.core.dataset
now allows string and bytes as well
Release v0.3.15
- added wrapper classes for association classes that implement
AssociationRuleProducer
(packageweka.associations
):AssociationRules
,AssociationRule
,item
- added
to_source
method toweka.classifiers.Classifier
andweka.filters.Filter
(underlying Java classes must implement the respectiveSourcable
interface)
Release v0.3.14
- fixed logging setup in
weka.core.jvm
to avoid global setting global logging
setup toDEBUG
(thanks to https://github.com/Arnie97)
Release v0.3.13
- upgraded to Weka 3.9.3
weka.jar
now included in PyPi package- exposed the following methods in
weka.classifiers.Evaluation
:
cumulative_margin_distribution
,sf_prior_entropy
,sf_scheme_entropy
Release v0.3.12
- upgraded to Weka 3.9.2
- properly initializing package support now, rather than adding package jars to classpath
- added
weka.core.ClassHelper
Java class for obtaining classes and static fields, as
javabridge only uses the system class loader
Release v0.3.11
- added
check_for_modified_class_attribute
method toFilterClassifier
class - added
complete_classname
method toweka.core.classes
module, which allows completion of partial classnames like.J48
toweka.classifiers.trees.J48
if there is a unique match;JavaObject.new_instance
andJavaObject.check_type
now make use of this functionality, allowing for instantiations likeClassifier(cls=".J48")
jvm.start(system_cp=True)
no longer fails with aKeyError: 'CLASSPATH'
if there is noCLASSPATH
environment variable defined- Libraries
mtl.jar
,core.jar
andarpack_combined_all.jar
were added as is to theweka.jar
in the 3.9.1 release instead of adding their content to it. Repackagedweka.jar
to fix this issue (#52)
Release v0.3.10
types.double_matrix_to_ndarray
no longer assumes a square matrix
(#48)len(Instances)
now returns the number of rows in the dataset (moduleweka.core.dataset
)- added method
insert_attribute
to theInstances
class - added class method
create_relational
to theAttribute
class - upgraded Weka to 3.9.1
Release v0.3.9
plot_learning_curve
method of moduleweka.plot.classifiers
now accepts a list of test sets;
*
is index of test set in label template string- added
missing_value()
methods toweka.core.dataset
module andInstance
class - output variable
y
for convenience methodcreate_instances_from_lists
in module
weka.core.dataset
is now optional - added convenience method
create_instances_from_matrices
toweka.core.dataset
module to easily create
anInstances
object from numpy matrices (x and y)
Release v0.3.8
- works with javabridge 1.0.14 now
Release v0.3.7
- upgraded Weka to 3.9.0