Releases: fracpete/python-weka-wrapper3
Releases · fracpete/python-weka-wrapper3
Release v0.2.8
- methods
create_instances_from_lists
andcreate_instances_from_matrices
(moduleweka.core.dataset
) now allow the specification of column names, for input and output variables.
Release v0.2.7
- Added property for attribute indices to
DistanceFunction
class (moduleweka.core.distances
) (thanks to Martin Trat, #39) - improved instantiation of classes, avoiding misleading output of exceptions
JavaArray
class (module:weka.core.classes
) now has__str__
and__repr__
methods that output classname and size
Release v0.2.6
- upgraded bundled Weka to 3.9.6
Release v0.2.5
- switched to
python-javabridge
, the new name (fork?) of thejavabridge
library Package.__str__
(weka.core.packages
module) method now returns a string rather than printing the name/version- added
to_numpy(...)
methods toInstance
andInstances
classes (moduleweka.core.dataset
) to make it easy to obtain a numpy array from the Weka dataset
Release v0.2.4
- added method
help_for
toweka.core.classes
module to generate a help screen for anweka.core.OptionHandler
class using just the classname. - the
to_help
method of theweka.core.classes.OptionHandler
class now allows to tweak the generated output a bit better (e.g., what sections to output). - setting window title of Matplotlib is now dependent on version (to avoid deprecation notice being output)
plot_classifier_errors
(moduleweka.plot.classifiers
) now plots the diagonal after adding all the plot data to get the right limits
Release v0.2.3
- added
weka.core.distances
module for distance functions, withDistanceFunction
base class - added
avg_silhouette_coefficient
method toweka.clusterers
to calculate the average silhouette coefficient
Release v0.2.2
- the
Package
class of theweka.core.packages
module now has aversion
property to quickly access the version which is stored in the meta-data; themetadata
property now returns a proper Python dictionary - added convenience methods to the
weka.core.packages
module:install_packages
to install more than one package,install_missing_package
andinstall_missing_packages
to install one or more packages if missing (can automatically stop the JVM and exit the process),uninstall_packages
to remove more than one package in one operation
Release v0.2.1
- the
ASEvaluation
class in theweka.attribute_selection
module now offers the following methods for attribute transformers like PCA:transformed_header
,transformed_data
,convert_instance
- classes derived from
weka.core.classes.JavaObject
are now serializable via pickle - added the method
copy_structure
to theweka.core.dataset.Instances
class to quickly get the header of a dataset - added the property
header
to the following classes that returns the training data structure:ASEvaluation
,ASSearch
,Associator
,Classifier
,Clusterer
,TSForecaster
- methods from
weka.core.serialization
have been moved intoweka.core.classes
, with the following methods getting theserialization_
prefix:write
,write_all
,read
,read_all
Release v0.2.0
classes.new_instance
method can take an options list now as well- added
classes.get_enum
method to return the instance of a Java enum item - added
classes.new_instance
method to create new instance of Java class - added
typeconv.jstring_list_to_string_list
method to convert ajava.util.List
containing strings into a Python list - added
typeconv.jdouble_to_float
method to convert ajava.lang.Double
to a Python float - in module
typeconv
renamed methods:string_array_to_list
tojstring_array_to_list
,string_list_to_array
tostring_list_to_jarray
,double_matrix_to_ndarray
tojdouble_matrix_to_ndarray
,enumeration_to_list
tojenumeration_to_list
,double_to_float
tofloat_to_jfloat
- added
weka.timeseries
module that wraps thetimeseriesForecasting
Weka package
Release v0.1.16
- upgraded Weka to 3.9.5