All Classes and Interfaces
Class
Description
Abstract scheme for learning associations.
Abstract clusterer.
Abstract class for objects that store instances to some destination.
Bean info class for the AbstractDataSink
Abstract class for objects that can provide instances from some source
Bean info class for AbstractDataSource.
Abstract clustering model that produces (for each test instance)
an estimate of the membership in each cluster
(ie.
Abstract class for objects that can provide some kind of evaluation for
classifier, clusterers etc.
Abstract superclass for all file loaders.
Abstract class for Savers that save to a file
Valid options are:
-i input arff file
The input filw in arff format.
The input filw in arff format.
Abstract class gives default implementation of setSource
methods.
Abstract class for Saver
Represents the abstract ancestor for string-based distance functions, like
EditDistance.
Abstract class for TestSetProducers that contains default
implementations of add/remove listener methods and defualt
visual representation.
BeanInfo class for AbstractTestSetProducer
An abstract instance filter that assumes instances form time-series data and
performs some merging of attribute values in the current instance with
attribute attribute values of some previous (or future) instance.
Abstract base class for TrainAndTestSetProducers that contains default
implementations of add/remove listener methods and defualt
visual representation.
Bean info class for AbstractTrainAndTestSetProducers
Abstract class for TrainingSetProducers that contains default
implementations of add/remove listener methods and default
visual representation
BeanInfo class for AbstractTrainingSetProducer
Class for boosting a nominal class classifier using the Adaboost M1 method.
An instance filter that adds a new attribute to the dataset.
A filter for adding the classification, the class distribution and an error flag to a dataset with a classifier.
A filter that adds a new nominal attribute representing the cluster assigned to each instance by the specified clustering algorithm.
An instance filter that creates a new attribute by applying a mathematical expression to existing attributes.
An instance filter that adds an ID attribute to the dataset.
Interface to something that can produce measures other than those
calculated by evaluation modules.
Meta classifier that enhances the performance of a regression base classifier.
An instance filter that changes a percentage of a given attributes values.
Adds the labels from the given list to an attribute if they are missing.
The ADNode class implements the ADTree datastructure which increases
the speed with which sub-contingency tables can be constructed from
a data set in an Instances object.
Class for generating an alternating decision tree.
Generates a people database and is based on the paper by Agrawal et al.:
R.
R.
This panel controls setting a list of algorithms for an experiment to
iterate over.
Class for performing operations on an algebraic vector
of floating-point values.
A simple instance filter that passes all instances directly
through.
Applies all known Javadoc-derived classes to a source file.
Alphabetic string tokenizer, tokens are to be formed only from contiguous alphabetic sequences.
AODE achieves highly accurate classification by averaging over all of a small space of alternative naive-Bayes-like models that have weaker (and hence less detrimental) independence assumptions than naive Bayes.
AODEsr augments AODE with Subsumption Resolution.AODEsr detects specializations between two attribute values at classification time and deletes the generalization attribute value.
For more information, see:
Fei Zheng, Geoffrey I.
For more information, see:
Fei Zheng, Geoffrey I.
Class implementing an Apriori-type algorithm.
Class for storing a set of items.
Reads a source that is in arff (attribute relation
file format) format.
Reads data from an ARFF file, either in incremental or batch mode.
A Panel representing an ARFF-Table and the associated filename.
Writes to a destination in arff text format.
A sorter for the ARFF-Viewer - necessary because of the custom CellRenderer.
A specialized JTable for the Arff-Viewer.
Handles the background colors for missing values differently than the
DefaultTableCellRenderer.
The model for the Arff-Viewer.
A little tool for viewing ARFF files.
The main panel of the ArffViewer.
Abstract attribute selection evaluation class
Abstract attribute selection search class.
This panel allows the user to select, configure, and run a scheme
that learns associations.
Bean that wraps around weka.associations
BeanInfo class for the Associator wrapper bean
GUI customizer for the associator wrapper bean
Class for evaluating Associaters.
Class for handling an attribute.
Interface for classes that evaluate attributes individually.
A general purpose class for parsing mathematical expressions
involving attribute values.
Creates a panel that displays the attributes contained in a set of
instances, letting the user select a single attribute for inspection.
This class locates and records the indices of a certain type of attributes,
recursively in case of Relational attributes.
This panel displays one dimensional views of the attributes in a
dataset.
Class encapsulating a change in the AttributePanel's selected x and y
attributes.
Interface for classes that want to listen for Attribute selection
changes in the attribute panel
Dimensionality of training and test data is reduced by attribute selection before being passed on to a classifier.
Attribute selection class.
A supervised attribute filter that can be used to select attributes.
Creates a panel that displays the attributes contained in a set of
instances, letting the user toggle whether each attribute is selected
or not (eg: so that unselected attributes can be removed before
classification).
This panel allows the user to select and configure an attribute
evaluator and a search method, set the
attribute of the current dataset to be used as the class, and perform
attribute selection using one of two selection modes (select using all the
training data or perform a n-fold cross validation---on each trial
selecting features using n-1 folds of the data).
Abstract attribute set evaluator.
A Utility class that contains summary information on an
the values that appear in a dataset for a particular attribute.
Bean that encapsulates displays bar graph summaries for attributes in
a data set.
Bean info class for the attribute summarizer bean
This panel displays summary statistics about an attribute: name, type
number/% of missing/unique values, number of distinct values.
Abstract attribute transformer.
Creates a panel that shows a visualization of an
attribute in a dataset.
Takes the results from a ResultProducer and submits
the average to the result listener.
Class for bagging a classifier to reduce variance.
Class representing a node of a BallTree.
Abstract class for splitting a ball tree's BallNode.
Class implementing the BallTree/Metric Tree algorithm for nearest neighbour search.
The connection to dataset is only a reference.
The connection to dataset is only a reference.
Abstract class for constructing a BallTree .
Class encapsulating a built classifier and a batch of instances to
test on.
Interface to something that can process a BatchClassifierEvent
Class encapsulating a built clusterer and a batch of instances to
test on.
Interface to something that can process a BatchClustererEvent
Marker interface for a loader/saver that can retrieve instances in batch mode
Implements Bayesian Logistic Regression for both Gaussian and Laplace Priors.
For more information, see
Alexander Genkin, David D.
For more information, see
Alexander Genkin, David D.
Bayes Network learning using various search algorithms and quality measures.
Base class for a Bayes Network classifier.
Base class for a Bayes Network classifier.
Generates random instances based on a Bayes network.
BayesNetEstimator is the base class for estimating the conditional probability tables of a Bayes network once the structure has been learned.
Bayes Network learning using various search algorithms and quality measures.
Base class for a Bayes Network classifier.
Base class for a Bayes Network classifier.
Interface specifying routines that all weka beans should implement
in order to allow the bean environment to exercise some control over the
bean and also to allow the bean to exercise some control over connections.
Class for encapsulating a connection between two beans.
Class that manages a set of beans.
BeanVisual encapsulates icons and label for a given bean.
BestFirst:
Searches the space of attribute subsets by greedy hillclimbing augmented with a backtracking facility.
Searches the space of attribute subsets by greedy hillclimbing augmented with a backtracking facility.
Class for building a best-first decision tree classifier.
This is the Exception thrown by BIFParser, if there
was an error in parsing the XMLBIF string or input
stream.
This class parses an inputstream or a string in
XMLBIF ver.
Builds a description of a Bayes Net classifier stored in XML BIF 0.3 format.
For more details on XML BIF see:
Fabio Cozman, Marek Druzdzel, Daniel Garcia (1998).
For more details on XML BIF see:
Fabio Cozman, Marek Druzdzel, Daniel Garcia (1998).
Class for storing a binary-data-only instance as a sparse vector.
Class for selecting a C4.5-like binary (!) split for a given dataset.
Class implementing a binary C4.5-like split on an attribute.
Cluster data generator designed for the BIRCH System
Dataset is generated with instances in K clusters.
Instances are 2-d data points.
Each cluster is characterized by the number of data points in itits radius and its center.
Dataset is generated with instances in K clusters.
Instances are 2-d data points.
Each cluster is characterized by the number of data points in itits radius and its center.
BMAEstimator estimates conditional probability tables of a Bayes network using Bayes Model Averaging (BMA).
This class takes any JComponent and outputs it to a BMP-file.
Class representing the body of a rule.
The class that constructs a ball tree bottom up.
BoundaryPanel.
This class extends BoundaryPanel with code for distributing the
processing necessary to create a visualization among a list of
remote machines.
BoundaryVisualizer.
A little helper class for browser related stuff.
Built-in function for +, -, *, /.
Built-in function for min, max, sum, avg, log10,
ln, sqrt, abs, exp, pow, threshold, floor, ceil and round.
Built-in function for uppercase, substring and trimblanks.
Class for performing a Bias-Variance decomposition on any classifier using the method specified in:
Ron Kohavi, David H.
Ron Kohavi, David H.
This class performs Bias-Variance decomposion on any classifier using the sub-sampled cross-validation procedure as specified in (1).
The Kohavi and Wolpert definition of bias and variance is specified in (2).
The Webb definition of bias and variance is specified in (3).
Geoffrey I.
The Kohavi and Wolpert definition of bias and variance is specified in (2).
The Webb definition of bias and variance is specified in (3).
Geoffrey I.
Reads a file that is C45 format.
Class for selecting a C4.5-type split for a given dataset.
Class for handling a tree structure that can
be pruned using C4.5 procedures.
Class for handling a tree structure that can
be pruned using C4.5 procedures and have nodes grafted on.
Class for handling a partial tree structure pruned using C4.5's
pruning heuristic.
Writes to a destination that is in the format used
by the C4.5 algorithm.
Therefore it outputs a names and a data file.
Therefore it outputs a names and a data file.
Class implementing a C4.5-type split on an attribute.
Base class for RBFKernel and PolyKernel that implements a simple LRU.
A class that describes the capabilites (e.g., handling certain types of
attributes, missing values, types of classes, etc.) of a specific
classifier.
enumeration of all capabilities
Classes implementing this interface return their capabilities in regards
to datasets.
Class implementing the rule generation procedure of the predictive apriori algorithm for class association rules.
Interface for learning class association rules.
Centers all numeric attributes in the given dataset to have zero mean (apart from the class attribute, if set).
CfsSubsetEval :
Evaluates the worth of a subset of attributes by considering the individual predictive ability of each feature along with the degree of redundancy between them.
Subsets of features that are highly correlated with the class while having low intercorrelation are preferred.
For more information see:
M.
Evaluates the worth of a subset of attributes by considering the individual predictive ability of each feature along with the degree of redundancy between them.
Subsets of features that are highly correlated with the class while having low intercorrelation are preferred.
For more information see:
M.
Changes the date format used by a date attribute.
Abstract superclass for tokenizers that take characters as delimiters.
Event encapsulating info for plotting a data point on the StripChart
Interface to something that can process a ChartEvent
Implements the Chebyshev distance.
Abstract general class for testing in Weka.
Class for examining the capabilities and finding problems with
associators.
Class for examining the capabilities and finding problems with
attribute selection schemes.
An extended JList that contains CheckBoxes.
Class for examining the capabilities and finding problems with
classifiers.
Class for examining the capabilities and finding problems with
clusterers.
Class for examining the capabilities and finding problems with
estimators.
class that contains info about the attribute types the estimator can estimate
estimator work on one attribute only
public class that contains info about the chosen attribute type
estimator work on one attribute only
Simple command line checking of classes that are editable in the GOE.
Class for examining the capabilities and finding problems with
kernels.
Simple command line checking of classes that implement OptionHandler.
Abstract general class for testing schemes in Weka.
a class for postprocessing the test-data
A simple class for checking the source generated from Classifiers
implementing the
weka.classifiers.Sourcable
interface.A simple class for checking the source generated from Filters
implementing the
weka.filters.Sourcable
interface.Class for manipulating chi-square mixture distributions.
ChiSquaredAttributeEval :
Evaluates the worth of an attribute by computing the value of the chi-squared statistic with respect to the class.
Evaluates the worth of an attribute by computing the value of the chi-squared statistic with respect to the class.
Cholesky Decomposition.
The CISearchAlgorithm class supports Bayes net structure search algorithms that are based on conditional independence test (as opposed to for example score based of cross validation based search algorithms).
Modified version of the Citation kNN multi instance classifier.
For more information see:
Jun Wang, Zucker, Jean-Daniel: Solving Multiple-Instance Problem: A Lazy Learning Approach.
For more information see:
Jun Wang, Zucker, Jean-Daniel: Solving Multiple-Instance Problem: A Lazy Learning Approach.
Filter that can set and unset the class index.
Bean that assigns a class attribute to a data set.
BeanInfo class for the class assigner bean
GUI customizer for the class assigner bean
A meta classifier for handling multi-class datasets with 2-class classifiers by building a random class-balanced tree structure.
For more info, check
Lin Dong, Eibe Frank, Stefan Kramer: Ensembles of Balanced Nested Dichotomies for Multi-class Problems.
For more info, check
Lin Dong, Eibe Frank, Stefan Kramer: Ensembles of Balanced Nested Dichotomies for Multi-class Problems.
This class is used for discovering classes that implement a certain
interface or a derived from a certain class.
compares two strings.
Abstract class for data generators for classifiers.
A simple meta-classifier that uses a clusterer for classification.
Class for doing classification using regression methods.
Abstract classifier.
Bean that wraps around weka.classifiers
BeanInfo class for the Classifier wrapper bean
GUI customizer for the classifier wrapper bean
Class for handling a rule (partial tree) for a decision list.
0* This panel allows the user to select and configure a classifier, set the
attribute of the current dataset to be used as the class, and evaluate the
classifier using a number of testing modes (test on the training data,
train/test on a percentage split, n-fold cross-validation, test on a separate
split).
A bean that evaluates the performance of batch trained classifiers
Bean info class for the classifier performance evaluator
A SplitEvaluator that produces results for a
classification scheme on a nominal class attribute.
Abstract class for classification models that can be used
recursively to split the data.
Classifier subset evaluator:
Evaluates attribute subsets on training data or a seperate hold out testing set.
Evaluates attribute subsets on training data or a seperate hold out testing set.
Class for handling a tree structure used for
classification.
Utility class that can add jar files to the classpath dynamically.
Changes the order of the classes so that the class values are no longer of in the order specified in the header.
This panel displays coloured labels for nominal attributes and a spectrum
for numeric attributes.
BeanInfo class for the class value picker bean
Yiling Yang, Xudong Guan, Jinyuan You: CLOPE: a fast and effective clustering algorithm for transactional data.
Ancestor to all ClusterDefinitions, i.e., subclasses that handle their
own parameters that the cluster generator only passes on.
Interface for clusterers.
Bean that wraps around weka.clusterers
BeanInfo class for the Clusterer wrapper bean
GUI customizer for the Clusterer wrapper bean
This panel allows the user to select and configure a clusterer, and evaluate
the clusterer using a number of testing modes (test on the training data,
train/test on a percentage split, test on a separate split).
A bean that evaluates the performance of batch trained clusterers
Bean info class for the clusterer performance evaluator
Class for evaluating clustering models.
Abstract class for cluster data generators.
A filter that uses a density-based clusterer to generate cluster membership values; filtered instances are composed of these values plus the class attribute (if set in the input data).
Class implementing the Cobweb and Classit clustering algorithms.
Note: the application of node operators (merging, splitting etc.) in terms of ordering and priority differs (and is somewhat ambiguous) between the original Cobweb and Classit papers.
Note: the application of node operators (merging, splitting etc.) in terms of ordering and priority differs (and is somewhat ambiguous) between the original Cobweb and Classit papers.
This class maintains a list that contains all the colornames from the
dotty standard and what color (in RGB) they represent
Class for building and using a Complement class Naive Bayes classifier.
For more information see,
Jason D.
For more information see,
Jason D.
A helper class for some common tasks with Dialogs, Icons, etc.
Interface to something that can accept remote connections and execute
a task.
Interface for conditional probability estimators.
Cells of this matrix correspond to counts of the number (or weight)
of predictions for each actual value / predicted value combination.
This class implements a single conjunctive rule learner that can predict for numeric and nominal class labels.
A rule consists of antecedents "AND"ed together and the consequent (class value) for the classification/regression.
A rule consists of antecedents "AND"ed together and the consequent (class value) for the classification/regression.
An event that is generated when a connection is established or dropped.
A listener for connect/disconnect events.
Interface for Beans that can receive (dis-)connection events generated when
(dis-)connecting data processing nodes in the Weka KnowledgeFlow.
Enables the user to insert a database URL, plus user/password to connect
to this database.
ConsistencySubsetEval :
Evaluates the worth of a subset of attributes by the level of consistency in the class values when the training instances are projected onto the subset of attributes.
Evaluates the worth of a subset of attributes by the level of consistency in the class values when the training instances are projected onto the subset of attributes.
A simple logger that outputs the logging information in the console.
Class encapsulating a Constant Expression.
Class implementing some statistical routines for contingency tables.
A specialized JFileChooser that lists all available file Loaders and Savers.
Utility routines for the converter package.
Helper class for saving data to files.
Helper class for loading data from files and URLs.
An instance filter that copies a range of attributes in the dataset.
Interface implemented by classes that can produce "shallow" copies
of their objects.
A class for providing centralized Copyright information.
Finds split points using correlation.
Bean that aids in analyzing cost/benefit tradeoffs.
Bean info class for the cost/benefit analysis
Generates points illustrating probablity cost tradeoffs that can be
obtained by varying the threshold value between classes.
Class for storing and manipulating a misclassification cost matrix.
Class for editing CostMatrix objects.
Abstract base class for cost-sensitive subset and attribute evaluators.
A meta subset evaluator that makes its base subset evaluator cost-sensitive.
A metaclassifier that makes its base classifier cost-sensitive.
SplitEvaluator that produces results for a classification scheme on a nominal class attribute, including weighted misclassification costs.
A meta subset evaluator that makes its base subset evaluator cost-sensitive.
Class implementing the CoverTree datastructure.
The class is very much a translation of the c source code made available by the authors.
For more information and original source code see:
Alina Beygelzimer, Sham Kakade, John Langford: Cover trees for nearest neighbor.
The class is very much a translation of the c source code made available by the authors.
For more information and original source code see:
Alina Beygelzimer, Sham Kakade, John Langford: Cover trees for nearest neighbor.
Bean for splitting instances into training ant test sets according to
a cross validation
BeanInfo class for the cross validation fold maker bean
GUI Customizer for the cross validation fold maker bean
Generates for each run, carries out an n-fold
cross-validation, using the set SplitEvaluator to generate some results.
Reads a source that is in comma separated or tab
separated format.
Takes results from a result producer and assembles them into comma separated value form.
Writes to a destination that is in csv format
Customizers who want to be able to close the customizer window
themselves can implement this window.
An interface for objects that are capable of supplying their own
custom GUI components.
Class for performing parameter selection by cross-validation for any classifier.
For more information, see:
R.
For more information, see:
R.
This meta classifier creates a number of disjoint, stratified folds out of the data and feeds each chunk of data to a copy of the supplied base classifier.
Database.java
Authors: Rainer Holzmann, Zhanna Melnikova-Albrecht, Matthias Schubert
Date: Aug 20, 2004
Time: 1:03:43 PM
$ Revision 1.4 $
Authors: Rainer Holzmann, Zhanna Melnikova-Albrecht, Matthias Schubert
Date: Aug 20, 2004
Time: 1:03:43 PM
$ Revision 1.4 $
Connects to a database.
A dialog to enter URL, username and password for a database connection.
Marker interface for a loader/saver that uses a database
Reads Instances from a Database.
Takes results from a result producer and sends them to a database.
Examines a database and extracts out the results
produced by the specified ResultProducer and submits them to the specified
ResultListener.
Writes to a database (tested with MySQL, InstantDB, HSQLDB).
DatabaseUtils provides utility functions for accessing the experiment
database.
Listener interface that customizer classes that are interested
in data format changes can implement.
Abstract superclass for data generators that generate data for classifiers
and clusterers.
Interface to something that can generate new instances based on
a set of input instances
A panel for generating artificial data via DataGenerators.
A meta classifier for handling multi-class datasets with 2-class classifiers by building a random data-balanced tree structure.
For more info, check
Lin Dong, Eibe Frank, Stefan Kramer: Ensembles of Balanced Nested Dichotomies for Multi-class Problems.
For more info, check
Lin Dong, Eibe Frank, Stefan Kramer: Ensembles of Balanced Nested Dichotomies for Multi-class Problems.
DataObject.java
Authors: Rainer Holzmann, Zhanna Melnikova-Albrecht, Matthias Schubert
Date: Aug 19, 2004
Time: 5:48:59 PM
$ Revision 1.4 $
Authors: Rainer Holzmann, Zhanna Melnikova-Albrecht, Matthias Schubert
Date: Aug 19, 2004
Time: 5:48:59 PM
$ Revision 1.4 $
Event encapsulating a data set
This panel controls setting a list of datasets for an experiment to
iterate over.
Indicator interface to something that can store instances to some
destination
Interface to something that is capable of being a source for data -
either batch or incremental data
Interface to something that can accept DataSetEvents
Bean that encapsulates weka.gui.visualize.VisualizePanel
Bean info class for the data visualizer
Basic implementation of DBSCAN clustering algorithm that should *not* be used as a reference for runtime benchmarks: more sophisticated implementations exist! Clustering of new instances is not supported.
A little bit extended DatabaseUtils class.
Conditional probability estimator for a discrete domain conditional upon
a discrete domain.
A helper class for debug output, logging, clocking, etc.
A little helper class for clocking and outputting times.
contains debug methods
A helper class for logging stuff.
This extended Random class enables one to print the generated random
numbers etc., before they are returned.
A little, simple helper class for logging stuff.
A class that can be used for timestamps in files, The toString() method
simply returns the associated Date object in a timestamp format.
Class for building and using a decision stump.
Class for building and using a simple decision table majority classifier.
For more information see:
Ron Kohavi: The Power of Decision Tables.
For more information see:
Ron Kohavi: The Power of Decision Tables.
Class providing hash table keys for DecisionTable
DECORATE is a meta-learner for building diverse ensembles of classifiers by using specially constructed artificial training examples.
Class encapsulating DefineFunction (used in TransformationDictionary).
Interface for clusterers that can estimate the density for a given instance.
A SplitEvaluator that produces results for a density based clusterer.
Simple symbolic probability estimator based on symbol counts.
Symbolic probability estimator based on symbol counts and a prior.
Symbolic probability estimator based on symbol counts and a prior.
Class for handling discrete functions.
Class encapsulating a Discretize Expression.
An instance filter that discretizes a range of numeric attributes in the dataset into nominal attributes.
An instance filter that discretizes a range of numeric attributes in the dataset into nominal attributes.
Interface for any class that can compute and return distances between two
instances.
This panel enables an experiment to be distributed to multiple hosts;
it also allows remote host names to be specified.
Class for handling a distribution of class values.
Conditional probability estimator for a discrete domain conditional upon
a numeric domain.
Class for building and using a Discriminative Multinomial Naive Bayes classifier.
Conditional probability estimator for a discrete domain conditional upon
a numeric domain.
This class parses input in DOT format, and
builds the datastructures that are passed to it.
A vector specialized on doubles.
Interface to something that can be drawn as a graph.
Class for building and using a decision table/naive bayes hybrid classifier.
This class is used in conjunction with the Node class to form a tree
structure.
Bayes Network learning using various search algorithms and quality measures.
Base class for a Bayes Network classifier.
Base class for a Bayes Network classifier.
Computes the Levenshtein edit distance between two strings.
Eigenvalues and eigenvectors of a real matrix.
Class representing an Element, i.e., a set of events/items.
Simple EM (expectation maximisation) class.
EM assigns a probability distribution to each instance which indicates the probability of it belonging to each of the clusters.
EM assigns a probability distribution to each instance which indicates the probability of it belonging to each of the clusters.
A meta classifier for handling multi-class datasets with 2-class classifiers by building an ensemble of nested dichotomies.
For more info, check
Lin Dong, Eibe Frank, Stefan Kramer: Ensembles of Balanced Nested Dichotomies for Multi-class Problems.
For more info, check
Lin Dong, Eibe Frank, Stefan Kramer: Ensembles of Balanced Nested Dichotomies for Multi-class Problems.
"Abstract" class for computing splitting criteria
based on the entropy of a class distribution.
Class for computing the entropy for a given distribution.
This class encapsulates a map of all environment and java system properties.
Interface for something that can utilize environment
variables.
EpsilonRange_ListElement.java
Authors: Rainer Holzmann, Zhanna Melnikova-Albrecht, Matthias Schubert
Date: Sep 7, 2004
Time: 2:12:34 PM
$ Revision 1.4 $
Authors: Rainer Holzmann, Zhanna Melnikova-Albrecht, Matthias Schubert
Date: Sep 7, 2004
Time: 2:12:34 PM
$ Revision 1.4 $
Interface for evaluators that calculate the "merit" of attributes/subsets
as the error of a learning scheme
Interface implemented by classes loaded dynamically to
visualize classifier errors in the explorer.
Abstract class for all estimators.
Contains static utility functions for Estimators.
EuclideanDataObject.java
Authors: Rainer Holzmann, Zhanna Melnikova-Albrecht, Matthias Schubert
Date: Aug 19, 2004
Time: 5:50:22 PM
$ Revision 1.4 $
Authors: Rainer Holzmann, Zhanna Melnikova-Albrecht, Matthias Schubert
Date: Aug 19, 2004
Time: 5:50:22 PM
$ Revision 1.4 $
Implementing Euclidean distance (or similarity) function.
One object defines not one distance but the data model in which the distances between objects of that data model can be computed.
Attention: For efficiency reasons the use of consistency checks (like are the data models of the two instances exactly the same), is low.
For more information, see:
Wikipedia.
One object defines not one distance but the data model in which the distances between objects of that data model can be computed.
Attention: For efficiency reasons the use of consistency checks (like are the data models of the two instances exactly the same), is low.
For more information, see:
Wikipedia.
Class for evaluating machine learning models.
Contains utility functions for generating lists of predictions in
various manners.
Interface for objects that want to be able to specify at any given
time whether their current configuration allows a particular event
to be generated.
ExhaustiveSearch :
Performs an exhaustive search through the space of attribute subsets starting from the empty set of attrubutes.
Performs an exhaustive search through the space of attribute subsets starting from the empty set of attrubutes.
Holds all the necessary configuration information for a standard
type experiment.
The main class for the experiment environment.
This class offers get methods for the default Experimenter settings in
the props file
weka/gui/experiment/Experimenter.props
.The main class for the Weka explorer.
This event can be fired in case the capabilities filter got changed
Interface for classes that listen for filter changes.
A common interface for panels to be displayed in the Explorer
A common interface for panels in the explorer that can handle logs
This class offers get methods for the default Explorer settings in
the props file
weka/gui/explorer/Explorer.props
.A data generator for generating y according to a given expression out of randomly generated x.
E.g., the mexican hat can be generated like this:
sin(abs(a1)) / abs(a1)
In addition to this function, the amplitude can be changed and gaussian noise can be added.
E.g., the mexican hat can be generated like this:
sin(abs(a1)) / abs(a1)
In addition to this function, the amplitude can be changed and gaussian noise can be added.
Provides a file filter for FileChoosers that accepts or rejects files
based on their extension.
Cluster data using the FarthestFirst algorithm.
For more information see:
Hochbaum, Shmoys (1985).
For more information see:
Hochbaum, Shmoys (1985).
Implements a fast vector class without synchronized
methods.
Abstract superclass for various types of field meta
data.
Inner class for an Interval.
Enumerated type for the closure.
Enumerated type for the Optype
Inner class for Values
Enumerated type for the property.
Class encapsulating a FieldRef Expression.
A PropertyEditor for File objects that lets the user select a file.
A simple file logger, that just logs to a single file.
Interface to a loader/saver that loads/saves from a file source.
An abstract class for instance filters: objects that take instances
as input, carry out some transformation on the instance and then
output the instance.
A wrapper bean for Weka filters
Bean info class for the Filter bean
GUI customizer for the filter bean
Class for running an arbitrary associator on data that has been passed through an arbitrary filter.
Class for running an arbitrary attribute evaluator on data that has been passed through an
arbitrary filter (note: filters that alter the order or number of attributes are not allowed).
Class for running an arbitrary classifier on data that has been passed through an arbitrary filter.
Class for running an arbitrary clusterer on data that has been passed through an arbitrary filter.
Class for running an arbitrary subset evaluator on data that has been passed through an arbitrary
filter (note: filters that alter the order or number of attributes are not allowed).
Locates all classes with certain capabilities.
This instance filter takes a range of N numeric attributes and replaces them with N-1 numeric attributes, the values of which are the difference between consecutive attribute values from the original instance.
Class for the format of floating point numbers
Small utility class for executing KnowledgeFlow
flows outside of the KnowledgeFlow application
Class implementing the FP-growth algorithm for finding large item sets without candidate generation.
Enum for holding different metric types
Inner class that handles a single binary item
The FromFile reads the structure of a Bayes net from a file in BIFF format.
Classifier for building 'Functional trees', which are classification trees that could have logistic regression functions at the inner nodes and/or leaves.
Class for Functional Inner tree structure.
Class for Functional Leaves tree version.
Class for Functional tree structure.
Abstract class for Functional tree structure.
Abstract superclass for PMML built-in and DefineFunctions.
GainRatioAttributeEval :
Evaluates the worth of an attribute by measuring the gain ratio with respect to the class.
GainR(Class, Attribute) = (H(Class) - H(Class | Attribute)) / H(Attribute).
Evaluates the worth of an attribute by measuring the gain ratio with respect to the class.
GainR(Class, Attribute) = (H(Class) - H(Class | Attribute)) / H(Attribute).
Class for computing the gain ratio for a given distribution.
Implementation of the Gaussian Prior update function based on
CLG Algorithm with a certain Trust Region Update.
Implements Gaussian Processes for regression without hyperparameter-tuning.
Class implementing a GSP algorithm for discovering sequential patterns in a sequential data set.
The attribute identifying the distinct data sequences contained in the set can be determined by the respective option.
The attribute identifying the distinct data sequences contained in the set can be determined by the respective option.
Class implementing import of PMML General Regression model.
This panel controls setting a list of values for an arbitrary
resultgenerator property for an experiment to iterate over.
A PropertyEditor for arrays of objects that themselves have
property editors.
A PropertyEditor for objects.
This class can generate the properties object that is normally loaded from
the
GenericObjectEditor.props
file (= PROPERTY_FILE).GeneticSearch:
Performs a search using the simple genetic algorithm described in Goldberg (1989).
For more information see:
David E.
Performs a search using the simple genetic algorithm described in Goldberg (1989).
For more information see:
David E.
This Bayes Network learning algorithm uses genetic search for finding a well scoring Bayes network structure.
This Bayes Network learning algorithm uses genetic search for finding a well scoring Bayes network structure.
Generates Javadoc comments from the class's globalInfo method.
This Bayes Network learning algorithm uses cross validation to estimate classification accuracy.
Implements Grading.
Class implementing a split for nodes added to a tree during grafting.
GraphConstants.java
This class represents an edge in the graph
Event for graphs
Describe interface
TextListener
here.This class represents a node in the Graph.
GraphPanel.java
Authors: Rainer Holzmann, Zhanna Melnikova-Albrecht
Date: Sep 16, 2004
Time: 10:28:19 AM
$ Revision 1.4 $
Authors: Rainer Holzmann, Zhanna Melnikova-Albrecht
Date: Sep 16, 2004
Time: 10:28:19 AM
$ Revision 1.4 $
A bean encapsulating weka.gui.treevisualize.TreeVisualizer
Bean info class for the graph viewer
Interface implemented by classes loaded dynamically to
visualize graphs in the explorer.
This class displays the graph we want to visualize.
GreedyStepwise :
Performs a greedy forward or backward search through the space of attribute subsets.
Performs a greedy forward or backward search through the space of attribute subsets.
Performs a grid search of parameter pairs for the a classifier (Y-axis, default is LinearRegression with the "Ridge" parameter) and the PLSFilter (X-axis, "# of Components") and chooses the best pair found for the actual predicting.
The initial grid is worked on with 2-fold CV to determine the values of the parameter pairs for the selected type of evaluation (e.g., accuracy).
The initial grid is worked on with 2-fold CV to determine the values of the parameter pairs for the selected type of evaluation (e.g., accuracy).
GUI interface to Bayesian Networks.
The main class for the Weka GUIChooser.
Specialized JFrame class.
Class representing the head of a rule.
This class lays out the vertices of a graph in a
hierarchy of vertical levels, with a number of nodes
in each level.
Hierarchical clustering class.
This class implements a parser to read properties that have
a hierarchy(i.e.
This Bayes Network learning algorithm uses a hill climbing algorithm adding, deleting and reversing arcs.
This Bayes Network learning algorithm uses a hill climbing algorithm adding, deleting and reversing arcs.
An event that is generated when a history is modified.
A listener for changes in a history.
Contructs Hidden Naive Bayes classification model with high classification accuracy and AUC.
For more information refer to:
H.
For more information refer to:
H.
Abstract attribute subset evaluator capable of evaluating subsets with
respect to a data set that is distinct from that used to initialize/
train the subset evaluator.
This panel controls setting a list of hosts for a RemoteExperiment to
use.
Class implementing a HyperPipe classifier.
Nearest-neighbour classifier.
K-nearest neighbours classifier.
This Bayes Network learning algorithm uses conditional independence tests to find a skeleton, finds V-nodes and applies a set of rules to find the directions of the remaining arrows.
Class for constructing an unpruned decision tree based on the ID3 algorithm.
Class for handling the impurity values when spliting the instances
Bean that evaluates incremental classifiers
Bean info class for the incremental classifier evaluator bean
GUI Customizer for the incremental classifier evaluator bean
Class encapsulating an incrementally built classifier and current instance
Interface to something that can process a IncrementalClassifierEvent
Marker interface for a loader/saver that can retrieve instances incrementally
Interface for an incremental probability estimators.
InfoGainAttributeEval :
Evaluates the worth of an attribute by measuring the information gain with respect to the class.
InfoGain(Class,Attribute) = H(Class) - H(Class | Attribute).
Evaluates the worth of an attribute by measuring the information gain with respect to the class.
InfoGain(Class,Attribute) = H(Class) - H(Class | Attribute).
Class for computing the information gain for a given distribution.
A simple panel for displaying information, e.g.
A specialized renderer that takes care of JLabels in a JList.
Class for handling an instance.
A comparator for the Instance class.
A bean that counts instances streamed to it.
Event that encapsulates a single instance or header information only
An event encapsulating an instance stream event.
A bean that joins two streams of instances into one.
Interface to something that can accept instance events
An interface for objects interested in listening to streams of instances.
A bean that produces a stream of instances from a file.
An interface for objects capable of producing streams of instances.
Convert the results of a database query into instances.
Class for handling an ordered set of weighted instances.
A bean that saves a stream of instances to a file.
Outputs the received results in arff format to a Writer.
This panel just displays relation name, number of instances, and number of
attributes.
Bean that converts an instance stream into a (batch) data set.
BeanInfo class for the InstanceStreamToBatchMaker bean
A bean that takes a stream of instances and displays in a table.
This is a very simple instance viewer - just displays the dataset as
text output as it would be written to a file.
A filter for detecting outliers and extreme values based on interquartile ranges.
Interface for classifiers that can output confidence intervals
A vector specialized on integers.
Learns an isotonic regression model.
Class for storing a set of items.
An iterated version of the Lovins stemmer.
Abstract utility class for handling settings common to
meta classifiers that build an ensemble from a single base learner.
Interface for classifiers that can induce models of growing
complexity one step at a time.
Class for generating a pruned or unpruned C4.5 decision tree.
Class for generating a grafted (pruned or unpruned) C4.5 decision tree.
Abstract superclass for classes that generate Javadoc comments and replace
the content between certain comment tags.
This class takes any JComponent and outputs it to a file.
A helper class for JList GUI elements with DefaultListModel or
derived models.
This class takes any JComponent and outputs it to a JPEG-file.
This class implements a propositional rule learner, Repeated Incremental Pruning to Produce Error Reduction (RIPPER), which was proposed by William W.
A helper class for JTable, e.g.
A helper class for Jython.
An indicator interface for Jython objects.
An indicator interface for serializable Jython objects.
This Bayes Network learning algorithm uses a hill climbing algorithm restricted by an order on the variables.
For more information see:
G.F.
For more information see:
G.F.
This Bayes Network learning algorithm uses a hill climbing algorithm restricted by an order on the variables.
For more information see:
G.F.
For more information see:
G.F.
Conditional probability estimator for a numeric domain conditional upon
a discrete domain (utilises separate kernel estimators for each discrete
conditioning value).
KDDataGenerator.
Class implementing the KDTree search algorithm for nearest neighbour search.
The connection to dataset is only a reference.
The connection to dataset is only a reference.
A class representing a KDTree node.
Class that splits up a KDTreeNode.
Abstract kernel.
Simple kernel density estimator.
Class for evaluating Kernels.
Converts the given set of predictor variables into a kernel matrix.
Conditional probability estimator for a numeric domain conditional upon
a numeric domain.
The class that splits a node into two such that the overall sum of squared distances of points to their centres on both sides of the (axis-parallel) splitting plane is minimum.
For more information see also:
Ashraf Masood Kibriya (2007).
For more information see also:
Ashraf Masood Kibriya (2007).
Startup class for the KnowledgeFlow.
Main GUI class for the KnowledgeFlow.
This class is a helper class for XML serialization using KOML .
K* is an instance-based classifier, that is the class of a test instance is based upon the class of those training instances similar to it, as determined by some similarity function.
A class representing the caching system used to keep track of each attribute
value and its corresponding scale factor or stop parameter.
A custom class which provides the environment for computing the
transformation probability of a specified test instance nominal
attribute to a specified train instance nominal attribute.
A custom class which provides the environment for computing the
transformation probability of a specified test instance numeric
attribute to a specified train instance numeric attribute.
Class for storing a set of items together with a class label.
Class for generating a multi-class alternating decision tree using the LogitBoost strategy.
This Bayes Network learning algorithm uses a Look Ahead Hill Climbing algorithm called LAGD Hill Climbing.
Implementation of the Gaussian Prior update function based on modified
CLG Algorithm (CLG-Lasso) with a certain Trust Region Update based
on Laplace Priors.
Performs latent semantic analysis and transformation of the data.
This is an event which is fired by a LayoutEngine once
a LayoutEngine finishes laying out the graph, so
that the Visualizer can repaint the screen to show
the changes.
This interface should be implemented by any class
which needs to receive LayoutCompleteEvents from
the LayoutEngine.
This interface class has been added to facilitate the addition
of other layout engines to this package.
Lazy Bayesian Rules Classifier.
Tells a sub-ResultProducer to reproduce the current
run for varying sized subsamples of the dataset.
Implements a least median sqaured linear regression utilising the existing weka LinearRegression class to form predictions.
This generator produces data for a display with 7 LEDs.
This panel displays legends for a list of plots.
A wrapper class for the liblinear tools (the liblinear classes, typically the jar file, need to be in the classpath to use this classifier).
Rong-En Fan, Kai-Wei Chang, Cho-Jui Hsieh, Xiang-Rui Wang, Chih-Jen Lin (2008).
Rong-En Fan, Kai-Wei Chang, Cho-Jui Hsieh, Xiang-Rui Wang, Chih-Jen Lin (2008).
A wrapper class for the libsvm tools (the libsvm
classes, typically the jar file, need to be in the classpath to use this
classifier).
LibSVM runs faster than SMO since it uses LibSVM to build the SVM classifier.
LibSVM allows users to experiment with One-class SVM, Regressing SVM, and nu-SVM supported by LibSVM tool.
LibSVM runs faster than SMO since it uses LibSVM to build the SVM classifier.
LibSVM allows users to experiment with One-class SVM, Regressing SVM, and nu-SVM supported by LibSVM tool.
Reads a source that is in libsvm format.
For more information about libsvm see:
http://www.csie.ntu.edu.tw/~cjlin/libsvm/
For more information about libsvm see:
http://www.csie.ntu.edu.tw/~cjlin/libsvm/
Writes to a destination that is in libsvm format.
For more information about libsvm see:
http://www.csie.ntu.edu.tw/~cjlin/libsvm/
For more information about libsvm see:
http://www.csie.ntu.edu.tw/~cjlin/libsvm/
LinearForwardSelection:
Extension of BestFirst.
Extension of BestFirst.
Class implementing the brute force search algorithm for nearest neighbour search.
Class for using linear regression for prediction.
Class for performing (ridged) linear regression using Tikhonov
regularization.
This can be used by the
neuralnode to perform all it's computations (as a Linear unit).
Lists the options of an OptionHandler
A dialog to present the user with a list of items, that the user can
make a selection from, or cancel the selection.
Class representing a set of literals, being either the body or the head
of a rule.
Classifier for building 'logistic model trees', which are classification trees with logistic regression functions at the leaves.
Class for logistic model tree structure.
Interface to something that can load Instances from an input source in some
format.
Loads data sets using weka.core.converter classes
This class is for loading resources from a JAR archive.
Bean info class for the loader bean
GUI Customizer for the loader bean
The ScoreBasedSearchAlgorithm class supports Bayes net structure search algorithms that are based on maximizing scores (as opposed to for example conditional independence based search algorithms).
Abstract superclass for all loggers.
Interface for objects that display log (permanent historical) and
status (transient) messages.
The logging level.
Class for building and using a multinomial logistic regression model with a ridge estimator.
There are some modifications, however, compared to the paper of leCessie and van Houwelingen(1992):
If there are k classes for n instances with m attributes, the parameter matrix B to be calculated will be an m*(k-1) matrix.
The probability for class j with the exception of the last class is
Pj(Xi) = exp(XiBj)/((sum[j=1..(k-1)]exp(Xi*Bj))+1)
The last class has probability
1-(sum[j=1..(k-1)]Pj(Xi))
= 1/((sum[j=1..(k-1)]exp(Xi*Bj))+1)
The (negative) multinomial log-likelihood is thus:
L = -sum[i=1..n]{
sum[j=1..(k-1)](Yij * ln(Pj(Xi)))
+(1 - (sum[j=1..(k-1)]Yij))
* ln(1 - sum[j=1..(k-1)]Pj(Xi))
} + ridge * (B^2)
In order to find the matrix B for which L is minimised, a Quasi-Newton Method is used to search for the optimized values of the m*(k-1) variables.
There are some modifications, however, compared to the paper of leCessie and van Houwelingen(1992):
If there are k classes for n instances with m attributes, the parameter matrix B to be calculated will be an m*(k-1) matrix.
The probability for class j with the exception of the last class is
Pj(Xi) = exp(XiBj)/((sum[j=1..(k-1)]exp(Xi*Bj))+1)
The last class has probability
1-(sum[j=1..(k-1)]Pj(Xi))
= 1/((sum[j=1..(k-1)]exp(Xi*Bj))+1)
The (negative) multinomial log-likelihood is thus:
L = -sum[i=1..n]{
sum[j=1..(k-1)](Yij * ln(Pj(Xi)))
+(1 - (sum[j=1..(k-1)]Yij))
* ln(1 - sum[j=1..(k-1)]Pj(Xi))
} + ridge * (B^2)
In order to find the matrix B for which L is minimised, a Quasi-Newton Method is used to search for the optimized values of the m*(k-1) variables.
Base/helper class for building logistic regression models with the LogitBoost algorithm.
Class for performing additive logistic regression.
Class for displaying a status area (made up of a variable number of lines)
and a log area.
This panel allows log and status messages to be posted.
Frame that shows the output from stdout and stderr.
Interface to be implemented by classes that should be able to write their
own output to the Weka logger.
A little helper class for setting the Look and Feel of the user interface.
A stemmer based on the Lovins stemmer, described here:
Julie Beth Lovins (1968).
Julie Beth Lovins (1968).
LU Decomposition.
Locally weighted learning.
M5Base.
M5Base.
Generates a decision list for regression problems using separate-and-conquer.
Simple probability estimator that places a single normal distribution
over the observed values.
Menu-based GUI for Weka, replacement for the GUIChooser.
DesktopPane with background image.
Specialized JInternalFrame class.
Specialized JFrame class.
Classes implementing this interface will be displayed in the "Extensions"
menu in the main GUI of Weka.
Class for handling a decision list.
Class for wrapping a Clusterer to make it return a distribution and density.
A filter that creates a new dataset with a boolean attribute replacing a nominal attribute.
ManhattanDataObject.java
Authors: Rainer Holzmann, Zhanna Melnikova-Albrecht, Matthias Schubert
Date: Aug 19, 2004
Time: 5:50:22 PM
$ Revision 1.4 $
Authors: Rainer Holzmann, Zhanna Melnikova-Albrecht, Matthias Schubert
Date: Aug 19, 2004
Time: 5:50:22 PM
$ Revision 1.4 $
Implements the Manhattan distance (or Taxicab geometry).
Class that maintains the mapping between incoming data set structure
and that of the mining schema.
Generates points illustrating the prediction margin.
Interface to something that can be matched with tree matching
algorithms.
Class for evaluating a string adhering the following grammar:
Modify numeric attributes according to a given expression
Utility class.
Deprecated.
Jama = Java Matrix class.
This panel displays a plot matrix of the user selected attributes
of a given data set.
Modified Diverse Density algorithm, with collective assumption.
More information about DD:
Oded Maron (1998).
More information about DD:
Oded Maron (1998).
Class that splits a BallNode of a ball tree using Uhlmann's described method.
For information see:
Jeffrey K.
For information see:
Jeffrey K.
Class that splits a BallNode of a ball tree based on the median value of the widest dimension of the points in the ball.
The class that splits a KDTree node based on the median value of a dimension in which the node's points have the widest spread.
For more information see also:
Jerome H.
For more information see also:
Jerome H.
A little helper class for Memory management.
A panel for displaying the memory usage.
Merges two values of a nominal attribute into one value.
Messages.
Messages.
Messages.
Messages.
Messages.
Messages.
Messages.
Messages.
Messages.
Messages.
Messages.
Messages.
Messages.
Messages.
Messages.
Messages.
A meta bean that encapsulates several other regular beans, useful for
grouping large KnowledgeFlows.
This metaclassifier makes its base classifier cost-sensitive using the method specified in
Pedro Domingos: MetaCost: A general method for making classifiers cost-sensitive.
Pedro Domingos: MetaCost: A general method for making classifiers cost-sensitive.
This class handles relationships between display names of properties
(or classes) and Methods that are associated with them.
A data generator for the simple 'Mexian Hat' function:
y = sin|x| / |x|
In addition to this simple function, the amplitude can be changed and gaussian noise can be added.
y = sin|x| / |x|
In addition to this simple function, the amplitude can be changed and gaussian noise can be added.
MI AdaBoost method, considers the geometric mean of posterior of instances inside a bag (arithmatic mean of log-posterior) and the expectation for a bag is taken inside the loss function.
For more information about Adaboost, see:
Yoav Freund, Robert E.
For more information about Adaboost, see:
Yoav Freund, Robert E.
Re-implement the Diverse Density algorithm, changes the testing procedure.
Oded Maron (1998).
Oded Maron (1998).
The class that builds a BallTree middle out.
For more information see also:
Andrew W.
For more information see also:
Andrew W.
The class that splits a KDTree node based on the midpoint value of a dimension in which the node's points have the widest spread.
For more information see also:
Andrew Moore (1991).
For more information see also:
Andrew Moore (1991).
EMDD model builds heavily upon Dietterich's Diverse Density (DD) algorithm.
It is a general framework for MI learning of converting the MI problem to a single-instance setting using EM.
It is a general framework for MI learning of converting the MI problem to a single-instance setting using EM.
Uses either standard or collective multi-instance assumption, but within linear regression.
Class encapsulating information about a MiningField.
This class encapsulates the mining schema from
a PMML xml file.
Multiple-Instance Nearest Neighbour with Distribution learner.
It uses gradient descent to find the weight for each dimension of each exeamplar from the starting point of 1.0.
It uses gradient descent to find the weight for each dimension of each exeamplar from the starting point of 1.0.
This classifier tries to find a suitable ball in the multiple-instance space, with a certain data point in the instance space as a ball center.
The polynomial kernel : K(x, y) = <x, y>^p or K(x, y) = (<x, y>+1)^p
The RBF kernel.
Implements John Platt's sequential minimal optimization algorithm for training a support vector classifier.
This implementation globally replaces all missing values and transforms nominal attributes into binary ones.
This implementation globally replaces all missing values and transforms nominal attributes into binary ones.
Implements Stuart Andrews' mi_SVM (Maximum pattern Margin Formulation of MIL).
A simple Wrapper method for applying standard propositional learners to multi-instance data.
For more information see:
E.
For more information see:
E.
Abtract class for manipulating mixture distributions.
Bean that can be used for displaying threshold curves (e.g.
Bean info class for the model performance chart
Abstract class for model selection criteria.
Class for boosting a classifier using the MultiBoosting method.
MultiBoosting is an extension to the highly successful AdaBoost technique for forming decision committees.
MultiBoosting is an extension to the highly successful AdaBoost technique for forming decision committees.
A metaclassifier for handling multi-class datasets with 2-class classifiers.
Applies several filters successively.
Multi-Instance classifiers can specify an additional Capabilities object
for the data in the relational attribute, since the format of multi-instance
data is fixed to "bag/NOMINAL,data/RELATIONAL,class".
Converts the multi-instance dataset into single instance dataset so that the Nominalize, Standardize and other type of filters or transformation can be applied to these data for the further preprocessing.
Note: the first attribute of the converted dataset is a nominal attribute and refers to the bagId.
Note: the first attribute of the converted dataset is a nominal attribute and refers to the bagId.
A Classifier that uses backpropagation to classify instances.
This network can be built by hand, created by an algorithm or both.
This network can be built by hand, created by an algorithm or both.
Multinomial BMA Estimator.
Abstract utility class for handling settings common to
meta classifiers that build an ensemble from multiple classifiers.
Class for selecting a classifier from among several using cross validation on the training data or the performance on the training data.
Class for a Naive Bayes classifier using estimator classes.
The NaiveBayes class generates a fixed Bayes network structure with arrows from the class variable to each of the attribute variables.
Class for building and using a multinomial Naive Bayes classifier.
Class for building and using a multinomial Naive Bayes classifier.
Class for building and using a simple Naive Bayes classifier.Numeric attributes are modelled by a normal distribution.
For more information, see
Richard Duda, Peter Hart (1973).
For more information, see
Richard Duda, Peter Hart (1973).
Class for a Naive Bayes classifier using estimator classes.
This class contains a color name and the rgb values of that color
Class for generating a decision tree with naive Bayes classifiers at the leaves.
For more information, see
Ron Kohavi: Scaling Up the Accuracy of Naive-Bayes Classifiers: A Decision-Tree Hybrid.
For more information, see
Ron Kohavi: Scaling Up the Accuracy of Naive-Bayes Classifiers: A Decision-Tree Hybrid.
Class for handling a naive bayes tree structure used for
classification.
Class for selecting a NB tree split.
Class implementing a "no-split"-split (leaf node) for naive bayes
trees.
Class implementing a NBTree split on an attribute.
A meta classifier for handling multi-class datasets with 2-class classifiers by building a random tree structure.
For more info, check
Lin Dong, Eibe Frank, Stefan Kramer: Ensembles of Balanced Nested Dichotomies for Multi-class Problems.
For more info, check
Lin Dong, Eibe Frank, Stefan Kramer: Ensembles of Balanced Nested Dichotomies for Multi-class Problems.
Conditional probability estimator for a numeric domain conditional upon
a discrete domain (utilises separate normal estimators for each discrete
conditioning value).
Abstract class for nearest neighbour search.
Abstract unit in a NeuralNetwork.
This is an interface used to create classes that can be used by the
neuralnode to perform all it's computations.
Class implementing import of PMML Neural Network model.
This class is used to represent a node in the neuralnet.
Splits a string into an n-gram with min and max
grams.
Conditional probability estimator for a numeric domain conditional upon
a numeric domain (using Mahalanobis distance).
Nearest-neighbor-like algorithm using non-nested generalized exemplars (which are hyperrectangles that can be viewed as if-then rules).
This class records all the data about a particular node for displaying.
This is an interface for classes that wish to take a node structure and
arrange them
Encapsulates an evaluatable nominal prediction: the predicted probability
distribution plus the actual class value.
Converts all nominal attributes into binary numeric attributes.
Converts all nominal attributes into binary numeric attributes.
Converts a nominal attribute (i.e.
An instance filter that converts all incoming instances into sparse format.
Simple probability estimator that places a single normal distribution
over the observed values.
Represents the abstract ancestor for normalizable distance functions, like
Euclidean or Manhattan distance.
Normalizes all numeric values in the given dataset (apart from the class attribute, if set).
An instance filter that normalize instances considering only numeric attributes and ignoring class index.
The normalized polynomial kernel.
K(x,y) = <x,y>/sqrt(<x,x><y,y>) where <x,y> = PolyKernel(x,y)
K(x,y) = <x,y>/sqrt(<x,x><y,y>) where <x,y> = PolyKernel(x,y)
Class for manipulating normal mixture distributions.
Class encapsulating a NormContinuous Expression.
Class encapsulating a NormDiscrete Expression.
Class implementing a "no-split"-split.
Exception that is raised by an object that is unable to process
data with missing values.
A dummy stemmer that performs no stemming at all.
Interface to a clusterer that can generate a requested number of
clusters
A filter that 'cleanses' the numeric data from values that are too small, too big or very close to a certain value (e.g., 0) and sets these values to a pre-defined default.
Encapsulates an evaluatable numeric prediction: the predicted class value
plus the actual class value.
Converts all numeric attributes into binary attributes (apart from the class attribute, if set): if the value of the numeric attribute is exactly zero, the value of the new attribute will be zero.
A filter for turning numeric attributes into
nominal ones.
Transforms numeric attributes using a given transformation method.
A simple instance filter that renames the relation, all attribute names and all nominal (and string) attribute values.
Class for building and using a 1R classifier; in other words, uses the minimum-error attribute for prediction, discretizing numeric attributes.
OneRAttributeEval :
Evaluates the worth of an attribute by using the OneR classifier.
Evaluates the worth of an attribute by using the OneR classifier.
Basic implementation of OPTICS clustering algorithm that should *not* be used as a reference for runtime benchmarks: more sophisticated implementations exist! Clustering of new instances is not supported.
Start the OPTICS Visualizer from command-line:
java weka.clusterers.forOPTICSAndDBScan.OPTICS_GUI.OPTICS_Visualizer [file.ser]
Implementation of Active-sets method with BFGS update to solve optimization
problem with only bounds constraints in multi-dimensions.
Class to store information about an option.
Interface to something that understands options.
Generates Javadoc comments from the OptionHandler's options.
Meta classifier that allows standard classification algorithms to be applied to ordinal class problems.
For more information see:
Eibe Frank, Mark Hall: A Simple Approach to Ordinal Classification.
For more information see:
Eibe Frank, Mark Hall: A Simple Approach to Ordinal Classification.
A dialog for setting various output format parameters.
A logger that logs all output on stdout and stderr to a file.
A print stream class to capture all data from stdout and stderr.
OutputZipper writes output to either gzipped files or to a
multi entry zip file.
Class for matrix manipulation used for pace regression.
Class for building pace regression linear models and using them for prediction.
Behaves the same as PairedTTester, only it uses the corrected
resampled t-test statistic.
A class for storing stats on a paired comparison (t-test and correlation)
A class for storing stats on a paired comparison.
Calculates T-Test statistics on data stored in a set of instances.
Helper class for Bayes Network classifiers.
CUP v0.11a beta 20060608 generated parser.
CUP v0.11a beta 20060608 generated parser.
Class for generating a PART decision list.
A filter that applies filters on subsets of attributes and assembles the output into a new dataset.
The class that measures the performance of a nearest
neighbour search (NNS) algorithm.
Discretizes numeric attributes using equal frequency binning, where the number of bins is equal to the square root of the number of non-missing values.
For more information, see:
Ying Yang, Geoffrey I.
For more information, see:
Ying Yang, Geoffrey I.
This class will place the Nodes of a tree.
This class will place the Nodes of a tree.
This class plots datasets in two dimensions.
Interface for classes that need to draw to the Plot2D panel *before*
Plot2D renders anything (eg.
This class is a container for plottable data.
A wrapper classifier for the PLSFilter, utilizing the PLSFilter's ability to perform predictions.
Runs Partial Least Square Regression over the given instances and computes the resulting beta matrix for prediction.
By default it replaces missing values and centers the data.
For more information see:
Tormod Naes, Tomas Isaksson, Tom Fearn, Tony Davies (2002).
By default it replaces missing values and centers the data.
For more information see:
Tormod Naes, Tomas Isaksson, Tom Fearn, Tony Davies (2002).
Abstract base class for all PMML classifiers.
This class is a factory class for reading/writing PMML models
Interface for all PMML models
Utility routines.
This class takes any JComponent and outputs it to a PNG-file.
Implements the Moore's method to split a node of a ball tree.
For more information please see section 2 of the 1st and 3.2.3 of the 2nd:
Andrew W.
For more information please see section 2 of the 1st and 3.2.3 of the 2nd:
Andrew W.
Simple probability estimator that places a single Poisson distribution
over the observed values.
The polynomial kernel : K(x, y) = <x, y>^p or K(x, y) = (<x, y>+1)^p
The PostscriptGraphics class extends the Graphics2D class to
produce an encapsulated postscript file rather than on-screen display.
This class takes any Component and outputs it to a Postscript file.
This filter should be extended by other unsupervised attribute
filters to allow processing of the class attribute if that's
required.
This kernel is based on a static kernel matrix that is read from a file.
This class encapsulates a linear regression function.
Encapsulates a single evaluatable prediction: the predicted value plus the
actual class value.
Bean that can can accept batch or incremental classifier events
and produce dataset or instance events which contain instances with
predictions appended.
Bean info class for PredictionAppender.
GUI Customizer for the prediction appender bean
Class representing a prediction node in an alternating tree.
Class implementing the predictive apriori algorithm to mine association rules.
It searches with an increasing support threshold for the best 'n' rules concerning a support-based corrected confidence value.
For more information see:
Tobias Scheffer: Finding Association Rules That Trade Support Optimally against Confidence.
It searches with an increasing support threshold for the best 'n' rules concerning a support-based corrected confidence value.
For more information see:
Tobias Scheffer: Finding Association Rules That Trade Support Optimally against Confidence.
This panel controls simple preprocessing of instances.
Performs a principal components analysis and transformation of the data.
Performs a principal components analysis and transformation of the data.
Dimensionality reduction is accomplished by choosing enough eigenvectors to account for some percentage of the variance in the original data -- default 0.95 (95%).
Based on code of the attribute selection scheme 'PrincipalComponents' by Mark Hall and Gabi Schmidberger.
Dimensionality reduction is accomplished by choosing enough eigenvectors to account for some percentage of the variance in the original data -- default 0.95 (95%).
Based on code of the attribute selection scheme 'PrincipalComponents' by Mark Hall and Gabi Schmidberger.
This class extends the component which is handed over in the constructor
by a print dialog.
This interface is for all JComponent classes that provide the ability to
print itself to a file.
This Panel enables the user to print the panel to various file formats.
This is an interface to plug various priors into
the Bayesian Logistic Regression Model.
Class implementing the prior estimattion of the predictive apriori algorithm
for mining association rules.
PriorityQueue.java
Authors: Rainer Holzmann, Zhanna Melnikova-Albrecht, Matthias Schubert
Date: Aug 27, 2004
Time: 5:36:35 PM
$ Revision 1.4 $
Authors: Rainer Holzmann, Zhanna Melnikova-Albrecht, Matthias Schubert
Date: Aug 27, 2004
Time: 5:36:35 PM
$ Revision 1.4 $
PriorityQueueElement.java
Authors: Rainer Holzmann, Zhanna Melnikova-Albrecht, Matthias Schubert
Date: Aug 31, 2004
Time: 6:43:18 PM
$ Revision 1.4 $
Authors: Rainer Holzmann, Zhanna Melnikova-Albrecht, Matthias Schubert
Date: Aug 31, 2004
Time: 6:43:18 PM
$ Revision 1.4 $
Class for building and using a PRISM rule set for classification.
Support for PropertyEditors with custom editors: puts the editor into
a separate frame.
This class stores information about properties to ignore or properties
that are allowed for a certain class.
Stores information on a property of an object: the class of the
object with the property; the property descriptor, and the current
value.
Support for drawing a property value in a component.
A helper class for accessing properties in nested objects, e.g., accessing
the "getRidge" method of a LinearRegression classifier part of
MultipleClassifierCombiner, e.g., Vote.
Contains a (property) path structure
Represents a single element of a property path
Allows the user to select any (supported) property of an object, including
properties that any of it's property values may have.
Displays a property sheet where (supported) properties of the target object
may be edited.
Converts a propositional dataset into a multi-instance dataset (with relational attribute).
Simple class that extends the Properties class so that the properties are
unable to be modified.
Class for handling a tree structure that can
be pruned using a pruning set.
Class for handling a partial tree structure that
can be pruned using a pruning set.
The Pearson VII function-based universal kernel.
For more information see:
B.
For more information see:
B.
QR Decomposition.
An event that is generated when a query is executed.
A listener for executing queries.
Represents a panel for entering an SQL query.
Class representing a FIFO queue.
Classifier for incremental learning of large datasets by way of racing logit-boosted committees.
For more information see:
Eibe Frank, Geoffrey Holmes, Richard Kirkby, Mark Hall: Racing committees for large datasets.
For more information see:
Eibe Frank, Geoffrey Holmes, Richard Kirkby, Mark Hall: Racing committees for large datasets.
Races the cross validation error of competing attribute subsets.
Class for building an ensemble of randomizable base classifiers.
Class for constructing a forest of random trees.
For more information see:
Leo Breiman (2001).
For more information see:
Leo Breiman (2001).
Interface to something that has random behaviour that is able to be
seeded with an integer.
Abstract utility class for handling settings common to randomizable
classifiers.
Abstract utility class for handling settings common to randomizable
clusterers.
Abstract utility class for handling settings common to randomizable
clusterers.
Abstract utility class for handling settings common to randomizable
meta classifiers that build an ensemble from a single base learner.
Abstract utility class for handling settings common to randomizable
meta classifiers that build an ensemble from multiple classifiers based
on a given random number seed.
Abstract utility class for handling settings common to randomizable
meta classifiers that build an ensemble from a single base learner.
Abstract utility class for handling settings common to randomizable
clusterers.
Randomly shuffles the order of instances passed through it.
Reduces the dimensionality of the data by
projecting it onto a lower dimensional subspace using a random matrix with
columns of unit length (i.e.
RandomRBF data is generated by first creating a random set of centers for each class.
RandomSearch :
Performs a Random search in the space of attribute subsets.
Performs a Random search in the space of attribute subsets.
Generates a single train/test split and calls the
appropriate SplitEvaluator to generate some results.
Chooses a random subset of attributes, either an absolute number or a percentage.
This method constructs a decision tree based classifier that maintains highest accuracy on training data and improves on generalization accuracy as it grows in complexity.
Class for constructing a tree that considers K
randomly chosen attributes at each node.
Class implementing some simple random variates generator.
Class representing a range of cardinal numbers.
Interface for search methods capable of producing a
ranked list of attributes.
Ranker :
Ranks attributes by their individual evaluations.
Ranks attributes by their individual evaluations.
RankSearch :
Uses an attribute/subset evaluator to rank all attributes.
Uses an attribute/subset evaluator to rank all attributes.
The RBF kernel.
Class that implements a normalized Gaussian radial basisbasis function network.
It uses the k-means clustering algorithm to provide the basis functions and learns either a logistic regression (discrete class problems) or linear regression (numeric class problems) on top of that.
It uses the k-means clustering algorithm to provide the basis functions and learns either a logistic regression (discrete class problems) or linear regression (numeric class problems) on top of that.
A data generator that produces data randomly by producing a decision list.
The decision list consists of rules.
Instances are generated randomly one by one.
The decision list consists of rules.
Instances are generated randomly one by one.
Simple class that extends the Instances class making it possible to create
subsets of instances that reference their source set.
Base class implementation for learning algorithm of SMOreg
Valid options are:
Class implementing import of PMML Regression model.
A regression scheme that employs any classifier on a copy of the data that has the class attribute (equal-width) discretized.
Abstract class for data generators for regression classifiers.
A SplitEvaluator that produces results for a
classification scheme on a numeric class attribute.
Implementation of SMO for support vector regression as described in :
A.J.
A.J.
Learn SVM for regression using SMO with Shevade, Keerthi, et al.
A propositionalization filter inspired by the RELAGGS algorithm.
It processes all relational attributes that fall into the user defined range (all others are skipped, i.e., not added to the output).
It processes all relational attributes that fall into the user defined range (all others are skipped, i.e., not added to the output).
This class locates and records the indices of relational attributes,
ReliefFAttributeEval :
Evaluates the worth of an attribute by repeatedly sampling an instance and considering the value of the given attribute for the nearest instance of the same and different class.
Evaluates the worth of an attribute by repeatedly sampling an instance and considering the value of the given attribute for the nearest instance of the same and different class.
Class that encapsulates a sub task for distributed boundary
visualization.
A general purpose server for executing Task objects sent via RMI.
Holds all the necessary configuration information for a distributed
experiment.
Class encapsulating information on progress of a remote experiment
Interface for classes that want to listen for updates on RemoteExperiment
progress
Class to encapsulate an experiment as a task that can be executed on
a remote host.
Class that encapsulates a result (and progress info) for part
of a distributed boundary visualization.
A filter that removes a range of attributes from the dataset.
This filter takes a dataset and outputs a specified fold for cross validation.
Determines which values (frequent or infrequent ones) of an (nominal) attribute are retained and filters the instances accordingly.
A filter that removes instances which are incorrectly classified.
A filter that removes a given percentage of a dataset.
A filter that removes a given range of instances of a dataset.
Removes attributes of a given type.
This filter removes attributes that do not vary at all or that vary too much.
Filters instances according to the value of an attribute.
A filter that generates output with a new order of the attributes.
This Bayes Network learning algorithm repeatedly uses hill climbing starting with a randomly generated network structure and return the best structure of the various runs.
This Bayes Network learning algorithm repeatedly uses hill climbing starting with a randomly generated network structure and return the best structure of the various runs.
Replaces all missing values for nominal and numeric attributes in a dataset with the modes and means from the training data.
Fast decision tree learner.
Produces a random subsample of a dataset using either sampling with replacement or without replacement.
The original dataset must fit entirely in memory.
The original dataset must fit entirely in memory.
Produces a random subsample of a dataset using either sampling with replacement or without replacement.
Produces a random subsample of a dataset using the reservoir sampling Algorithm "R" by Vitter.
Helper class for logistic model trees (weka.classifiers.trees.lmt.LMT) to implement the
splitting criterion based on residuals.
Helper class for logistic model trees (weka.classifiers.trees.lmt.LMT) to implement the
splitting criterion based on residuals of the LogitBoost algorithm.
An event that is generated when a different Result is activated in the
ResultPanel.
A listener that is notified if another Result is activated in the
ResultPanel.
A component that accepts named stringbuffers and displays the name in a list
box.
Extension of KeyAdapter that implements Serializable.
Extension of MouseAdapter that implements Serializable.
Interface for objects able to listen for results obtained
by a ResultProducer
This matrix is a container for the datasets and classifier setups and
their statistics.
This matrix is a container for the datasets and classifier setups and
their statistics.
This matrix is a container for the datasets and classifier setups and
their statistics.
This matrix is a container for the datasets and classifier setups and
their statistics.
This matrix is a container for the datasets and classifier setups and
their statistics.
This matrix is a container for the datasets and classifier setups and
their statistics.
This matrix is a container for the datasets and classifier setups and
their statistics.
Represents a panel for displaying the results of a query in table format.
This interface defines the methods required for an object
that produces results for different randomizations of a dataset.
Represents an extended JTable, containing a table model based on a ResultSet
and the corresponding query.
Represents an extended JTable, containing a table model based on a ResultSet
and the corresponding query.
Handles the background colors for missing values differently than the
DefaultTableCellRenderer.
The model for an SQL ResultSet.
This panel controls simple analysis of experimental results.
ResultVectorTableModel.java
Authors: Rainer Holzmann, Zhanna Melnikova-Albrecht
Date: Sep 12, 2004
Time: 9:23:31 PM
$ Revision 1.4 $
Authors: Rainer Holzmann, Zhanna Melnikova-Albrecht
Date: Sep 12, 2004
Time: 9:23:31 PM
$ Revision 1.4 $
For classes that should return their source control revision.
Contains utility functions for handling revisions.
Enumeration of source control types.
An implementation of a RIpple-DOwn Rule learner.
It generates a default rule first and then the exceptions for the default rule with the least (weighted) error rate.
It generates a default rule first and then the exceptions for the default rule with the least (weighted) error rate.
Class for construction a Rotation Forest.
Class representing a rule with a body and a head.
Abstract class of generic rule
Generates a single m5 tree or rule
Class implementing the rule generation procedure of the predictive apriori algorithm.
Class for storing an (class) association rule.
Constructs a node for use in an m5 tree or rule
This class implements the statistics functions used in the
propositional rule learner, from the simpler ones like count of
true/false positive/negatives, filter data based on the ruleset, etc.
This panel controls configuration of lower and upper run numbers
in an experiment.
This panel controls the running of an experiment.
This class handles the saving of StringBuffers to files.
Interface to something that can save Instances to an output destination in some
format.
Saves data sets using weka.core.converter classes
Bean info class for the saver bean
GUI Customizer for the saver bean
A scanner for mathematical expressions.
A scanner for evaluating whether an Instance is to be included in a subset
or not.
Bean that encapsulates weka.gui.visualize.MatrixPanel for displaying a
scatter plot matrix.
Bean info class for the scatter plot matrix bean
Class for performing the Sequential Scatter Search.
Interface for allowing to score a classifier
This is the base class for all search algorithms for learning Bayes networks.
Represents a selected value from a finite set of values, where each
value is a Tag (i.e.
A PropertyEditor that uses tags, where the tags are obtained from a
weka.core.SelectedTag object.
Class representing a sequence of elements/itemsets.
SequentialDatabase.java
Authors: Rainer Holzmann, Zhanna Melnikova-Albrecht, Matthias Schubert
Date: Aug 20, 2004
Time: 1:23:38 PM
$ Revision 1.4 $
Authors: Rainer Holzmann, Zhanna Melnikova-Albrecht, Matthias Schubert
Date: Aug 20, 2004
Time: 1:23:38 PM
$ Revision 1.4 $
SERFileFilter.java
Authors: Rainer Holzmann, Zhanna Melnikova-Albrecht
Date: Sep 15, 2004
Time: 6:54:56 PM
$ Revision 1.4 $
Authors: Rainer Holzmann, Zhanna Melnikova-Albrecht
Date: Sep 15, 2004
Time: 6:54:56 PM
$ Revision 1.4 $
Defines an interface for objects able to produce two output streams of
instances.
A helper class for determining serialVersionUIDs and checking whether
classes contain one and/or need one.
A wrapper around a serialized classifier model.
Reads a source that contains serialized Instances.
Serializes the instances to a file with extension bsi.
A bean that saves serialized models
Bean info class for the serialized model saver bean
GUI Customizer for the SerializedModelSaver bean
Class for storing an object in serialized form in memory.
This class enables one to change the UID of a serialized object and therefore
not losing the data stored in the binary format.
SERObject.java
Authors: Rainer Holzmann, Zhanna Melnikova-Albrecht
Date: Sep 15, 2004
Time: 9:43:00 PM
$ Revision 1.4 $
Authors: Rainer Holzmann, Zhanna Melnikova-Albrecht
Date: Sep 15, 2004
Time: 9:43:00 PM
$ Revision 1.4 $
A panel that displays an instance summary for a set of instances and lets the
user open a set of instances from either a file or URL.
This panel switches between simple and advanced experiment setup panels.
This panel controls the configuration of an experiment.
Cluster data using the sequential information bottleneck algorithm.
Note: only hard clustering scheme is supported.
Note: only hard clustering scheme is supported.
This can be used by the
neuralnode to perform all it's computations (as a sigmoid unit).
This filter is a superclass for simple batch filters.
Class implementing minimal cost-complexity pruning.
Note when dealing with missing values, use "fractional instances" method instead of surrogate split method.
For more information, see:
Leo Breiman, Jerome H.
Note when dealing with missing values, use "fractional instances" method instead of surrogate split method.
For more information, see:
Leo Breiman, Jerome H.
Creates a very simple command line for invoking the main method of
classes.
Creates a very simple command line for invoking the main method of
classes.
A class for commandline completion of classnames.
Class for editing SimpleDateFormat strings.
SimpleEstimator is used for estimating the conditional probability tables of a Bayes network once the structure has been learned.
This filter contains common behavior of the SimpleBatchFilter and the
SimpleStreamFilter.
Cluster data using the k means algorithm
Learns a simple linear regression model.
Classifier for building linear logistic regression models.
Reduces MI data into mono-instance data.
This panel controls the configuration of an experiment.
This filter is a superclass for simple stream filters.
This Bayes Network learning algorithm uses the general purpose search method of simulated annealing to find a well scoring network structure.
For more information see:
R.R.
For more information see:
R.R.
This Bayes Network learning algorithm uses the general purpose search method of simulated annealing to find a well scoring network structure.
For more information see:
R.R.
For more information see:
R.R.
Abstract utility class for handling settings common to meta
associators that use a single base associator.
Abstract utility class for handling settings common to meta
classifiers that use a single base learner.
Meta-clusterer for enhancing a base clusterer.
Class representing a single cardinal number.
Singular Value Decomposition.
The class that splits a node into two based on the midpoint value of the dimension in which the node's rectangle is widest.
Implements John Platt's sequential minimal optimization algorithm for training a support vector classifier.
This implementation globally replaces all missing values and transforms nominal attributes into binary ones.
This implementation globally replaces all missing values and transforms nominal attributes into binary ones.
SMOreg implements the support vector machine for regression.
Stores a set of integer of a given size.
Resamples a dataset by applying the Synthetic
Minority Oversampling TEchnique (SMOTE).
A wrapper class for the Snowball stemmers.
Represents a TableModel with sorting functionality.
Helper class for sorting the columns.
Interface for classifiers that can be converted to Java source.
Interface for filters that can be converted to Java source.
Class for storing an instance as a sparse vector.
An instance filter that converts all incoming sparse instances into non-sparse format.
Class implementing some mathematical functions.
Implements the stochastic variant of the Pegasos (Primal Estimated sub-GrAdient SOlver for SVM) method of Shalev-Shwartz et al.
A Splash window.
Abstract class for computing splitting criteria
with respect to distributions of class values.
Interface for objects that determine a split point on an attribute
Interface to objects able to generate a fixed set of results for
a particular split of a dataset.
Abstract class representing a splitter node in an alternating tree.
Produces a random subsample of a dataset.
Represents a little tool for querying SQL databases.
A little dialog containing the SqlViewer.
Class implementing a stack.
Combines several classifiers using the stacking method.
Implements StackingC (more efficient version of stacking).
For more information, see
A.K.
For more information, see
A.K.
Standardizes all numeric attributes in the given dataset to have zero mean and unit variance (apart from the class attribute, if set).
Interface to something that is a start point for a flow and
can be launched programatically.
Interface for search methods capable of doing something sensible
given a starting set of attributes.
Interface to something that can be notified of a successful startup
Class implementing some distributions, tests, etc.
Class implementing a statistical routine needed by J48 to
compute its error estimate.
A class to store simple statistics
Interface for all stemming algorithms.
A helper class for using the stemmers.
Class that can test whether a given string is a stop word.
This filter takes a dataset and outputs a specified fold for cross validation.
Interface for filters can work with a stream of instances.
Implementation of the subsequence kernel (SSK) as described in [1] and of the subsequence kernel with lambda pruning (SSK-LP) as described in [2].
For more information, see
Huma Lodhi, Craig Saunders, John Shawe-Taylor, Nello Cristianini, Christopher J.
For more information, see
Huma Lodhi, Craig Saunders, John Shawe-Taylor, Nello Cristianini, Christopher J.
This class locates and records the indices of String attributes,
recursively in case of Relational attributes.
Converts a string attribute (i.e.
Converts String attributes into a set of attributes representing word occurrence (depending on the tokenizer) information from the text contained in the strings.
Bean that can display a horizontally scrolling strip chart.
Bean info class for the strip chart bean
GUI Customizer for the strip chart bean
Interface for something that can describe the structure of what
is encapsulated in a named event type as an empty set of
Instances (i.e.
Filters instances according to a user-specified expression.
Grammar:
boolexpr_list ::= boolexpr_list boolexpr_part | boolexpr_part;
boolexpr_part ::= boolexpr:e {: parser.setResult(e); :} ;
boolexpr ::= BOOLEAN
| true
| false
| expr < expr
| expr <= expr
| expr > expr
| expr >= expr
| expr = expr
| ( boolexpr )
| not boolexpr
| boolexpr and boolexpr
| boolexpr or boolexpr
| ATTRIBUTE is STRING
;
expr ::= NUMBER
| ATTRIBUTE
| ( expr )
| opexpr
| funcexpr
;
opexpr ::= expr + expr
| expr - expr
| expr * expr
| expr / expr
;
funcexpr ::= abs ( expr )
| sqrt ( expr )
| log ( expr )
| exp ( expr )
| sin ( expr )
| cos ( expr )
| tan ( expr )
| rint ( expr )
| floor ( expr )
| pow ( expr for base , expr for exponent )
| ceil ( expr )
;
Notes:
- NUMBER
any integer or floating point number
(but not in scientific notation!)
- STRING
any string surrounded by single quotes;
the string may not contain a single quote though.
- ATTRIBUTE
the following placeholders are recognized for
attribute values:
- CLASS for the class value in case a class attribute is set.
- ATTxyz with xyz a number from 1 to # of attributes in the
dataset, representing the value of indexed attribute.
Examples:
- extracting only mammals and birds from the 'zoo' UCI dataset:
(CLASS is 'mammal') or (CLASS is 'bird')
- extracting only animals with at least 2 legs from the 'zoo' UCI dataset:
(ATT14 >= 2)
- extracting only instances with non-missing 'wage-increase-second-year'
from the 'labor' UCI dataset:
not ismissing(ATT3)
Grammar:
boolexpr_list ::= boolexpr_list boolexpr_part | boolexpr_part;
boolexpr_part ::= boolexpr:e {: parser.setResult(e); :} ;
boolexpr ::= BOOLEAN
| true
| false
| expr < expr
| expr <= expr
| expr > expr
| expr >= expr
| expr = expr
| ( boolexpr )
| not boolexpr
| boolexpr and boolexpr
| boolexpr or boolexpr
| ATTRIBUTE is STRING
;
expr ::= NUMBER
| ATTRIBUTE
| ( expr )
| opexpr
| funcexpr
;
opexpr ::= expr + expr
| expr - expr
| expr * expr
| expr / expr
;
funcexpr ::= abs ( expr )
| sqrt ( expr )
| log ( expr )
| exp ( expr )
| sin ( expr )
| cos ( expr )
| tan ( expr )
| rint ( expr )
| floor ( expr )
| pow ( expr for base , expr for exponent )
| ceil ( expr )
;
Notes:
- NUMBER
any integer or floating point number
(but not in scientific notation!)
- STRING
any string surrounded by single quotes;
the string may not contain a single quote though.
- ATTRIBUTE
the following placeholders are recognized for
attribute values:
- CLASS for the class value in case a class attribute is set.
- ATTxyz with xyz a number from 1 to # of attributes in the
dataset, representing the value of indexed attribute.
Examples:
- extracting only mammals and birds from the 'zoo' UCI dataset:
(CLASS is 'mammal') or (CLASS is 'bird')
- extracting only animals with at least 2 legs from the 'zoo' UCI dataset:
(ATT14 >= 2)
- extracting only instances with non-missing 'wage-increase-second-year'
from the 'labor' UCI dataset:
not ismissing(ATT3)
Interface for attribute subset evaluators.
SubsetSizeForwardSelection:
Extension of LinearForwardSelection.
Extension of LinearForwardSelection.
A data generator that produces data points in hyperrectangular subspace clusters.
A single cluster for the SubspaceCluster
datagenerator
Interface to something that provides a short textual summary (as opposed
to toString() which is usually a fairly complete description) of itself.
Interface for filters that make use of a class attribute.
SVMAttributeEval :
Evaluates the worth of an attribute by using an SVM classifier.
Evaluates the worth of an attribute by using an SVM classifier.
Reads a source that is in svm light format.
For more information about svm light see:
http://svmlight.joachims.org/
For more information about svm light see:
http://svmlight.joachims.org/
Writes to a destination that is in svm light format.
For more information about svm light see:
http://svmlight.joachims.org/
For more information about svm light see:
http://svmlight.joachims.org/
Swaps two values of a nominal attribute.
CUP generated interface containing symbol constants.
CUP generated interface containing symbol constants.
SymmetricalUncertAttributeEval :
Evaluates the worth of an attribute by measuring the symmetrical uncertainty with respect to the class.
Evaluates the worth of an attribute by measuring the symmetrical uncertainty with respect to the class.
This Logger just sends messages to System.err.
This class prints some information about the system setup, like Java
version, JVM settings etc.
This Bayes Network learning algorithm uses tabu search for finding a well scoring Bayes network structure.
This Bayes Network learning algorithm uses tabu search for finding a well scoring Bayes network structure.
A
Tag
simply associates a numeric ID with a String description.This Bayes Network learning algorithm determines the maximum weight spanning tree and returns a Naive Bayes network augmented with a tree.
For more information see:
N.
For more information see:
N.
This Bayes Network learning algorithm determines the maximum weight spanning tree and returns a Naive Bayes network augmented with a tree.
For more information see:
N.
For more information see:
N.
Class to encapsulate information about a Target.
Interface to something that can be remotely executed as a task.
Interface for objects that display log and display information on
running tasks.
A class holding information for tasks being executed
on RemoteEngines.
Used for paper references in the Javadoc and for BibTex generation.
the possible fields
the different types of information
For classes that are based on some kind of publications.
Generates Javadoc comments from the TechnicalInformationHandler's data.
This class pipelines print/println's to several PrintStreams.
Finds rules according to confirmation measure (Tertius-type algorithm).
For more information see:
P.
For more information see:
P.
Class to represent a test.
Interface for different kinds of Testers in the Experimenter.
Generates artificial datasets for testing.
Event encapsulating a test set
Interface to something that can accpet test set events
Bean that accepts data sets and produces test sets
Bean info class for the test set maker bean.
Interface to something that can produce test sets
Loads all text files in a directory and uses the subdirectory names as class labels.
Event that encapsulates some textual information
Interface to something that can process a TextEvent
Bean that collects and displays pieces of text
Bean info class for the text viewer
Generates points illustrating prediction tradeoffs that can be obtained
by varying the threshold value between classes.
Event encapsulating classifier performance data based on
varying a threshold over the classifier's predicted probabilities
Interface to something that can accept ThresholdDataEvents
A metaclassifier that selecting a mid-point threshold on the probability output by a Classifier.
This panel is a VisualizePanel, with the added ablility to display the
area under the ROC curve if an ROC curve is chosen.
An instance filter that assumes instances form time-series data and replaces attribute values in the current instance with the difference between the current value and the equivalent attribute attribute value of some previous (or future) instance.
An instance filter that assumes instances form time-series data and replaces attribute values in the current instance with the equivalent attribute values of some previous (or future) instance.
A superclass for all tokenizer algorithms.
The class implementing the TopDown construction method of ball trees.
Event encapsulating a training set
Interface to something that can accept and process training set events
Bean that accepts a data sets and produces a training set
Bean info class for the training set maker bean
Interface to something that can produce a training set
Bean that accepts data sets, training sets, test sets and produces
both a training and test set by randomly spliting the data
Bean info class for the train test split maker bean
GUI customizer for the train test split maker bean
This class will parse a dotty file and construct a tree structure from it
with Edge's and Node's
An event containing the user selection from the tree display
Interface implemented by classes that wish to recieve user selection events
from a tree displayer.
The class that measures the performance of a tree based
nearest neighbour search algorithm.
Interface implemented by classes loaded dynamically to
visualize classifier results in the explorer.
Class for displaying a Node structure in Swing.
A class representing a Trie data structure for strings.
Represents an iterator over a trie
Represents a node in the trie.
Encapsulates performance functions for two-class problems.
Class representing a two-way split on a nominal attribute, of the form:
either 'is some_value' or 'is not some_value'.
Class representing a two-way split on a numeric attribute, of the form:
either 'is invalid input: '<' some_value' or 'is >= some_value'.
Exception that is raised when trying to use some data that has no
class assigned to it, but a class is needed to perform the operation.
Exception that is raised when trying to use something that has no
reference to a dataset, when one is required.
Interface implemented by classes that support undo.
Abstract unsupervised attribute evaluator.
Interface for filters that do not need a class attribute.
Abstract unsupervised attribute subset evaluator.
Exception that is raised by an object that is unable to process some of the
attribute types it has been passed.
Exception that is raised by an object that is unable to process the
class type of the data it has been passed.
Interface to incremental classification models that can learn using
one instance at a time.
Interface to incremental cluster models that can learn using one instance at
a time.
UpdateQueue.java
Authors: Rainer Holzmann, Zhanna Melnikova-Albrecht, Matthias Schubert
Date: Aug 27, 2004
Time: 5:36:35 PM
$ Revision 1.4 $
Authors: Rainer Holzmann, Zhanna Melnikova-Albrecht, Matthias Schubert
Date: Aug 27, 2004
Time: 5:36:35 PM
$ Revision 1.4 $
UpdateQueueElement.java
Authors: Rainer Holzmann, Zhanna Melnikova-Albrecht, Matthias Schubert
Date: Aug 31, 2004
Time: 6:43:18 PM
$ Revision 1.4 $
Authors: Rainer Holzmann, Zhanna Melnikova-Albrecht, Matthias Schubert
Date: Aug 31, 2004
Time: 6:43:18 PM
$ Revision 1.4 $
Interface to a loader that can load from a http url
Interactively classify through visual means.
Interface to something that can accept requests from a user to perform
some action
Class implementing some simple utility methods.
Stores some statistics.
Part of ADTree implementation.
This class contains the version number of the current WEKA release and some
methods for comparing another version string.
Classification by voting feature intervals.
A downsized version of the ArffViewer, displaying only one Instances-Object.
Interface to something that has a visible (via BeanVisual) reprentation
Event encapsulating error information for a learning scheme
that can be visualized in the DataVisualizer
Interface to something that can accept VisualizableErrorEvents
A slightly extended MatrixPanel for better support in the Explorer.
This panel allows the user to visualize a dataset (and if provided) a
classifier's/clusterer's predictions in two dimensions.
This event Is fired to a listeners 'userDataEvent' function when
The user on the VisualizePanel clicks submit.
Interface implemented by a class that is interested in receiving
submited shapes from a visualize panel.
Interface implemented by classes loaded dynamically to
visualize classifier results in the explorer.
This class contains utility routines for visualization
Class for combining classifiers.
Implementation of the voted perceptron algorithm by Freund and Schapire.
WAODE contructs the model called Weightily Averaged One-Dependence Estimators.
For more information, see
L.
For more information, see
L.
A filter for wavelet transformation.
For more information see:
Wikipedia (2004).
For more information see:
Wikipedia (2004).
Interface to something that makes use of the information provided
by instance weights.
Class for Weka-specific exceptions.
This panel records the number of weka tasks running and displays a
simple bird animation while their are active tasks
Interface to something that can wrap around a class of Weka
algorithms (classifiers, filters etc).
Implements Winnow and Balanced Winnow algorithms by Littlestone.
For more information, see
N.
For more information, see
N.
A simple tokenizer that is using the java.util.StringTokenizer class to tokenize the strings.
WrapperSubsetEval:
Evaluates attribute sets by using a learning scheme.
Evaluates attribute sets by using a learning scheme.
Cluster data using the X-means algorithm.
X-Means is K-Means extended by an Improve-Structure part In this part of the algorithm the centers are attempted to be split in its region.
X-Means is K-Means extended by an Improve-Structure part In this part of the algorithm the centers are attempted to be split in its region.
This serializer contains some read/write methods for common classes that
are not beans-conform.
This class serializes and deserializes a KnowledgeFlow setup to and fro XML.
This class serializes and deserializes a Classifier instance to and
fro XML.
This class offers some methods for generating, reading and writing
XML documents.
It can only handle UTF-8.
It can only handle UTF-8.
This class serializes and deserializes an Experiment instance to and
fro XML.
It omits the
It omits the
options
from the Experiment, since these are handled
by the get/set-methods.XML representation of the Instances class.
A class for transforming options listed in XML to a regular WEKA command
line string.
With this class objects can be serialized to XML instead into a binary
format.
This class handles relationships between display names of properties
(or classes) and Methods that are associated with them.
Reads a source that is in the XML version of the ARFF format.
Writes to a destination that is in the XML version of the ARFF format.
This class is a helper class for XML serialization using
XStream .
Stores split information.
Class for building and using a 0-R classifier.
weka.core.matrix.Matrix
instead - only for backwards compatibility.