Package com.aliasi.classify

Classes for classifying data and evaluation.


Interface Summary
BaseClassifier<E> The BaseClassifier interface specifies a single method for first-best classification.
Classifier<E,C extends Classification> Deprecated. Use BaseClassifier or one if its subinterfaces.
ConditionalClassifier<E> The ConditionalClassifier interface specifies a single method for n-best classification with conditional category probabilities.
JointClassifier<E> The JointClassifier interface specifies a single method for n-best classification with joint input and category probabilities.
RankedClassifier<E> The RankedClassifier interface specifies a single classification method that returns n-best classifications of inputs.
ScoredClassifier<E> The ScoredClassifier interface specifies a single method for n-best scored classification.

Class Summary
BaseClassifierEvaluator<E> A BaseClassifierEvaluator provides an evaluation harness for first-best classifiers.
BernoulliClassifier<E> A BernoulliClassifier provides a feature-based classifier where feature values are reduced to booleans based on a specified threshold.
BigVectorClassifier A BigVectorClassifier provides an efficient linear classifier implementation for large numbers of categories.
BinaryLMClassifier A BinaryLMClassifier is a boolean dynamic language model classifier for use when there are two categories, but training data is only available for one of the categories.
Classification A Classification provides a first-best category.
Classified<E> A Classified represents an object that has been classified with a first-best classification.
ClassifierEvaluator<E,C extends Classification> Deprecated. Use BaseClassifierEvaluator or one of its subclasses.
ConditionalClassification A ConditionalClassification is a scored classification which estimates conditional probabilities of categories given an input.
ConditionalClassifierEvaluator<E> A ConditionalClassifierEvaluator provides an evaluation harness for conditional probability-based n-best classifiers.
ConfusionMatrix An instance of ConfusionMatrix represents a quantitative comparison between two classifiers over a fixed set of categories on a number of test cases.
DynamicLMClassifier<L extends LanguageModel.Dynamic> A DynamicLMClassifier is a language model classifier that accepts training events of categorized character sequences.
JointClassification A JointClassification is a conditional classification derived from a joint probability assignment to each category and the object being classified.
JointClassifierEvaluator<E> A JointClassifierEvaluator provides an evaluation harness for joint probability-based n-best classifiers.
KnnClassifier<E> A KnnClassifier implements k-nearest-neighor classification based on feature extraction and a vector proximity or distance.
LMClassifier<L extends LanguageModel,M extends MultivariateDistribution> An LMClassifier performs joint probability-based classification of character sequences into non-overlapping categories based on language models for each category and a multivariate distribution over categories.
LogisticRegressionClassifier<E> A LogisticRegressionClassifier provides conditional probability classifications of input objects using an underlying logistic regression model and feature extractor.
NaiveBayesClassifier A NaiveBayesClassifier provides a trainable naive Bayes text classifier, with tokens as features.
PerceptronClassifier<E> A PerceptronClassifier implements a binary classifier based on an averaged kernel-based perceptron.
PrecisionRecallEvaluation A PrecisionRecallEvaluation collects and reports a suite of descriptive statistics for binary classification tasks.
RankedClassification A RankedClassification provides a classification with an ordered n-best list of category results.
RankedClassified<E> A RankedClassified represents an object that has been classified with a ranked classification.
RankedClassifierEvaluator<E> A RankedClassifierEvaluator provides an evaluation harness for ranked classifiers.
ScoredClassification A ScoredClassification is a ranked classification where each category also has a score that determines the ranking.
ScoredClassifierEvaluator<E> A ScoredClassifierEvaluator provides an evaluation harness for score-based classifiers.
ScoredPrecisionRecallEvaluation A ScoredPrecisionRecallEvaluation provides an evaluation of possible precision-recall operating points and other summary statistics The single method ScoredPrecisionRecallEvaluation.addCase(boolean,double) is used to populate the evaluation, with the first argument representing whether the response was correct and the second the score that was assigned.
TfIdfClassifierTrainer<E> A TfIdfClassifierTrainer provides a framework for training discriminative classifiers based on term-frequency (TF) and inverse document frequency (IDF) weighting of features.
TradNaiveBayesClassifier A TradNaiveBayesClassifier implements a traditional token-based approach to naive Bayes text classification.
XValidatingClassificationCorpus<E> Deprecated. Use XValidatingObjectCorpus with type com.aliasi.corpus.ObjectHandler<Classified<E>> instead.

Package com.aliasi.classify Description

Classes for classifying data and evaluation. Throughout, we use the term "category" rather than "class" or "type", to avoid confusion with the object-oriented notion of class in Java.