Cookbook - Revision history

Grau at 14:47, 31 May 2013

2013-05-31T14:47:09Z

← Older revision		Revision as of 14:47, 31 May 2013
Line 7:		Line 7:
	Jstacs is listed in the [http://mloss.org/software/ machine learning open-source software (mloss)] repository.		Jstacs is listed in the [http://mloss.org/software/ machine learning open-source software (mloss)] repository.

	The complete API documentation can be found at [http://www.jstacs.de/api-2.0/ http://www.jstacs.de/api-2.0/].		The complete API documentation can be found at [http://www.jstacs.de/api-2.1/ http://www.jstacs.de/api-2.1/].

	A reference card of Jstacs classes and methods can be found [http://www.jstacs.de/downloads/refcard.pdf as a separate download].		A reference card of Jstacs classes and methods can be found [http://www.jstacs.de/downloads/refcard.pdf as a separate download].
Line 14:		Line 14:

	A coarse view on the structure of Jstacs is presented in Figure below.		A coarse view on the structure of Jstacs is presented in Figure below.
	Being a library for statistical analysis and classification of sequence data, Jstacs is organized around the abstract class [http://www.jstacs.de/api-2.0//de/jstacs/classifiers/AbstractClassifier.html AbstractClassifier], the interface [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/StatisticalModel.html StatisticalModel] and its two sub-interfaces [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/trainable/TrainableStatisticalModel.html TrainableStatisticalModel], and [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel].		Being a library for statistical analysis and classification of sequence data, Jstacs is organized around the abstract class [http://www.jstacs.de/api-2.1//de/jstacs/classifiers/AbstractClassifier.html AbstractClassifier], the interface [http://www.jstacs.de/api-2.1//de/jstacs/sequenceScores/statisticalModels/StatisticalModel.html StatisticalModel] and its two sub-interfaces [http://www.jstacs.de/api-2.1//de/jstacs/sequenceScores/statisticalModels/trainable/TrainableStatisticalModel.html TrainableStatisticalModel], and [http://www.jstacs.de/api-2.1//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel].

	[[File:Classes.png\|frame\|center\|Part of the class structure of Jstacs. Interfaces are depicted in red, abstract classes in blue, concrete classes in green, and enums in orange. Continuous transitions represent inheritance, whereas arrows with diamond heads represent usage.]]		[[File:Classes.png\|frame\|center\|Part of the class structure of Jstacs. Interfaces are depicted in red, abstract classes in blue, concrete classes in green, and enums in orange. Continuous transitions represent inheritance, whereas arrows with diamond heads represent usage.]]

	[http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/StatisticalModel.html StatisticalModel] s represent statistical models in general, which can compute the log-likelihood of a given input sequence and define prior densities on their parameters. The abstract implementation [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/trainable/AbstractTrainSM.html AbstractTrainSM] of [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/trainable/TrainableStatisticalModel.html TrainableStatisticalModel] is the base class of many generatively learned models such as Bayesian networks, hidden Markov models, or mixture models, and can be learned from a single input data set. In constrast, [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel] s provide all facilities for numerical optimization of parameters, which is especially necessary for discriminative parameter learning. The abstract base class of all [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel] implementations is [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/AbstractDifferentiableStatisticalModel.html AbstractDifferentiableStatisticalModel]. Currently, [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel] s include Bayesian networks, Markov models, a ZOOPS model, and mixture models.		[http://www.jstacs.de/api-2.1//de/jstacs/sequenceScores/statisticalModels/StatisticalModel.html StatisticalModel] s represent statistical models in general, which can compute the log-likelihood of a given input sequence and define prior densities on their parameters. The abstract implementation [http://www.jstacs.de/api-2.1//de/jstacs/sequenceScores/statisticalModels/trainable/AbstractTrainSM.html AbstractTrainSM] of [http://www.jstacs.de/api-2.1//de/jstacs/sequenceScores/statisticalModels/trainable/TrainableStatisticalModel.html TrainableStatisticalModel] is the base class of many generatively learned models such as Bayesian networks, hidden Markov models, or mixture models, and can be learned from a single input data set. In constrast, [http://www.jstacs.de/api-2.1//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel] s provide all facilities for numerical optimization of parameters, which is especially necessary for discriminative parameter learning. The abstract base class of all [http://www.jstacs.de/api-2.1//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel] implementations is [http://www.jstacs.de/api-2.1//de/jstacs/sequenceScores/statisticalModels/differentiable/AbstractDifferentiableStatisticalModel.html AbstractDifferentiableStatisticalModel]. Currently, [http://www.jstacs.de/api-2.1//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel] s include Bayesian networks, Markov models, a ZOOPS model, and mixture models.

	[http://www.jstacs.de/api-2.0//de/jstacs/classifiers/AbstractClassifier.html AbstractClassifier] defines the general properties of a classifier. Its sub-class [http://www.jstacs.de/api-2.0//de/jstacs/classifiers/AbstractScoreBasedClassifier.html AbstractScoreBasedClassifier] adds additional methods for the classification of sequences based on a sequence and class-specific score.		[http://www.jstacs.de/api-2.1//de/jstacs/classifiers/AbstractClassifier.html AbstractClassifier] defines the general properties of a classifier. Its sub-class [http://www.jstacs.de/api-2.1//de/jstacs/classifiers/AbstractScoreBasedClassifier.html AbstractScoreBasedClassifier] adds additional methods for the classification of sequences based on a sequence and class-specific score.
	Two concrete sub-classes of [http://www.jstacs.de/api-2.0//de/jstacs/classifiers/AbstractScoreBasedClassifier.html AbstractScoreBasedClassifier] are the [http://www.jstacs.de/api-2.0//de/jstacs/classifiers/trainSMBased/TrainSMBasedClassifier.html TrainSMBasedClassifier], which works on [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/trainable/TrainableStatisticalModel.html TrainableStatisticalModel] s, and the [http://www.jstacs.de/api-2.0//de/jstacs/classifiers/differentiableSequenceScoreBased/gendismix/GenDisMixClassifier.html GenDisMixClassifier], which works on [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel].		Two concrete sub-classes of [http://www.jstacs.de/api-2.1//de/jstacs/classifiers/AbstractScoreBasedClassifier.html AbstractScoreBasedClassifier] are the [http://www.jstacs.de/api-2.1//de/jstacs/classifiers/trainSMBased/TrainSMBasedClassifier.html TrainSMBasedClassifier], which works on [http://www.jstacs.de/api-2.1//de/jstacs/sequenceScores/statisticalModels/trainable/TrainableStatisticalModel.html TrainableStatisticalModel] s, and the [http://www.jstacs.de/api-2.1//de/jstacs/classifiers/differentiableSequenceScoreBased/gendismix/GenDisMixClassifier.html GenDisMixClassifier], which works on [http://www.jstacs.de/api-2.1//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel].

	[http://www.jstacs.de/api-2.0//de/jstacs/classifiers/AbstractClassifier.html AbstractClassifier] s can be assessed either on dedicated training and test data sets or in [http://www.jstacs.de/api-2.0//de/jstacs/classifiers/assessment/ClassifierAssessment.html ClassifierAssessment] s like [http://www.jstacs.de/api-2.0//de/jstacs/classifiers/assessment/KFoldCrossValidation.html KFoldCrossValidation] or [http://www.jstacs.de/api-2.0//de/jstacs/classifiers/assessment/RepeatedHoldOutExperiment.html RepeatedHoldOutExperiment]. The performance measures used in such an assessment are collected in [http://www.jstacs.de/api-2.0//de/jstacs/classifiers/performanceMeasures/PerformanceMeasureParameterSet.html PerformanceMeasureParameterSet] s containing sub-classes of the abstract class [http://www.jstacs.de/api-2.0//de/jstacs/classifiers/performanceMeasures/AbstractPerformanceMeasure.html AbstractPerformanceMeasure].		[http://www.jstacs.de/api-2.1//de/jstacs/classifiers/AbstractClassifier.html AbstractClassifier] s can be assessed either on dedicated training and test data sets or in [http://www.jstacs.de/api-2.1//de/jstacs/classifiers/assessment/ClassifierAssessment.html ClassifierAssessment] s like [http://www.jstacs.de/api-2.1//de/jstacs/classifiers/assessment/KFoldCrossValidation.html KFoldCrossValidation] or [http://www.jstacs.de/api-2.1//de/jstacs/classifiers/assessment/RepeatedHoldOutExperiment.html RepeatedHoldOutExperiment]. The performance measures used in such an assessment are collected in [http://www.jstacs.de/api-2.1//de/jstacs/classifiers/performanceMeasures/PerformanceMeasureParameterSet.html PerformanceMeasureParameterSet] s containing sub-classes of the abstract class [http://www.jstacs.de/api-2.1//de/jstacs/classifiers/performanceMeasures/AbstractPerformanceMeasure.html AbstractPerformanceMeasure].

	A more detailed view on all of these classes will be given in the remainder of this cookbook.		A more detailed view on all of these classes will be given in the remainder of this cookbook.

Grau at 13:14, 15 May 2012

2012-05-15T13:14:18Z

← Older revision		Revision as of 13:14, 15 May 2012
Line 8:		Line 8:

	The complete API documentation can be found at [http://www.jstacs.de/api-2.0/ http://www.jstacs.de/api-2.0/].		The complete API documentation can be found at [http://www.jstacs.de/api-2.0/ http://www.jstacs.de/api-2.0/].

			A reference card of Jstacs classes and methods can be found [http://www.jstacs.de/downloads/refcard.pdf as a separate download].

	== General structure of Jstacs ==		== General structure of Jstacs ==

Keilwagen at 06:32, 14 May 2012

2012-05-14T06:32:02Z

← Older revision		Revision as of 06:32, 14 May 2012
Line 1:		Line 1:
	''You can also download a [http://www.jstacs.de/downloads/Cookbook.pdf PDF version] of this cookbook.''		''You can also download a [http://www.jstacs.de/downloads/Cookbook.pdf PDF version] of this cookbook.''

	A coarse view on the structure of Jstacs is presented in ~~the~~ Figure below.		Sequence analysis is one of the major subjects of bioinformatics. Several existing libraries combine the representation of biological sequences with exact and approximate pattern matching as well as alignment algorithms. We present Jstacs, an open source Java library, which focuses on the statistical analysis of biological sequences instead. Jstacs comprises an efficient representation of sequence data and provides implementations of many statistical models with generative and discriminative approaches for parameter learning. Using Jstacs, classifiers can be assessed and compared on test datasets or by cross-validation experiments evaluating several performance measures. Due to its strictly object-oriented design Jstacs is easy to use and readily extensible.

			Jstacs is a joint project of the groups [http://www.informatik.uni-halle.de/arbeitsgruppen/bioinformatik/ Bioinformatics] and [http://www.informatik.uni-halle.de/arbeitsgruppen/mustererkennung/ Pattern Recognition and Bioinformatics] at the [http://www.informatik.uni-halle.de/ Institute of Computer Science] of [http://www.uni-halle.de/ Martin Luther University Halle-Wittenberg] and the [http://dig.ipk-gatersleben.de/ Research Group Data Inspection] at the [http://www.ipk-gatersleben.de/ Leibniz Institute of Plant Genetics and Crop Plant Research].

			Jstacs is listed in the [http://mloss.org/software/ machine learning open-source software (mloss)] repository.

			The complete API documentation can be found at [http://www.jstacs.de/api-2.0/ http://www.jstacs.de/api-2.0/].

			== General structure of Jstacs ==

			A coarse view on the structure of Jstacs is presented in Figure below.
	Being a library for statistical analysis and classification of sequence data, Jstacs is organized around the abstract class [http://www.jstacs.de/api-2.0//de/jstacs/classifiers/AbstractClassifier.html AbstractClassifier], the interface [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/StatisticalModel.html StatisticalModel] and its two sub-interfaces [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/trainable/TrainableStatisticalModel.html TrainableStatisticalModel], and [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel].		Being a library for statistical analysis and classification of sequence data, Jstacs is organized around the abstract class [http://www.jstacs.de/api-2.0//de/jstacs/classifiers/AbstractClassifier.html AbstractClassifier], the interface [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/StatisticalModel.html StatisticalModel] and its two sub-interfaces [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/trainable/TrainableStatisticalModel.html TrainableStatisticalModel], and [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel].

	[[File:Classes.png\|frame\|center\|Part of the class structure of Jstacs. Interfaces are depicted in red, abstract classes in blue, concrete classes in green, and enums in orange. Continuous transitions represent inheritance, whereas arrows represent usage.]]		[[File:Classes.png\|frame\|center\|Part of the class structure of Jstacs. Interfaces are depicted in red, abstract classes in blue, concrete classes in green, and enums in orange. Continuous transitions represent inheritance, whereas arrows with diamond heads represent usage.]]

	[http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/StatisticalModel.html StatisticalModel] s represent statistical models in general, which can compute the log-likelihood of a given input sequence and define prior densities on their parameters. The abstract implementation [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/trainable/AbstractTrainSM.html AbstractTrainSM] of [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/trainable/TrainableStatisticalModel.html TrainableStatisticalModel] is the base class of many generatively learned models such as Bayesian networks, hidden Markov models, or mixture models, and can be learned from a single input data set. In constrast, [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel] s provide all facilities for numerical optimization of parameters, which is especially necessary for discriminative parameter learning. The abstract base class of all [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel] implementations is [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/AbstractDifferentiableStatisticalModel.html AbstractDifferentiableStatisticalModel]. Currently, [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel] s include Bayesian networks, Markov models, a ZOOPS model, and mixture models.		[http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/StatisticalModel.html StatisticalModel] s represent statistical models in general, which can compute the log-likelihood of a given input sequence and define prior densities on their parameters. The abstract implementation [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/trainable/AbstractTrainSM.html AbstractTrainSM] of [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/trainable/TrainableStatisticalModel.html TrainableStatisticalModel] is the base class of many generatively learned models such as Bayesian networks, hidden Markov models, or mixture models, and can be learned from a single input data set. In constrast, [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel] s provide all facilities for numerical optimization of parameters, which is especially necessary for discriminative parameter learning. The abstract base class of all [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel] implementations is [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/AbstractDifferentiableStatisticalModel.html AbstractDifferentiableStatisticalModel]. Currently, [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel] s include Bayesian networks, Markov models, a ZOOPS model, and mixture models.
Line 23:		Line 33:
	We are aware that a library of this size seems daunting on first sight -- and on second sight as well. However, we hope that despite the inevitable complexity and size of such a library, this cookbook may help to get a picture of the structure, design principles, and capabilities of Jstacs.		We are aware that a library of this size seems daunting on first sight -- and on second sight as well. However, we hope that despite the inevitable complexity and size of such a library, this cookbook may help to get a picture of the structure, design principles, and capabilities of Jstacs.

	This cookbook is structured as follows: in the section [[Starter: Data handling]], we explain how data are represented in Jstacs, and how you can read data from files.		This cookbook is structured as follows: in the section [[Quick start: Jstacs in a nutshell]], we give a very brief introduction to Jstacs enabling to run first programs without reading the complete cookbook.

			In section [[Starter: Data handling]], we explain how data are represented in Jstacs, and how you can read data from files.

	In section [[Intermediate course: XMLParser, Parameters, and Results]], we present some facilities, an XML parser and the representation of parameters and results, that are used frequently within Jstacs and are necessary for the following parts.		In section [[Intermediate course: XMLParser, Parameters, and Results]], we present some facilities, an XML parser and the representation of parameters and results, that are used frequently within Jstacs and are necessary for the following parts.
Line 38:		Line 50:

	== Contents ==		== Contents ==
			* [[Quick start: Jstacs in a nutshell]]
	* [[Starter: Data handling]]		* [[Starter: Data handling]]
	* [[Intermediate course: XMLParser, Parameters, and Results]]		* [[Intermediate course: XMLParser, Parameters, and Results]]

Grau at 13:59, 2 February 2012

2012-02-02T13:59:13Z

← Older revision		Revision as of 13:59, 2 February 2012
Line 1:		Line 1:
			''You can also download a [http://www.jstacs.de/downloads/Cookbook.pdf PDF version] of this cookbook.''

	A coarse view on the structure of Jstacs is presented in the Figure below.		A coarse view on the structure of Jstacs is presented in the Figure below.
	Being a library for statistical analysis and classification of sequence data, Jstacs is organized around the abstract class [http://www.jstacs.de/api-2.0//de/jstacs/classifiers/AbstractClassifier.html AbstractClassifier], the interface [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/StatisticalModel.html StatisticalModel] and its two sub-interfaces [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/trainable/TrainableStatisticalModel.html TrainableStatisticalModel], and [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel].		Being a library for statistical analysis and classification of sequence data, Jstacs is organized around the abstract class [http://www.jstacs.de/api-2.0//de/jstacs/classifiers/AbstractClassifier.html AbstractClassifier], the interface [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/StatisticalModel.html StatisticalModel] and its two sub-interfaces [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/trainable/TrainableStatisticalModel.html TrainableStatisticalModel], and [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel].

Grau at 13:08, 2 February 2012

2012-02-02T13:08:32Z

Grau at 23:05, 1 February 2012

2012-02-01T23:05:55Z

← Older revision		Revision as of 23:05, 1 February 2012
Line 37:		Line 37:
	Finally, in the [[Recipes \| last section]], we give a number of executable code examples that may serve as a starting point of your own classes and applications.		Finally, in the [[Recipes \| last section]], we give a number of executable code examples that may serve as a starting point of your own classes and applications.

	* [[Starter:~~_Data_handling~~]]		* [[Starter: Data handling]]
	* [[~~Intermediate_course~~:~~_XMLParser~~,~~_Parameters~~,~~_and_Results~~]]		* [[Intermediate course: XMLParser, Parameters, and Results]]
	* [[~~First_main_course~~:~~_SequenceScores~~]]		* [[First main course: SequenceScores]]
	* [[~~Second_main_course~~:~~_Classifiers~~]]		* [[Second main course: Classifiers]]
	* [[~~Intermediate_course~~:~~_Optimization~~]]		* [[Intermediate course: Optimization]]
	* [[Dessert:~~_Alignments~~,~~_Utils~~,~~_and_goodies~~]]		* [[Dessert: Alignments, Utils, and goodies]]
	* [[Recipes]]		* [[Recipes]]

Grau at 23:04, 1 February 2012

2012-02-01T23:04:29Z

← Older revision		Revision as of 23:04, 1 February 2012
Line 36:		Line 36:

	Finally, in the [[Recipes \| last section]], we give a number of executable code examples that may serve as a starting point of your own classes and applications.		Finally, in the [[Recipes \| last section]], we give a number of executable code examples that may serve as a starting point of your own classes and applications.

			* [[Starter:_Data_handling]]
			* [[Intermediate_course:_XMLParser,_Parameters,_and_Results]]
			* [[First_main_course:_SequenceScores]]
			* [[Second_main_course:_Classifiers]]
			* [[Intermediate_course:_Optimization]]
			* [[Dessert:_Alignments,_Utils,_and_goodies]]
			* [[Recipes]]

Grau: /* About this cookbook */

2012-02-01T23:02:45Z

About this cookbook

← Older revision		Revision as of 23:02, 1 February 2012
Line 23:		Line 23:
	We are aware that a library of this size seems daunting on first sight -- and on second sight as well. However, we hope that despite the inevitable complexity and size of such a library, this cookbook may help to get a picture of the structure, design principles, and capabilities of Jstacs.		We are aware that a library of this size seems daunting on first sight -- and on second sight as well. However, we hope that despite the inevitable complexity and size of such a library, this cookbook may help to get a picture of the structure, design principles, and capabilities of Jstacs.

	This cookbook is structured as follows: in the first section, we explain how data are represented in Jstacs, and how you can read data from files.		This cookbook is structured as follows: in the [[Starter:_Data_handling \| first section]], we explain how data are represented in Jstacs, and how you can read data from files.

	In the ~~second~~ section, we present some facilities, an XML parser and the representation of parameters and results, that are used frequently within Jstacs and are necessary for the following parts.		In the [[Intermediate_course:_XMLParser,_Parameters,_and_Results \| second section]], we present some facilities, an XML parser and the representation of parameters and results, that are used frequently within Jstacs and are necessary for the following parts.

	In the third section, we present sequence scores, statistical models, and their sub-interfaces and sub-classes. We explain the methods defined in these interfaces and classes, and we show how you can create and use their existing implementations.		In the [[First_main_course:_SequenceScores \| third section]], we present sequence scores, statistical models, and their sub-interfaces and sub-classes. We explain the methods defined in these interfaces and classes, and we show how you can create and use their existing implementations.

	In the ~~fourth~~ section, we explain classifiers and assessment of classifiers using different performance measures.		In the [[Second_main_course:_Classifiers \| fourth section]], we explain classifiers and assessment of classifiers using different performance measures.

	In the ~~fifth~~ section, we present the facilities for numerical optimization.		In the [[Intermediate_course:_Optimization \| fifth section]], we present the facilities for numerical optimization.

	In the ~~sixth~~ section, we list utility classes and methods, that we think might be of help for your own implementations.		In the [[Dessert:_Alignments,_Utils,_and_goodies \| sixth section]], we list utility classes and methods, that we think might be of help for your own implementations.

	Finally, in the last section, we give a number of executable code examples that may serve as a starting point of your own classes and applications.		Finally, in the [[Recipes \| last section]], we give a number of executable code examples that may serve as a starting point of your own classes and applications.

Grau: Created page with "== General structure of Jstacs == A coarse view on the structure of Jstacs is presented in Figure #fig:classes (link). Being a library for statistical analysis and classific..."

2012-02-01T22:46:48Z

Created page with "== General structure of Jstacs == A coarse view on the structure of Jstacs is presented in Figure #fig:classes (link). Being a library for statistical analysis and classific..."

New page

== General structure of Jstacs ==

A coarse view on the structure of Jstacs is presented in Figure [[#fig:classes (link)]].
Being a library for statistical analysis and classification of sequence data, Jstacs is organized around the abstract class [http://www.jstacs.de/api-2.0//de/jstacs/classifiers/AbstractClassifier.html AbstractClassifier], the interface [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/StatisticalModel.html StatisticalModel] and its two sub-interfaces [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/trainable/TrainableStatisticalModel.html TrainableStatisticalModel], and [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel].

[[File:classes.jpg|thumb|Part of the class structure of Jstacs. Interfaces are depicted in red, abstract classes in blue, concrete classes in green, and enums in orange. Continuous transitions represent inheritance, whereas arrows represent usage.]]

[http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/StatisticalModel.html StatisticalModel] s represent statistical models in general, which can compute the log-likelihood of a given input sequence and define prior densities on their parameters. The abstract implementation [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/trainable/AbstractTrainSM.html AbstractTrainSM] of [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/trainable/TrainableStatisticalModel.html TrainableStatisticalModel] is the base class of many generatively learned models such as Bayesian networks, hidden Markov models, or mixture models, and can be learned from a single input data set. In constrast, [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel] s provide all facilities for numerical optimization of parameters, which is especially necessary for discriminative parameter learning. The abstract base class of all [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel] implementations is [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/AbstractDifferentiableStatisticalModel.html AbstractDifferentiableStatisticalModel]. Currently, [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel] s include Bayesian networks, Markov models, a ZOOPS model, and mixture models.

[http://www.jstacs.de/api-2.0//de/jstacs/classifiers/AbstractClassifier.html AbstractClassifier] defines the general properties of a classifier. Its sub-class [http://www.jstacs.de/api-2.0//de/jstacs/classifiers/AbstractScoreBasedClassifier.html AbstractScoreBasedClassifier] adds additional methods for the classification of sequences based on a sequence and class-specific score.
Two concrete sub-classes of [http://www.jstacs.de/api-2.0//de/jstacs/classifiers/AbstractScoreBasedClassifier.html AbstractScoreBasedClassifier] are the [http://www.jstacs.de/api-2.0//de/jstacs/classifiers/trainSMBased/TrainSMBasedClassifier.html TrainSMBasedClassifier], which works on [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/trainable/TrainableStatisticalModel.html TrainableStatisticalModel] s, and the [http://www.jstacs.de/api-2.0//de/jstacs/classifiers/differentiableSequenceScoreBased/gendismix/GenDisMixClassifier.html GenDisMixClassifier], which works on [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel].

[http://www.jstacs.de/api-2.0//de/jstacs/classifiers/AbstractClassifier.html AbstractClassifier] s can be assessed either on dedicated training and test data sets or in [http://www.jstacs.de/api-2.0//de/jstacs/classifiers/assessment/ClassifierAssessment.html ClassifierAssessment] s like [http://www.jstacs.de/api-2.0//de/jstacs/classifiers/assessment/KFoldCrossValidation.html KFoldCrossValidation] or [http://www.jstacs.de/api-2.0//de/jstacs/classifiers/assessment/RepeatedHoldOutExperiment.html RepeatedHoldOutExperiment]. The performance measures used in such an assessment are collected in [http://www.jstacs.de/api-2.0//de/jstacs/classifiers/performanceMeasures/PerformanceMeasureParameterSet.html PerformanceMeasureParameterSet] s containing sub-classes of the abstract class [http://www.jstacs.de/api-2.0//de/jstacs/classifiers/performanceMeasures/AbstractPerformanceMeasure.html AbstractPerformanceMeasure].

A more detailed view on all of these classes will be given in the remainder of this cookbook.

== About this cookbook ==

This document is not a cookbook in the sense of a collection of recipes. The intention of this cookbook is rather to learn how to cook with the ingredients and tools provided by Jstacs.

Nonetheless, we present a collection of recipes in the last section, where you find the code of executable code examples that can also be downloaded from <font color=red>[xxx xxx]</font>.

We are aware that a library of this size seems daunting on first sight -- and on second sight as well. However, we hope that despite the inevitable complexity and size of such a library, this cookbook may help to get a picture of the structure, design principles, and capabilities of Jstacs.

This cookbook is structured as follows: in the first section, we explain how data are represented in Jstacs, and how you can read data from files.

In the second section, we present some facilities, an XML parser and the representation of parameters and results, that are used frequently within Jstacs and are necessary for the following parts.

In the third section, we present sequence scores, statistical models, and their sub-interfaces and sub-classes. We explain the methods defined in these interfaces and classes, and we show how you can create and use their existing implementations.

In the fourth section, we explain classifiers and assessment of classifiers using different performance measures.

In the fifth section, we present the facilities for numerical optimization.

In the sixth section, we list utility classes and methods, that we think might be of help for your own implementations.

Finally, in the last section, we give a number of executable code examples that may serve as a starting point of your own classes and applications.

← Older revision		Revision as of 13:08, 2 February 2012
Line 1:		Line 1:
	~~== General structure of Jstacs ==~~		A coarse view on the structure of Jstacs is presented in the Figure below.

	A coarse view on the structure of Jstacs is presented in Figure ~~[[#fig:classes (link)]]~~.
	Being a library for statistical analysis and classification of sequence data, Jstacs is organized around the abstract class [http://www.jstacs.de/api-2.0//de/jstacs/classifiers/AbstractClassifier.html AbstractClassifier], the interface [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/StatisticalModel.html StatisticalModel] and its two sub-interfaces [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/trainable/TrainableStatisticalModel.html TrainableStatisticalModel], and [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel].		Being a library for statistical analysis and classification of sequence data, Jstacs is organized around the abstract class [http://www.jstacs.de/api-2.0//de/jstacs/classifiers/AbstractClassifier.html AbstractClassifier], the interface [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/StatisticalModel.html StatisticalModel] and its two sub-interfaces [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/trainable/TrainableStatisticalModel.html TrainableStatisticalModel], and [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel].

	[[File:~~classes~~.~~jpg~~\|~~thumb~~\|Part of the class structure of Jstacs. Interfaces are depicted in red, abstract classes in blue, concrete classes in green, and enums in orange. Continuous transitions represent inheritance, whereas arrows represent usage.]]		[[File:Classes.png\|frame\|center\|Part of the class structure of Jstacs. Interfaces are depicted in red, abstract classes in blue, concrete classes in green, and enums in orange. Continuous transitions represent inheritance, whereas arrows represent usage.]]

	[http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/StatisticalModel.html StatisticalModel] s represent statistical models in general, which can compute the log-likelihood of a given input sequence and define prior densities on their parameters. The abstract implementation [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/trainable/AbstractTrainSM.html AbstractTrainSM] of [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/trainable/TrainableStatisticalModel.html TrainableStatisticalModel] is the base class of many generatively learned models such as Bayesian networks, hidden Markov models, or mixture models, and can be learned from a single input data set. In constrast, [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel] s provide all facilities for numerical optimization of parameters, which is especially necessary for discriminative parameter learning. The abstract base class of all [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel] implementations is [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/AbstractDifferentiableStatisticalModel.html AbstractDifferentiableStatisticalModel]. Currently, [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel] s include Bayesian networks, Markov models, a ZOOPS model, and mixture models.		[http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/StatisticalModel.html StatisticalModel] s represent statistical models in general, which can compute the log-likelihood of a given input sequence and define prior densities on their parameters. The abstract implementation [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/trainable/AbstractTrainSM.html AbstractTrainSM] of [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/trainable/TrainableStatisticalModel.html TrainableStatisticalModel] is the base class of many generatively learned models such as Bayesian networks, hidden Markov models, or mixture models, and can be learned from a single input data set. In constrast, [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel] s provide all facilities for numerical optimization of parameters, which is especially necessary for discriminative parameter learning. The abstract base class of all [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel] implementations is [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/AbstractDifferentiableStatisticalModel.html AbstractDifferentiableStatisticalModel]. Currently, [http://www.jstacs.de/api-2.0//de/jstacs/sequenceScores/statisticalModels/differentiable/DifferentiableStatisticalModel.html DifferentiableStatisticalModel] s include Bayesian networks, Markov models, a ZOOPS model, and mixture models.
Line 19:		Line 17:
	This document is not a cookbook in the sense of a collection of recipes. The intention of this cookbook is rather to learn how to cook with the ingredients and tools provided by Jstacs.		This document is not a cookbook in the sense of a collection of recipes. The intention of this cookbook is rather to learn how to cook with the ingredients and tools provided by Jstacs.

	Nonetheless, we present a collection of recipes in the last section, where you find the code of executable code examples that can also be downloaded ~~from <font color=red>~~[~~xxx xxx~~]~~</font>~~.		Nonetheless, we present a collection of recipes in the last section, where you find the code of executable code examples that can also be downloaded [http://www.jstacs.de/downloads/recipes.zip as a zip file].

	We are aware that a library of this size seems daunting on first sight -- and on second sight as well. However, we hope that despite the inevitable complexity and size of such a library, this cookbook may help to get a picture of the structure, design principles, and capabilities of Jstacs.		We are aware that a library of this size seems daunting on first sight -- and on second sight as well. However, we hope that despite the inevitable complexity and size of such a library, this cookbook may help to get a picture of the structure, design principles, and capabilities of Jstacs.

	This cookbook is structured as follows: in the [[Starter:~~_Data_handling \| first section~~]], we explain how data are represented in Jstacs, and how you can read data from files.		This cookbook is structured as follows: in the section [[Starter: Data handling]], we explain how data are represented in Jstacs, and how you can read data from files.

	In ~~the~~ [[~~Intermediate_course~~:~~_XMLParser~~,~~_Parameters~~,~~_and_Results \| second section~~]], we present some facilities, an XML parser and the representation of parameters and results, that are used frequently within Jstacs and are necessary for the following parts.		In section [[Intermediate course: XMLParser, Parameters, and Results]], we present some facilities, an XML parser and the representation of parameters and results, that are used frequently within Jstacs and are necessary for the following parts.

	In ~~the~~ [[~~First_main_course~~:~~_SequenceScores \| third section~~]], we present sequence scores, statistical models, and their sub-interfaces and sub-classes. We explain the methods defined in these interfaces and classes, and we show how you can create and use their existing implementations.		In section [[First main course: SequenceScores]], we present sequence scores, statistical models, and their sub-interfaces and sub-classes. We explain the methods defined in these interfaces and classes, and we show how you can create and use their existing implementations.

	In ~~the~~ [[~~Second_main_course~~:~~_Classifiers \| fourth section~~]], we explain classifiers and assessment of classifiers using different performance measures.		In section [[Second main course: Classifiers]], we explain classifiers and assessment of classifiers using different performance measures.

	In ~~the~~ [[~~Intermediate_course~~:~~_Optimization \| fifth section~~]], we present the facilities for numerical optimization.		In section [[Intermediate course: Optimization]] we present the facilities for numerical optimization.

	In ~~the~~ [[Dessert:~~_Alignments~~,~~_Utils~~,~~_and_goodies \| sixth section~~]], we list utility classes and methods, that we think might be of help for your own implementations.		In section [[Dessert: Alignments, Utils, and goodies]], we list utility classes and methods, that we think might be of help for your own implementations.

	Finally, in ~~the~~ [[Recipes ~~\| last section~~]], we give a number of executable code examples that may serve as a starting point of your own classes and applications.		Finally, in section [[Recipes]], we give a number of executable code examples that may serve as a starting point of your own classes and applications.

			== Contents ==
	* [[Starter: Data handling]]		* [[Starter: Data handling]]
	* [[Intermediate course: XMLParser, Parameters, and Results]]		* [[Intermediate course: XMLParser, Parameters, and Results]]