Changeset 7498:945c2a301da2 in orange


Ignore:
Timestamp:
02/04/11 18:23:07 (3 years ago)
Author:
anze <anze.staric@…>
Branch:
default
Convert:
d71d78d3f8eed7640729db849df29b1ec3cc4241
Message:

:var: -> .. attribute

File:
1 edited

Legend:

Unmodified
Added
Removed
  • orange/Orange/classification/bayes.py

    r7495 r7498  
    175175    All attributes can also be set as constructor parameters. 
    176176     
    177     :var adjustTreshold: If set and the class is binary, the classifier's 
    178             threshold will be set as to optimize the classification accuracy. 
    179             The threshold is tuned by observing the probabilities predicted on 
    180             learning data. Setting it to True can increase the 
    181             accuracy considerably 
    182     :var m: m for m-estimate. If set, m-estimation of probabilities 
    183             will be used using :class:`orange.ProbabilityEstimatorConstructor_m` 
    184             This attribute is ignored if you also set estimatorConstructor. 
    185     :var estimatorConstructor: Probability estimator constructor for 
    186             prior class probabilities. Defaults to 
    187             :class:`orange.ProbabilityEstimatorConstructor_relative` 
    188             Setting this attribute disables the above described attribute m. 
    189     :var conditionalEstimatorConstructor: Probability estimator constructor 
    190             for conditional probabilities for discrete features. If omitted, 
    191             the estimator for prior probabilities will be used. 
    192     :var conditionalEstimatorConstructorContinuous: Probability estimator 
    193             constructor for conditional probabilities for continuous features. 
    194             Defaults to  
    195             :class:`orange.ConditionalProbabilityEstimatorConstructor_loess`  
     177    .. attribute:: adjustTreshold 
     178     
     179        If set and the class is binary, the classifier's 
     180        threshold will be set as to optimize the classification accuracy. 
     181        The threshold is tuned by observing the probabilities predicted on 
     182        learning data. Setting it to True can increase the 
     183        accuracy considerably 
     184         
     185    .. attribute:: m 
     186     
     187        m for m-estimate. If set, m-estimation of probabilities 
     188        will be used using :class:`orange.ProbabilityEstimatorConstructor_m` 
     189        This attribute is ignored if you also set estimatorConstructor. 
     190         
     191    .. attribute:: estimatorConstructor 
     192     
     193        Probability estimator constructor for 
     194        prior class probabilities. Defaults to 
     195        :class:`orange.ProbabilityEstimatorConstructor_relative` 
     196        Setting this attribute disables the above described attribute m. 
     197         
     198    .. attribute:: conditionalEstimatorConstructor 
     199     
     200        Probability estimator constructor 
     201        for conditional probabilities for discrete features. If omitted, 
     202        the estimator for prior probabilities will be used. 
     203         
     204    .. attribute:: conditionalEstimatorConstructorContinuous 
     205     
     206        Probability estimator constructor for conditional probabilities for 
     207        continuous features. Defaults to  
     208        :class:`orange.ConditionalProbabilityEstimatorConstructor_loess`  
    196209    """ 
    197210     
     
    253266    :type baseClassifier: :class:`Orange.core.BayesLearner` 
    254267     
    255     :var distribution: Stores probabilities of classes, i.e. p(C) for each 
    256             class C. 
    257     :var estimator: An object that returns a probability of class p(C) for a 
    258             given class C. 
    259     :var conditionalDistributions: A list of conditional probabilities. 
    260     :var conditionalEstimators: A list of estimators for conditional 
    261             probabilities 
    262     :var normalize: Tells whether the returned probabilities should be 
    263             normalized (default: True) 
    264     :var adjustThreshold: For binary classes, this tells the learner to 
    265             determine the optimal threshold probability according to 0-1 
    266             loss on the training set. For multiple class problems, it has 
    267             no effect. 
     268    .. attribute:: distribution 
     269     
     270        Stores probabilities of classes, i.e. p(C) for each class C. 
     271         
     272    .. attribute:: estimator 
     273     
     274        An object that returns a probability of class p(C) for a given class C. 
     275         
     276    .. attribute:: conditionalDistributions 
     277     
     278        A list of conditional probabilities. 
     279         
     280    .. attribute:: conditionalEstimators 
     281     
     282        A list of estimators for conditional probabilities 
     283         
     284    .. attribute:: adjustThreshold 
     285     
     286        For binary classes, this tells the learner to 
     287        determine the optimal threshold probability according to 0-1 
     288        loss on the training set. For multiple class problems, it has 
     289        no effect. 
    268290    """ 
    269291     
Note: See TracChangeset for help on using the changeset viewer.