MATLAB File Help: prtRvVq |

prtRvVq

prtRvVq Vector quantization random variable RV = prtRvVq creates a prtRvVq object with empty means and probabilities. The means and probabilties must be set either directly, or by calling the MLE method. Vector quanitization uses k-means to discretize the data space using nCategories means. The means are the discrete points in space and have probabilies representing their prominence in the data. The pdf is calculated by mapping to the nearest entry of the means and giving the data point the corresponding entry in probabilities. RV = prtRvVq(PROPERTY1, VALUE1,...) creates a prtRvVq object RV with properties as specified by PROPERTY/VALUE pairs. A prtRvVq object inherits all properties from the prtRv class. In addition, it has the following properties: nCategories - The number of categories means - The means of each catergory that are used to approximate the density probabilities - The probabilities of each category A prtRvVq object inherits all methods from the prtRv class. The MLE method can be used to estimate the distribution parameters from data. Example: dataSet = prtDataGenUnimodal; % Load a dataset consisting of % 2 features dataSet = retainFeatures(dataSet,1); % Retain only the first feature RV = prtRvVq; % Create a prtRvVq object RV = RV.mle(dataSet); % Compute the VQ parameters % form the data RV.plotPdf % Plot the pdf

Class Details

Superclasses | prtRv |

Sealed | false |

Construct on load | false |

prtRvVq | Vector quantization random variable |

dataSet | The training prtDataSet, only stored if verboseStorage is true. |

dataSetSummary | Structure that summarizes prtDataSet. |

isCrossValidateValid | |

isSupervised | |

isTrained | Indicates if prtAction object has been trained. |

means | The means |

nCategories | The number of categories |

name | |

nameAbbreviation | |

plotOptions | |

probabilities | The probabilities |

showProgressBar | |

userData | User specified data |

verboseStorage | Specifies whether or not to store the training prtDataset. |

cdf | Output the cdf of the random variable evaluated at the points specified | |

crossValidate | Cross validate prtAction using prtDataSet and cross validation keys. | |

draw | Draw random samples from the distribution described by the prtRv object | |

get | get the object properties | |

kfolds | Perform K-folds cross-validation of prtAction | |

logPdf | Output the log pdf of the random variable evaluated at the points specified | |

mle | Compute the maximum likelihood estimate | |

optimize | Optimize action parameter by exhaustive function maximization. | |

Output the pdf of the random variable evaluated at the points specified | ||

plotCdf | Plot the cdf of the prtRv | |

plotLogPdf | Plot the pdf of the prtRv | |

plotPdf | Plot the pdf of the prtRv | |

run | Run a prtAction object on a prtDataSet object. | |

set | set the object properties | |

train | Train a prtAction object using training a prtDataSet object. | |

vq |