DSL_dataGenerator

<< Click to Display Table of Contents >>

Navigation:  Reference Manual >

DSL_dataGenerator

Header file: datagenerator.h


DSL_dataGenerator(DSL_network &net);

To create a DSL_dataGenerator instance, you need to pass a reference to DSL_network, which will be used as a source probability distribution for the data generator.


int GenerateData(DSL_dataset &ds);

Generate data and store the results in the DSL_dataset


int GenerateData(const char *filename, 

    const DSL_datasetWriteParams *params = NULL);

Generate data and write the results to a text file. To fine tune the output format, pass the pointer to the DSL_datasetWriteParams object.


int GenerateData(DSL_dataGeneratorOutput &out);

Generate data and write the results to an abstracted output. In order to use this method, create a class derived from DSL_dataGeneratorOutput , which is a pure abstract class declared in datagenerator.h header.


void SetNumberOfRecords(int numrec);

int GetNumberOfRecords() const;

Set/get the number of records to generate.


void SetRandSeed(int seed);

int GetRandSeed() const;

Set/get the seed used to initialize the random generator. Defaults to zero, which causes the value based on system clock to be used as seed.


void SetMissingValuePercent(int perc);

int GetMissingValuePercent() const;

Set/get the percentage of missing values. Defaults to zero.


void SetBiasSamplesByEvidence(bool bias);

bool GetBiasSamplesByEvidence() const;

If set to true, generates a data file from the posterior joint probability distribution (i.e., biased by the observations) rather than from the original joint probability distribution. Defaults to false.


int SetSelectedNodes(const std::vector<int> &selection);

const std::vector<int>& GetSelectedNodes() const;

Set/get the nodes included in the output from GenerateData. By default the selection vector is empty, which means that all nodes will be included.