Examples of weka.filters.unsupervised.attribute.NumericCleaner

weka.filters.unsupervised.attribute.NumericCleaner

A filter that 'cleanses' the numeric data from values that are too small, too big or very close to a certain value (e.g., 0) and sets these values to a pre-defined default.

Valid options are:

 -D Turns on output of debugging information.

 -min <double> The minimum threshold. (default -Double.MAX_VALUE)

 -min-default <double> The replacement for values smaller than the minimum threshold. (default -Double.MAX_VALUE)

 -max <double> The maximum threshold. (default Double.MAX_VALUE)

 -max-default <double> The replacement for values larger than the maximum threshold. (default Double.MAX_VALUE)

 -closeto <double> The number values are checked for closeness. (default 0)

 -closeto-default <double> The replacement for values that are close to '-closeto'. (default 0)

 -closeto-tolerance <double> The tolerance below which numbers are considered being close to  to each other. (default 1E-6)

 -decimals <int> The number of decimals to round to, -1 means no rounding at all. (default -1)

 -R <col1,col2,...> The list of columns to cleanse, e.g., first-last or first-3,5-last. (default first-last)

 -V Inverts the matching sense.

 -include-class Whether to include the class in the cleansing. The class column will always be skipped, if this flag is not present. (default no)

@author fracpete (fracpete at waikato dot ac dot nz) @version $Revision: 5543 $

    if (filter == null) {
      filter = (Filter) setup(getFilter(), x, y);
      filter.setInputFormat(inst);
      data = Filter.useFilter(inst, filter);
      // make sure that the numbers don't get too small - otherwise NaNs!
      Filter cleaner = new NumericCleaner();
      cleaner.setInputFormat(data);
      data = Filter.useFilter(data, cleaner);
    }


    // setup classifier
    classifier = (Classifier) setup(getClassifier(), x, y);

    if (filter == null) {
      filter = (Filter) setup(getFilter(), x, y);
      filter.setInputFormat(inst);
      data = Filter.useFilter(inst, filter);
      // make sure that the numbers don't get too small - otherwise NaNs!
      Filter cleaner = new NumericCleaner();
      cleaner.setInputFormat(data);
      data = Filter.useFilter(data, cleaner);
    }


    // setup classifier
    classifier = (Classifier) setup(getClassifier(), x, y);

Examples of weka.filters.unsupervised.attribute.NumericCleaner

Related Classes of weka.filters.unsupervised.attribute.NumericCleaner