private String statusMessagePrefix() {
return getCustomName()
+ "$"
+ hashCode()
+ "|"
+ ((m_Filter instanceof OptionHandler
&& Utils.joinOptions(((OptionHandler) m_Filter).getOptions()).length() > 0)
? Utils.joinOptions(((OptionHandler) m_Filter).getOptions()) + "|"
: "");
}
/**
* Parses a given list of options.
*
* <p>
* <!-- options-start -->
* Valid options are:
*
* <p>
*
* <pre> -delimiters <value>
* The delimiters to use
* (default ' \r\n\t.,;:'"()?!').</pre>
*
* <pre> -max <int>
* The max size of the Ngram (default = 3).</pre>
*
* <pre> -min <int>
* The min size of the Ngram (default = 1).</pre>
*
* <!-- options-end -->
*
* @param options the list of options as an array of strings
* @throws Exception if an option is not supported
*/
public void setOptions(String[] options) throws Exception {
String value;
super.setOptions(options);
value = Utils.getOption("max", options);
if (value.length() != 0) setNGramMaxSize(Integer.parseInt(value));
else setNGramMaxSize(3);
value = Utils.getOption("min", options);
if (value.length() != 0) setNGramMinSize(Integer.parseInt(value));
else setNGramMinSize(1);
}
/**
* Sets the OptionHandler's options using the given list. All options will be set (or reset)
* during this call (i.e. incremental setting of options is not possible).
* <!-- options-start -->
* Valid options are:
*
* <p>
*
* <pre> -S <sample size>
* Set sample size
* (default: 4)
* </pre>
*
* <pre> -G <seed>
* Set the seed used to generate samples
* (default: 0)
* </pre>
*
* <pre> -D
* Produce debugging output
* (default no debugging output)
* </pre>
*
* <!-- options-end -->
*
* @param options the list of options as an array of strings
* @throws Exception if an option is not supported
*/
public void setOptions(String[] options) throws Exception {
String curropt = Utils.getOption('S', options);
if (curropt.length() != 0) {
setSampleSize(Integer.parseInt(curropt));
} else setSampleSize(4);
curropt = Utils.getOption('G', options);
if (curropt.length() != 0) {
setRandomSeed(Long.parseLong(curropt));
} else {
setRandomSeed(0);
}
setDebug(Utils.getFlag('D', options));
}
/**
* Returns a string that describes the filter as source. The filter will be contained in a class
* with the given name (there may be auxiliary classes), and will contain two methods with these
* signatures:
*
* <pre><code>
* // converts one row
* public static Object[] filter(Object[] i);
* // converts a full dataset (first dimension is row index)
* public static Object[][] filter(Object[][] i);
* </code></pre>
*
* where the array <code>i</code> contains elements that are either Double, String, with missing
* values represented as null. The generated code is public domain and comes with no warranty.
*
* @param className the name that should be given to the source class.
* @param data the dataset used for initializing the filter
* @return the object source described by a string
* @throws Exception if the source can't be computed
*/
public String toSource(String className, Instances data) throws Exception {
StringBuffer result;
boolean[] process;
int i;
result = new StringBuffer();
// determine what attributes were processed
process = new boolean[data.numAttributes()];
for (i = 0; i < data.numAttributes(); i++) {
process[i] = (data.attribute(i).isNumeric() && (i != data.classIndex()));
}
result.append("class " + className + " {\n");
result.append("\n");
result.append(" /** lists which attributes will be processed */\n");
result.append(
" protected final static boolean[] PROCESS = new boolean[]{"
+ Utils.arrayToString(process)
+ "};\n");
result.append("\n");
result.append(" /** the computed means */\n");
result.append(
" protected final static double[] MEANS = new double[]{"
+ Utils.arrayToString(m_Means)
+ "};\n");
result.append("\n");
result.append(" /** the computed standard deviations */\n");
result.append(
" protected final static double[] STDEVS = new double[]{"
+ Utils.arrayToString(m_StdDevs)
+ "};\n");
result.append("\n");
result.append(" /**\n");
result.append(" * filters a single row\n");
result.append(" * \n");
result.append(" * @param i the row to process\n");
result.append(" * @return the processed row\n");
result.append(" */\n");
result.append(" public static Object[] filter(Object[] i) {\n");
result.append(" Object[] result;\n");
result.append("\n");
result.append(" result = new Object[i.length];\n");
result.append(" for (int n = 0; n < i.length; n++) {\n");
result.append(" if (PROCESS[n] && (i[n] != null)) {\n");
result.append(" if (STDEVS[n] > 0)\n");
result.append(" result[n] = (((Double) i[n]) - MEANS[n]) / STDEVS[n];\n");
result.append(" else\n");
result.append(" result[n] = ((Double) i[n]) - MEANS[n];\n");
result.append(" }\n");
result.append(" else {\n");
result.append(" result[n] = i[n];\n");
result.append(" }\n");
result.append(" }\n");
result.append("\n");
result.append(" return result;\n");
result.append(" }\n");
result.append("\n");
result.append(" /**\n");
result.append(" * filters multiple rows\n");
result.append(" * \n");
result.append(" * @param i the rows to process\n");
result.append(" * @return the processed rows\n");
result.append(" */\n");
result.append(" public static Object[][] filter(Object[][] i) {\n");
result.append(" Object[][] result;\n");
result.append("\n");
result.append(" result = new Object[i.length][];\n");
result.append(" for (int n = 0; n < i.length; n++) {\n");
result.append(" result[n] = filter(i[n]);\n");
result.append(" }\n");
result.append("\n");
result.append(" return result;\n");
result.append(" }\n");
result.append("}\n");
return result.toString();
}
