/**
* Compute the number of all possible conditions that could appear in a rule of a given data. For
* nominal attributes, it's the number of values that could appear; for numeric attributes, it's
* the number of values * 2, i.e. <= and >= are counted as different possible conditions.
*
* @param data the given data
* @return number of all conditions of the data
*/
public static double numAllConditions(Instances data) {
double total = 0;
Enumeration attEnum = data.enumerateAttributes();
while (attEnum.hasMoreElements()) {
Attribute att = (Attribute) attEnum.nextElement();
if (att.isNominal()) total += (double) att.numValues();
else total += 2.0 * (double) data.numDistinctValues(att);
}
return total;
}
public static void analyze_accuracy_NHBS(int rng_seed) throws Exception {
HashMap<String, Object> population_params = load_defaults(null);
RawLoader rl = new RawLoader(population_params, true, false, rng_seed);
List<DrugUser> learningData = rl.getLearningData();
Instances nhbs_data =
new Instances("learning_instances", DrugUser.getAttInfo(), learningData.size());
for (DrugUser du : learningData) {
nhbs_data.add(du.getInstance());
}
System.out.println(nhbs_data.toSummaryString());
nhbs_data.setClass(DrugUser.getAttribMap().get("hcv_state"));
// wishlist: remove infrequent values
// weka.filters.unsupervised.instance.RemoveFrequentValues()
Filter f1 = new RemoveUseless();
f1.setInputFormat(nhbs_data);
nhbs_data = Filter.useFilter(nhbs_data, f1);
System.out.println("NHBS IDU 2009 Dataset");
System.out.println("Summary of input:");
// System.out.printlnnhbs_data.toSummaryString());
System.out.println(" Num of classes: " + nhbs_data.numClasses());
System.out.println(" Num of attributes: " + nhbs_data.numAttributes());
for (int idx = 0; idx < nhbs_data.numAttributes(); ++idx) {
Attribute attr = nhbs_data.attribute(idx);
System.out.println("" + idx + ": " + attr.toString());
System.out.println(" distinct values:" + nhbs_data.numDistinctValues(idx));
// System.out.println("" + attr.enumerateValues());
}
ArrayList<String> options = new ArrayList<String>();
options.add("-Q");
options.add("" + rng_seed);
// System.exit(0);
// nhbs_data.deleteAttributeAt(0); //response ID
// nhbs_data.deleteAttributeAt(16); //zip
// Classifier classifier = new NNge(); //best nearest-neighbor classifier: 40.00
// ROC=0.60
// Classifier classifier = new MINND();
// Classifier classifier = new CitationKNN();
// Classifier classifier = new LibSVM(); //requires LibSVM classes. only gets 37.7%
// Classifier classifier = new SMOreg();
Classifier classifier = new Logistic();
// ROC=0.686
// Classifier classifier = new LinearNNSearch();
// LinearRegression: Cannot handle multi-valued nominal class!
// Classifier classifier = new LinearRegression();
// Classifier classifier = new RandomForest();
// String[] options = {"-I", "100", "-K", "4"}; //-I trees, -K features per tree. generally,
// might want to optimize (or not
// https://cwiki.apache.org/confluence/display/MAHOUT/Random+Forests)
// options.add("-I"); options.add("100"); options.add("-K"); options.add("4");
// ROC=0.673
// KStar classifier = new KStar();
// classifier.setGlobalBlend(20); //the amount of not greedy, in percent
// ROC=0.633
// Classifier classifier = new AdaBoostM1();
// ROC=0.66
// Classifier classifier = new MultiBoostAB();
// ROC=0.67
// Classifier classifier = new Stacking();
// ROC=0.495
// J48 classifier = new J48(); // new instance of tree //building a C45 tree classifier
// ROC=0.585
// String[] options = new String[1];
// options[0] = "-U"; // unpruned tree
// classifier.setOptions(options); // set the options
classifier.setOptions((String[]) options.toArray(new String[0]));
// not needed before CV: http://weka.wikispaces.com/Use+WEKA+in+your+Java+code
// classifier.buildClassifier(nhbs_data); // build classifier
// evaluation
Evaluation eval = new Evaluation(nhbs_data);
eval.crossValidateModel(classifier, nhbs_data, 10, new Random(1)); // 10-fold cross validation
System.out.println(eval.toSummaryString("\nResults\n\n", false));
System.out.println(eval.toClassDetailsString());
// System.out.println(eval.toCumulativeMarginDistributionString());
}
public static void test_NHBS_old() throws Exception {
// load the data
CSVLoader loader = new CSVLoader();
// these must come before the getDataSet()
// loader.setEnclosureCharacters(",\'\"S");
// loader.setNominalAttributes("16,71"); //zip code, drug name
// loader.setStringAttributes("");
// loader.setDateAttributes("0,1");
// loader.setSource(new File("hcv/data/NHBS/IDU2_HCV_model_012913_cleaned_for_weka.csv"));
loader.setSource(new File("/home/sasha/hcv/code/data/IDU2_HCV_model_012913_cleaned.csv"));
Instances nhbs_data = loader.getDataSet();
loader.setMissingValue("NOVALUE");
// loader.setMissingValue("");
nhbs_data.deleteAttributeAt(12); // zip code
nhbs_data.deleteAttributeAt(1); // date - redundant with age
nhbs_data.deleteAttributeAt(0); // date
System.out.println("classifying attribute:");
nhbs_data.setClassIndex(1); // new index 3->2->1
nhbs_data.attribute(1).getMetadata().toString(); // HCVEIARSLT1
// wishlist: perhaps it would be smarter to throw out unclassified instance? they interfere
// with the scoring
nhbs_data.deleteWithMissingClass();
// nhbs_data.setClass(new Attribute("HIVRSLT"));//.setClassIndex(1); //2nd column. all are
// mostly negative
// nhbs_data.setClass(new Attribute("HCVEIARSLT1"));//.setClassIndex(2); //3rd column
// #14, i.e. rds_fem, should be made numeric
System.out.println("NHBS IDU 2009 Dataset");
System.out.println("Summary of input:");
// System.out.printlnnhbs_data.toSummaryString());
System.out.println(" Num of classes: " + nhbs_data.numClasses());
System.out.println(" Num of attributes: " + nhbs_data.numAttributes());
for (int idx = 0; idx < nhbs_data.numAttributes(); ++idx) {
Attribute attr = nhbs_data.attribute(idx);
System.out.println("" + idx + ": " + attr.toString());
System.out.println(" distinct values:" + nhbs_data.numDistinctValues(idx));
// System.out.println("" + attr.enumerateValues());
}
// System.exit(0);
// nhbs_data.deleteAttributeAt(0); //response ID
// nhbs_data.deleteAttributeAt(16); //zip
// Classifier classifier = new NNge(); //best nearest-neighbor classifier: 40.00
// Classifier classifier = new MINND();
// Classifier classifier = new CitationKNN();
// Classifier classifier = new LibSVM(); //requires LibSVM classes. only gets 37.7%
// Classifier classifier = new SMOreg();
// Classifier classifier = new LinearNNSearch();
// LinearRegression: Cannot handle multi-valued nominal class!
// Classifier classifier = new LinearRegression();
Classifier classifier = new RandomForest();
String[] options = {
"-I", "100", "-K", "4"
}; // -I trees, -K features per tree. generally, might want to optimize (or not
// https://cwiki.apache.org/confluence/display/MAHOUT/Random+Forests)
classifier.setOptions(options);
// Classifier classifier = new Logistic();
// KStar classifier = new KStar();
// classifier.setGlobalBlend(20); //the amount of not greedy, in percent
// does poorly
// Classifier classifier = new AdaBoostM1();
// Classifier classifier = new MultiBoostAB();
// Classifier classifier = new Stacking();
// building a C45 tree classifier
// J48 classifier = new J48(); // new instance of tree
// String[] options = new String[1];
// options[0] = "-U"; // unpruned tree
// classifier.setOptions(options); // set the options
// classifier.buildClassifier(nhbs_data); // build classifier
// wishlist: remove infrequent values
// weka.filters.unsupervised.instance.RemoveFrequentValues()
Filter f1 = new RemoveUseless();
f1.setInputFormat(nhbs_data);
nhbs_data = Filter.useFilter(nhbs_data, f1);
// evaluation
Evaluation eval = new Evaluation(nhbs_data);
eval.crossValidateModel(classifier, nhbs_data, 10, new Random(1));
System.out.println(eval.toSummaryString("\nResults\n\n", false));
System.out.println(eval.toClassDetailsString());
// System.out.println(eval.toCumulativeMarginDistributionString());
}