/**
* Compare two datasets to see if they differ.
*
* @param data1 one set of instances
* @param data2 the other set of instances
* @throws Exception if the datasets differ
*/
protected void compareDatasets(Instances data1, Instances data2) throws Exception {
if (m_CheckHeader) {
if (!data2.equalHeaders(data1)) {
throw new Exception("header has been modified\n" + data2.equalHeadersMsg(data1));
}
}
if (!(data2.numInstances() == data1.numInstances())) {
throw new Exception("number of instances has changed");
}
for (int i = 0; i < data2.numInstances(); i++) {
Instance orig = data1.instance(i);
Instance copy = data2.instance(i);
for (int j = 0; j < orig.numAttributes(); j++) {
if (orig.isMissing(j)) {
if (!copy.isMissing(j)) {
throw new Exception("instances have changed");
}
} else {
if (m_CompareValuesAsString) {
if (!orig.toString(j).equals(copy.toString(j))) {
throw new Exception("instances have changed");
}
} else {
if (Math.abs(orig.value(j) - copy.value(j)) > m_MaxDiffValues) {
throw new Exception("instances have changed");
}
}
}
if (Math.abs(orig.weight() - copy.weight()) > m_MaxDiffWeights) {
throw new Exception("instance weights have changed");
}
}
}
}
public String[] extractKeyphrases(String document, int phraseCount) {
List<String> keyWords = new ArrayList<String>();
List<Instance> instances = null;
try {
myLogger.info("-- Extracting Keyphrases... ");
instances = myExtractKeyphrases(document, phraseCount);
} catch (Exception e) {
System.err.println(e.getMessage());
e.printStackTrace();
}
for (Instance anInstance : instances) {
String instanceStr = anInstance.toString();
// http://www.fao.org/aos/agrovoc#c_23903,'Calliandra
// calothyrsus',0.009212,0.000122,1,1,2,0.975066,1,True
// myLogger.info(instanceStr);
// pick whatever data you need
String keyWord =
instanceStr.substring(instanceStr.indexOf(",") + 1, instanceStr.indexOf(",0"));
if (keyWord.startsWith("'") && keyWord.endsWith("'")) {
keyWord = keyWord.substring(1, keyWord.length() - 1);
}
keyWords.add(keyWord);
}
String[] phrases = new String[keyWords.size()];
keyWords.toArray(phrases);
myLogger.info("Keyphrases: " + Arrays.toString(phrases));
return phrases;
}
/** Queries the user enough to make a database query to retrieve experiment results. */
protected void setInstancesFromDBaseQuery() {
try {
if (m_InstanceQuery == null) {
m_InstanceQuery = new InstanceQuery();
}
String dbaseURL = m_InstanceQuery.getDatabaseURL();
dbaseURL =
(String)
JOptionPane.showInputDialog(
this,
"Enter the database URL",
"Query Database",
JOptionPane.PLAIN_MESSAGE,
null,
null,
dbaseURL);
if (dbaseURL == null) {
m_FromLab.setText("Cancelled");
return;
}
m_InstanceQuery.setDatabaseURL(dbaseURL);
m_InstanceQuery.connectToDatabase();
if (!m_InstanceQuery.experimentIndexExists()) {
m_FromLab.setText("No experiment index");
return;
}
m_FromLab.setText("Getting experiment index");
Instances index =
m_InstanceQuery.retrieveInstances("SELECT * FROM " + InstanceQuery.EXP_INDEX_TABLE);
if (index.numInstances() == 0) {
m_FromLab.setText("No experiments available");
return;
}
m_FromLab.setText("Got experiment index");
DefaultListModel lm = new DefaultListModel();
for (int i = 0; i < index.numInstances(); i++) {
lm.addElement(index.instance(i).toString());
}
JList jl = new JList(lm);
ListSelectorDialog jd = new ListSelectorDialog(null, jl);
int result = jd.showDialog();
if (result != ListSelectorDialog.APPROVE_OPTION) {
m_FromLab.setText("Cancelled");
return;
}
Instance selInst = index.instance(jl.getSelectedIndex());
Attribute tableAttr = index.attribute(InstanceQuery.EXP_RESULT_COL);
String table = InstanceQuery.EXP_RESULT_PREFIX + selInst.toString(tableAttr);
setInstancesFromDatabaseTable(table);
} catch (Exception ex) {
m_FromLab.setText("Problem reading database");
}
}
public String classifyInstance(Instance wekaInstance) {
String label = null;
try {
double labelIndex = bayesNet.classifyInstance(wekaInstance);
wekaInstance.setClassValue(labelIndex);
label = wekaInstance.toString(wekaInstance.classIndex());
} catch (Exception e) {
System.err.println(e.getMessage());
e.printStackTrace();
System.exit(-1);
}
return label;
}
/**
* Compare two datasets to see if they differ.
*
* @param data1 one set of instances
* @param data2 the other set of instances
* @throws Exception if the datasets differ
*/
protected void compareDatasets(Instances data1, Instances data2) throws Exception {
if (data1.numAttributes() != data2.numAttributes())
throw new Exception("number of attributes has changed");
if (!(data2.numInstances() == data1.numInstances()))
throw new Exception("number of instances has changed");
for (int i = 0; i < data2.numInstances(); i++) {
Instance orig = data1.instance(i);
Instance copy = data2.instance(i);
for (int j = 0; j < orig.numAttributes(); j++) {
if (orig.isMissing(j)) {
if (!copy.isMissing(j)) throw new Exception("instances have changed");
} else if (!orig.toString(j).equals(copy.toString(j))) {
throw new Exception("instances have changed");
}
if (orig.weight() != copy.weight()) throw new Exception("instance weights have changed");
}
}
}
@Override
public Instances labelData(String data) throws Exception {
Instances unlabeled = new Instances(new BufferedReader(new FileReader(data)));
// set class attribute
unlabeled.setClassIndex(unlabeled.numAttributes() - 1);
// create copy
Instances labeled = new Instances(unlabeled);
for (int i = 0; i < unlabeled.numInstances(); i++) {
Instance ui = unlabeled.instance(i);
double clsLabel = this.classifier.classifyInstance(ui);
labeled.instance(i).setClassValue(clsLabel);
System.out.println(ui.toString() + " -> " + unlabeled.classAttribute().value((int) clsLabel));
}
return labeled;
}
/** Queries the user enough to make a database query to retrieve experiment results. */
protected void setInstancesFromDBaseQuery() {
try {
if (m_InstanceQuery == null) {
m_InstanceQuery = new InstanceQuery();
}
String dbaseURL = m_InstanceQuery.getDatabaseURL();
String username = m_InstanceQuery.getUsername();
String passwd = m_InstanceQuery.getPassword();
/*dbaseURL = (String) JOptionPane.showInputDialog(this,
"Enter the database URL",
"Query Database",
JOptionPane.PLAIN_MESSAGE,
null,
null,
dbaseURL);*/
DatabaseConnectionDialog dbd = new DatabaseConnectionDialog(null, dbaseURL, username);
dbd.setVisible(true);
// if (dbaseURL == null) {
if (dbd.getReturnValue() == JOptionPane.CLOSED_OPTION) {
m_FromLab.setText("Cancelled");
return;
}
dbaseURL = dbd.getURL();
username = dbd.getUsername();
passwd = dbd.getPassword();
m_InstanceQuery.setDatabaseURL(dbaseURL);
m_InstanceQuery.setUsername(username);
m_InstanceQuery.setPassword(passwd);
m_InstanceQuery.setDebug(dbd.getDebug());
m_InstanceQuery.connectToDatabase();
if (!m_InstanceQuery.experimentIndexExists()) {
System.err.println("not found");
m_FromLab.setText("No experiment index");
m_InstanceQuery.disconnectFromDatabase();
return;
}
System.err.println("found");
m_FromLab.setText("Getting experiment index");
Instances index =
m_InstanceQuery.retrieveInstances("SELECT * FROM " + InstanceQuery.EXP_INDEX_TABLE);
if (index.numInstances() == 0) {
m_FromLab.setText("No experiments available");
m_InstanceQuery.disconnectFromDatabase();
return;
}
m_FromLab.setText("Got experiment index");
DefaultListModel lm = new DefaultListModel();
for (int i = 0; i < index.numInstances(); i++) {
lm.addElement(index.instance(i).toString());
}
JList jl = new JList(lm);
jl.setSelectedIndex(0);
int result;
// display dialog only if there's not just one result!
if (jl.getModel().getSize() != 1) {
ListSelectorDialog jd = new ListSelectorDialog(null, jl);
result = jd.showDialog();
} else {
result = ListSelectorDialog.APPROVE_OPTION;
}
if (result != ListSelectorDialog.APPROVE_OPTION) {
m_FromLab.setText("Cancelled");
m_InstanceQuery.disconnectFromDatabase();
return;
}
Instance selInst = index.instance(jl.getSelectedIndex());
Attribute tableAttr = index.attribute(InstanceQuery.EXP_RESULT_COL);
String table = InstanceQuery.EXP_RESULT_PREFIX + selInst.toString(tableAttr);
setInstancesFromDatabaseTable(table);
} catch (Exception ex) {
// 1. print complete stacktrace
ex.printStackTrace();
// 2. print message in panel
m_FromLab.setText("Problem reading database: '" + ex.getMessage() + "'");
}
}