/**
* Process a dataset for classification
*
* @return Nothing
*/
public void processClassifierDataset() throws IOException {
try {
ndata = IS.getNumInstances();
ninputs = Attributes.getInputNumAttributes();
nvariables = ninputs + Attributes.getOutputNumAttributes();
// Check that there is only one output variable and
// it is nominal
if (Attributes.getOutputNumAttributes() > 1) {
System.out.println("This algorithm can not process MIMO datasets");
System.out.println("All outputs but the first one will be removed");
}
boolean noOutputs = false;
if (Attributes.getOutputNumAttributes() < 1) {
System.out.println("This algorithm cannot process datasets without outputs");
System.out.println("Zero-valued output generated");
noOutputs = true;
}
// Initialice and fill our own tables
X = new double[ndata][ninputs];
missing = new boolean[ndata][ninputs];
C = new int[ndata];
// Maximum and minimum of inputs
imax = new double[ninputs];
imin = new double[ninputs];
// Maximum and minimum for output data
omax = 0;
omin = 0;
// All values are casted into double/integer
nclasses = 0;
for (int i = 0; i < X.length; i++) {
Instance inst = IS.getInstance(i);
for (int j = 0; j < ninputs; j++) {
X[i][j] = IS.getInputNumericValue(i, j);
missing[i][j] = inst.getInputMissingValues(j);
if (X[i][j] > imax[j] || i == 0) imax[j] = X[i][j];
if (X[i][j] < imin[j] || i == 0) imin[j] = X[i][j];
}
if (noOutputs) C[i] = 0;
else C[i] = (int) IS.getOutputNumericValue(i, 0);
if (C[i] > nclasses) nclasses = C[i];
}
nclasses++;
System.out.println("Number of classes=" + nclasses);
} catch (Exception e) {
System.out.println("DBG: Exception in readSet");
e.printStackTrace();
}
}
/**
* Process a dataset file for a clustering problem.
*
* @param nfexamples Name of the dataset file
* @param train The dataset file is for training or for test
* @throws java.io.IOException if there is any semantical, lexical or sintactical error in the
* input file.
*/
public void processClusterDataset(String nfexamples, boolean train) throws IOException {
try {
// Load in memory a dataset that contains a classification problem
IS.readSet(nfexamples, train);
nData = IS.getNumInstances();
nInputs = Attributes.getInputNumAttributes();
nVariables = nInputs + Attributes.getOutputNumAttributes();
if (Attributes.getOutputNumAttributes() != 0) {
System.out.println("This algorithm can not process datasets with outputs");
System.out.println("All outputs will be removed");
}
// Initialize and fill our own tables
X = new double[nData][nInputs];
missing = new boolean[nData][nInputs];
// Maximum and minimum of inputs
iMaximum = new double[nInputs];
iMinimum = new double[nInputs];
// Maximum and minimum for output data
oMaximum = 0;
oMinimum = 0;
// All values are casted into double/integer
nClasses = 0;
for (int i = 0; i < X.length; i++) {
Instance inst = IS.getInstance(i);
for (int j = 0; j < nInputs; j++) {
X[i][j] = IS.getInputNumericValue(i, j);
missing[i][j] = inst.getInputMissingValues(j);
if (X[i][j] > iMaximum[j] || i == 0) {
iMaximum[j] = X[i][j];
}
if (X[i][j] < iMinimum[j] || i == 0) {
iMinimum[j] = X[i][j];
}
}
}
} catch (Exception e) {
System.out.println("DBG: Exception in readSet");
e.printStackTrace();
}
}
/**
* Process a dataset for modelling
*
* @return Nothing
*/
public void processModelDataset() throws IOException {
try {
// Load in memory a dataset that contains a classification problem
// IS.readSet(nfejemplos,train);
ndata = IS.getNumInstances();
ninputs = Attributes.getInputNumAttributes();
nvariables = ninputs + Attributes.getOutputNumAttributes();
if (Attributes.getOutputNumAttributes() > 1) {
System.out.println("This algorithm can not process MIMO datasets");
System.out.println("All outputs but the first one will be removed");
}
boolean noOutputs = false;
if (Attributes.getOutputNumAttributes() < 1) {
System.out.println("This algorithm can not process datasets without outputs");
System.out.println("Zero-valued output generated");
noOutputs = true;
}
// Initialice and fill our own tables
X = new double[ndata][ninputs];
missing = new boolean[ndata][ninputs];
Y = new double[ndata];
// Maximum and minimum of inputs
imax = new double[ninputs];
imin = new double[ninputs];
// Maximum and minimum for output data
omax = 0;
omin = 0;
// All values are casted into double/integer
nclasses = 0;
for (int i = 0; i < X.length; i++) {
Instance inst = IS.getInstance(i);
for (int j = 0; j < ninputs; j++) {
X[i][j] = IS.getInputNumericValue(i, j);
missing[i][j] = inst.getInputMissingValues(j);
if (X[i][j] > imax[j] || i == 0) imax[j] = X[i][j];
if (X[i][j] < imin[j] || i == 0) imin[j] = X[i][j];
}
if (noOutputs) Y[i] = 0;
else Y[i] = IS.getOutputNumericValue(i, 0);
if (Y[i] > omax || i == 0) omax = Y[i];
if (Y[i] < omin || i == 0) omin = Y[i];
}
} catch (Exception e) {
System.out.println("DBG: Exception in readSet");
e.printStackTrace();
}
}
/**
* Returs the type of the dataset 0-Modelling, 1-Clasiffication, 2-Clustering
*
* @return type of the dataset 0-Modelling, 1-Clasiffication, 2-Clustering
*/
public int datasetType() {
if (Attributes.getOutputNumAttributes() >= 1) {
if (Attributes.hasNominalAttributes()) return (1);
else return (0);
} else return (2);
}
/** Process the training and test files provided in the parameters file to the constructor. */
public void process() {
double[] outputs;
double[] outputs2;
Instance neighbor;
double dist, mean;
int actual;
int[] N = new int[nneigh];
double[] Ndist = new double[nneigh];
boolean allNull;
svm_problem SVMp = null;
svm_parameter SVMparam = new svm_parameter();
svm_model svr = null;
svm_node SVMn[];
double[] outputsCandidate = null;
boolean same = true;
Vector instancesSelected = new Vector();
Vector instancesSelected2 = new Vector();
// SVM PARAMETERS
SVMparam.C = C;
SVMparam.cache_size = 10; // 10MB of cache
SVMparam.degree = degree;
SVMparam.eps = eps;
SVMparam.gamma = gamma;
SVMparam.nr_weight = 0;
SVMparam.nu = nu;
SVMparam.p = p;
SVMparam.shrinking = shrinking;
SVMparam.probability = 0;
if (kernelType.compareTo("LINEAR") == 0) {
SVMparam.kernel_type = svm_parameter.LINEAR;
} else if (kernelType.compareTo("POLY") == 0) {
SVMparam.kernel_type = svm_parameter.POLY;
} else if (kernelType.compareTo("RBF") == 0) {
SVMparam.kernel_type = svm_parameter.RBF;
} else if (kernelType.compareTo("SIGMOID") == 0) {
SVMparam.kernel_type = svm_parameter.SIGMOID;
}
SVMparam.svm_type = svm_parameter.EPSILON_SVR;
try {
// Load in memory a dataset that contains a classification problem
IS.readSet(input_train_name, true);
int in = 0;
int out = 0;
ndatos = IS.getNumInstances();
nvariables = Attributes.getNumAttributes();
nentradas = Attributes.getInputNumAttributes();
nsalidas = Attributes.getOutputNumAttributes();
X = new String[ndatos][2]; // matrix with transformed data
mostCommon = new String[nvariables];
SVMp = new svm_problem();
SVMp.l = ndatos;
SVMp.y = new double[SVMp.l];
SVMp.x = new svm_node[SVMp.l][nentradas + 1];
for (int l = 0; l < SVMp.l; l++) {
for (int n = 0; n < Attributes.getInputNumAttributes() + 1; n++) {
SVMp.x[l][n] = new svm_node();
}
}
for (int i = 0; i < ndatos; i++) {
Instance inst = IS.getInstance(i);
SVMp.y[i] = inst.getAllOutputValues()[0];
for (int n = 0; n < Attributes.getInputNumAttributes(); n++) {
SVMp.x[i][n].index = n;
SVMp.x[i][n].value = inst.getAllInputValues()[n];
SVMp.y[i] = inst.getAllOutputValues()[0];
}
// end of instance
SVMp.x[i][nentradas].index = -1;
}
if (svm.svm_check_parameter(SVMp, SVMparam) != null) {
System.out.println("SVM parameter error in training:");
System.out.println(svm.svm_check_parameter(SVMp, SVMparam));
System.exit(-1);
}
// train the SVM
if (ndatos > 0) {
svr = svm.svm_train(SVMp, SVMparam);
}
for (int i = 0; i < ndatos; i++) {
Instance inst = IS.getInstance(i);
X[i][0] = new String(String.valueOf(inst.getAllOutputValues()[0]));
// the values used for regression
SVMn = new svm_node[Attributes.getInputNumAttributes() + 1];
for (int n = 0; n < Attributes.getInputNumAttributes(); n++) {
SVMn[n] = new svm_node();
SVMn[n].index = n;
SVMn[n].value = inst.getAllInputValues()[n];
}
SVMn[nentradas] = new svm_node();
SVMn[nentradas].index = -1;
// pedict the class
X[i][1] = new String(String.valueOf((svm.svm_predict(svr, SVMn))));
}
} catch (Exception e) {
System.out.println("Dataset exception = " + e);
e.printStackTrace();
System.exit(-1);
}
write_results(output_train_name);
/** ************************************************************************************ */
try {
// Load in memory a dataset that contains a classification
// problem
IS.readSet(input_test_name, false);
int in = 0;
int out = 0;
ndatos = IS.getNumInstances();
nvariables = Attributes.getNumAttributes();
nentradas = Attributes.getInputNumAttributes();
nsalidas = Attributes.getOutputNumAttributes();
X = new String[ndatos][2]; // matrix with transformed data
// data
mostCommon = new String[nvariables];
for (int i = 0; i < ndatos; i++) {
Instance inst = IS.getInstance(i);
X[i][0] = new String(String.valueOf(inst.getAllOutputValues()[0]));
SVMn = new svm_node[Attributes.getInputNumAttributes() + 1];
for (int n = 0; n < Attributes.getInputNumAttributes(); n++) {
SVMn[n] = new svm_node();
SVMn[n].index = n;
SVMn[n].value = inst.getAllInputValues()[n];
}
SVMn[nentradas] = new svm_node();
SVMn[nentradas].index = -1;
// pedict the class
X[i][1] = new String(String.valueOf(svm.svm_predict(svr, SVMn)));
}
} catch (Exception e) {
System.out.println("Dataset exception = " + e);
e.printStackTrace();
System.exit(-1);
}
System.out.println("escribiendo test");
write_results(output_test_name);
}
/**
* Process a dataset file for a classification problem.
*
* @param nfejemplos Name of the dataset file
* @param train The dataset file is for training or for test
* @throws java.io.IOException if there is any semantical, lexical or sintactical error in the
* input file.
*/
public void processClassifierDataset(String nfejemplos, boolean train) throws IOException {
try {
// Load in memory a dataset that contains a classification problem
IS.readSet(nfejemplos, train);
nData = IS.getNumInstances();
nInputs = Attributes.getInputNumAttributes();
nVariables = nInputs + Attributes.getOutputNumAttributes();
// Check that there is only one output variable and
// it is nominal
if (Attributes.getOutputNumAttributes() > 1) {
System.out.println("This algorithm can not process MIMO datasets");
System.out.println("All outputs but the first one will be removed");
}
boolean noOutputs = false;
if (Attributes.getOutputNumAttributes() < 1) {
System.out.println("This algorithm can not process datasets without outputs");
System.out.println("Zero-valued output generated");
noOutputs = true;
}
// Initialize and fill our own tables
X = new double[nData][nInputs];
missing = new boolean[nData][nInputs];
C = new int[nData];
// Maximum and minimum of inputs
iMaximum = new double[nInputs];
iMinimum = new double[nInputs];
// Maximum and minimum for output data
oMaximum = 0;
oMinimum = 0;
// All values are casted into double/integer
nClasses = 0;
for (int i = 0; i < X.length; i++) {
Instance inst = IS.getInstance(i);
for (int j = 0; j < nInputs; j++) {
X[i][j] = IS.getInputNumericValue(i, j);
missing[i][j] = inst.getInputMissingValues(j);
if (X[i][j] > iMaximum[j] || i == 0) {
iMaximum[j] = X[i][j];
}
if (X[i][j] < iMinimum[j] || i == 0) {
iMinimum[j] = X[i][j];
}
}
if (noOutputs) {
C[i] = 0;
} else {
C[i] = (int) IS.getOutputNumericValue(i, 0);
}
if (C[i] > nClasses) {
nClasses = C[i];
}
}
nClasses++;
System.out.println("Number of classes=" + nClasses);
} catch (Exception e) {
System.out.println("DBG: Exception in readSet");
e.printStackTrace();
}
}
/**
* This method reads all the information in a DB and load it to memory.
*
* @param fileName is the database file name.
* @param isTrain is a flag that indicate if the database is for a train or for a test.
* @throws DatasetException if there is any semantical error in the input file.
* @throws HeaderFormatException if there is any lexical or sintactical error in the header of the
* input file
*/
public void readSet(String fileName, boolean isTrain)
throws DatasetException, HeaderFormatException {
String line;
System.out.println("Opening the file: " + fileName + ".");
// Parsing the header of the DB.
errorLogger = new FormatErrorKeeper();
// Declaring an instance parser
InstanceParser parser = new InstanceParser(fileName, isTrain);
// Reading information in the header, i.e., @relation, @attribute, @inputs and @outputs
parseHeader(parser, isTrain);
System.out.println(
" The number of output attributes is: " + Attributes.getOutputNumAttributes());
// The attributes statistics are init if we are in train mode.
if (isTrain && Attributes.getOutputNumAttributes() == 1) {
Attributes.initStatistics();
}
// A temporal vector is used to store the instances read.
System.out.println("\n\n > Reading the data ");
Vector tempSet = new Vector(1000, 100000);
while ((line = parser.getLine()) != null) {
// System.out.println (" > Data line: " + line );
tempSet.addElement(new Instance(line, isTrain, tempSet.size()));
}
// The vector of instances is converted to an array of instances.
int sizeInstance = tempSet.size();
System.out.println(" > Number of instances read: " + tempSet.size());
instanceSet = new Instance[sizeInstance];
for (int i = 0; i < sizeInstance; i++) {
instanceSet[i] = (Instance) tempSet.elementAt(i);
}
// System.out.println("After converting all instances");
// System.out.println("The error logger has any error: "+errorLogger.getNumErrors());
if (errorLogger.getNumErrors() > 0) {
System.out.println(
"There has been " + errorLogger.getAllErrors().size() + " errors in the Dataset format.");
for (int k = 0; k < errorLogger.getNumErrors(); k++) {
errorLogger.getError(k).print();
}
throw new DatasetException(
"There has been " + errorLogger.getAllErrors().size() + " errors in the Dataset format",
errorLogger.getAllErrors());
}
System.out.println(
"\n > Finishing the statistics: (isTrain)"
+ isTrain
+ ", (# out attributes)"
+ Attributes.getOutputNumAttributes());
// If being on a train dataset, the statistics are finished
if (isTrain && Attributes.getOutputNumAttributes() == 1) {
Attributes.finishStatistics();
}
System.out.println(" >> File LOADED CORRECTLY!!");
} // end of InstanceSet constructor.
/** Process the training and test files provided in the parameters file to the constructor. */
public void process() {
// declarations
double[] outputs;
double[] outputs2;
Instance neighbor;
double dist, mean;
int actual;
Randomize rnd = new Randomize();
Instance ex;
gCenter kmeans = null;
int iterations = 0;
double E;
double prevE;
int totalMissing = 0;
boolean allMissing = true;
rnd.setSeed(semilla);
// PROCESS
try {
// Load in memory a dataset that contains a classification problem
IS.readSet(input_train_name, true);
int in = 0;
int out = 0;
ndatos = IS.getNumInstances();
nvariables = Attributes.getNumAttributes();
nentradas = Attributes.getInputNumAttributes();
nsalidas = Attributes.getOutputNumAttributes();
X = new String[ndatos][nvariables]; // matrix with transformed data
kmeans = new gCenter(K, ndatos, nvariables);
timesSeen = new FreqList[nvariables];
mostCommon = new String[nvariables];
// first, we choose k 'means' randomly from all
// instances
totalMissing = 0;
for (int i = 0; i < ndatos; i++) {
Instance inst = IS.getInstance(i);
if (inst.existsAnyMissingValue()) totalMissing++;
}
if (totalMissing == ndatos) allMissing = true;
else allMissing = false;
for (int numMeans = 0; numMeans < K; numMeans++) {
do {
actual = (int) (ndatos * rnd.Rand());
ex = IS.getInstance(actual);
} while (ex.existsAnyMissingValue() && !allMissing);
kmeans.copyCenter(ex, numMeans);
}
// now, iterate adjusting clusters' centers and
// instances to them
prevE = 0;
iterations = 0;
do {
for (int i = 0; i < ndatos; i++) {
Instance inst = IS.getInstance(i);
kmeans.setClusterOf(inst, i);
}
// set new centers
kmeans.recalculateCenters(IS);
// compute RMSE
E = 0;
for (int i = 0; i < ndatos; i++) {
Instance inst = IS.getInstance(i);
E += kmeans.distance(inst, kmeans.getClusterOf(i));
}
iterations++;
// System.out.println(iterations+"\t"+E);
if (Math.abs(prevE - E) == 0) iterations = maxIter;
else prevE = E;
} while (E > minError && iterations < maxIter);
for (int i = 0; i < ndatos; i++) {
Instance inst = IS.getInstance(i);
in = 0;
out = 0;
for (int j = 0; j < nvariables; j++) {
Attribute a = Attributes.getAttribute(j);
direccion = a.getDirectionAttribute();
tipo = a.getType();
if (direccion == Attribute.INPUT) {
if (tipo != Attribute.NOMINAL && !inst.getInputMissingValues(in)) {
X[i][j] = new String(String.valueOf(inst.getInputRealValues(in)));
} else {
if (!inst.getInputMissingValues(in)) X[i][j] = inst.getInputNominalValues(in);
else {
actual = kmeans.getClusterOf(i);
X[i][j] = new String(kmeans.valueAt(actual, j));
}
}
in++;
} else {
if (direccion == Attribute.OUTPUT) {
if (tipo != Attribute.NOMINAL && !inst.getOutputMissingValues(out)) {
X[i][j] = new String(String.valueOf(inst.getOutputRealValues(out)));
} else {
if (!inst.getOutputMissingValues(out)) X[i][j] = inst.getOutputNominalValues(out);
else {
actual = kmeans.getClusterOf(i);
X[i][j] = new String(kmeans.valueAt(actual, j));
}
}
out++;
}
}
}
}
} catch (Exception e) {
System.out.println("Dataset exception = " + e);
e.printStackTrace();
System.exit(-1);
}
write_results(output_train_name);
/** ************************************************************************************ */
// does a test file associated exist?
if (input_train_name.compareTo(input_test_name) != 0) {
try {
// Load in memory a dataset that contains a classification problem
IStest.readSet(input_test_name, false);
int in = 0;
int out = 0;
ndatos = IStest.getNumInstances();
nvariables = Attributes.getNumAttributes();
nentradas = Attributes.getInputNumAttributes();
nsalidas = Attributes.getOutputNumAttributes();
for (int i = 0; i < ndatos; i++) {
Instance inst = IStest.getInstance(i);
in = 0;
out = 0;
for (int j = 0; j < nvariables; j++) {
Attribute a = Attributes.getAttribute(j);
direccion = a.getDirectionAttribute();
tipo = a.getType();
if (direccion == Attribute.INPUT) {
if (tipo != Attribute.NOMINAL && !inst.getInputMissingValues(in)) {
X[i][j] = new String(String.valueOf(inst.getInputRealValues(in)));
} else {
if (!inst.getInputMissingValues(in)) X[i][j] = inst.getInputNominalValues(in);
else {
actual = kmeans.getClusterOf(i);
X[i][j] = new String(kmeans.valueAt(actual, j));
}
}
in++;
} else {
if (direccion == Attribute.OUTPUT) {
if (tipo != Attribute.NOMINAL && !inst.getOutputMissingValues(out)) {
X[i][j] = new String(String.valueOf(inst.getOutputRealValues(out)));
} else {
if (!inst.getOutputMissingValues(out)) X[i][j] = inst.getOutputNominalValues(out);
else {
actual = kmeans.getClusterOf(i);
X[i][j] = new String(kmeans.valueAt(actual, j));
}
}
out++;
}
}
}
}
} catch (Exception e) {
System.out.println("Dataset exception = " + e);
e.printStackTrace();
System.exit(-1);
}
write_results(output_test_name);
}
}
/** Process the training and test files provided in the parameters file to the constructor. */
public void process() {
try {
// Load in memory a dataset that contains a classification problem
IS.readSet(input_train_name, true);
int in = 0;
int out = 0;
ndatos = IS.getNumInstances();
nvariables = Attributes.getNumAttributes();
nentradas = Attributes.getInputNumAttributes();
nsalidas = Attributes.getOutputNumAttributes();
X = new String[ndatos][nvariables]; // matrix with transformed data
boolean[] isMissed =
new boolean[ndatos]; // vector which points out instances with missed data
try {
FileWriter file_write = new FileWriter(output_train_name);
file_write.write(IS.getHeader());
// now, print the normalized data
file_write.write("@data\n");
// file_write.close();
PrintWriter pw = new PrintWriter(file_write);
for (int i = 0; i < ndatos; i++) {
Instance inst = IS.getInstance(i);
if (!inst.existsAnyMissingValue()) {
inst.printAsOriginal(pw);
// file_write.write(inst.toString()); // DOES NOT WRITE BACK NON-DEF DIRECTION
// ATTRIBUTES!!!!
file_write.write("\n");
}
}
pw.close();
file_write.close();
} catch (IOException e) {
System.out.println("IO exception = " + e);
System.exit(-1);
}
} catch (Exception e) {
System.out.println("Dataset exception = " + e);
e.printStackTrace();
System.exit(-1);
}
// does a test file associated exist?
if (input_train_name.compareTo(input_test_name) != 0) {
try {
// Load in memory a dataset that contains a classification problem
IS.readSet(input_test_name, false);
int in = 0;
int out = 0;
ndatos = IS.getNumInstances();
nvariables = Attributes.getNumAttributes();
nentradas = Attributes.getInputNumAttributes();
nsalidas = Attributes.getOutputNumAttributes();
X = new String[ndatos][nvariables]; // matrix with transformed data
boolean[] isMissed =
new boolean[ndatos]; // vector which points out instances with missed data
try {
FileWriter file_write = new FileWriter(output_test_name);
file_write.write(IS.getHeader());
// now, print the normalized data
file_write.write("@data\n");
PrintWriter pw = new PrintWriter(file_write);
for (int i = 0; i < ndatos; i++) {
Instance inst = IS.getInstance(i);
if (!inst.existsAnyMissingValue()) {
inst.printAsOriginal(pw);
file_write.write("\n");
}
}
pw.close();
file_write.close();
} catch (IOException e) {
System.out.println("IO exception = " + e);
System.exit(-1);
}
} catch (Exception e) {
System.out.println("Dataset exception = " + e);
e.printStackTrace();
System.exit(-1);
}
}
// write_results(); / since there ins't any data transformation, is not needed
}
/** Process the training and test files provided in the parameters file to the constructor. */
public void process() {
double[] outputs;
double[] outputs2;
try {
FileWriter file_write = new FileWriter(output_train_name);
try {
// Load in memory a dataset that contains a classification problem
IS.readSet(input_train_name, true);
int in = 0;
int out = 0;
int in2 = 0;
int out2 = 0;
int lastMissing = -1;
boolean fin = false;
boolean stepNext = false;
ndatos = IS.getNumInstances();
nvariables = Attributes.getNumAttributes();
nentradas = Attributes.getInputNumAttributes();
nsalidas = Attributes.getOutputNumAttributes();
String[] row = null;
X = new Vector[ndatos]; // matrix with transformed data
for (int i = 0; i < ndatos; i++) X[i] = new Vector();
timesSeen = new FreqList[nvariables];
mostCommon = new String[nvariables];
file_write.write(IS.getHeader());
// now, print the normalized data
file_write.write("@data\n");
// now, search for missed data, and replace them with
// the most common value
for (int i = 0; i < ndatos; i++) {
Instance inst = IS.getInstance(i);
in = 0;
out = 0;
row = new String[nvariables];
for (int j = 0; j < nvariables; j++) {
Attribute a = Attributes.getAttribute(j);
direccion = a.getDirectionAttribute();
tipo = a.getType();
if (direccion == Attribute.INPUT) {
if (tipo != Attribute.NOMINAL && !inst.existsAnyMissingValue()) {
row[j] = new String(String.valueOf(inst.getInputRealValues(in)));
} else {
if (!inst.existsAnyMissingValue()) row[j] = inst.getInputNominalValues(in);
else {
// missing data
outputs = inst.getAllOutputValues();
in2 = 0;
out2 = 0;
for (int attr = 0; attr < nvariables; attr++) {
Attribute b = Attributes.getAttribute(attr);
direccion = b.getDirectionAttribute();
tipo = b.getType();
if (direccion == Attribute.INPUT) {
if (tipo != Attribute.NOMINAL && !inst.getInputMissingValues(in2)) {
row[attr] = new String(String.valueOf(inst.getInputRealValues(in2)));
} else {
if (!inst.getInputMissingValues(in2))
row[attr] = inst.getInputNominalValues(in2);
}
in2++;
} else {
if (direccion == Attribute.OUTPUT) {
if (tipo != Attribute.NOMINAL && !inst.getOutputMissingValues(out2)) {
row[attr] = new String(String.valueOf(inst.getOutputRealValues(out2)));
} else {
if (!inst.getOutputMissingValues(out2))
row[attr] = inst.getOutputNominalValues(out2);
}
out2++;
}
}
}
// make frecuencies for each attribute
for (int attr = 0; attr < nvariables; attr++) {
Attribute b = Attributes.getAttribute(attr);
direccion = b.getDirectionAttribute();
tipo = b.getType();
if (direccion == Attribute.INPUT && inst.getInputMissingValues(attr)) {
lastMissing = attr;
timesSeen[attr] = new FreqList();
for (int m = 0; m < ndatos; m++) {
Instance inst2 = IS.getInstance(m);
outputs2 = inst2.getAllOutputValues();
boolean sameClass = true;
// are they same concept instances??
for (int k = 0; k < nsalidas && sameClass; k++)
if (outputs[k] != outputs2[k]) sameClass = false;
if (sameClass) {
if (tipo != Attribute.NOMINAL && !inst2.getInputMissingValues(attr)) {
timesSeen[attr].AddElement(
new String(String.valueOf(inst2.getInputRealValues(attr))));
} else {
if (!inst2.getInputMissingValues(attr)) {
timesSeen[attr].AddElement(inst2.getInputNominalValues(attr));
}
}
}
}
}
}
for (int attr = 0; attr < nvariables; attr++) {
if (direccion == Attribute.INPUT && inst.getInputMissingValues(attr)) {
timesSeen[attr].reset();
}
}
fin = false;
stepNext = false;
while (!fin) {
in2 = 0;
for (int attr = 0; attr < nvariables && !fin; attr++) {
Attribute b = Attributes.getAttribute(attr);
direccion = b.getDirectionAttribute();
tipo = b.getType();
if (direccion == Attribute.INPUT && inst.getInputMissingValues(in2)) {
if (stepNext) {
timesSeen[attr].iterate();
stepNext = false;
}
if (timesSeen[attr].outOfBounds()) {
stepNext = true;
if (attr == lastMissing) fin = true;
timesSeen[attr].reset();
}
if (!fin)
row[attr] =
((ValueFreq) timesSeen[attr].getCurrent())
.getValue(); // replace missing data
}
in2++;
}
if (!fin) {
stepNext = true;
file_write.write(row[0]);
for (int y = 1; y < nvariables; y++) {
file_write.write("," + row[y]);
}
file_write.write("\n");
// X[i].addElement(row);
// row = (String[])row.clone();
}
}
}
}
in++;
} else {
if (direccion == Attribute.OUTPUT) {
if (tipo != Attribute.NOMINAL && !inst.getOutputMissingValues(out)) {
row[j] = new String(String.valueOf(inst.getOutputRealValues(out)));
} else {
if (!inst.getOutputMissingValues(out)) row[j] = inst.getOutputNominalValues(out);
else row[j] = new String("?");
}
out++;
}
}
}
if (!inst.existsAnyMissingValue()) {
file_write.write(row[0]);
for (int y = 1; y < nvariables; y++) {
file_write.write("," + row[y]);
}
file_write.write("\n");
}
}
} catch (Exception e) {
System.out.println("Dataset exception = " + e);
e.printStackTrace();
System.exit(-1);
}
file_write.close();
} catch (IOException e) {
System.out.println("IO exception = " + e);
e.printStackTrace();
System.exit(-1);
}
/** ************************************************************************************ */
// does a test file associated exist?
if (input_train_name.compareTo(input_test_name) != 0) {
try {
FileWriter file_write = new FileWriter(output_test_name);
try {
// Load in memory a dataset that contains a classification problem
IS.readSet(input_test_name, false);
int in = 0;
int out = 0;
int in2 = 0;
int out2 = 0;
int lastMissing = -1;
boolean fin = false;
boolean stepNext = false;
ndatos = IS.getNumInstances();
nvariables = Attributes.getNumAttributes();
nentradas = Attributes.getInputNumAttributes();
nsalidas = Attributes.getOutputNumAttributes();
String[] row = null;
X = new Vector[ndatos]; // matrix with transformed data
for (int i = 0; i < ndatos; i++) X[i] = new Vector();
timesSeen = new FreqList[nvariables];
mostCommon = new String[nvariables];
file_write.write(IS.getHeader());
// now, print the normalized data
file_write.write("@data\n");
// now, search for missed data, and replace them with
// the most common value
for (int i = 0; i < ndatos; i++) {
Instance inst = IS.getInstance(i);
in = 0;
out = 0;
row = new String[nvariables];
for (int j = 0; j < nvariables; j++) {
Attribute a = Attributes.getAttribute(j);
direccion = a.getDirectionAttribute();
tipo = a.getType();
if (direccion == Attribute.INPUT) {
if (tipo != Attribute.NOMINAL && !inst.existsAnyMissingValue()) {
row[j] = new String(String.valueOf(inst.getInputRealValues(in)));
} else {
if (!inst.existsAnyMissingValue()) row[j] = inst.getInputNominalValues(in);
else {
// missing data
outputs = inst.getAllOutputValues();
in2 = 0;
out2 = 0;
for (int attr = 0; attr < nvariables; attr++) {
Attribute b = Attributes.getAttribute(attr);
direccion = b.getDirectionAttribute();
tipo = b.getType();
if (direccion == Attribute.INPUT) {
if (tipo != Attribute.NOMINAL && !inst.getInputMissingValues(in2)) {
row[attr] = new String(String.valueOf(inst.getInputRealValues(in2)));
} else {
if (!inst.getInputMissingValues(in2))
row[attr] = inst.getInputNominalValues(in2);
}
in2++;
} else {
if (direccion == Attribute.OUTPUT) {
if (tipo != Attribute.NOMINAL && !inst.getOutputMissingValues(out2)) {
row[attr] = new String(String.valueOf(inst.getOutputRealValues(out2)));
} else {
if (!inst.getOutputMissingValues(out2))
row[attr] = inst.getOutputNominalValues(out2);
}
out2++;
}
}
}
// make frecuencies for each attribute
for (int attr = 0; attr < nvariables; attr++) {
Attribute b = Attributes.getAttribute(attr);
direccion = b.getDirectionAttribute();
tipo = b.getType();
if (direccion == Attribute.INPUT && inst.getInputMissingValues(attr)) {
lastMissing = attr;
timesSeen[attr] = new FreqList();
for (int m = 0; m < ndatos; m++) {
Instance inst2 = IS.getInstance(m);
outputs2 = inst2.getAllOutputValues();
boolean sameClass = true;
// are they same concept instances??
for (int k = 0; k < nsalidas && sameClass; k++)
if (outputs[k] != outputs2[k]) sameClass = false;
if (sameClass) {
if (tipo != Attribute.NOMINAL && !inst2.getInputMissingValues(attr)) {
timesSeen[attr].AddElement(
new String(String.valueOf(inst2.getInputRealValues(attr))));
} else {
if (!inst2.getInputMissingValues(attr)) {
timesSeen[attr].AddElement(inst2.getInputNominalValues(attr));
}
}
}
}
}
}
for (int attr = 0; attr < nvariables; attr++) {
if (direccion == Attribute.INPUT && inst.getInputMissingValues(attr)) {
timesSeen[attr].reset();
}
}
fin = false;
stepNext = false;
while (!fin) {
in2 = 0;
for (int attr = 0; attr < nvariables && !fin; attr++) {
Attribute b = Attributes.getAttribute(attr);
direccion = b.getDirectionAttribute();
tipo = b.getType();
if (direccion == Attribute.INPUT && inst.getInputMissingValues(in2)) {
if (stepNext) {
timesSeen[attr].iterate();
stepNext = false;
}
if (timesSeen[attr].outOfBounds()) {
stepNext = true;
if (attr == lastMissing) fin = true;
timesSeen[attr].reset();
}
if (!fin)
row[attr] =
((ValueFreq) timesSeen[attr].getCurrent())
.getValue(); // replace missing data
}
in2++;
}
if (!fin) {
stepNext = true;
file_write.write(row[0]);
for (int y = 1; y < nvariables; y++) {
file_write.write("," + row[y]);
}
file_write.write("\n");
// X[i].addElement(row);
// row = (String[])row.clone();
}
}
}
}
in++;
} else {
if (direccion == Attribute.OUTPUT) {
if (tipo != Attribute.NOMINAL && !inst.getOutputMissingValues(out)) {
row[j] = new String(String.valueOf(inst.getOutputRealValues(out)));
} else {
if (!inst.getOutputMissingValues(out))
row[j] = inst.getOutputNominalValues(out);
else row[j] = new String("?");
}
out++;
}
}
}
if (!inst.existsAnyMissingValue()) {
file_write.write(row[0]);
for (int y = 1; y < nvariables; y++) {
file_write.write("," + row[y]);
}
file_write.write("\n");
}
}
} catch (Exception e) {
System.out.println("Dataset exception = " + e);
e.printStackTrace();
System.exit(-1);
}
file_write.close();
} catch (IOException e) {
System.out.println("IO exception = " + e);
e.printStackTrace();
System.exit(-1);
}
}
}
