static void getSegments(dataSeq x, dataSet X2)
{
int rand = randomTool.getOneRandom_int(-100, 100);
if (rand <= 0)//forward
{
for (int node = 0; node < x.Count;)
{
int step = getStep();
dataSeq x2 = new dataSeq(x, node, step + Global.overlapLength);
X2.Add(x2);
node += step;
}
}
else//backward
{
for (int node = x.Count - 1; node >= 0;)
{
int step = getStep();
dataSeq x2 = new dataSeq(x, node, step + Global.overlapLength, false);
X2.Add(x2);
node -= step;
}
}
}
public static dataSet structSplit(dataSet X)
{
//make fractions
dataSet X2 = new dataSet(X.NTag, X.NFeature);
for (int t = 0; t < X.Count; t++)
{
dataSeq x = X[t];
if (Global.structReg && Global.miniSize != 0)
{
/*int step = getStep();
* //if (x.Count > 4 * step)
* if (x.Count > 4 * step && Global.segStep.ToString().Contains(".") == false)//divide x to 2 segments, then do fine segments
* {
* int rand = randomTool.getOneRandom_int(step, x.Count - step);
* dataSeq x1 = new dataSeq(x, 0, rand);
* dataSeq x2 = new dataSeq(x, rand, x.Count);
* getSegments(x1, X2);
* getSegments(x2, X2);
* }
* else*/
getSegments(x, X2);
}
else
{
X2.Add(x);
}
}
return(X2);
}
public static void dataSplit(dataSet X, double v1, double v2, dataSet X1, dataSet X2)
{
if (v2 < v1)
{
throw new Exception("error");
}
X1.Clear();
X2.Clear();
X1.setDataInfo(X);
X2.setDataInfo(X);
int n1 = (int)(X.Count * v1);
int n2 = (int)(X.Count * v2);
for (int i = 0; i < X.Count; i++)
{
if (i >= n1 && i < n2)
{
X1.Add(X[i]);
}
else
{
X2.Add(X[i]);
}
}
}
void initForMulti()
{
_simiBiAry = new double[Global.nTask, Global.nTask];
for (int i = 0; i < Global.nTask; i++)
{
_simiBiAry[i, i] = 1;
}
if (_XList != null)
{
_newXList = new List <dataSet>();
List <int> sizeList = new List <int>();
int maxSize = 0;
for (int i = 0; i < _XList.Count; i++)
{
dataSet Xi = _XList[i];
int size = Xi.Count;
sizeList.Add(size);
if (maxSize < size)
{
maxSize = size;
}
}
for (int i = 0; i < Global.nTask; i++)
{
dataSet X = new dataSet();
dataSet Xi = _XList[i];
foreach (dataSeq x in Xi)
{
X.Add(x);
}
//to make Xs in newXList have the same length
for (int k = sizeList[i]; k < maxSize; k++)
{
X.Add(null);
}
_newXList.Add(X);
}
}
}
public dataSet randomShuffle()
{
List <int> ri = randomTool <int> .getShuffledIndexList(this.Count);
dataSet X = new dataSet(this.NTag, this.NFeature);
foreach (int i in ri)
{
X.Add(this[i]);
}
return(X);
}
public static void dataSplit(dataSet X, double v, dataSet X1, dataSet X2)
{
X1.Clear();
X2.Clear();
X1.setDataInfo(X);
X2.setDataInfo(X);
int n = (int)(X.Count * v);
for (int i = 0; i < X.Count; i++)
{
if (i < n)
{
X1.Add(X[i]);
}
else
{
X2.Add(X[i]);
}
}
}
public static void dataSizeScale(dataSet X)
{
dataSet XX = new dataSet();
XX.setDataInfo(X);
foreach (dataSeq im in X)
{
XX.Add(im);
}
X.Clear();
int n = (int)(XX.Count * Global.trainSizeScale);
for (int i = 0; i < n; i++)
{
int j = i;
if (j > XX.Count - 1)
{
j %= XX.Count - 1;
}
X.Add(XX[j]);
}
X.setDataInfo(XX);
}
public static void loadData_multi(List <dataSet> XList, dataSet X, List <dataSet> XXList)
{
XList.Clear();
XXList.Clear();
//load train data
baseHashSet <int> checkSet = new baseHashSet <int>();
for (int i = 0; i < Global.nTask; i++)
{
string dat_i = i.ToString() + Global.fFeatureTrain;
string tag_i = i.ToString() + Global.fGoldTrain;
dataSet Xi = new dataSet(dat_i, tag_i);
dataSizeScale(Xi);
checkSet.Add(Xi.NFeatureTemp);
XList.Add(Xi);
}
if (checkSet.Count > 1)
{
throw new Exception("inconsistent features among multi tasks!");
}
//make nTag consistent among different tasks
int maxNTag = 0;
foreach (dataSet Xi in XList)
{
if (maxNTag < Xi.NTag)
{
maxNTag = Xi.NTag;
}
}
for (int i = 0; i < Global.nTask; i++)
{
XList[i].NTag = maxNTag;
}
//add to merged data
X.NTag = XList[0].NTag;
X.NFeatureTemp = XList[0].NFeatureTemp;
foreach (dataSet Xi in XList)
{
foreach (dataSeq im in Xi)
{
X.Add(im);
}
}
Global.swLog.WriteLine("data sizes (1, ..., T):");
for (int i = 0; i < Global.nTask; i++)
{
dataSet Xi = XList[i];
Global.swLog.WriteLine(" " + Xi.Count.ToString());
}
Global.swLog.WriteLine();
//load test data
for (int i = 0; i < Global.nTask; i++)
{
string dat_i = i.ToString() + Global.fFeatureTest;
string tag_i = i.ToString() + Global.fGoldTest;
dataSet Xtest = new dataSet(dat_i, tag_i);
XXList.Add(Xtest);
}
for (int i = 0; i < Global.nTask; i++)
{
XXList[i].NTag = maxNTag;
}
}