public static LabeledDataset <SentimentLabel, SparseVector <double> > InitBowSpace(BowSpace bowSpace,
IEnumerable <LabeledExample <SentimentLabel, string> > labeledExamples, IEnumerable <string> initExamples = null)
{
LabeledExample <SentimentLabel, string>[] examples = labeledExamples as LabeledExample <SentimentLabel, string>[] ?? labeledExamples.ToArray();
List <SparseVector <double> > bowData;
if (initExamples != null)
{
Preconditions.CheckArgument(!(bowSpace is DeltaBowSpace <SentimentLabel>));
bowSpace.Initialize(initExamples);
bowData = examples.Select(le => bowSpace.ProcessDocument(le.Example)).ToList();
}
else
{
bowData = bowSpace is DeltaBowSpace <SentimentLabel>
?((DeltaBowSpace <SentimentLabel>)bowSpace).Initialize(new LabeledDataset <SentimentLabel, string>(examples))
: bowSpace.Initialize(examples.Select(d => d.Example));
}
var bowDataset = new LabeledDataset <SentimentLabel, SparseVector <double> >();
for (int i = 0; i < bowData.Count; i++)
{
bowDataset.Add(examples[i].Label, bowData[i]);
}
return(bowDataset);
}
public override void Train(ILabeledExampleCollection <SentimentLabel, SparseVector <double> > dataset)
{
Preconditions.CheckState(BowSpace != null);
var replDataset = new LabeledDataset <SentimentLabel, SparseVector <double> >();
foreach (LabeledExample <SentimentLabel, SparseVector <double> > le in dataset)
{
SparseVector <double> vector1, vector2;
Replicate(le.Example, out vector1, out vector2);
replDataset.Add(new LabeledExample <SentimentLabel, SparseVector <double> >(
le.Label == SentimentLabel.Neutral ? SentimentLabel.Negative : le.Label, vector1));
replDataset.Add(new LabeledExample <SentimentLabel, SparseVector <double> >(
le.Label == SentimentLabel.Neutral ? SentimentLabel.Positive : le.Label, vector2));
}
mClassifier = CreateModel();
mClassifier.Train(replDataset);
IsTrained = true;
}
static LabeledDataset <string, SparseVector <double> > CreateSingleFeatureDataset(LabeledDataset <BlogMetaData, SparseVector <double> > srcDataset, ClassType classType, int fIdx)
{
SparseVector <double> minValues, maxValues;
GetExtremes(srcDataset, out minValues, out maxValues);
LabeledDataset <string, SparseVector <double> > dataset = new LabeledDataset <string, SparseVector <double> >();
((IEnumerable <LabeledExample <BlogMetaData, SparseVector <double> > >)srcDataset).ToList()
.ForEach(x => dataset.Add(new LabeledExample <string, SparseVector <double> >(AnalysisUtils.GetLabel(x.Label, classType),
new SparseVector <double>(
new double[] { (x.Example[fIdx] - minValues[fIdx]) / (maxValues[fIdx] - minValues[fIdx]) } // simple normalization
))));
return(dataset);
}
private static LabeledDataset <int, int> NewData(int[,] labelCounts, bool sortShuffled = false)
{
var result = new LabeledDataset <int, int>();
for (int i = 0, k = 1; i <= labelCounts.GetUpperBound(0); i++)
{
int label = labelCounts[i, 0], count = labelCounts[i, 1];
for (int j = 0; j < count; j++)
{
result.Add(label, k++);
}
}
if (sortShuffled)
{
result.GroupLabels(true);
}
return(result);
}
protected override ILabeledDataset <LblT, SparseVector <double> > MapTrainSet(int foldN, ILabeledDataset <LblT, string> trainSet)
{
BowSpace bowSpace;
Preconditions.CheckState(!mFoldBowSpaces.TryGetValue(foldN, out bowSpace));
Preconditions.CheckState(mFoldBowSpaces.TryAdd(foldN, bowSpace = BowSpaceFunc()));
List <SparseVector <double> > bowData = bowSpace is DeltaBowSpace <LblT>
?((DeltaBowSpace <LblT>)bowSpace).Initialize(trainSet)
: bowSpace.Initialize(trainSet.Select(d => d.Example));
var bowDataset = new LabeledDataset <LblT, SparseVector <double> >();
for (int i = 0; i < bowData.Count; i++)
{
bowDataset.Add(trainSet[i].Label, bowData[i]);
}
return(bowDataset);
}
public void TrainModels(IEnumerable <Author> authors)
{
foreach (Author author in authors)
{
LabeledDataset <string, SparseVector <double> > ds = new LabeledDataset <string, SparseVector <double> >();
foreach (Author otherAuthor in authors)
{
if (otherAuthor != author && !otherAuthor.mIsTagged)
{
foreach (Text text in otherAuthor.mTexts)
{
ds.Add(new LabeledExample <string, SparseVector <double> >(otherAuthor.mName, text.mFeatureVectors[mSelector]));
}
}
}
SvmMulticlassClassifier <string> model = new SvmMulticlassClassifier <string>();
model.C = Convert.ToDouble(Utils.GetConfigValue("SvmMultiClassC", "5000"));
model.Train(ds);
mModels.Add(author.mName, model);
}
}
public void Train(ILabeledExampleCollection <LblT, string> dataset)
{
Preconditions.CheckState(!IsTrained);
Preconditions.CheckNotNull(dataset);
Preconditions.CheckNotNull(BowSpace);
Preconditions.CheckNotNull(FeatureProcessor);
Preconditions.CheckNotNull(Model);
// preprocess the text
foreach (LabeledExample <LblT, string> le in dataset)
{
le.Example = FeatureProcessor.Run(le.Example);
}
// bow vectors
List <SparseVector <double> > bowData = BowSpace is DeltaBowSpace <LblT>
?(BowSpace as DeltaBowSpace <LblT>).Initialize(dataset as ILabeledDataset <LblT, string> ?? new LabeledDataset <LblT, string>(dataset))
: BowSpace.Initialize(dataset.Select(d => d.Example));
var bowDataset = new LabeledDataset <LblT, SparseVector <double> >();
for (int i = 0; i < bowData.Count; i++)
{
bowDataset.Add(dataset[i].Label, bowData[i]);
}
// train
if (OnTrainModel == null)
{
Model.Train(bowDataset);
}
else
{
OnTrainModel(this, bowDataset);
}
IsTrained = true;
}
public override void Run(object[] args)
{
// prepare data
IStemmer stemmer;
Set <string> .ReadOnly stopWords;
TextMiningUtils.GetLanguageTools(Language.English, out stopWords, out stemmer);
// Create a tokenizer.
var tokenizer = new UnicodeTokenizer
{
MinTokenLen = 2, // Each token must be at least 2 characters long.
Filter = TokenizerFilter.AlphaStrict // Tokens can consist of alphabetic characters only.
};
// take data for two classes from cvs file
var data = new List <LabeledTweet>(GetLabeledTweets().Where(lt => lt.Polarity != 2)).ToList();
// Create a bag-of-words space.
var bowSpc = new BowSpace
{
Tokenizer = tokenizer, // Assign the tokenizer.
StopWords = stopWords, // Assign the stop words.
Stemmer = stemmer, // Assign the stemmer.
MinWordFreq = 1, // A term must appear at least n-times in the corpus for it to be part of the vocabulary.
MaxNGramLen = 2, // Terms consisting of at most n-consecutive words will be considered.
WordWeightType = WordWeightType.TermFreq, // Set the weighting scheme for the bag-of-words vectors to TF.
//WordWeightType = WordWeightType.TfIdf, // Set the weighting scheme for the bag-of-words vectors to TF-IDF.
NormalizeVectors = true, // The TF-IDF vectors will be normalized.
CutLowWeightsPerc = 0 // The terms with the lowest weights, summing up to 20% of the overall weight sum, will be removed from each TF-IDF vector.
};
ArrayList <SparseVector <double> > bowData = bowSpc.Initialize(data.Select(d => d.Text));
// label data
var labeledSet = new LabeledDataset <string, SparseVector <double> >();
for (int i = 0; i < data.Count; i++)
{
labeledSet.Add(data[i].Label, bowData[i]);
}
labeledSet.Shuffle();
int testSize = labeledSet.Count / 10;
var trainingSet = new LabeledDataset <string, SparseVector <double> >(labeledSet.Skip(testSize));
var testSet = new LabeledDataset <string, SparseVector <double> >(labeledSet.Take(testSize));
//-------------------- SVM
var svmBinClass = new SvmBinaryClassifier <string> {
VerbosityLevel = SvmLightVerbosityLevel.Off
};
if (args.Any())
{
svmBinClass.C = (int)args[0];
}
//svmBinClass.BiasedHyperplane = true;
//svmBinClass.CustomParams = "-t 3"; // non-linear kernel
//svmBinClass.CustomParams = String.Format("-j {0}",j);
svmBinClass.Train(trainingSet);
int correct = 0;
double avgDist = 0;
foreach (LabeledExample <string, SparseVector <double> > labeledExample in testSet)
{
var prediction = svmBinClass.Predict(labeledExample.Example);
//Output.WriteLine("actual: {0}\tpredicted: {1}\t score: {2:0.0000}", labeledExample.Label, prediction.BestClassLabel, prediction.BestScore);
avgDist += prediction.BestScore;
if (prediction.BestClassLabel == labeledExample.Label)
{
correct++;
}
}
Output.WriteLine("Accuracy: {0:0.00}", 100.0 * correct / testSet.Count);
Output.WriteLine("Avg. distance: {0:0.00}", avgDist / testSet.Count);
Result.Add("accuracy", (double)correct / testSet.Count);
Result.Add("classifier", svmBinClass);
Result.Add("labeled_data", labeledSet);
}
public Vector2D[] ComputeLayout(LayoutSettings settings)
{
UnlabeledDataset <SparseVector <double> > dataset = new UnlabeledDataset <SparseVector <double> >(mDataset);
// clustering
mLogger.Info("ComputeLayout", "Clustering ...");
KMeansFast kMeans = new KMeansFast(mKClust);
kMeans.Eps = mKMeansEps;
kMeans.Random = mRandom;
kMeans.Trials = 1;
ClusteringResult clustering = kMeans.Cluster(mDataset); // throws ArgumentValueException
// determine reference instances
UnlabeledDataset <SparseVector <double> > dsRefInst = new UnlabeledDataset <SparseVector <double> >();
foreach (Cluster cluster in clustering.Roots)
{
SparseVector <double> centroid
= cluster.Items.Count > 0 ? cluster.ComputeCentroid(mDataset, CentroidType.NrmL2) : new SparseVector <double>();
dsRefInst.Add(centroid); // dataset of reference instances
dataset.Add(centroid); // add centroids to the main dataset
}
// position reference instances
mLogger.Info("ComputeLayout", "Positioning reference instances ...");
SparseMatrix <double> simMtx = ModelUtils.GetDotProductSimilarity(dsRefInst, mSimThresh, /*fullMatrix=*/ false);
StressMajorizationLayout sm = new StressMajorizationLayout(dsRefInst.Count, new DistFunc(simMtx));
sm.Random = mRandom;
Vector2D[] centrPos = sm.ComputeLayout();
// k-NN
mLogger.Info("ComputeLayout", "Computing similarities ...");
simMtx = ModelUtils.GetDotProductSimilarity(dataset, mSimThresh, /*fullMatrix=*/ true);
mLogger.Info("ComputeLayout", "Constructing system of linear equations ...");
LabeledDataset <double, SparseVector <double> > lsqrDs = new LabeledDataset <double, SparseVector <double> >();
foreach (IdxDat <SparseVector <double> > simMtxRow in simMtx)
{
if (simMtxRow.Dat.Count <= 1)
{
mLogger.Warn("ComputeLayout", "Instance #{0} has no neighborhood.", simMtxRow.Idx);
}
ArrayList <KeyDat <double, int> > knn = new ArrayList <KeyDat <double, int> >(simMtxRow.Dat.Count);
foreach (IdxDat <double> item in simMtxRow.Dat)
{
if (item.Idx != simMtxRow.Idx)
{
knn.Add(new KeyDat <double, int>(item.Dat, item.Idx));
}
}
knn.Sort(DescSort <KeyDat <double, int> > .Instance);
int count = Math.Min(knn.Count, mKNN);
SparseVector <double> eq = new SparseVector <double>();
double wgt = 1.0 / (double)count;
for (int i = 0; i < count; i++)
{
eq.InnerIdx.Add(knn[i].Dat);
eq.InnerDat.Add(-wgt);
}
eq.InnerIdx.Sort(); // *** sort only indices
eq[simMtxRow.Idx] = 1;
lsqrDs.Add(0, eq);
}
Vector2D[] layout = new Vector2D[dataset.Count - mKClust];
for (int i = dataset.Count - mKClust, j = 0; i < dataset.Count; i++, j++)
{
SparseVector <double> eq = new SparseVector <double>(new IdxDat <double>[] { new IdxDat <double>(i, 1) });
lsqrDs.Add(centrPos[j].X, eq);
}
LSqrModel lsqr = new LSqrModel();
lsqr.Train(lsqrDs);
for (int i = 0; i < layout.Length; i++)
{
layout[i].X = lsqr.Solution[i];
}
for (int i = lsqrDs.Count - mKClust, j = 0; i < lsqrDs.Count; i++, j++)
{
lsqrDs[i].Label = centrPos[j].Y;
}
lsqr.Train(lsqrDs);
for (int i = 0; i < layout.Length; i++)
{
layout[i].Y = lsqr.Solution[i];
}
return(settings == null ? layout : settings.AdjustLayout(layout));
}
// TODO: exceptions
public Vector2D[] Update(int numDequeue, IEnumerable <SparseVector <double> > newInst, bool test, LayoutSettings settings, ref PtInfo[] ptInfo, int _count)
{
// clustering
mLogger.Info("Update", "Clustering ...");
/*prof*/ StopWatch sw = new StopWatch();
mKMeans.Eps = mKMeansEps;
int iter = 0;
mKMeans.Update(numDequeue, newInst, ref iter);
/*prof*/ sw.Save("cl.txt", _count, iter.ToString());
// determine reference instances
/*prof*/ sw.Reset();
UnlabeledDataset <SparseVector <double> > dsRefInst = new UnlabeledDataset <SparseVector <double> >();
UnlabeledDataset <SparseVector <double> > dsNewInst = new UnlabeledDataset <SparseVector <double> >(newInst);
foreach (SparseVector <double> centroid in mKMeans.GetCentroids())
{
dsRefInst.Add(centroid); // dataset of reference instances
dsNewInst.Add(centroid); // dataset of new instances
}
// position reference instances
mLogger.Info("Update", "Positioning reference instances ...");
SparseMatrix <double> simMtx = ModelUtils.GetDotProductSimilarity(dsRefInst, mSimThresh, /*fullMatrix=*/ false);
StressMajorizationLayout sm = new StressMajorizationLayout(dsRefInst.Count, new DistFunc(simMtx));
sm.Random = mRandom;
sm.MaxSteps = int.MaxValue;
sm.MinDiff = 1E-3;
mRefPos = sm.ComputeLayout(/*settings=*/ null, mRefPos /*make this a property!!!*/);
/*prof*/ sw.Save("sm.txt", _count);
// k-NN
/*prof*/ sw.Reset();
DateTime t = DateTime.Now;
mLogger.Info("Update", "Computing similarities ...");
// update list of neighborhoods
mPatches.RemoveRange(mDataset.Count - mKClust, mKClust);
mPatches.RemoveRange(0, numDequeue);
// remove instances from [dataset and] neighborhoods
foreach (Patch patch in mPatches)
{
if (patch.Min != null && (patch.Min.Idx < numDequeue || patch.Max.Idx >= mDataset.Count - mKClust))
{
int oldCount = patch.List.Count;
ArrayList <KeyDat <double, Patch> > tmp = new ArrayList <KeyDat <double, Patch> >();
foreach (KeyDat <double, Patch> item in patch.List)
{
if (item.Dat.Idx >= numDequeue && item.Dat.Idx < mDataset.Count - mKClust)
{
tmp.Add(item);
}
//else
//{
// Console.WriteLine("Remove {0}", item.Dat.Idx - numDequeue);
//}
}
patch.List = tmp;
patch.ProcessList();
patch.NeedUpdate = patch.List.Count < mKNn && oldCount >= mKNn;
}
}
// update dataset
mDataset.RemoveRange(mDataset.Count - mKClust, mKClust);
mDataset.RemoveRange(0, numDequeue);
// add new instances to dataset
int preAddCount = mDataset.Count;
mDataset.AddRange(dsNewInst);
// precompute transposed matrices
SparseMatrix <double> trNewInst = ModelUtils.GetTransposedMatrix(dsNewInst);
SparseMatrix <double> trDataset = ModelUtils.GetTransposedMatrix(mDataset);
// add new instances to neighborhoods
for (int i = 0; i < dsNewInst.Count; i++)
{
mPatches.Add(new Patch(-1));
mPatches.Last.NeedUpdate = true;
}
for (int i = 0; i < mPatches.Count; i++)
{
mPatches[i].Idx = i;
}
for (int i = 0; i < mPatches.Count; i++)
{
Patch patch = mPatches[i];
SparseVector <double> vec = mDataset[i];
if (vec != null)
{
if (patch.NeedUpdate) // full update required
{
//if (i == 1347) { Console.WriteLine("full update"); }
SparseVector <double> simVec = ModelUtils.GetDotProductSimilarity(trDataset, mDataset.Count, vec, mSimThresh);
ArrayList <KeyDat <double, int> > tmp = new ArrayList <KeyDat <double, int> >();
foreach (IdxDat <double> item in simVec)
{
if (item.Idx != i)
{
tmp.Add(new KeyDat <double, int>(item.Dat, item.Idx));
}
}
tmp.Sort(new Comparer2());
int count = Math.Min(tmp.Count, mKNnExt);
patch.List.Clear();
for (int j = 0; j < count; j++)
{
patch.List.Add(new KeyDat <double, Patch>(tmp[j].Key, mPatches[tmp[j].Dat]));
}
patch.ProcessList();
patch.NeedUpdate = false;
}
else // only new instances need to be considered
{
//if (i == 1347) { Console.WriteLine("partial update"); }
SparseVector <double> simVec = ModelUtils.GetDotProductSimilarity(trNewInst, dsNewInst.Count, vec, mSimThresh);
// check if further processing is needed
bool needMerge = false;
if (test)
{
foreach (IdxDat <double> item in simVec)
{
if (item.Dat >= patch.MinSim)
{
needMerge = true;
//Console.WriteLine("{0} {1}", item.Dat, patch.MinSim);
break;
}
}
}
else
{
foreach (IdxDat <double> item in simVec)
{
if (item.Dat > patch.MinSim)
{
needMerge = true;
//Console.WriteLine("{0} {1}", item.Dat, patch.MinSim);
break;
}
}
}
if (needMerge || patch.List.Count < mKNn)
{
//if (i == 1347) { Console.WriteLine("merge"); }
int oldCount = patch.List.Count;
ArrayList <KeyDat <double, Patch> > tmp = new ArrayList <KeyDat <double, Patch> >();
foreach (IdxDat <double> item in simVec)
{
tmp.Add(new KeyDat <double, Patch>(item.Dat, mPatches[item.Idx + preAddCount]));
}
// merge the two lists
// TODO: speed this up
patch.List.AddRange(tmp);
patch.List.Sort(new Comparer());
// trim list to size
if (oldCount >= mKNn)
{
patch.List.RemoveRange(oldCount, patch.List.Count - oldCount);
}
patch.ProcessList();
}
}
}
}
/*prof*/ sw.Save("knn.txt", _count);
// *** Test ***
sw.Reset();
ModelUtils.GetDotProductSimilarity(mDataset, mSimThresh, /*fullMatrix=*/ true);
sw.Save("selfSim.txt", _count, mDataset.Count.ToString());
if (test)
{
simMtx = ModelUtils.GetDotProductSimilarity(mDataset, mSimThresh, /*fullMatrix=*/ true);
ArrayList <Patch> patches = new ArrayList <Patch>();
for (int i = 0; i < mDataset.Count; i++)
{
patches.Add(new Patch(i));
}
foreach (IdxDat <SparseVector <double> > simMtxRow in simMtx)
{
if (simMtxRow.Dat.Count <= 1)
{
mLogger.Warn("Update", "Instance #{0} has no neighborhood.", simMtxRow.Idx);
}
ArrayList <KeyDat <double, int> > knn = new ArrayList <KeyDat <double, int> >(simMtxRow.Dat.Count);
foreach (IdxDat <double> item in simMtxRow.Dat)
{
if (item.Idx != simMtxRow.Idx)
{
knn.Add(new KeyDat <double, int>(item.Dat, item.Idx));
}
}
knn.Sort(new Comparer2());
int count = Math.Min(knn.Count, mKNnExt);
for (int i = 0; i < count; i++)
{
patches[simMtxRow.Idx].List.Add(new KeyDat <double, Patch>(knn[i].Key, patches[knn[i].Dat]));
}
patches[simMtxRow.Idx].ProcessList();
}
// compare
if (patches.Count != mPatches.Count)
{
throw new Exception("Count mismatch.");
}
for (int i = 0; i < mPatches.Count; i++)
{
if (patches[i].List.Count < mKNn && patches[i].List.Count != mPatches[i].List.Count)
{
Console.WriteLine(mPatches[i].List.Count);
Console.WriteLine(patches[i].List.Count);
Output(mPatches[i].List);
Output(patches[i].List);
Console.WriteLine(i);
throw new Exception("List count mismatch.");
}
int count = Math.Min(mPatches[i].List.Count, mKNn);
for (int j = 0; j < count; j++)
{
//Console.WriteLine("{4} {0}-{1} {2}-{3}", mPatches[i].List[j].Key, mPatches[i].List[j].Dat.Idx, patches[i].List[j].Key, patches[i].List[j].Dat.Idx, i);
if (mPatches[i].List[j].Key != patches[i].List[j].Key || mPatches[i].List[j].Dat.Idx != patches[i].List[j].Dat.Idx)
{
Console.WriteLine("i:{4} fast:{0}-{1} slow:{2}-{3}", mPatches[i].List[j].Key, mPatches[i].List[j].Dat.Idx, patches[i].List[j].Key, patches[i].List[j].Dat.Idx, i);
int idxFast = mPatches[i].List[j].Dat.Idx;
int idxSlow = patches[i].List[j].Dat.Idx;
Console.WriteLine("slow @ fast idx: {0}", GetKey(patches[i].List, idxFast));
Console.WriteLine("fast @ slow idx: {0}", GetKey(mPatches[i].List, idxSlow));
throw new Exception("Patch item mismatch.");
}
}
}
}
// *** End of test ***
//Console.WriteLine("Number of patches: {0}", mPatches.Count);
//int waka = 0;
//foreach (Patch patch in mPatches)
//{
// waka += patch.List.Count;
//}
//Console.WriteLine("Avg list size: {0}", (double)waka / (double)mPatches.Count);
Console.WriteLine((DateTime.Now - t).TotalMilliseconds);
/*prof*/ sw.Reset();
mLogger.Info("Update", "Constructing system of linear equations ...");
LabeledDataset <double, SparseVector <double> > lsqrDs = new LabeledDataset <double, SparseVector <double> >();
Vector2D[] layout = new Vector2D[mDataset.Count - mKClust];
foreach (Patch patch in mPatches)
{
int count = Math.Min(patch.List.Count, mKNn);
SparseVector <double> eq = new SparseVector <double>();
double wgt = 1.0 / (double)count;
for (int i = 0; i < count; i++)
{
eq.InnerIdx.Add(patch.List[i].Dat.Idx);
eq.InnerDat.Add(-wgt);
}
eq.InnerIdx.Sort(); // *** sort only indices
eq[patch.Idx] = 1;
lsqrDs.Add(0, eq);
}
for (int i = mDataset.Count - mKClust, j = 0; i < mDataset.Count; i++, j++)
{
SparseVector <double> eq = new SparseVector <double>(new IdxDat <double>[] { new IdxDat <double>(i, 1) });
lsqrDs.Add(mRefPos[j].X, eq);
}
LSqrModel lsqr = new LSqrModel();
mSolX.RemoveRange(0, numDequeue);
double[] aux = new double[mKClust];
mSolX.CopyTo(mSolX.Count - mKClust, aux, 0, mKClust);
mSolX.RemoveRange(mSolX.Count - mKClust, mKClust);
foreach (SparseVector <double> newVec in newInst)
{
mSolX.Add(0);
}
mSolX.AddRange(aux);
lsqr.InitialSolution = mSolX.ToArray();
lsqr.Train(lsqrDs);
mSolX = lsqr.Solution.GetWritableCopy();
//for (int i = 0; i < lsqr.InitialSolution.Length; i++)
//{
// Console.WriteLine("{0}\t{1}", lsqr.InitialSolution[i], lsqr.Solution[i]);
//}
for (int i = 0; i < layout.Length; i++)
{
layout[i].X = lsqr.Solution[i];
}
for (int i = lsqrDs.Count - mKClust, j = 0; i < lsqrDs.Count; i++, j++)
{
lsqrDs[i].Label = mRefPos[j].Y;
}
mSolY.RemoveRange(0, numDequeue);
aux = new double[mKClust];
mSolY.CopyTo(mSolY.Count - mKClust, aux, 0, mKClust);
mSolY.RemoveRange(mSolY.Count - mKClust, mKClust);
foreach (SparseVector <double> newVec in newInst)
{
mSolY.Add(0);
}
mSolY.AddRange(aux);
lsqr.InitialSolution = mSolY.ToArray();
lsqr.Train(lsqrDs);
mSolY = lsqr.Solution.GetWritableCopy();
for (int i = 0; i < layout.Length; i++)
{
layout[i].Y = lsqr.Solution[i];
}
/*prof*/ sw.Save("lsqr.txt", _count);
// -----------------------------------------------------------------
// make ptInfo
// -----------------------------------------------------------------
ptInfo = new PtInfo[layout.Length];
int ii = 0;
foreach (Vector2D pt in layout)
{
ptInfo[ii] = new PtInfo();
ptInfo[ii].X = pt.X;
ptInfo[ii].Y = pt.Y;
ptInfo[ii].Vec = mDataset[ii];
ii++;
}
// -----------------------------------------------------------------
return(settings == null ? layout : settings.AdjustLayout(layout));
}
public Vector2D[] ComputeLayout(LayoutSettings settings)
{
// clustering
mLogger.Info("ComputeLayout", "Clustering ...");
mKMeans = new IncrementalKMeans(mKClust);
mKMeans.Eps = mKMeansEps;
mKMeans.Random = mRandom;
mKMeans.Trials = 3;
ClusteringResult clustering = mKMeans.Cluster(mDataset); // throws ArgumentValueException
// determine reference instances
UnlabeledDataset <SparseVector <double> > dsRefInst = new UnlabeledDataset <SparseVector <double> >();
foreach (SparseVector <double> centroid in mKMeans.GetCentroids())
{
dsRefInst.Add(centroid); // dataset of reference instances
mDataset.Add(centroid); // add centroids to the main dataset
}
// position reference instances
mLogger.Info("ComputeLayout", "Positioning reference instances ...");
SparseMatrix <double> simMtx = ModelUtils.GetDotProductSimilarity(dsRefInst, mSimThresh, /*fullMatrix=*/ false);
StressMajorizationLayout sm = new StressMajorizationLayout(dsRefInst.Count, new DistFunc(simMtx));
sm.Random = mRandom;
sm.MaxSteps = int.MaxValue;
sm.MinDiff = 0.00001;
mRefPos = sm.ComputeLayout();
// k-NN
mLogger.Info("ComputeLayout", "Computing similarities ...");
simMtx = ModelUtils.GetDotProductSimilarity(mDataset, mSimThresh, /*fullMatrix=*/ true);
mLogger.Info("ComputeLayout", "Constructing system of linear equations ...");
LabeledDataset <double, SparseVector <double> > lsqrDs = new LabeledDataset <double, SparseVector <double> >();
mPatches = new ArrayList <Patch>(mDataset.Count);
for (int i = 0; i < mDataset.Count; i++)
{
mPatches.Add(new Patch(i));
}
foreach (IdxDat <SparseVector <double> > simMtxRow in simMtx)
{
if (simMtxRow.Dat.Count <= 1)
{
mLogger.Warn("ComputeLayout", "Instance #{0} has no neighborhood.", simMtxRow.Idx);
}
ArrayList <KeyDat <double, int> > knn = new ArrayList <KeyDat <double, int> >(simMtxRow.Dat.Count);
foreach (IdxDat <double> item in simMtxRow.Dat)
{
if (item.Idx != simMtxRow.Idx)
{
knn.Add(new KeyDat <double, int>(item.Dat, item.Idx));
}
}
knn.Sort(DescSort <KeyDat <double, int> > .Instance);
int count = Math.Min(knn.Count, mKNnExt);
for (int i = 0; i < count; i++)
{
mPatches[simMtxRow.Idx].List.Add(new KeyDat <double, Patch>(knn[i].Key, mPatches[knn[i].Dat]));
}
mPatches[simMtxRow.Idx].ProcessList();
count = Math.Min(knn.Count, mKNn);
SparseVector <double> eq = new SparseVector <double>();
double wgt = 1.0 / (double)count;
for (int i = 0; i < count; i++)
{
eq.InnerIdx.Add(knn[i].Dat);
eq.InnerDat.Add(-wgt);
}
eq.InnerIdx.Sort(); // *** sort only indices
eq[simMtxRow.Idx] = 1;
lsqrDs.Add(0, eq);
}
Vector2D[] layout = new Vector2D[mDataset.Count - mKClust];
for (int i = mDataset.Count - mKClust, j = 0; i < mDataset.Count; i++, j++)
{
SparseVector <double> eq = new SparseVector <double>(new IdxDat <double>[] { new IdxDat <double>(i, 1) });
lsqrDs.Add(mRefPos[j].X, eq);
}
LSqrModel lsqr = new LSqrModel();
lsqr.Train(lsqrDs);
mSolX = lsqr.Solution.GetWritableCopy();
for (int i = 0; i < layout.Length; i++)
{
layout[i].X = lsqr.Solution[i];
}
for (int i = lsqrDs.Count - mKClust, j = 0; i < lsqrDs.Count; i++, j++)
{
lsqrDs[i].Label = mRefPos[j].Y;
}
lsqr.Train(lsqrDs);
mSolY = lsqr.Solution.GetWritableCopy();
for (int i = 0; i < layout.Length; i++)
{
layout[i].Y = lsqr.Solution[i];
}
return(settings == null ? layout : settings.AdjustLayout(layout));
}
static void Main(string[] args)
{
Random rnd = new Random(1);
string[] featureNames = "ttr,brunet,honore,hl,ttrLemma,brunetLemma,honoreLemma,hlLemma,ari,flesch,fog,rWords,rChars,rSyllables,rComplex,M04,M05,M06,M07,M08,M09,M10,M11,M12,M13".Split(',');
LabeledDataset <BlogMetaData, SparseVector <double> > dataset = new LabeledDataset <BlogMetaData, SparseVector <double> >();
Console.WriteLine("Analiziram besedila...");
foreach (string fileName in Directory.GetFiles(Config.DataFolder, "*.xml"))
{
// load XML
Console.WriteLine("Datoteka {0}...", fileName);
XmlDocument doc = new XmlDocument();
doc.LoadXml(File.ReadAllText(fileName).Replace("xmlns=\"http://www.tei-c.org/ns/1.0\"", ""));
Corpus corpus = new Corpus();
corpus.LoadFromXmlFile(fileName, /*tagLen=*/ int.MaxValue);
#if TEST_CHUNKER
Text text = null;
#else
Text text = new Text(corpus, doc.SelectSingleNode("//header/naslov").InnerText, doc.SelectSingleNode("//header/blog").InnerText /*blog identifier is used as author identifier*/);
text.ComputeFeatures(); // compute Detextive features
#endif
// run chunker
Console.WriteLine("Racunam znacilke...");
ArrayList <Chunk> chunks = Chunker.GetChunks(doc);
chunks = new ArrayList <Chunk>(chunks.Where(x => !x.mInner)); // get non-inner chunks only
chunks.ForEach(x => x.mType = MapChunkType(x.mType)); // move chunks from Other_* to main categories
#if TEST_CHUNKER
return;
#endif
// get blog meta-data
BlogMetaData metaData = new BlogMetaData();
metaData.mAuthorAge = doc.SelectSingleNode("//header/avtorStarost").InnerText;
metaData.mAuthorEducation = doc.SelectSingleNode("//header/avtorIzobrazba").InnerText;
metaData.mAuthorGender = doc.SelectSingleNode("//header/avtorSpol").InnerText;
metaData.mAuthorLocation = doc.SelectSingleNode("//header/avtorRegija").InnerText;
metaData.mBlog = doc.SelectSingleNode("//header/blog").InnerText;
// compute features M04-M13 from Stamatatos et al.: Automatic Text Categorization in Terms of Genre and Author (2000)
double totalChunks = chunks.Count;
double[] M = new double[10];
double numNP = chunks.Count(x => x.mType == ChunkType.NP);
double numVP = chunks.Count(x => x.mType == ChunkType.VP);
double numAP = chunks.Count(x => x.mType == ChunkType.AP);
double numPP = chunks.Count(x => x.mType == ChunkType.PP);
double numCON = chunks.Count(x => x.mType == ChunkType.CON);
if (totalChunks > 0)
{
M[0] = numNP / totalChunks;
M[1] = numVP / totalChunks;
M[2] = numAP / totalChunks;
M[3] = numPP / totalChunks;
M[4] = numCON / totalChunks;
}
double numWordsNP = chunks.Where(x => x.mType == ChunkType.NP).Select(x => x.mItems.Count).Sum();
M[5] = numNP == 0 ? 0 : (numWordsNP / numNP);
double numWordsVP = chunks.Where(x => x.mType == ChunkType.VP).Select(x => x.mItems.Count).Sum();
M[6] = numVP == 0 ? 0 : (numWordsVP / numVP);
double numWordsAP = chunks.Where(x => x.mType == ChunkType.AP).Select(x => x.mItems.Count).Sum();
M[7] = numAP == 0 ? 0 : (numWordsAP / numAP);
double numWordsPP = chunks.Where(x => x.mType == ChunkType.PP).Select(x => x.mItems.Count).Sum();
M[8] = numPP == 0 ? 0 : (numWordsPP / numPP);
double numWordsCON = chunks.Where(x => x.mType == ChunkType.CON).Select(x => x.mItems.Count).Sum();
M[9] = numCON == 0 ? 0 : (numWordsCON / numCON);
// create dataset
SparseVector <double> vec = new SparseVector <double>();
int i = 0;
foreach (string featureName in "ttr,brunet,honore,hl,ttrLemma,brunetLemma,honoreLemma,hlLemma,ari,flesch,fog,rWords,rChars,rSyllables,rComplex".Split(','))
{
if (double.IsNaN(text.mFeatures[featureName]) || double.IsInfinity(text.mFeatures[featureName]))
{
vec[i++] = 0;
}
else
{
vec[i++] = text.mFeatures[featureName];
}
}
foreach (double val in M)
{
vec[i++] = val;
}
dataset.Add(new LabeledExample <BlogMetaData, SparseVector <double> >(metaData, vec));
string htmlFileName = Config.HtmlFolder + "\\" + Path.GetFileNameWithoutExtension(fileName) + ".html";
Output.SaveHtml(featureNames, vec, doc, chunks, htmlFileName);
}
// save as Orange and Weka file
Console.WriteLine("Zapisujem datoteke Weka ARFF in Orange TAB...");
foreach (ClassType classType in new ClassType[] { ClassType.AuthorName, ClassType.AuthorAge, ClassType.AuthorGender, ClassType.AuthorEducation, ClassType.AuthorLocation })
{
Output.SaveArff(featureNames, dataset, classType, Config.OutputFolder + "\\" + string.Format("OPA-{0}.arff", classType));
Output.SaveTab(featureNames, dataset, classType, Config.OutputFolder + "\\" + string.Format("OPA-{0}.tab", classType));
}
// evaluate features via classification
Console.WriteLine("Evalviram znacilke s klasifikacijskimi modeli...");
PerfData <string> perfData = new PerfData <string>();
ArrayList <Pair <string, IModel <string> > > models = new ArrayList <Pair <string, IModel <string> > >();
// create classifiers
NearestCentroidClassifier <string> ncc = new NearestCentroidClassifier <string>();
ncc.Similarity = new SingleFeatureSimilarity();
models.Add(new Pair <string, IModel <string> >("NCC", ncc));
//KnnClassifier<string, SparseVector<double>> knn = new KnnClassifier<string, SparseVector<double>>(new SingleFeatureSimilarity());
//models.Add(new Pair<string, IModel<string>>("kNN", knn)); // *** kNN is too slow
SvmMulticlassClassifier <string> svm = new SvmMulticlassClassifier <string>();
models.Add(new Pair <string, IModel <string> >("SVM", svm));
MajorityClassifier <string, SparseVector <double> > maj = new MajorityClassifier <string, SparseVector <double> >();
models.Add(new Pair <string, IModel <string> >("Majority", maj));
MajorityClassifier <string, SparseVector <double> > backupCfy = new MajorityClassifier <string, SparseVector <double> >();
foreach (Pair <string, IModel <string> > modelInfo in models) // iterate over different classifiers
{
Console.WriteLine("Kasifikacijski model: {0}...", modelInfo.First);
foreach (ClassType classType in new ClassType[] { ClassType.AuthorName, ClassType.AuthorAge, ClassType.AuthorEducation, ClassType.AuthorGender, ClassType.AuthorLocation }) // iterate over different class types
{
Console.WriteLine("Ciljni razred: {0}...", classType);
for (int fIdx = 0; fIdx < featureNames.Count(); fIdx++) // iterate over different features
{
Console.WriteLine("Znacilka: {0}...", featureNames[fIdx]);
LabeledDataset <string, SparseVector <double> > datasetWithSingleFeature = CreateSingleFeatureDataset(dataset, classType, fIdx);
datasetWithSingleFeature.Shuffle(rnd);
LabeledDataset <string, SparseVector <double> > trainSet, testSet;
for (int foldNum = 1; foldNum <= 10; foldNum++)
{
Console.WriteLine("Sklop " + foldNum + " / 10...");
datasetWithSingleFeature.SplitForCrossValidation(/*numFolds=*/ 10, foldNum, out trainSet, out testSet);
IModel <string> model = modelInfo.Second;
backupCfy.Train(trainSet);
// if there is only one class in trainSet, switch to MajorityClassifier
if (((IEnumerable <LabeledExample <string, SparseVector <double> > >)trainSet).Select(x => x.Label).Distinct().Count() == 1)
{
model = backupCfy;
}
else
{
string cacheFileName = Config.OutputFolder + "\\svm-" + classType + "-" + featureNames[fIdx] + "-" + foldNum + ".bin";
if (model is SvmMulticlassClassifier <string> && File.Exists(cacheFileName))
{
using (BinarySerializer bs = new BinarySerializer(cacheFileName, FileMode.Open))
{
((SvmMulticlassClassifier <string>)model).Load(bs);
}
}
else
{
model.Train(trainSet);
}
#if CACHE_MODELS
if (model is SvmMulticlassFast <string> )
{
using (BinarySerializer bs = new BinarySerializer(cacheFileName, FileMode.Create))
{
model.Save(bs);
}
}
#endif
}
foreach (LabeledExample <string, SparseVector <double> > lblEx in testSet)
{
Prediction <string> pred = model.Predict(lblEx.Example);
if (pred.Count == 0)
{
pred = backupCfy.Predict(lblEx.Example);
} // if the model is unable to make a prediction, use MajorityClassifier instead
perfData.GetPerfMatrix(classType.ToString(), modelInfo.First + "\t" + featureNames[fIdx], foldNum).AddCount(lblEx.Label, pred.BestClassLabel);
}
}
}
}
}
// train full models
Console.WriteLine("Treniram klasifikacijske modele...");
models.Clear();
SvmMulticlassClassifier <string> svmFull = new SvmMulticlassClassifier <string>();
models.Add(new Pair <string, IModel <string> >("SVM", svmFull));
//NearestCentroidClassifier<string> nccFull = new NearestCentroidClassifier<string>();
//nccFull.Similarity = new ManhattanSimilarity();
//models.Add(new Pair<string, IModel<string>>("NCC", nccFull));
foreach (Pair <string, IModel <string> > modelInfo in models) // iterate over different classifiers
{
Console.WriteLine("Kasifikacijski model: {0}...", modelInfo.First);
IModel <string> model = modelInfo.Second;
foreach (ClassType classType in new ClassType[] { ClassType.AuthorName, ClassType.AuthorAge, ClassType.AuthorEducation, ClassType.AuthorGender, ClassType.AuthorLocation }) // iterate over different class types
{
Console.WriteLine("Ciljni razred: {0}...", classType);
LabeledDataset <string, SparseVector <double> > nrmDataset = CreateNormalizedDataset(dataset, classType);
nrmDataset.Shuffle(rnd);
LabeledDataset <string, SparseVector <double> > trainSet, testSet;
for (int foldNum = 1; foldNum <= 10; foldNum++)
{
Console.WriteLine("Sklop " + foldNum + " / 10...");
nrmDataset.SplitForCrossValidation(/*numFolds=*/ 10, foldNum, out trainSet, out testSet);
backupCfy.Train(trainSet);
// if there is only one class in trainSet, switch to MajorityClassifier
if (((IEnumerable <LabeledExample <string, SparseVector <double> > >)trainSet).Select(x => x.Label).Distinct().Count() == 1)
{
model = backupCfy;
}
else
{
string cacheFileName = Config.OutputFolder + "\\svm-" + classType + "-full-" + foldNum + ".bin";
if (model is SvmMulticlassClassifier <string> && File.Exists(cacheFileName))
{
using (BinarySerializer bs = new BinarySerializer(cacheFileName, FileMode.Open))
{
((SvmMulticlassClassifier <string>)model).Load(bs);
}
}
else
{
model.Train(trainSet);
}
#if CACHE_MODELS
if (model is SvmMulticlassFast <string> )
{
using (BinarySerializer bs = new BinarySerializer(cacheFileName, FileMode.Create))
{
model.Save(bs);
}
}
#endif
}
foreach (LabeledExample <string, SparseVector <double> > lblEx in testSet)
{
Prediction <string> pred = model.Predict(lblEx.Example);
if (pred.Count == 0)
{
pred = backupCfy.Predict(lblEx.Example);
} // if the model is unable to make a prediction, use MajorityClassifier instead
perfData.GetPerfMatrix(classType.ToString(), modelInfo.First + "\tfull", foldNum).AddCount(lblEx.Label, pred.BestClassLabel);
}
}
// save model
string modelFileName = Config.OutputFolder + "\\" + modelInfo.First + "-" + classType + ".model";
if (!File.Exists(modelFileName))
{
using (BinarySerializer bs = new BinarySerializer(modelFileName, FileMode.Create))
{
model.Train(nrmDataset);
model.Save(bs);
}
}
}
}
using (StreamWriter w = new StreamWriter(Config.OutputFolder + "\\ClassifierEval.txt"))
{
w.WriteLine("*** Macro F1 ***");
w.WriteLine();
w.WriteLine("\t" + perfData.ToString(null, PerfMetric.MacroF1));
w.WriteLine();
w.WriteLine("*** Micro F1 ***");
w.WriteLine();
w.WriteLine("\t" + perfData.ToString(null, PerfMetric.MicroF1));
w.WriteLine();
w.WriteLine("*** Macro accuracy ***");
w.WriteLine();
w.WriteLine("\t" + perfData.ToString(null, PerfMetric.MacroAccuracy));
w.WriteLine();
w.WriteLine("*** Micro accuracy ***");
w.WriteLine();
w.WriteLine("\t" + perfData.ToString(null, PerfMetric.MicroAccuracy));
}
// all done
Console.WriteLine("Koncano.");
}
static void Main(string[] args)
{
try
{
if (args.Length < 2)
{
OutputHelp();
}
else
{
int cutOff = 2;
int numIter = 50;
int numThreads = 1;
string corpusFileName = null, modelFileName = null, lexiconFileName = null;
bool verbose = false;
if (ParseParams(args, ref verbose, ref cutOff, ref numIter, ref numThreads, ref corpusFileName, ref modelFileName, ref lexiconFileName))
{
Logger logger = Logger.GetRootLogger();
if (!verbose)
{
logger.LocalLevel = Logger.Level.Off;
logger.LocalProgressOutputType = Logger.ProgressOutputType.Off;
}
else
{
logger.LocalOutputType = Logger.OutputType.Custom;
Logger.CustomOutput = new Logger.CustomOutputDelegate(delegate(string loggerName, Logger.Level level, string funcName, Exception e,
string message, object[] msgArgs) { Console.WriteLine(message, msgArgs); });
}
Corpus corpus = new Corpus();
logger.Info(/*funcName=*/ null, "Nalagam učni korpus ...");
corpus.LoadFromXmlFile(corpusFileName, /*tagLen=*/ -1);
GC.Collect();
long oldMemUse = Process.GetCurrentProcess().PrivateMemorySize64;
PatriciaTree suffixTree = new PatriciaTree();
foreach (TaggedWord word in corpus.TaggedWords)
{
suffixTree.AddWordTagPair(word.WordLower, word.Tag);
}
if (lexiconFileName != null)
{
logger.Info(/*funcName=*/ null, "Nalagam leksikon ...");
StreamReader lexReader = new StreamReader(lexiconFileName);
string lexLine;
while ((lexLine = lexReader.ReadLine()) != null)
{
string[] lexData = lexLine.Split('\t');
suffixTree.AddWordTagPair(lexData[0].ToLower(), lexData[2]);
}
lexReader.Close();
}
GC.Collect();
long memUse = Process.GetCurrentProcess().PrivateMemorySize64;
Console.WriteLine("Poraba pomnilnika (drevo končnic): {0:0.00} MB", (double)(memUse - oldMemUse) / 1048576.0);
oldMemUse = memUse;
suffixTree.PropagateTags();
GC.Collect();
memUse = Process.GetCurrentProcess().PrivateMemorySize64;
Console.WriteLine("Poraba pomnilnika (propagirane oznake): {0:0.00} MB", (double)(memUse - oldMemUse) / 1048576.0);
MaximumEntropyClassifierFast <string> model = new MaximumEntropyClassifierFast <string>();
LabeledDataset <string, BinaryVector> dataset = new LabeledDataset <string, BinaryVector>();
Dictionary <string, int> featureSpace = new Dictionary <string, int>();
logger.Info(/*funcName=*/ null, "Pripravljam vektorje značilk ...");
for (int i = 0; i < corpus.TaggedWords.Count; i++)
{
logger.ProgressFast(Logger.Level.Info, /*funcName=*/ null, "{0} / {1}", i + 1, corpus.TaggedWords.Count);
BinaryVector featureVector = corpus.GenerateFeatureVector(i, featureSpace, /*extendFeatureSpace=*/ true, suffixTree);
dataset.Add(corpus.TaggedWords[i].Tag, featureVector);
}
logger.Info(/*funcName=*/ null, "Gradim model ...");
DateTime startTime = DateTime.Now;
model.CutOff = cutOff;
model.NumThreads = numThreads;
model.NumIter = numIter;
model.Train(dataset);
TimeSpan span = DateTime.Now - startTime;
logger.Info(/*funcName=*/ null, "Trajanje gradnje modela: {0:00}:{1:00}:{2:00}.{3:000}.", span.Hours, span.Minutes, span.Seconds, span.Milliseconds);
logger.Info(/*funcName=*/ null, "Zapisujem model ...");
BinarySerializer writer = new BinarySerializer(modelFileName, FileMode.Create);
suffixTree.Save(writer);
Utils.SaveDictionary(featureSpace, writer);
model.Save(writer);
writer.Close();
logger.Info(/*funcName=*/ null, "Končano.");
}
}
}
catch (Exception exception)
{
Console.WriteLine();
Console.WriteLine("*** Nepričakovana napaka. Podrobnosti: {0}\r\n{1}", exception, exception.StackTrace);
}
}