コード例 #1
0
        private ClusteringResult CreateSingleCluster(IUnlabeledExampleCollection <SparseVector <double> > dataset)
        {
            ClusteringResult clustering = new ClusteringResult();
            Cluster          root       = new Cluster();

            for (int i = 0; i < dataset.Count; i++)
            {
                root.Items.Add(i);
            }
            clustering.AddRoot(root);
            CentroidData centroid = new CentroidData();

            centroid.Items.AddRange(root.Items);
            centroid.Update(dataset);
            centroid.UpdateCentroidLen();
            mCentroids = new ArrayList <CentroidData>();
            mCentroids.Add(centroid);
            return(clustering);
        }
コード例 #2
0
        public ClusteringResult Cluster(int numOutdated, IUnlabeledExampleCollection <SparseVector <double> > batch)
        {
            Utils.ThrowException(batch == null ? new ArgumentNullException("batch") : null);
            Utils.ThrowException(numOutdated < 0 ? new ArgumentOutOfRangeException("numOutdated") : null);
            if (mDataset == null)
            {
                // initialize
                mLogger.Trace("Cluster", "Initializing ...");
                Utils.ThrowException(numOutdated > 0 ? new ArgumentOutOfRangeException("numOutdated") : null);
                //Utils.ThrowException(batch.Count == 0 ? new ArgumentValueException("batch") : null);
                if (batch.Count == 0)
                {
                    return(new ClusteringResult());
                }
                kMeans(batch, Math.Min(mK, batch.Count));
                mDataset = new UnlabeledDataset <SparseVector <double> >(batch);
                foreach (CentroidData centroid in mCentroids)
                {
                    centroid.Tag = mTopicId++;
                }
                //OutputState();
            }
            else
            {
                // update clusters
                Utils.ThrowException(numOutdated > mDataset.Count ? new ArgumentOutOfRangeException("numOutdated") : null);
                if (numOutdated == 0 && batch.Count == 0)
                {
                    return(GetClusteringResult());
                }
                mLogger.Trace("Cluster", "Updating clusters ...");
                // assign new instances
                double dummy;
                Assign(mCentroids, ModelUtils.GetTransposedMatrix(batch), batch.Count, /*offs=*/ mDataset.Count, out dummy);
                mDataset.AddRange(batch);
                // remove outdated instances
                foreach (CentroidData centroid in mCentroids)
                {
                    foreach (int item in centroid.CurrentItems)
                    {
                        if (item >= numOutdated)
                        {
                            centroid.Items.Add(item);
                        }
                    }
                    centroid.Update(mDataset);
                    centroid.UpdateCentroidLen();
                }
                mDataset.RemoveRange(0, numOutdated);
                ArrayList <CentroidData> centroidsNew = new ArrayList <CentroidData>(mCentroids.Count);
                foreach (CentroidData centroid in mCentroids)
                {
                    if (centroid.CurrentItems.Count > 0)
                    {
                        centroidsNew.Add(centroid);
                        Set <int> tmp = new Set <int>();
                        foreach (int idx in centroid.CurrentItems)
                        {
                            tmp.Add(idx - numOutdated);
                        }
                        centroid.CurrentItems.Inner.SetItems(tmp);
                    }
                }
                if (centroidsNew.Count == 0) // reset
                {
                    mCentroids = null;
                    mDataset   = null;
                    return(new ClusteringResult());
                }
                mCentroids = centroidsNew;
                // execute main loop
                kMeansMainLoop(mDataset, mCentroids);
                //OutputState();
            }
            // adjust k
            double minQual; // *** not used at the moment
            int    minQualIdx;
            double qual = GetClustQual(out minQual, out minQualIdx);

            if (qual < mQualThresh)
            {
                while (qual < mQualThresh) // split cluster at minQualIdx
                {
                    mLogger.Trace("Cluster", "Increasing k to {0} ...", mCentroids.Count + 1);
                    mCentroids.Add(mCentroids[minQualIdx].Clone());
                    mCentroids.Last.Tag = mTopicId++;
                    kMeansMainLoop(mDataset, mCentroids);
                    if (mCentroids.Last.CurrentItems.Count > mCentroids[minQualIdx].CurrentItems.Count)
                    {
                        // swap topic identifiers
                        object tmp = mCentroids.Last.Tag;
                        mCentroids.Last.Tag        = mCentroids[minQualIdx].Tag;
                        mCentroids[minQualIdx].Tag = tmp;
                    }
                    qual = GetClustQual(out minQual, out minQualIdx);
                    //OutputState();
                }
            }
            else if (numOutdated > 0)
            {
                while (qual > mQualThresh && mCentroids.Count > 1) // join clusters
                {
                    mLogger.Trace("Cluster", "Decreasing k to {0} ...", mCentroids.Count - 1);
                    ArrayList <CentroidData> centroidsCopy = mCentroids.DeepClone();
                    if (mCentroids.Count == 2) // create single cluster
                    {
                        object topicId = mCentroids[0].CurrentItems.Count > mCentroids[1].CurrentItems.Count ? mCentroids[0].Tag : mCentroids[1].Tag;
                        mCentroids = new ArrayList <CentroidData>();
                        mCentroids.Add(new CentroidData());
                        for (int i = 0; i < mDataset.Count; i++)
                        {
                            mCentroids.Last.Items.Add(i);
                        }
                        mCentroids.Last.Tag = topicId;
                        mCentroids.Last.Update(mDataset);
                        mCentroids.Last.UpdateCentroidLen();
                    }
                    else
                    {
                        int idx1, idx2;
                        GetMostSimilarClusters(out idx1, out idx2);
                        CentroidData c1      = mCentroids[idx1];
                        CentroidData c2      = mCentroids[idx2];
                        object       topicId = c1.CurrentItems.Count > c2.CurrentItems.Count ? c1.Tag : c2.Tag;
                        mCentroids.RemoveAt(idx2);
                        c1.Items.AddRange(c1.CurrentItems);
                        c1.Items.AddRange(c2.CurrentItems);
                        c1.Tag = topicId;
                        c1.Update(mDataset);
                        c1.UpdateCentroidLen();
                        kMeansMainLoop(mDataset, mCentroids);
                    }
                    qual = GetClustQual();
                    if (qual >= mQualThresh)
                    {
                        mLogger.Trace("Cluster", "Accepted solution at k = {0}.", mCentroids.Count);
                    }
                    else
                    {
                        mCentroids = centroidsCopy;
                    }
                    //OutputState();
                }
            }
            OutputState();
            return(GetClusteringResult());
        }