/**
* Single row scoring, on properly ordered data. Will return NaN if any data element contains a
* NaN. Returns the cluster-number, which is mostly an internal value. Last data element refers to
* the response variable, which is not used for k-means.
*/
@Override
protected double score0(double[] data) {
for (int i = 0; i < data.length - 1; i++) { // Normalize the data before scoring
ValueArray.Column C = _va._cols[i];
double d = data[i];
if (_normalized) {
d -= C._mean;
if (C._sigma != 0.0 && !Double.isNaN(C._sigma)) d /= C._sigma;
}
data[i] = d;
}
data[data.length - 1] = Double.NaN; // Response variable column not used
return KMeans.closest(_clusters, data, new ClusterDist())._cluster;
}
@Override
public void map(Key key) {
_rows = new long[_clusters.length];
_dist = new double[_clusters.length];
assert key.home();
ValueArray va = DKV.get(_arykey).get();
AutoBuffer bits = va.getChunk(key);
int rows = va.rpc(ValueArray.getChunkIndex(key));
double[] values = new double[_cols.length - 1];
ClusterDist cd = new ClusterDist();
for (int row = 0; row < rows; row++) {
KMeans.datad(va, bits, row, _cols, _normalized, values);
KMeans.closest(_clusters, values, cd);
_rows[cd._cluster]++;
_dist[cd._cluster] += cd._dist;
}
_arykey = null;
_cols = null;
_clusters = null;
}
/**
* Creates a new ValueArray with classes. New ValueArray is not aligned with source one
* unfortunately so have to send results to each chunk owner using Atomic.
*/
@Override
public void map(Key key) {
assert key.home();
if (Job.isRunning(_job.self())) {
ValueArray va = DKV.get(_arykey).get();
AutoBuffer bits = va.getChunk(key);
long startRow = va.startRow(ValueArray.getChunkIndex(key));
int rows = va.rpc(ValueArray.getChunkIndex(key));
int rpc = (int) (ValueArray.CHUNK_SZ / ROW_SIZE);
long chunk = ValueArray.chknum(startRow, va.numRows(), ROW_SIZE);
long updatedChk = chunk;
long updatedRow = startRow;
double[] values = new double[_cols.length - 1];
ClusterDist cd = new ClusterDist();
int[] clusters = new int[rows];
int count = 0;
for (int row = 0; row < rows; row++) {
KMeans.datad(va, bits, row, _cols, _normalized, values);
KMeans.closest(_clusters, values, cd);
chunk = ValueArray.chknum(startRow + row, va.numRows(), ROW_SIZE);
if (chunk != updatedChk) {
updateClusters(clusters, count, updatedChk, va.numRows(), rpc, updatedRow);
updatedChk = chunk;
updatedRow = startRow + row;
count = 0;
}
clusters[count++] = cd._cluster;
}
if (count > 0) updateClusters(clusters, count, chunk, va.numRows(), rpc, updatedRow);
_job.updateProgress(1);
}
_job = null;
_arykey = null;
_cols = null;
_clusters = null;
}