@Override
public void reduce(DRemoteTask rt) {
KMeansScore kms = (KMeansScore) rt;
if (_rows == null) {
_rows = kms._rows;
_dist = kms._dist;
} else {
Utils.add(_rows, kms._rows);
Utils.add(_dist, kms._dist);
}
}
public static byte [] unzipBytes(byte [] bs, Compression cmp) {
InputStream is = null;
int off = 0;
try {
switch(cmp) {
case NONE: // No compression
return bs;
case ZIP: {
ZipInputStream zis = new ZipInputStream(new ByteArrayInputStream(bs));
ZipEntry ze = zis.getNextEntry(); // Get the *FIRST* entry
// There is at least one entry in zip file and it is not a directory.
if( ze != null && !ze.isDirectory() ) {
is = zis;
break;
}
zis.close();
return bs; // Don't crash, ignore file if cannot unzip
}
case GZIP:
is = new GZIPInputStream(new ByteArrayInputStream(bs));
break;
default:
assert false:"cmp = " + cmp;
}
// If reading from a compressed stream, estimate we can read 2x uncompressed
assert( is != null ):"is is NULL, cmp = " + cmp;
bs = new byte[bs.length * 2];
// Now read from the (possibly compressed) stream
while( off < bs.length ) {
int len = is.read(bs, off, bs.length - off);
if( len < 0 )
break;
off += len;
if( off == bs.length ) { // Dataset is uncompressing alot! Need more space...
if( bs.length >= ValueArray.CHUNK_SZ )
break; // Already got enough
bs = Arrays.copyOf(bs, bs.length * 2);
}
}
} catch( IOException ioe ) { // Stop at any io error
Log.err(ioe);
} finally {
Utils.close(is);
}
return bs;
}
/**
* Simple GLM wrapper to enable launching GLM from command line.
*
* <p>Example input: java -jar target/h2o.jar -name=test -runMethod water.util.GLMRunner
* -file=smalldata/logreg/prostate.csv -y=CAPSULE -family=binomial
*
* @param args
* @throws InterruptedException
*/
public static void main(String[] args) throws InterruptedException {
try {
GLMArgs ARGS = new GLMArgs();
new Arguments(args).extract(ARGS);
System.out.println("==================<GLMRunner START>===================");
ValueArray ary = Utils.loadAndParseKey(ARGS.file);
int ycol;
try {
ycol = Integer.parseInt(ARGS.y);
} catch (NumberFormatException e) {
ycol = ary.getColumnIds(new String[] {ARGS.y})[0];
}
int ncols = ary.numCols();
if (ycol < 0 || ycol >= ary.numCols()) {
System.err.println("invalid y column: " + ycol);
H2O.exit(-1);
}
int[] xcols;
if (ARGS.xs.equalsIgnoreCase("all")) {
xcols = new int[ncols - 1];
for (int i = 0; i < ycol; ++i) xcols[i] = i;
for (int i = ycol; i < ncols - 1; ++i) xcols[i] = i + 1;
} else {
System.out.println("xs = " + ARGS.xs);
String[] names = ARGS.xs.split(",");
xcols = new int[names.length];
try {
for (int i = 0; i < names.length; ++i) xcols[i] = Integer.valueOf(names[i]);
} catch (NumberFormatException e) {
xcols = ary.getColumnIds(ARGS.xs.split(","));
}
}
for (int x : xcols)
if (x < 0) {
System.err.println("Invalid predictor specification " + ARGS.xs);
H2O.exit(-1);
}
GLMJob j =
DGLM.startGLMJob(
DGLM.getData(ary, xcols, ycol, null, true),
new ADMMSolver(ARGS.lambda, ARGS._alpha),
new GLMParams(Family.valueOf(ARGS.family)),
null,
ARGS.xval,
true);
System.out.print("[GLM] computing model...");
int progress = 0;
while (!j.isDone()) {
int p = (int) (100 * j.progress());
int dots = p - progress;
progress = p;
for (int i = 0; i < dots; ++i) System.out.print('.');
Thread.sleep(250);
}
Log.debug(Sys.GENLM, "DONE.");
GLMModel m = j.get();
String[] colnames = ary.colNames();
System.out.println("Intercept" + " = " + m._beta[ncols - 1]);
for (int i = 0; i < xcols.length; ++i) {
System.out.println(colnames[i] + " = " + m._beta[i]);
}
} catch (Throwable t) {
Log.err(t);
} finally { // we're done. shutdown the cloud
Log.debug(Sys.GENLM, "==================<GLMRunner DONE>===================");
UDPRebooted.suicide(UDPRebooted.T.shutdown, H2O.SELF);
}
}
