protected void testScalarExpression(String expr, double result) {
Key key = executeExpression(expr);
ValueArray va = ValueArray.value(key);
assertEquals(va.numRows(), 1);
assertEquals(va.numCols(), 1);
assertEquals(result, va.datad(0, 0), 0.0);
UKV.remove(key);
}
// Test kaggle/creditsample-test data
@org.junit.Test
public void kaggle_credit() {
Key okey = loadAndParseFile("credit.hex", "smalldata/kaggle/creditsample-training.csv.gz");
UKV.remove(Key.make("smalldata/kaggle/creditsample-training.csv.gz_UNZIPPED"));
UKV.remove(Key.make("smalldata\\kaggle\\creditsample-training.csv.gz_UNZIPPED"));
ValueArray val = DKV.get(okey).get();
// Check parsed dataset
final int n = new int[] {4, 2, 1}[ValueArray.LOG_CHK - 20];
assertEquals("Number of chunks", n, val.chunks());
assertEquals("Number of rows", 150000, val.numRows());
assertEquals("Number of cols", 12, val.numCols());
// setup default values for DRF
int ntrees = 3;
int depth = 30;
int gini = StatType.GINI.ordinal();
int seed = 42;
StatType statType = StatType.values()[gini];
final int cols[] =
new int[] {0, 2, 3, 4, 5, 7, 8, 9, 10, 11, 1}; // ignore column 6, classify column 1
// Start the distributed Random Forest
final Key modelKey = Key.make("model");
DRFJob result =
hex.rf.DRF.execute(
modelKey,
cols,
val,
ntrees,
depth,
1024,
statType,
seed,
true,
null,
-1,
Sampling.Strategy.RANDOM,
1.0f,
null,
0,
0,
false);
// Wait for completion on all nodes
RFModel model = result.get();
assertEquals("Number of classes", 2, model.classes());
assertEquals("Number of trees", ntrees, model.size());
model.deleteKeys();
UKV.remove(modelKey);
UKV.remove(okey);
}
public static Response redirect(JsonObject fromPageResponse, Key rfModelKey) {
RFModel rfModel = DKV.get(rfModelKey).get();
ValueArray data = DKV.get(rfModel._dataKey).get();
return redirect(
fromPageResponse,
null,
rfModelKey,
rfModel._dataKey,
rfModel._totalTrees,
data.numCols() - 1,
null,
true,
false);
}
/*@org.junit.Test*/ public void covtype() {
// Key okey = loadAndParseFile("covtype.hex", "smalldata/covtype/covtype.20k.data");
// Key okey = loadAndParseFile("covtype.hex", "../datasets/UCI/UCI-large/covtype/covtype.data");
// Key okey = loadAndParseFile("covtype.hex", "/home/0xdiag/datasets/standard/covtype.data");
Key okey = loadAndParseFile("mnist.hex", "smalldata/mnist/mnist8m.10k.csv.gz");
// Key okey = loadAndParseFile("mnist.hex", "/home/0xdiag/datasets/mnist/mnist8m.csv");
ValueArray val = UKV.get(okey);
// setup default values for DRF
int ntrees = 8;
int depth = 999;
int gini = StatType.ENTROPY.ordinal();
int seed = 42;
StatType statType = StatType.values()[gini];
final int cols[] = new int[val.numCols()];
for (int i = 1; i < cols.length; i++) cols[i] = i - 1;
cols[cols.length - 1] = 0; // Class is in column 0 for mnist
// Start the distributed Random Forest
final Key modelKey = Key.make("model");
DRFJob result =
hex.rf.DRF.execute(
modelKey,
cols,
val,
ntrees,
depth,
1024,
statType,
seed,
true,
null,
-1,
Sampling.Strategy.RANDOM,
1.0f,
null,
0,
0,
false);
// Wait for completion on all nodes
RFModel model = result.get();
assertEquals("Number of classes", 10, model.classes());
assertEquals("Number of trees", ntrees, model.size());
model.deleteKeys();
UKV.remove(modelKey);
UKV.remove(okey);
}
/**
* 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);
}
}
public void testDataFrameStructure(Key k, int rows, int cols) {
ValueArray v = ValueArray.value(k);
assertEquals(v.numRows(), rows);
assertEquals(v.numCols(), cols);
}
