/**
* Delete v1, v2 after potential modifying operations during processing: enums and/or train/test
* adaptation.
*/
private void simpleCMTest(
Frame v1,
Frame v2,
String[] actualDomain,
String[] predictedDomain,
String[] expectedDomain,
double[][] expectedCM,
boolean debug,
boolean toEnum) {
Scope.enter();
try {
ConfusionMatrix cm = buildCM(v1.vecs()[0].toEnum(), v2.vecs()[0].toEnum());
// -- DEBUG --
if (debug) {
System.err.println("actual : " + Arrays.toString(actualDomain));
System.err.println("predicted : " + Arrays.toString(predictedDomain));
System.err.println("CM domain : " + Arrays.toString(cm._domain));
System.err.println("expected CM domain: " + Arrays.toString(expectedDomain) + "\n");
for (int i = 0; i < cm._cm.length; i++) System.err.println(Arrays.toString(cm._cm[i]));
System.err.println("");
System.err.println(cm.toASCII());
}
// -- -- --
assertCMEqual(expectedDomain, expectedCM, cm);
} finally {
if (v1 != null) v1.delete();
if (v2 != null) v2.delete();
Scope.exit();
}
}
private void simpleCMTest(
String f1,
String f2,
String[] expectedActualDomain,
String[] expectedPredictDomain,
String[] expectedDomain,
double[][] expectedCM,
boolean debug,
boolean toEnum) {
try {
Frame v1 = parseFrame(Key.make("v1.hex"), find_test_file(f1));
Frame v2 = parseFrame(Key.make("v2.hex"), find_test_file(f2));
v2 = v1.makeCompatible(v2);
simpleCMTest(
v1,
v2,
expectedActualDomain,
expectedPredictDomain,
expectedDomain,
expectedCM,
debug,
toEnum);
} catch (IOException e) {
e.printStackTrace();
}
}
@Override
public void map(Chunk[] ix, NewChunk[] ncs) {
final Vec[] vecs = new Vec[_cols.length];
final Vec anyv = _base.anyVec();
final long nrow = anyv.length();
long r = ix[0].at80(0);
int last_ci = anyv.elem2ChunkIdx(r < nrow ? r : 0); // memoize the last chunk index
long last_c0 = anyv._espc[last_ci]; // ... last chunk start
long last_c1 = anyv._espc[last_ci + 1]; // ... last chunk end
Chunk[] last_cs = new Chunk[vecs.length]; // ... last chunks
for (int c = 0; c < _cols.length; c++) {
vecs[c] = _base.vecs()[_cols[c]];
last_cs[c] = vecs[c].elem2BV(last_ci);
}
for (int i = 0; i < ix[0]._len; i++) {
// select one row
r = ix[0].at80(i) - 1; // next row to select
if (r < 0) continue;
if (r >= nrow) {
for (int c = 0; c < vecs.length; c++) ncs[c].addNum(Double.NaN);
} else {
if (r < last_c0 || r >= last_c1) {
last_ci = anyv.elem2ChunkIdx(r);
last_c0 = anyv._espc[last_ci];
last_c1 = anyv._espc[last_ci + 1];
for (int c = 0; c < vecs.length; c++) last_cs[c] = vecs[c].elem2BV(last_ci);
}
for (int c = 0; c < vecs.length; c++) ncs[c].addNum(last_cs[c].at(r));
}
}
}
@Override
Val apply(Env env, Env.StackHelp stk, AST asts[]) {
Val v = stk.track(asts[1].exec(env));
if (v instanceof ValRow) {
ValRow vv = (ValRow) v;
return vv.slice(asts[2].columns(vv._names));
}
Frame fr = v.getFrame();
int[] cols = asts[2].columns(fr.names());
Frame fr2 = new Frame();
if (cols.length == 0) { // Empty inclusion list?
} else if (cols[0] >= 0) { // Positive (inclusion) list
if (cols[cols.length - 1] > fr.numCols())
throw new IllegalArgumentException(
"Column must be an integer from 0 to " + (fr.numCols() - 1));
for (int col : cols) fr2.add(fr.names()[col], fr.vecs()[col]);
} else { // Negative (exclusion) list
fr2 = new Frame(fr); // All of them at first
Arrays.sort(cols); // This loop depends on the values in sorted order
for (int col : cols)
if (0 <= -col - 1 && -col - 1 < fr.numCols()) fr2.remove(-col - 1); // Remove named column
}
return new ValFrame(fr2);
}
@Test
public void testAggregatorBinary() {
CreateFrame cf = new CreateFrame();
cf.rows = 1000;
cf.cols = 10;
cf.categorical_fraction = 0.6;
cf.integer_fraction = 0.0;
cf.binary_fraction = 0.0;
cf.real_range = 100;
cf.integer_range = 100;
cf.missing_fraction = 0.1;
cf.factors = 5;
cf.seed = 1234;
Frame frame = cf.execImpl().get();
AggregatorModel.AggregatorParameters parms = new AggregatorModel.AggregatorParameters();
parms._train = frame._key;
parms._radius_scale = 1.0;
parms._transform = DataInfo.TransformType.NORMALIZE;
parms._categorical_encoding = Model.Parameters.CategoricalEncodingScheme.Binary;
long start = System.currentTimeMillis();
AggregatorModel agg = new Aggregator(parms).trainModel().get(); // 0.905
System.out.println(
"AggregatorModel finished in: "
+ (System.currentTimeMillis() - start) / 1000.
+ " seconds");
agg.checkConsistency();
Frame output = agg._output._output_frame.get();
System.out.println(output.toTwoDimTable(0, 10));
Log.info("Number of exemplars: " + agg._exemplars.length);
// Assert.assertTrue(agg._exemplars.length==649);
output.remove();
frame.remove();
agg.remove();
}
private static void assertRowFrameEquals(double[] expected, Frame actual) {
assertEquals(1, actual.numRows());
assertEquals(expected.length, actual.numCols());
for (int i = 0; i < expected.length; i++) {
assertEquals("Wrong sum in column " + actual.name(i), expected[i], actual.vec(i).at(0), 1e-8);
}
}
@Override
public Response serve() {
Frame fr = DKV.get(data_key.value()).get();
if (fr == null) return RequestServer._http404.serve();
// Build a frame with the selected Vecs
Frame fr2 = new Frame(new String[0], new Vec[0]);
int[] idxs = vecs.value();
for (int idx : idxs) // The selected frame columns
fr2.add(fr._names[idx], fr._vecs[idx]);
// Add the class-vec last
Vec cvec = class_vec.value();
fr2.add(fr._names[class_vec._colIdx.get()], cvec);
domain = cvec.domain(); // Class/enum/factor names
mtrys = features.value() == null ? (int) (Math.sqrt(idxs.length) + 0.5) : features.value();
DRF drf =
DRF.start(
DRF.makeKey(),
fr2,
depth.value(),
ntrees.value(),
mtrys,
sample_rate.value(),
seed.value());
drf.get(); // Block for result
cm = drf.cm(); // Get CM result
return new Response(Response.Status.done, this, -1, -1, null);
}
@Test
public void testBasicDdply() {
Frame fr = null;
String tree =
"(ddply hex [1] { x . (mean (cols x 2) TRUE)})"; // Group-By on col 1 (not 0) mean of col 2
try {
fr = chkTree(tree, "smalldata/iris/iris_wheader.csv");
chkDim(fr, 2, 23);
chkFr(fr, 0, 0, 2.0); // Group 2.0, mean is 3.5
chkFr(fr, 1, 0, 3.5);
chkFr(fr, 0, 1, 2.2); // Group 2.2, mean is 4.5
chkFr(fr, 1, 1, 4.5);
chkFr(fr, 0, 7, 2.8); // Group 2.8, mean is 5.043, largest group
chkFr(fr, 1, 7, 5.042857142857143);
chkFr(fr, 0, 22, 4.4); // Group 4.4, mean is 1.5, last group
chkFr(fr, 1, 22, 1.5);
fr.delete();
fr =
chkTree(
"(ddply hex [1] { x . (sum (* (cols x 2) (cols x 3)))})",
"smalldata/iris/iris_wheader.csv");
chkDim(fr, 2, 23);
} finally {
if (fr != null) fr.delete();
Keyed.remove(Key.make("hex"));
}
}
@Test
public void testCatGroup() {
Frame fr = null;
String tree =
"(GB hex [4] nrow 0 \"all\" mean 2 \"all\")"; // Group-By on col 4, no order-by, nrow and
// mean of col 2
try {
fr = chkTree(tree, "smalldata/iris/iris_wheader.csv");
chkDim(fr, 3, 3);
chkFr(fr, 0, 0, "Iris-setosa");
chkFr(fr, 1, 0, 50);
chkFr(fr, 2, 0, 1.464);
chkFr(fr, 0, 1, "Iris-versicolor");
chkFr(fr, 1, 1, 50);
chkFr(fr, 2, 1, 4.26);
chkFr(fr, 0, 2, "Iris-virginica");
chkFr(fr, 1, 2, 50);
chkFr(fr, 2, 2, 5.552);
fr.delete();
fr = chkTree("(GB hex [1] mode 4 \"all\" )", "smalldata/iris/iris_wheader.csv");
chkDim(fr, 2, 23);
} finally {
if (fr != null) fr.delete();
Keyed.remove(Key.make("hex"));
}
}
@Test
public void testAllAggs() {
Frame fr = null;
try {
String tree =
"(GB hex [4] nrow 0 \"rm\" mean 1 \"rm\" sum 1 \"rm\" min 1 \"rm\" max 1 \"rm\" )";
fr = chkTree(tree, "smalldata/iris/iris_wheader.csv");
chkDim(fr, 6, 3);
chkFr(fr, 0, 0, "Iris-setosa");
chkFr(fr, 1, 0, 50); // nrow
chkFr(fr, 2, 0, 3.418); // mean
chkFr(fr, 3, 0, 170.9); // sum
chkFr(fr, 4, 0, 2.3); // min
chkFr(fr, 5, 0, 4.4); // max
chkFr(fr, 0, 1, "Iris-versicolor");
chkFr(fr, 1, 1, 50); // nrow
chkFr(fr, 2, 1, 2.770); // mean
chkFr(fr, 3, 1, 138.5); // sum
chkFr(fr, 4, 1, 2.0); // min
chkFr(fr, 5, 1, 3.4); // max
chkFr(fr, 0, 2, "Iris-virginica");
chkFr(fr, 1, 2, 50); // nrow
chkFr(fr, 2, 2, 2.974); // mean
chkFr(fr, 3, 2, 148.7); // sum
chkFr(fr, 4, 2, 2.2); // min
chkFr(fr, 5, 2, 3.8); // max
} finally {
if (fr != null) fr.delete();
Keyed.remove(Key.make("hex"));
}
}
private static void assertColFrameEquals(double[] expected, Frame actual) {
assertEquals(1, actual.numCols());
assertEquals(expected.length, actual.numRows());
for (int i = 0; i < expected.length; i++) {
assertEquals("Wrong sum in row " + i, expected[i], actual.vec(0).at(i), 1e-8);
}
}
// Adapt a trained model to a test dataset with different enums
/*@Test*/ public void testModelAdapt() {
File file1 = TestUtil.find_test_file("./smalldata/kaggle/KDDTrain.arff.gz");
Key fkey1 = NFSFileVec.make(file1);
Key dest1 = Key.make("KDDTrain.hex");
File file2 = TestUtil.find_test_file("./smalldata/kaggle/KDDTest.arff.gz");
Key fkey2 = NFSFileVec.make(file2);
Key dest2 = Key.make("KDDTest.hex");
GBM gbm = null;
Frame fr = null;
try {
gbm = new GBM();
gbm.source = ParseDataset2.parse(dest1, new Key[] {fkey1});
UKV.remove(fkey1);
gbm.response = gbm.source.remove(41); // Response is col 41
gbm.ntrees = 2;
gbm.max_depth = 8;
gbm.learn_rate = 0.2f;
gbm.min_rows = 10;
gbm.nbins = 50;
gbm.invoke();
// The test data set has a few more enums than the train
Frame ftest = ParseDataset2.parse(dest2, new Key[] {fkey2});
Frame preds = gbm.score(ftest);
} finally {
UKV.remove(dest1); // Remove original hex frame key
if (gbm != null) {
UKV.remove(gbm.dest()); // Remove the model
UKV.remove(gbm.response._key);
gbm.remove(); // Remove GBM Job
if (fr != null) fr.remove();
}
}
}
static Frame exec_str(String str, String id) {
Val val = Exec.exec(str);
switch (val.type()) {
case Val.FRM:
Frame fr = val.getFrame();
Key k = Key.make(id);
// Smart delete any prior top-level result
Iced i = DKV.getGet(k);
if (i instanceof Lockable) ((Lockable) i).delete();
else if (i instanceof Keyed) ((Keyed) i).remove();
else if (i != null)
throw new IllegalArgumentException("Attempting to overright an unexpected key");
DKV.put(fr = new Frame(k, fr._names, fr.vecs()));
System.out.println(fr);
checkSaneFrame();
return fr;
case Val.NUM:
System.out.println("num= " + val.getNum());
assert id == null;
checkSaneFrame();
return null;
case Val.STR:
System.out.println("str= " + val.getStr());
assert id == null;
checkSaneFrame();
return null;
default:
throw water.H2O.fail();
}
}
@Test
public void testExpandCatsIris() throws InterruptedException, ExecutionException {
double[][] iris =
ard(
ard(6.3, 2.5, 4.9, 1.5, 1),
ard(5.7, 2.8, 4.5, 1.3, 1),
ard(5.6, 2.8, 4.9, 2.0, 2),
ard(5.0, 3.4, 1.6, 0.4, 0),
ard(6.0, 2.2, 5.0, 1.5, 2));
double[][] iris_expandR =
ard(
ard(0, 1, 0, 6.3, 2.5, 4.9, 1.5),
ard(0, 1, 0, 5.7, 2.8, 4.5, 1.3),
ard(0, 0, 1, 5.6, 2.8, 4.9, 2.0),
ard(1, 0, 0, 5.0, 3.4, 1.6, 0.4),
ard(0, 0, 1, 6.0, 2.2, 5.0, 1.5));
String[] iris_cols = new String[] {"sepal_len", "sepal_wid", "petal_len", "petal_wid", "class"};
String[][] iris_domains =
new String[][] {null, null, null, null, new String[] {"setosa", "versicolor", "virginica"}};
Frame fr = null;
try {
fr = parse_test_file(Key.make("iris.hex"), "smalldata/iris/iris_wheader.csv");
DataInfo dinfo =
new DataInfo(
Key.make(),
fr,
null,
0,
true,
DataInfo.TransformType.NONE,
DataInfo.TransformType.NONE,
false,
false,
false, /* weights */
false, /* offset */
false, /* fold */
false);
Log.info("Original matrix:\n" + colFormat(iris_cols, "%8.7s") + ArrayUtils.pprint(iris));
double[][] iris_perm = ArrayUtils.permuteCols(iris, dinfo._permutation);
Log.info(
"Permuted matrix:\n"
+ colFormat(iris_cols, "%8.7s", dinfo._permutation)
+ ArrayUtils.pprint(iris_perm));
double[][] iris_exp = GLRM.expandCats(iris_perm, dinfo);
Log.info(
"Expanded matrix:\n"
+ colExpFormat(iris_cols, iris_domains, "%8.7s", dinfo._permutation)
+ ArrayUtils.pprint(iris_exp));
Assert.assertArrayEquals(iris_expandR, iris_exp);
} catch (Throwable t) {
t.printStackTrace();
throw new RuntimeException(t);
} finally {
if (fr != null) fr.delete();
}
}
@Override
protected void init() {
if (validation != null && n_folds != 0)
throw new UnsupportedOperationException(
"Cannot specify a validation dataset and non-zero number of cross-validation folds.");
if (n_folds < 0)
throw new UnsupportedOperationException(
"The number of cross-validation folds must be >= 0.");
super.init();
xval_models = new Key[n_folds];
for (int i = 0; i < xval_models.length; ++i)
xval_models[i] = Key.make(dest().toString() + "_xval" + i);
int rIndex = 0;
for (int i = 0; i < source.vecs().length; i++)
if (source.vecs()[i] == response) {
rIndex = i;
break;
}
_responseName = source._names != null && rIndex >= 0 ? source._names[rIndex] : "response";
_train = selectVecs(source);
_names = new String[cols.length];
for (int i = 0; i < cols.length; i++) _names[i] = source._names[cols[i]];
// Compute source response domain
if (classification) _sourceResponseDomain = getVectorDomain(response);
// Is validation specified?
if (validation != null) {
// Extract a validation response
int idx = validation.find(source.names()[rIndex]);
if (idx == -1)
throw new IllegalArgumentException(
"Validation set does not have a response column called " + _responseName);
_validResponse = validation.vecs()[idx];
// Compute output confusion matrix domain for classification:
// - if validation dataset is specified then CM domain is union of train and validation
// response domains
// else it is only domain of response column.
if (classification) {
_validResponseDomain = getVectorDomain(_validResponse);
if (_validResponseDomain != null) {
_cmDomain = Utils.domainUnion(_sourceResponseDomain, _validResponseDomain);
if (!Arrays.deepEquals(_sourceResponseDomain, _validResponseDomain)) {
_fromModel2CM =
Model.getDomainMapping(
_cmDomain,
_sourceResponseDomain,
false); // transformation from model produced response ~> cmDomain
_fromValid2CM =
Model.getDomainMapping(
_cmDomain,
_validResponseDomain,
false); // transformation from validation response domain ~> cmDomain
}
} else _cmDomain = _sourceResponseDomain;
} /* end of if classification */
} else if (classification) _cmDomain = _sourceResponseDomain;
}
/**
* Annotate the number of columns and rows of the validation data set in the job parameter JSON
* @return JsonObject annotated with num_cols and num_rows of the validation data set
*/
@Override protected JsonObject toJSON() {
JsonObject jo = super.toJSON();
if (validation != null) {
jo.getAsJsonObject("validation").addProperty("num_cols", validation.numCols());
jo.getAsJsonObject("validation").addProperty("num_rows", validation.numRows());
}
return jo;
}
public static NewChunk createNC(String fname, String[] data, int cidx, int len) {
NewChunk[] nchunks = Frame.createNewChunks(fname, Vec.T_STR, cidx);
for (int i = 0; i < len; i++) {
nchunks[0].addStr(data[i] != null ? data[i] : null);
}
Frame.closeNewChunks(nchunks);
return nchunks[0];
}
/**
* Annotate the number of columns and rows of the training data set in the job parameter JSON
* @return JsonObject annotated with num_cols and num_rows of the training data set
*/
@Override protected JsonObject toJSON() {
JsonObject jo = super.toJSON();
if (source != null) {
jo.getAsJsonObject("source").addProperty("num_cols", source.numCols());
jo.getAsJsonObject("source").addProperty("num_rows", source.numRows());
}
return jo;
}
public final Row extractDenseRow(double[] vals, Row row) {
row.bad = false;
row.rid = 0;
row.cid = 0;
if (row.weight == 0) return row;
if (_skipMissing)
for (double d : vals)
if (Double.isNaN(d)) {
row.bad = true;
return row;
}
int nbins = 0;
for (int i = 0; i < _cats; ++i) {
int c = getCategoricalId(i, Double.isNaN(vals[i]) ? _catModes[i] : (int) vals[i]);
if (c >= 0) row.binIds[nbins++] = c;
}
row.nBins = nbins;
final int n = _nums;
int numValsIdx = 0;
for (int i = 0; i < n; ++i) {
if (isInteractionVec(i)) {
int offset;
InteractionWrappedVec iwv = ((InteractionWrappedVec) _adaptedFrame.vec(_cats + i));
int v1 = _adaptedFrame.find(iwv.v1());
int v2 = _adaptedFrame.find(iwv.v2());
if (v1 < _cats)
offset = getCategoricalId(v1, Double.isNaN(vals[v1]) ? _catModes[v1] : (int) vals[v1]);
else if (v2 < _cats)
offset = getCategoricalId(v2, Double.isNaN(vals[v2]) ? _catModes[v1] : (int) vals[v2]);
else offset = 0;
row.numVals[numValsIdx + offset] = vals[_cats + i]; // essentially: vals[v1] * vals[v2])
numValsIdx += nextNumericIdx(i);
} else {
double d = vals[_cats + i]; // can be NA if skipMissing() == false
if (Double.isNaN(d)) d = _numMeans[numValsIdx];
if (_normMul != null && _normSub != null)
d = (d - _normSub[numValsIdx]) * _normMul[numValsIdx];
row.numVals[numValsIdx++] = d;
}
}
int off = responseChunkId(0);
for (int i = off; i < Math.min(vals.length, off + _responses); ++i) {
try {
row.response[i] = vals[responseChunkId(i)];
} catch (Throwable t) {
throw new RuntimeException(t);
}
if (_normRespMul != null)
row.response[i] = (row.response[i] - _normRespSub[i]) * _normRespMul[i];
if (Double.isNaN(row.response[i])) {
row.bad = true;
return row;
}
}
return row;
}
@Test
public void testColumnwisesumOnEmptyFrame() {
Frame fr = register(new Frame(Key.<Frame>make()));
Val val = Rapids.exec("(sumaxis " + fr._key + " 0 0)");
assertTrue(val instanceof ValFrame);
Frame res = register(val.getFrame());
assertEquals(res.numCols(), 0);
assertEquals(res.numRows(), 0);
}
public static NewChunk createNC(String fname, int cidx, int len) {
NewChunk[] nchunks = Frame.createNewChunks(fname, Vec.T_NUM, cidx);
int starVal = cidx * 1000;
for (int i = 0; i < len; i++) {
nchunks[0].addNum(starVal + i);
}
Frame.closeNewChunks(nchunks);
return nchunks[0];
}
protected final Frame selectFrame(Frame frame) {
Vec[] vecs = new Vec[cols.length];
String[] names = new String[cols.length];
for( int i = 0; i < cols.length; i++ ) {
vecs[i] = frame.vecs()[cols[i]];
names[i] = frame.names()[cols[i]];
}
return new Frame(names, vecs);
}
@Test
public void testCategoricalProstate() throws InterruptedException, ExecutionException {
GLRM job = null;
GLRMModel model = null;
Frame train = null;
final int[] cats = new int[] {1, 3, 4, 5}; // Categoricals: CAPSULE, RACE, DPROS, DCAPS
try {
Scope.enter();
train = parse_test_file(Key.make("prostate.hex"), "smalldata/logreg/prostate.csv");
for (int i = 0; i < cats.length; i++)
Scope.track(train.replace(cats[i], train.vec(cats[i]).toCategoricalVec())._key);
train.remove("ID").remove();
DKV.put(train._key, train);
GLRMParameters parms = new GLRMParameters();
parms._train = train._key;
parms._k = 8;
parms._gamma_x = parms._gamma_y = 0.1;
parms._regularization_x = GLRMModel.GLRMParameters.Regularizer.Quadratic;
parms._regularization_y = GLRMModel.GLRMParameters.Regularizer.Quadratic;
parms._init = GLRM.Initialization.PlusPlus;
parms._transform = DataInfo.TransformType.STANDARDIZE;
parms._recover_svd = false;
parms._max_iterations = 200;
try {
job = new GLRM(parms);
model = job.trainModel().get();
Log.info(
"Iteration "
+ model._output._iterations
+ ": Objective value = "
+ model._output._objective);
model.score(train).delete();
ModelMetricsGLRM mm = (ModelMetricsGLRM) ModelMetrics.getFromDKV(model, train);
Log.info(
"Numeric Sum of Squared Error = "
+ mm._numerr
+ "\tCategorical Misclassification Error = "
+ mm._caterr);
} catch (Throwable t) {
t.printStackTrace();
throw new RuntimeException(t);
} finally {
job.remove();
}
} catch (Throwable t) {
t.printStackTrace();
throw new RuntimeException(t);
} finally {
if (train != null) train.delete();
if (model != null) model.delete();
Scope.exit();
}
}
// private constructor called by filterExpandedColumns
private DataInfo(
DataInfo dinfo,
Frame fr,
double[] normMul,
double[] normSub,
int[][] catLevels,
int[] catModes) {
_fullCatOffsets = dinfo._catOffsets;
if (!dinfo._useAllFactorLevels) {
_fullCatOffsets = dinfo._catOffsets.clone();
for (int i = 0; i < _fullCatOffsets.length; ++i)
_fullCatOffsets[i] += i; // add for the skipped zeros.
}
_offset = dinfo._offset;
_weights = dinfo._weights;
_fold = dinfo._fold;
_valid = false;
_interactions = dinfo._interactions;
_interactionVecs = dinfo._interactionVecs;
assert dinfo._predictor_transform != null;
assert dinfo._response_transform != null;
_predictor_transform = dinfo._predictor_transform;
_response_transform = dinfo._response_transform;
_skipMissing = dinfo._skipMissing;
_imputeMissing = dinfo._imputeMissing;
_adaptedFrame = fr;
_catOffsets = MemoryManager.malloc4(catLevels.length + 1);
_catMissing = new boolean[catLevels.length];
Arrays.fill(_catMissing, !(dinfo._imputeMissing || dinfo._skipMissing));
int s = 0;
for (int i = 0; i < catLevels.length; ++i) {
_catOffsets[i] = s;
s += catLevels[i].length;
}
_catLvls = catLevels;
_catOffsets[_catOffsets.length - 1] = s;
_responses = dinfo._responses;
_cats = catLevels.length;
_nums =
fr.numCols()
- _cats
- dinfo._responses
- (_offset ? 1 : 0)
- (_weights ? 1 : 0)
- (_fold ? 1 : 0);
_numOffsets = _nums == 0 ? new int[0] : dinfo._numOffsets.clone();
int diff = _numOffsets.length > 0 ? _numOffsets[0] - s : 0;
for (int i = 0; i < _numOffsets.length; i++) // need to shift everyone down by the offset!
_numOffsets[i] -= diff;
_useAllFactorLevels = true; // dinfo._useAllFactorLevels;
_numMeans = new double[_nums];
_normMul = normMul;
_normSub = normSub;
_catModes = catModes;
for (int i = 0; i < _nums; i++) _numMeans[i] = _adaptedFrame.vec(_cats + i).mean();
}
@Override
public void compute2() {
// Lock all possible data
dataset.read_lock(jobKey);
// Create a template vector for each segment
final Vec[][] templates = makeTemplates(dataset, ratios);
final int nsplits = templates.length;
assert nsplits == ratios.length + 1 : "Unexpected number of split templates!";
// Launch number of distributed FJ for each split part
final Vec[] datasetVecs = dataset.vecs();
splits = new Frame[nsplits];
for (int s = 0; s < nsplits; s++) {
Frame split = new Frame(destKeys[s], dataset.names(), templates[s]);
split.delete_and_lock(jobKey);
splits[s] = split;
}
setPendingCount(1);
H2O.submitTask(
new H2OCountedCompleter(FrameSplitter.this) {
@Override
public void compute2() {
setPendingCount(nsplits);
for (int s = 0; s < nsplits; s++) {
new FrameSplitTask(
new H2OCountedCompleter(this) { // Completer for this task
@Override
public void compute2() {}
@Override
public boolean onExceptionalCompletion(
Throwable ex, CountedCompleter caller) {
synchronized (
FrameSplitter
.this) { // synchronized on this since can be accessed from
// different workers
workersExceptions =
workersExceptions != null
? Arrays.copyOf(workersExceptions, workersExceptions.length + 1)
: new Throwable[1];
workersExceptions[workersExceptions.length - 1] = ex;
}
tryComplete(); // we handle the exception so wait perform normal
// completion
return false;
}
},
datasetVecs,
ratios,
s)
.asyncExec(splits[s]);
}
tryComplete(); // complete the computation of nsplits-tasks
}
});
tryComplete(); // complete the computation of thrown tasks
}
// --------------------------------------------------------------------------
// Build an entire layer of all K trees
protected DHistogram[][][] buildLayer(
final Frame fr,
final int nbins,
int nbins_cats,
final DTree ktrees[],
final int leafs[],
final DHistogram hcs[][][],
boolean subset,
boolean build_tree_one_node) {
// Build K trees, one per class.
// Build up the next-generation tree splits from the current histograms.
// Nearly all leaves will split one more level. This loop nest is
// O( #active_splits * #bins * #ncols )
// but is NOT over all the data.
ScoreBuildOneTree sb1ts[] = new ScoreBuildOneTree[_nclass];
Vec vecs[] = fr.vecs();
for (int k = 0; k < _nclass; k++) {
final DTree tree = ktrees[k]; // Tree for class K
if (tree == null) continue;
// Build a frame with just a single tree (& work & nid) columns, so the
// nested MRTask ScoreBuildHistogram in ScoreBuildOneTree does not try
// to close other tree's Vecs when run in parallel.
Frame fr2 = new Frame(Arrays.copyOf(fr._names, _ncols + 1), Arrays.copyOf(vecs, _ncols + 1));
fr2.add(fr._names[idx_tree(k)], vecs[idx_tree(k)]);
fr2.add(fr._names[idx_work(k)], vecs[idx_work(k)]);
fr2.add(fr._names[idx_nids(k)], vecs[idx_nids(k)]);
if (idx_weight() >= 0) fr2.add(fr._names[idx_weight()], vecs[idx_weight()]);
// Start building one of the K trees in parallel
H2O.submitTask(
sb1ts[k] =
new ScoreBuildOneTree(
this,
k,
nbins,
nbins_cats,
tree,
leafs,
hcs,
fr2,
subset,
build_tree_one_node,
_improvPerVar,
_model._parms._distribution));
}
// Block for all K trees to complete.
boolean did_split = false;
for (int k = 0; k < _nclass; k++) {
final DTree tree = ktrees[k]; // Tree for class K
if (tree == null) continue;
sb1ts[k].join();
if (sb1ts[k]._did_split) did_split = true;
}
// The layer is done.
return did_split ? hcs : null;
}
@Test
public void testRowwisesumOnFrameWithNonnumericColumnsOnly() {
Frame fr = register(new Frame(Key.<Frame>make(), ar("c1", "s1"), aro(vc2, vs1)));
Val val = Rapids.exec("(sumaxis " + fr._key + " 1 1)");
assertTrue(val instanceof ValFrame);
Frame res = register(val.getFrame());
assertEquals("Unexpected column name", "sum", res.name(0));
assertEquals("Unexpected column type", Vec.T_NUM, res.types()[0]);
assertColFrameEquals(ard(Double.NaN, Double.NaN, Double.NaN, Double.NaN, Double.NaN), res);
}
@Test
public void testRowwisesumOnFrameWithTimeColumnsOnly() {
Frame fr = register(new Frame(Key.<Frame>make(), ar("t1", "s", "t2"), aro(vt1, vs1, vt2)));
Val val = Rapids.exec("(sumaxis " + fr._key + " 1 1)");
assertTrue(val instanceof ValFrame);
Frame res = register(val.getFrame());
assertEquals("Unexpected column name", "sum", res.name(0));
assertEquals("Unexpected column type", Vec.T_TIME, res.types()[0]);
assertColFrameEquals(ard(30000000, 30000040, 30000060, 30000080, 30000120), res);
}
@Test
public void testRowwisesumWithoutNaRm() {
Frame fr =
register(new Frame(Key.<Frame>make(), ar("i1", "d1", "d2", "d3"), aro(vi1, vd1, vd2, vd3)));
Val val = Rapids.exec("(sumaxis " + fr._key + " 0 1)");
assertTrue(val instanceof ValFrame);
Frame res = register(val.getFrame());
assertColFrameEquals(ard(1.7, 2.9, Double.NaN, 10.3, Double.NaN), res);
assertEquals("sum", res.name(0));
}
@Override
Val apply(Env env, Env.StackHelp stk, AST asts[]) {
Frame fr = stk.track(asts[1].exec(env)).getFrame();
if (fr.numCols() == 1 && fr.numRows() == 1) {
if (fr.anyVec().isNumeric() || fr.anyVec().isBad()) return new ValNum(fr.anyVec().at(0));
else if (fr.anyVec().isString())
return new ValStr(fr.anyVec().atStr(new BufferedString(), 0).toString());
return new ValStr(fr.domains()[0][(int) fr.anyVec().at8(0)]);
}
return new ValFrame(fr); // did not flatten
}
