@Test
public void testDomains() {
Frame frame = parse_test_file("smalldata/junit/weather.csv");
for (String s : new String[] {"MaxWindSpeed", "RelHumid9am", "Cloud9am"}) {
Vec v = frame.vec(s);
Vec newV = v.toCategoricalVec();
frame.remove(s);
frame.add(s, newV);
v.remove();
}
DKV.put(frame);
AggregatorModel.AggregatorParameters parms = new AggregatorModel.AggregatorParameters();
parms._train = frame._key;
parms._radius_scale = 10;
AggregatorModel agg = new Aggregator(parms).trainModel().get();
Frame output = agg._output._output_frame.get();
Assert.assertTrue(output.numRows() < 0.5 * frame.numRows());
boolean same = true;
for (int i = 0; i < frame.numCols(); ++i) {
if (frame.vec(i).isCategorical()) {
same = (frame.domains()[i].length == output.domains()[i].length);
if (!same) break;
}
}
frame.remove();
output.remove();
agg.remove();
Assert.assertFalse(same);
}
@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();
}
// @Ignore("PUBDEV-1643")
@Test
public void testDuplicatesCarsGrid() {
Grid grid = null;
Frame fr = null;
Vec old = null;
try {
fr = parse_test_file("smalldata/junit/cars_20mpg.csv");
fr.remove("name").remove(); // Remove unique id
old = fr.remove("economy");
fr.add("economy", old); // response to last column
DKV.put(fr);
// Setup random hyperparameter search space
HashMap<String, Object[]> hyperParms =
new HashMap<String, Object[]>() {
{
put("_ntrees", new Integer[] {5, 5});
put("_max_depth", new Integer[] {2, 2});
put("_mtries", new Integer[] {-1, -1});
put("_sample_rate", new Double[] {.1, .1});
}
};
// Fire off a grid search
DRFModel.DRFParameters params = new DRFModel.DRFParameters();
params._train = fr._key;
params._response_column = "economy";
// Get the Grid for this modeling class and frame
Job<Grid> gs = GridSearch.startGridSearch(null, params, hyperParms);
grid = gs.get();
// Check that duplicate model have not been constructed
Model[] models = grid.getModels();
assertTrue("Number of returned models has to be > 0", models.length > 0);
// But all off them should be same
Key<Model> modelKey = models[0]._key;
for (Model m : models) {
assertTrue("Number of constructed models has to be equal to 1", modelKey == m._key);
}
} finally {
if (old != null) {
old.remove();
}
if (fr != null) {
fr.remove();
}
if (grid != null) {
grid.remove();
}
}
}
@Test
public void testChunks() {
Frame frame = parse_test_file("smalldata/covtype/covtype.20k.data");
AggregatorModel.AggregatorParameters parms = new AggregatorModel.AggregatorParameters();
parms._train = frame._key;
parms._radius_scale = 3.0;
long start = System.currentTimeMillis();
AggregatorModel agg = new Aggregator(parms).trainModel().get(); // 0.418
System.out.println(
"AggregatorModel finished in: "
+ (System.currentTimeMillis() - start) / 1000.
+ " seconds");
agg.checkConsistency();
Frame output = agg._output._output_frame.get();
Log.info("Number of exemplars: " + agg._exemplars.length);
// Assert.assertTrue(agg._exemplars.length==1993);
output.remove();
agg.remove();
for (int i : new int[] {1, 2, 5, 10, 50, 100}) {
Key key = Key.make();
RebalanceDataSet rb = new RebalanceDataSet(frame, key, i);
H2O.submitTask(rb);
rb.join();
Frame rebalanced = DKV.get(key).get();
parms = new AggregatorModel.AggregatorParameters();
parms._train = frame._key;
parms._radius_scale = 3.0;
start = System.currentTimeMillis();
AggregatorModel agg2 =
new Aggregator(parms).trainModel().get(); // 0.373 0.504 0.357 0.454 0.368 0.355
System.out.println(
"AggregatorModel finished in: "
+ (System.currentTimeMillis() - start) / 1000.
+ " seconds");
agg2.checkConsistency();
Log.info("Number of exemplars for " + i + " chunks: " + agg2._exemplars.length);
rebalanced.delete();
Assert.assertTrue(
Math.abs(agg._exemplars.length - agg2._exemplars.length)
== 0); // < agg._exemplars.length*0);
output = agg2._output._output_frame.get();
output.remove();
agg2.remove();
}
frame.delete();
}
@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);
}
public void dropInteractions() { // only called to cleanup the InteractionWrappedVecs!
if (_interactions != null) {
Vec[] vecs = _adaptedFrame.remove(_interactionVecs);
for (Vec v : vecs) v.remove();
_interactions = null;
}
}
// 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();
}
}
}
// ==========================================================================
public void basicGBM(String fname, String hexname, PrepData prep) {
File file = TestUtil.find_test_file(fname);
if (file == null) return; // Silently abort test if the file is missing
Key fkey = NFSFileVec.make(file);
Key dest = Key.make(hexname);
GBM gbm = null;
Frame fr = null;
try {
gbm = new GBM();
gbm.source = fr = ParseDataset2.parse(dest, new Key[] {fkey});
UKV.remove(fkey);
int idx = prep.prep(fr);
if (idx < 0) {
gbm.classification = false;
idx = ~idx;
}
String rname = fr._names[idx];
gbm.response = fr.vecs()[idx];
fr.remove(idx); // Move response to the end
fr.add(rname, gbm.response);
gbm.ntrees = 4;
gbm.max_depth = 4;
gbm.min_rows = 1;
gbm.nbins = 50;
gbm.cols = new int[fr.numCols()];
for (int i = 0; i < gbm.cols.length; i++) gbm.cols[i] = i;
gbm.learn_rate = .2f;
gbm.invoke();
fr = gbm.score(gbm.source);
GBM.GBMModel gbmmodel = UKV.get(gbm.dest());
// System.out.println(gbmmodel.toJava());
} finally {
UKV.remove(dest); // 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();
}
}
}
@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();
}
}
@Test
public void testCollisionOfDRFParamsChecksum() {
Frame fr = null;
try {
fr = parse_test_file("smalldata/junit/cars.csv");
fr.remove("name").remove();
Vec old = fr.remove("economy (mpg)");
fr.add("economy (mpg)", old); // response to last column
DKV.put(fr);
// {"_model_id":null,"_train":{"name":"_83da9e0754c5eb9f6b812fe17e7945e5","type":"Key"},"_valid":null,"_nfolds":0,"_keep_cross_validation_predictions":false,"_fold_assignment":"AUTO","_distribution":"AUTO","_tweedie_power":1.5,"_ignored_columns":null,"_ignore_const_cols":true,"_weights_column":null,"_offset_column":null,"_fold_column":null,"_score_each_iteration":false,"_response_column":"economy (mpg)","_balance_classes":false,"_max_after_balance_size":5.0,"_class_sampling_factors":null,"_max_hit_ratio_k":10,"_max_confusion_matrix_size":20,"_checkpoint":null,"_ntrees":9,"_max_depth":15,"_min_rows":1.0,"_nbins":20,"_nbins_cats":1024,"_r2_stopping":0.999999,"_seed":-4522296119273841674,"_nbins_top_level":1024,"_build_tree_one_node":false,"_initial_score_interval":4000,"_score_interval":4000,"_mtries":3,"_sample_rate":0.6499997,"_binomial_double_trees":false}
DRFModel.DRFParameters params1 = new DRFModel.DRFParameters();
params1._train = fr._key;
params1._response_column = "economy (mpg)";
params1._seed = -4522296119273841674L;
params1._mtries = 3;
params1._max_depth = 15;
params1._ntrees = 9;
params1._sample_rate = 0.6499997f;
// {"_model_id":null,"_train":{"name":"_83da9e0754c5eb9f6b812fe17e7945e5","type":"Key"},"_valid":null,"_nfolds":0,"_keep_cross_validation_predictions":false,"_fold_assignment":"AUTO","_distribution":"AUTO","_tweedie_power":1.5,"_ignored_columns":null,"_ignore_const_cols":true,"_weights_column":null,"_offset_column":null,"_fold_column":null,"_score_each_iteration":false,"_response_column":"economy (mpg)","_balance_classes":false,"_max_after_balance_size":5.0,"_class_sampling_factors":null,"_max_hit_ratio_k":10,"_max_confusion_matrix_size":20,"_checkpoint":null,"_ntrees":13,"_max_depth":1,"_min_rows":1.0,"_nbins":20,"_nbins_cats":1024,"_r2_stopping":0.999999,"_seed":-4522296119273841674,"_nbins_top_level":1024,"_build_tree_one_node":false,"_initial_score_interval":4000,"_score_interval":4000,"_mtries":1,"_sample_rate":0.6499997,"_binomial_double_trees":false}
DRFModel.DRFParameters params2 = new DRFModel.DRFParameters();
params2._train = fr._key;
params2._response_column = "economy (mpg)";
params2._seed = -4522296119273841674L;
params2._mtries = 1;
params2._max_depth = 1;
params2._ntrees = 13;
params2._sample_rate = 0.6499997f;
long csum1 = params1.checksum();
long csum2 = params2.checksum();
Assert.assertNotEquals("Checksums shoudl be different", csum1, csum2);
} finally {
if (fr != null) {
fr.remove();
}
}
}
private void checkTree(String tree, boolean expectThrow) {
// Frame r = frame(new double[][]{{-1},{1},{2},{3},{4},{5},{6},{254}});
// Key ahex = Key.make("a.hex");
// Frame fr = new Frame(ahex, null, new Vec[]{r.remove(0)});
// r.delete();
// DKV.put(ahex, fr);
Frame fr = parse_test_file(Key.make("a.hex"), "smalldata/iris/iris_wheader.csv");
fr.remove(4).remove();
try {
Val val = Exec.exec(tree);
Assert.assertFalse(expectThrow);
System.out.println(val.toString());
if (val instanceof ValFrame) {
Frame fr2 = ((ValFrame) val)._fr;
System.out.println(fr2.vec(0));
fr2.remove();
}
} catch (IllegalArgumentException iae) {
if (!expectThrow) throw iae;
} finally {
fr.delete();
}
}
private void applyTrainingFrameSideEffects() {
int numCols = _modelBuilderTrain.numCols();
String responseVecName = _modelBuilderTrain.names()[numCols - 1];
Vec responseVec = _modelBuilderTrain.remove(numCols - 1);
final boolean use_weights_column = (_parms.weights_column != null);
final boolean use_start_column = (_parms.start_column != null);
if (use_weights_column) {
Vec weightsVec = _parms.weights_column;
int idxInRawFrame = _train.find(weightsVec);
if (idxInRawFrame < 0) {
throw new RuntimeException("CoxPHDriver failed to find weightVec");
}
String weightsVecName = _parms.train().names()[idxInRawFrame];
_modelBuilderTrain.add(weightsVecName, weightsVec);
}
if (use_start_column) {
Vec startVec = _parms.start_column;
int idxInRawFrame = _train.find(startVec);
if (idxInRawFrame < 0) {
throw new RuntimeException("CoxPHDriver failed to find startVec");
}
String startVecName = _parms.train().names()[idxInRawFrame];
_modelBuilderTrain.add(startVecName, startVec);
}
{
Vec stopVec = _parms.stop_column;
int idxInRawFrame = _train.find(stopVec);
if (idxInRawFrame < 0) {
throw new RuntimeException("CoxPHDriver failed to find stopVec");
}
String stopVecName = _parms.train().names()[idxInRawFrame];
_modelBuilderTrain.add(stopVecName, stopVec);
}
_modelBuilderTrain.add(responseVecName, responseVec);
}
@Test
public void testCovtype() {
Frame frame = parse_test_file("smalldata/covtype/covtype.20k.data");
AggregatorModel.AggregatorParameters parms = new AggregatorModel.AggregatorParameters();
parms._train = frame._key;
parms._radius_scale = 5.0;
long start = System.currentTimeMillis();
AggregatorModel agg = new Aggregator(parms).trainModel().get(); // 0.179
System.out.println(
"AggregatorModel finished in: "
+ (System.currentTimeMillis() - start) / 1000.
+ " seconds");
agg.checkConsistency();
frame.delete();
Frame output = agg._output._output_frame.get();
Log.info("Exemplars: " + output.toString());
output.remove();
Log.info("Number of exemplars: " + agg._exemplars.length);
// Assert.assertTrue(agg._exemplars.length==615);
agg.remove();
}
@Ignore
@Test
public void testMNIST() {
Frame frame = parse_test_file("bigdata/laptop/mnist/train.csv.gz");
AggregatorModel.AggregatorParameters parms = new AggregatorModel.AggregatorParameters();
parms._train = frame._key;
parms._radius_scale = 100.0;
long start = System.currentTimeMillis();
AggregatorModel agg = new Aggregator(parms).trainModel().get();
System.out.println(
"AggregatorModel finished in: "
+ (System.currentTimeMillis() - start) / 1000.
+ " seconds");
agg.checkConsistency();
frame.delete();
Frame output = agg._output._output_frame.get();
// Log.info("Exemplars: " + output);
output.remove();
Log.info("Number of exemplars: " + agg._exemplars.length);
agg.remove();
}
/**
* Compute the L2 norm for each row of the frame
*
* @param fr Input frame
* @return Vec containing L2 values for each row, is in K-V store
*/
public static Vec getL2(final Frame fr, final double[] scale) {
// add workspace vec at end
final int idx = fr.numCols();
assert (scale.length == idx) : "Mismatch for number of columns";
fr.add("L2", fr.anyVec().makeZero());
Vec res;
try {
new MRTask2() {
@Override
public void map(Chunk[] cs) {
for (int r = 0; r < cs[0]._len; r++) {
double norm2 = 0;
for (int i = 0; i < idx; i++) norm2 += Math.pow(cs[i].at0(r) * scale[i], 2);
cs[idx].set0(r, Math.sqrt(norm2));
}
}
}.doAll(fr);
} finally {
res = fr.remove(idx);
}
res.rollupStats();
return res;
}
private void applyScoringFrameSideEffects() {
final int offset_ncol = _parms.offset_columns == null ? 0 : _parms.offset_columns.length;
if (offset_ncol == 0) {
return;
}
int numCols = _modelBuilderTrain.numCols();
String responseVecName = _modelBuilderTrain.names()[numCols - 1];
Vec responseVec = _modelBuilderTrain.remove(numCols - 1);
for (int i = 0; i < offset_ncol; i++) {
Vec offsetVec = _parms.offset_columns[i];
int idxInRawFrame = _train.find(offsetVec);
if (idxInRawFrame < 0) {
throw new RuntimeException("CoxPHDriver failed to find offsetVec");
}
String offsetVecName = _parms.train().names()[idxInRawFrame];
_modelBuilderTrain.add(offsetVecName, offsetVec);
}
_modelBuilderTrain.add(responseVecName, responseVec);
}
@Ignore
@Test
public void testCovtypeMemberIndices() {
Frame frame = parse_test_file("smalldata/covtype/covtype.20k.data");
AggregatorModel.AggregatorParameters parms = new AggregatorModel.AggregatorParameters();
parms._train = frame._key;
parms._radius_scale = 5.0;
long start = System.currentTimeMillis();
AggregatorModel agg = new Aggregator(parms).trainModel().get(); // 1.489
System.out.println(
"AggregatorModel finished in: "
+ (System.currentTimeMillis() - start) / 1000.
+ " seconds");
agg.checkConsistency();
// Frame assignment = new Frame(new Vec[]{(Vec)agg._exemplar_assignment_vec_key.get()});
// Frame.export(assignment, "/tmp/assignment", "yada", true);
// Log.info("Exemplars: " + new Frame(new
// Vec[]{(Vec)agg._exemplar_assignment_vec_key.get()}).toString(0,20000));
Log.info("Number of exemplars: " + agg._exemplars.length);
Key<Frame> memberKey = Key.make();
for (int i = 0; i < agg._exemplars.length; ++i) {
Frame members = agg.scoreExemplarMembers(memberKey, i);
assert (members.numRows() == agg._counts[i]);
// Log.info(members);
members.delete();
}
Frame output = agg._output._output_frame.get();
output.remove();
Log.info("Number of exemplars: " + agg._exemplars.length);
// Assert.assertTrue(agg._exemplars.length==615);
frame.delete();
agg.remove();
}
public Frame extractFrame(int startIdx, int endIdx) {
Frame f = subframe(startIdx, endIdx);
remove(startIdx, endIdx);
return f;
}
// @Ignore("PUBDEV-1648")
@Test
public void testRandomCarsGrid() {
Grid grid = null;
DRFModel drfRebuilt = null;
Frame fr = null;
try {
fr = parse_test_file("smalldata/junit/cars.csv");
fr.remove("name").remove();
Vec old = fr.remove("economy (mpg)");
fr.add("economy (mpg)", old); // response to last column
DKV.put(fr);
// Setup random hyperparameter search space
HashMap<String, Object[]> hyperParms = new HashMap<>();
// Construct random grid search space
long seed = System.nanoTime();
Random rng = new Random(seed);
// Limit to 1-3 randomly, 4 times. Average total number of models is
// 2^4, or 16. Max is 81 models.
Integer ntreesDim = rng.nextInt(3) + 1;
Integer maxDepthDim = rng.nextInt(3) + 1;
Integer mtriesDim = rng.nextInt(3) + 1;
Integer sampleRateDim = rng.nextInt(3) + 1;
Integer[] ntreesArr = interval(1, 15);
ArrayList<Integer> ntreesList = new ArrayList<>(Arrays.asList(ntreesArr));
Collections.shuffle(ntreesList);
Integer[] ntreesSpace = new Integer[ntreesDim];
for (int i = 0; i < ntreesDim; i++) {
ntreesSpace[i] = ntreesList.get(i);
}
Integer[] maxDepthArr = interval(1, 10);
ArrayList<Integer> maxDepthList = new ArrayList<>(Arrays.asList(maxDepthArr));
Collections.shuffle(maxDepthList);
Integer[] maxDepthSpace = new Integer[maxDepthDim];
for (int i = 0; i < maxDepthDim; i++) {
maxDepthSpace[i] = maxDepthList.get(i);
}
Integer[] mtriesArr = interval(1, 5);
ArrayList<Integer> mtriesList = new ArrayList<>(Arrays.asList(mtriesArr));
Collections.shuffle(mtriesList);
Integer[] mtriesSpace = new Integer[mtriesDim];
for (int i = 0; i < mtriesDim; i++) {
mtriesSpace[i] = mtriesList.get(i);
}
Double[] sampleRateArr = interval(0.01, 0.99, 0.01);
ArrayList<Double> sampleRateList = new ArrayList<>(Arrays.asList(sampleRateArr));
Collections.shuffle(sampleRateList);
Double[] sampleRateSpace = new Double[sampleRateDim];
for (int i = 0; i < sampleRateDim; i++) {
sampleRateSpace[i] = sampleRateList.get(i);
}
hyperParms.put("_ntrees", ntreesSpace);
hyperParms.put("_max_depth", maxDepthSpace);
hyperParms.put("_mtries", mtriesSpace);
hyperParms.put("_sample_rate", sampleRateSpace);
// Fire off a grid search
DRFModel.DRFParameters params = new DRFModel.DRFParameters();
params._train = fr._key;
params._response_column = "economy (mpg)";
// Get the Grid for this modeling class and frame
Job<Grid> gs = GridSearch.startGridSearch(null, params, hyperParms);
grid = gs.get();
System.out.println("Test seed: " + seed);
System.out.println("ntrees search space: " + Arrays.toString(ntreesSpace));
System.out.println("max_depth search space: " + Arrays.toString(maxDepthSpace));
System.out.println("mtries search space: " + Arrays.toString(mtriesSpace));
System.out.println("sample_rate search space: " + Arrays.toString(sampleRateSpace));
// Check that cardinality of grid
Model[] ms = grid.getModels();
int numModels = ms.length;
System.out.println("Grid consists of " + numModels + " models");
assertEquals(
"Number of models should match hyper space size",
numModels,
ntreesDim * maxDepthDim * sampleRateDim * mtriesDim + grid.getFailureCount());
// Pick a random model from the grid
HashMap<String, Object[]> randomHyperParms = new HashMap<>();
Integer ntreeVal = ntreesSpace[rng.nextInt(ntreesSpace.length)];
randomHyperParms.put("_ntrees", new Integer[] {ntreeVal});
Integer maxDepthVal = maxDepthSpace[rng.nextInt(maxDepthSpace.length)];
randomHyperParms.put("_max_depth", maxDepthSpace);
Integer mtriesVal = mtriesSpace[rng.nextInt(mtriesSpace.length)];
randomHyperParms.put("_max_depth", mtriesSpace);
Double sampleRateVal = sampleRateSpace[rng.nextInt(sampleRateSpace.length)];
randomHyperParms.put("_sample_rate", sampleRateSpace);
// TODO: DRFModel drfFromGrid = (DRFModel) g2.model(randomHyperParms).get();
// Rebuild it with it's parameters
params._ntrees = ntreeVal;
params._max_depth = maxDepthVal;
params._mtries = mtriesVal;
drfRebuilt = new DRF(params).trainModel().get();
// Make sure the MSE metrics match
// double fromGridMSE = drfFromGrid._output._scored_train[drfFromGrid._output._ntrees]._mse;
double rebuiltMSE = drfRebuilt._output._scored_train[drfRebuilt._output._ntrees]._mse;
// System.out.println("The random grid model's MSE: " + fromGridMSE);
System.out.println("The rebuilt model's MSE: " + rebuiltMSE);
// assertEquals(fromGridMSE, rebuiltMSE);
} finally {
if (fr != null) {
fr.remove();
}
if (grid != null) {
grid.remove();
}
if (drfRebuilt != null) {
drfRebuilt.remove();
}
}
}
public DataInfo filterExpandedColumns(int[] cols) {
assert _predictor_transform != null;
assert _response_transform != null;
if (cols == null) return deep_clone();
int hasIcpt = (cols.length > 0 && cols[cols.length - 1] == fullN()) ? 1 : 0;
int i = 0, j = 0, ignoredCnt = 0;
// public DataInfo(Frame fr, int hasResponses, boolean useAllFactorLvls, double [] normSub,
// double [] normMul, double [] normRespSub, double [] normRespMul){
int[][] catLvls = new int[_cats][];
int[] ignoredCols = MemoryManager.malloc4(_nums + _cats);
// first do categoricals...
if (_catOffsets != null) {
int coff = _useAllFactorLevels ? 0 : 1;
while (i < cols.length && cols[i] < _catOffsets[_catOffsets.length - 1]) {
int[] levels = MemoryManager.malloc4(_catOffsets[j + 1] - _catOffsets[j]);
int k = 0;
while (i < cols.length && cols[i] < _catOffsets[j + 1])
levels[k++] = (cols[i++] - _catOffsets[j]) + coff;
if (k > 0) catLvls[j] = Arrays.copyOf(levels, k);
++j;
}
}
int[] catModes = _catModes;
for (int k = 0; k < catLvls.length; ++k) if (catLvls[k] == null) ignoredCols[ignoredCnt++] = k;
if (ignoredCnt > 0) {
int[][] cs = new int[_cats - ignoredCnt][];
catModes = new int[_cats - ignoredCnt];
int y = 0;
for (int c = 0; c < catLvls.length; ++c)
if (catLvls[c] != null) {
catModes[y] = _catModes[c];
cs[y++] = catLvls[c];
}
assert y == cs.length;
catLvls = cs;
}
// now numerics
int prev = j = 0;
for (; i < cols.length; ++i) {
for (int k = prev; k < (cols[i] - numStart()); ++k) {
ignoredCols[ignoredCnt++] = k + _cats;
++j;
}
prev = ++j;
}
for (int k = prev; k < _nums; ++k) ignoredCols[ignoredCnt++] = k + _cats;
Frame f = new Frame(_adaptedFrame.names().clone(), _adaptedFrame.vecs().clone());
if (ignoredCnt > 0) f.remove(Arrays.copyOf(ignoredCols, ignoredCnt));
assert catLvls.length < f.numCols() : "cats = " + catLvls.length + " numcols = " + f.numCols();
double[] normSub = null;
double[] normMul = null;
int id = Arrays.binarySearch(cols, numStart());
if (id < 0) id = -id - 1;
int nnums = cols.length - id - hasIcpt;
int off = numStart();
if (_normSub != null) {
normSub = new double[nnums];
for (int k = id; k < (id + nnums); ++k) normSub[k - id] = _normSub[cols[k] - off];
}
if (_normMul != null) {
normMul = new double[nnums];
for (int k = id; k < (id + nnums); ++k) normMul[k - id] = _normMul[cols[k] - off];
}
// public DataInfo(Frame train, Frame valid, int nResponses, boolean useAllFactorLevels,
// TransformType predictor_transform, TransformType response_transform, boolean skipMissing,
// boolean imputeMissing, boolean missingBucket, boolean weight, boolean offset, boolean fold) {
DataInfo dinfo = new DataInfo(this, f, normMul, normSub, catLvls, catModes);
dinfo._activeCols = cols;
return dinfo;
}
@Test
public void testLosses() throws InterruptedException, ExecutionException {
long seed = 0xDECAF;
Random rng = new Random(seed);
Frame train = null;
final int[] cats = new int[] {1, 3, 4, 5}; // Categoricals: CAPSULE, RACE, DPROS, DCAPS
final GLRMParameters.Regularizer[] regs =
new GLRMParameters.Regularizer[] {
GLRMParameters.Regularizer.Quadratic,
GLRMParameters.Regularizer.L1,
GLRMParameters.Regularizer.NonNegative,
GLRMParameters.Regularizer.OneSparse,
GLRMParameters.Regularizer.UnitOneSparse,
GLRMParameters.Regularizer.Simplex
};
Scope.enter();
try {
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);
for (GLRMParameters.Loss loss :
new GLRMParameters.Loss[] {
GLRMParameters.Loss.Quadratic,
GLRMParameters.Loss.Absolute,
GLRMParameters.Loss.Huber,
GLRMParameters.Loss.Poisson,
GLRMParameters.Loss.Hinge,
GLRMParameters.Loss.Logistic
}) {
for (GLRMParameters.Loss multiloss :
new GLRMParameters.Loss[] {
GLRMParameters.Loss.Categorical, GLRMParameters.Loss.Ordinal
}) {
GLRMModel model = null;
try {
Scope.enter();
long myseed = rng.nextLong();
Log.info("GLRM using seed = " + myseed);
GLRMParameters parms = new GLRMParameters();
parms._train = train._key;
parms._transform = DataInfo.TransformType.NONE;
parms._k = 5;
parms._loss = loss;
parms._multi_loss = multiloss;
parms._init = GLRM.Initialization.SVD;
parms._regularization_x = regs[rng.nextInt(regs.length)];
parms._regularization_y = regs[rng.nextInt(regs.length)];
parms._gamma_x = Math.abs(rng.nextDouble());
parms._gamma_y = Math.abs(rng.nextDouble());
parms._recover_svd = false;
parms._seed = myseed;
parms._verbose = false;
parms._max_iterations = 500;
GLRM job = new GLRM(parms);
try {
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) {
throw t;
} finally {
job.remove();
}
} catch (Throwable t) {
t.printStackTrace();
throw new RuntimeException(t);
} finally {
if (model != null) model.delete();
Scope.exit();
}
}
}
} finally {
if (train != null) train.delete();
Scope.exit();
}
}
@Test
public void testChicago() {
Frame weather = null, crimes = null, census = null;
String oldtz = Exec.exec("(getTimeZone)").getStr();
try {
weather = parse_test_file(Key.make("weather.hex"), "smalldata/chicago/chicagoAllWeather.csv");
crimes =
parse_test_file(Key.make("crimes.hex"), "smalldata/chicago/chicagoCrimes10k.csv.zip");
String fname = "smalldata/chicago/chicagoCensus.csv";
File f = find_test_file(fname);
assert f != null && f.exists() : " file not found: " + fname;
NFSFileVec nfs = NFSFileVec.make(f);
ParseSetup ps = ParseSetup.guessSetup(new Key[] {nfs._key}, false, 1);
ps.getColumnTypes()[1] = Vec.T_ENUM;
census = ParseDataset.parse(Key.make("census.hex"), new Key[] {nfs._key}, true, ps);
census =
exec_str(
"(colnames= census.hex [0 1 2 3 4 5 6 7 8] [\"Community.Area.Number\" \"COMMUNITY.AREA.NAME\" \"PERCENT.OF.HOUSING.CROWDED\" \"PERCENT.HOUSEHOLDS.BELOW.POVERTY\" \"PERCENT.AGED.16..UNEMPLOYED\" \"PERCENT.AGED.25..WITHOUT.HIGH.SCHOOL.DIPLOMA\" \"PERCENT.AGED.UNDER.18.OR.OVER.64\" \"PER.CAPITA.INCOME.\" \"HARDSHIP.INDEX\"])",
"census.hex");
crimes =
exec_str(
"(colnames= crimes.hex [0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21] [\"ID\" \"Case.Number\" \"Date\" \"Block\" \"IUCR\" \"Primary.Type\" \"Description\" \"Location.Description\" \"Arrest\" \"Domestic\" \"Beat\" \"District\" \"Ward\" \"Community.Area\" \"FBI.Code\" \"X.Coordinate\" \"Y.Coordinate\" \"Year\" \"Updated.On\" \"Latitude\" \"Longitude\" \"Location\"])",
"crimes.hex");
exec_str("(setTimeZone \"Etc/UTC\")", null);
crimes =
exec_str(
"(colnames= (= crimes.hex (tmp= unary_op_6 (day (tmp= nary_op_5 (as.Date (cols crimes.hex [2]) \"%m/%d/%Y %I:%M:%S %p\")))) [22] [0:9999]) 22 \"Day\")",
"crimes.hex");
crimes =
exec_str(
"(colnames= (= crimes.hex (tmp= binary_op_31 (+ (tmp= unary_op_7 (month nary_op_5)) #1)) [23] [0:9999]) 23 \"Month\")",
"crimes.hex");
Keyed.remove(Key.make("nary_op_30"));
crimes =
exec_str(
"(colnames= (= crimes.hex (tmp= binary_op_32 (+ (tmp= binary_op_9 (- (tmp= unary_op_8 (year nary_op_5)) #1900)) #1900)) [17] [0:9999]) 17 \"Year\")",
"crimes.hex");
crimes =
exec_str(
"(colnames= (= crimes.hex (tmp= unary_op_10 (week nary_op_5)) [24] [0:9999]) 24 \"WeekNum\")",
"crimes.hex");
Keyed.remove(Key.make("binary_op_32"));
Keyed.remove(Key.make("binary_op_31"));
Keyed.remove(Key.make("unary_op_8"));
checkSaneFrame();
crimes =
exec_str(
"(colnames= (= crimes.hex (tmp= unary_op_11 (dayOfWeek nary_op_5)) [25] [0:9999]) 25 \"WeekDay\")",
"crimes.hex");
Keyed.remove(
Key.make(
"nfs:\\C:\\Users\\cliffc\\Desktop\\h2o-3\\smalldata\\chicago\\chicagoCrimes10k.csv.zip"));
crimes =
exec_str(
"(colnames= (= crimes.hex (tmp= unary_op_12 (hour nary_op_5)) [26] [0:9999]) 26 \"HourOfDay\")",
"crimes.hex");
crimes =
exec_str(
"(colnames= (= crimes.hex (tmp= nary_op_16 (ifelse (tmp= binary_op_15 (| (tmp= binary_op_13 (== unary_op_11 \"Sun\")) (tmp= binary_op_14 (== unary_op_11 \"Sat\")))) 1 0)) [27] [0:9999]) 27 \"Weekend\")",
"crimes.hex");
// Season is incorrectly assigned in the original chicago demo; picks up the Weekend flag
crimes =
exec_str(
"(colnames= (= crimes.hex nary_op_16 [28] [0:9999]) 28 \"Season\")", "crimes.hex");
// Standard "head of 10 rows" pattern for printing
Frame subset_33 = exec_str("(rows crimes.hex [0:10])", "subset_33");
Keyed.remove(Key.make("subset_33"));
Keyed.remove(Key.make("subset_33"));
Keyed.remove(Key.make("unary_op_29"));
Keyed.remove(Key.make("nary_op_28"));
Keyed.remove(Key.make("nary_op_27"));
Keyed.remove(Key.make("nary_op_26"));
Keyed.remove(Key.make("binary_op_25"));
Keyed.remove(Key.make("binary_op_24"));
Keyed.remove(Key.make("binary_op_23"));
Keyed.remove(Key.make("binary_op_22"));
Keyed.remove(Key.make("binary_op_21"));
Keyed.remove(Key.make("binary_op_20"));
Keyed.remove(Key.make("binary_op_19"));
Keyed.remove(Key.make("binary_op_18"));
Keyed.remove(Key.make("binary_op_17"));
Keyed.remove(Key.make("nary_op_16"));
Keyed.remove(Key.make("binary_op_15"));
Keyed.remove(Key.make("binary_op_14"));
Keyed.remove(Key.make("binary_op_13"));
Keyed.remove(Key.make("unary_op_12"));
Keyed.remove(Key.make("unary_op_11"));
Keyed.remove(Key.make("unary_op_10"));
Keyed.remove(Key.make("binary_op_9"));
Keyed.remove(Key.make("unary_op_8"));
Keyed.remove(Key.make("unary_op_7"));
Keyed.remove(Key.make("unary_op_6"));
Keyed.remove(Key.make("nary_op_5"));
checkSaneFrame();
// Standard "head of 10 rows" pattern for printing
Frame subset_34 = exec_str("(rows crimes.hex [0:10])", "subset_34");
Keyed.remove(Key.make("subset_34"));
census =
exec_str(
"(colnames= census.hex [0 1 2 3 4 5 6 7 8] [\"Community.Area\" \"COMMUNITY.AREA.NAME\" \"PERCENT.OF.HOUSING.CROWDED\" \"PERCENT.HOUSEHOLDS.BELOW.POVERTY\" \"PERCENT.AGED.16..UNEMPLOYED\" \"PERCENT.AGED.25..WITHOUT.HIGH.SCHOOL.DIPLOMA\" \"PERCENT.AGED.UNDER.18.OR.OVER.64\" \"PER.CAPITA.INCOME.\" \"HARDSHIP.INDEX\"])",
"census.hex");
Keyed.remove(Key.make("subset_34"));
Frame subset_35 = exec_str("(cols crimes.hex [-3])", "subset_35");
Frame subset_36 = exec_str("(cols weather.hex [-1])", "subset_36");
subset_36 =
exec_str(
"(colnames= subset_36 [0 1 2 3 4 5] [\"Month\" \"Day\" \"Year\" \"maxTemp\" \"meanTemp\" \"minTemp\"])",
"subset_36");
crimes.remove();
weather.remove();
// nary_op_37 = merge( X Y ); Vecs in X & nary_op_37 shared
Frame nary_op_37 = exec_str("(merge subset_35 census.hex FALSE FALSE)", "nary_op_37");
// nary_op_38 = merge( nary_op_37 subset_36); Vecs in nary_op_38 and nary_pop_37 and X shared
Frame subset_41 =
exec_str(
"(rows (tmp= nary_op_38 (merge nary_op_37 subset_36 TRUE FALSE)) (tmp= binary_op_40 (<= (tmp= nary_op_39 (h2o.runif nary_op_38 30792152736.5179)) #0.8)))",
"subset_41");
// Standard "head of 10 rows" pattern for printing
Frame subset_44 = exec_str("(rows subset_41 [0:10])", "subset_44");
Keyed.remove(Key.make("subset_44"));
Keyed.remove(Key.make("subset_44"));
Keyed.remove(Key.make("binary_op_40"));
Keyed.remove(Key.make("nary_op_37"));
Frame subset_43 =
exec_str("(rows nary_op_38 (tmp= binary_op_42 (> nary_op_39 #0.8)))", "subset_43");
// Chicago demo continues on past, but this is all I've captured for now
checkSaneFrame();
} finally {
Exec.exec(
"(setTimeZone \""
+ oldtz
+ "\")"); // Restore time zone (which is global, and will affect following tests)
if (weather != null) weather.remove();
if (crimes != null) crimes.remove();
if (census != null) census.remove();
for (String s :
new String[] {
"nary_op_5",
"unary_op_6",
"unary_op_7",
"unary_op_8",
"binary_op_9",
"unary_op_10",
"unary_op_11",
"unary_op_12",
"binary_op_13",
"binary_op_14",
"binary_op_15",
"nary_op_16",
"binary_op_17",
"binary_op_18",
"binary_op_19",
"binary_op_20",
"binary_op_21",
"binary_op_22",
"binary_op_23",
"binary_op_24",
"binary_op_25",
"nary_op_26",
"nary_op_27",
"nary_op_28",
"unary_op_29",
"binary_op_30",
"binary_op_31",
"binary_op_32",
"subset_33",
"subset_34",
"subset_35",
"subset_36",
"nary_op_37",
"nary_op_38",
"nary_op_39",
"binary_op_40",
"subset_41",
"binary_op_42",
"subset_43",
"subset_44",
}) Keyed.remove(Key.make(s));
}
}
@Test
public void testSetColumnLossCats() 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
Scope.enter();
try {
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 = 12;
parms._loss = GLRMParameters.Loss.Quadratic;
parms._multi_loss = GLRMParameters.Loss.Categorical;
parms._loss_by_col =
new GLRMParameters.Loss[] {
GLRMParameters.Loss.Ordinal, GLRMParameters.Loss.Poisson, GLRMParameters.Loss.Absolute
};
parms._loss_by_col_idx = new int[] {3 /* DPROS */, 1 /* AGE */, 6 /* VOL */};
parms._init = GLRM.Initialization.PlusPlus;
parms._min_step_size = 1e-5;
parms._recover_svd = false;
parms._max_iterations = 2000;
try {
job = new GLRM(parms);
model = job.trainModel().get();
Log.info(
"Iteration "
+ model._output._iterations
+ ": Objective value = "
+ model._output._objective);
GLRMTest.checkLossbyCol(parms, model);
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();
}
}
@Test
public void testExpandCatsProstate() throws InterruptedException, ExecutionException {
double[][] prostate =
ard(
ard(0, 71, 1, 0, 0, 4.8, 14.0, 7),
ard(1, 70, 1, 1, 0, 8.4, 21.8, 5),
ard(0, 73, 1, 3, 0, 10.0, 27.4, 6),
ard(1, 68, 1, 0, 0, 6.7, 16.7, 6));
double[][] pros_expandR =
ard(
ard(1, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 71, 4.8, 14.0, 7),
ard(0, 1, 0, 0, 0, 1, 0, 0, 1, 1, 0, 70, 8.4, 21.8, 5),
ard(0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 0, 73, 10.0, 27.4, 6),
ard(1, 0, 0, 0, 0, 1, 0, 0, 1, 1, 0, 68, 6.7, 16.7, 6));
String[] pros_cols =
new String[] {"Capsule", "Age", "Race", "Dpros", "Dcaps", "PSA", "Vol", "Gleason"};
String[][] pros_domains =
new String[][] {
new String[] {"No", "Yes"},
null,
new String[] {"Other", "White", "Black"},
new String[] {"None", "UniLeft", "UniRight", "Bilobar"},
new String[] {"No", "Yes"},
null,
null,
null
};
final int[] cats = new int[] {1, 3, 4, 5}; // Categoricals: CAPSULE, RACE, DPROS, DCAPS
Frame fr = null;
try {
Scope.enter();
fr = parse_test_file(Key.make("prostate.hex"), "smalldata/logreg/prostate.csv");
for (int i = 0; i < cats.length; i++)
Scope.track(fr.replace(cats[i], fr.vec(cats[i]).toCategoricalVec())._key);
fr.remove("ID").remove();
DKV.put(fr._key, fr);
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(pros_cols, "%8.7s") + ArrayUtils.pprint(prostate));
double[][] pros_perm = ArrayUtils.permuteCols(prostate, dinfo._permutation);
Log.info(
"Permuted matrix:\n"
+ colFormat(pros_cols, "%8.7s", dinfo._permutation)
+ ArrayUtils.pprint(pros_perm));
double[][] pros_exp = GLRM.expandCats(pros_perm, dinfo);
Log.info(
"Expanded matrix:\n"
+ colExpFormat(pros_cols, pros_domains, "%8.7s", dinfo._permutation)
+ ArrayUtils.pprint(pros_exp));
Assert.assertArrayEquals(pros_expandR, pros_exp);
} catch (Throwable t) {
t.printStackTrace();
throw new RuntimeException(t);
} finally {
if (fr != null) fr.delete();
Scope.exit();
}
}
void testModelAdaptation(String train, String test, PrepData dprep, boolean exactAdaptation) {
DRFModel model = null;
Frame frTest = null;
Frame frTrain = null;
Key trainKey = Key.make("train.hex");
Key testKey = Key.make("test.hex");
Frame[] frAdapted = null;
try {
// Prepare a simple model
frTrain = parseFrame(trainKey, train);
model = runDRF(frTrain, dprep);
// Load test dataset - test data contains input columns matching train data,
// BUT each input requires adaptation. Moreover, test data contains additional columns
// containing correct value mapping.
frTest = parseFrame(testKey, test);
Assert.assertEquals(
"TEST CONF ERROR: The test dataset should contain 2*<number of input columns>+1!",
2 * (frTrain.numCols() - 1) + 1,
frTest.numCols());
// Adapt test dataset
frAdapted = model.adapt(frTest, exactAdaptation); // do/do not perform translation to enums
Assert.assertEquals("Adapt method should return two frames", 2, frAdapted.length);
Assert.assertEquals(
"Test expects that all columns in test dataset has to be adapted",
dprep.needAdaptation(frTrain),
frAdapted[1].numCols());
// Compare vectors
Frame adaptedFrame = frAdapted[0];
// System.err.println(frTest.toStringAll());
// System.err.println(adaptedFrame.toStringAll());
for (int av = 0; av < frTrain.numCols() - 1; av++) {
int ev = av + frTrain.numCols();
Vec actV = adaptedFrame.vecs()[av];
Vec expV = frTest.vecs()[ev];
Assert.assertEquals(
"Different number of rows in test vectors", expV.length(), actV.length());
for (long r = 0; r < expV.length(); r++) {
if (expV.isNA(r))
Assert.assertTrue(
"Badly adapted vector - expected NA! Col: " + av + ", row: " + r, actV.isNA(r));
else {
Assert.assertTrue(
"Badly adapted vector - expected value but get NA! Col: " + av + ", row: " + r,
!actV.isNA(r));
Assert.assertEquals(
"Badly adapted vector - wrong values! Col: " + av + ", row: " + r,
expV.at8(r),
actV.at8(r));
}
}
}
} finally {
// Test cleanup
if (model != null) UKV.remove(model._selfKey);
if (frTrain != null) frTrain.remove();
UKV.remove(trainKey);
if (frTest != null) frTest.remove();
UKV.remove(testKey);
// Remove adapted vectors which were saved into KV-store, rest of vectors are remove by
// frTest.remove()
if (frAdapted != null) frAdapted[1].remove();
}
}
public void dropWeights() {
if (!_weights) return;
_adaptedFrame.remove(weightChunkId());
_weights = false;
}
public DataInfo filterExpandedColumns(int[] cols) {
assert _predictor_transform != null;
assert _response_transform != null;
if (cols == null) return this;
int i = 0, j = 0, ignoredCnt = 0;
// public DataInfo(Frame fr, int hasResponses, boolean useAllFactorLvls, double [] normSub,
// double [] normMul, double [] normRespSub, double [] normRespMul){
int[][] catLvls = new int[_cats][];
int[] ignoredCols = MemoryManager.malloc4(_nums + _cats);
// first do categoricals...
if (_catOffsets != null) {
int coff = _useAllFactorLevels ? 0 : 1;
while (i < cols.length && cols[i] < _catOffsets[_catOffsets.length - 1]) {
int[] levels = MemoryManager.malloc4(_catOffsets[j + 1] - _catOffsets[j]);
int k = 0;
while (i < cols.length && cols[i] < _catOffsets[j + 1])
levels[k++] = cols[i++] - _catOffsets[j] + coff;
if (k > 0) catLvls[j] = Arrays.copyOf(levels, k);
++j;
}
}
for (int k = 0; k < catLvls.length; ++k) if (catLvls[k] == null) ignoredCols[ignoredCnt++] = k;
if (ignoredCnt > 0) {
int[][] c = new int[_cats - ignoredCnt][];
int y = 0;
for (int[] catLvl : catLvls) if (catLvl != null) c[y++] = catLvl;
assert y == c.length;
catLvls = c;
}
// now numerics
int prev = j = 0;
for (; i < cols.length; ++i) {
for (int k = prev; k < (cols[i] - numStart()); ++k) {
ignoredCols[ignoredCnt++] = k + _cats;
++j;
}
prev = ++j;
}
for (int k = prev; k < _nums; ++k) ignoredCols[ignoredCnt++] = k + _cats;
Frame f = new Frame(_adaptedFrame.names().clone(), _adaptedFrame.vecs().clone());
if (ignoredCnt > 0) f.remove(Arrays.copyOf(ignoredCols, ignoredCnt));
assert catLvls.length < f.numCols() : "cats = " + catLvls.length + " numcols = " + f.numCols();
double[] normSub = null;
double[] normMul = null;
int id = Arrays.binarySearch(cols, numStart());
if (id < 0) id = -id - 1;
int nnums = cols.length - id;
int off = numStart();
if (_normSub != null) {
normSub = new double[nnums];
for (int k = id; k < cols.length; ++k) normSub[k - id] = _normSub[cols[k] - off];
}
if (_normMul != null) {
normMul = new double[nnums];
for (int k = id; k < cols.length; ++k) normMul[k - id] = _normMul[cols[k] - off];
}
DataInfo dinfo =
new DataInfo(
_key,
f,
normMul,
normSub,
catLvls,
_responses,
_predictor_transform,
_response_transform,
_skipMissing,
_imputeMissing,
_weights,
_offset,
_fold);
// do not put activeData into K/V - active data is recreated on each node based on active
// columns
dinfo._activeCols = cols;
return dinfo;
}
// @Ignore("PUBDEV-1648")
@Test
public void testRandomCarsGrid() {
Grid grid = null;
GBMModel gbmRebuilt = null;
Frame fr = null;
Vec old = null;
try {
fr = parse_test_file("smalldata/junit/cars.csv");
fr.remove("name").remove();
old = fr.remove("economy (mpg)");
fr.add("economy (mpg)", old); // response to last column
DKV.put(fr);
// Setup random hyperparameter search space
HashMap<String, Object[]> hyperParms = new HashMap<>();
hyperParms.put("_distribution", new DistributionFamily[] {DistributionFamily.gaussian});
// Construct random grid search space
Random rng = new Random();
Integer ntreesDim = rng.nextInt(4) + 1;
Integer maxDepthDim = rng.nextInt(4) + 1;
Integer learnRateDim = rng.nextInt(4) + 1;
Integer[] ntreesArr = interval(1, 25);
ArrayList<Integer> ntreesList = new ArrayList<>(Arrays.asList(ntreesArr));
Collections.shuffle(ntreesList);
Integer[] ntreesSpace = new Integer[ntreesDim];
for (int i = 0; i < ntreesDim; i++) {
ntreesSpace[i] = ntreesList.get(i);
}
Integer[] maxDepthArr = interval(1, 10);
ArrayList<Integer> maxDepthList = new ArrayList<>(Arrays.asList(maxDepthArr));
Collections.shuffle(maxDepthList);
Integer[] maxDepthSpace = new Integer[maxDepthDim];
for (int i = 0; i < maxDepthDim; i++) {
maxDepthSpace[i] = maxDepthList.get(i);
}
Double[] learnRateArr = interval(0.01, 1.0, 0.01);
ArrayList<Double> learnRateList = new ArrayList<>(Arrays.asList(learnRateArr));
Collections.shuffle(learnRateList);
Double[] learnRateSpace = new Double[learnRateDim];
for (int i = 0; i < learnRateDim; i++) {
learnRateSpace[i] = learnRateList.get(i);
}
hyperParms.put("_ntrees", ntreesSpace);
hyperParms.put("_max_depth", maxDepthSpace);
hyperParms.put("_learn_rate", learnRateSpace);
// Fire off a grid search
GBMModel.GBMParameters params = new GBMModel.GBMParameters();
params._train = fr._key;
params._response_column = "economy (mpg)";
// Get the Grid for this modeling class and frame
Job<Grid> gs = GridSearch.startGridSearch(null, params, hyperParms);
grid = gs.get();
System.out.println("ntrees search space: " + Arrays.toString(ntreesSpace));
System.out.println("max_depth search space: " + Arrays.toString(maxDepthSpace));
System.out.println("learn_rate search space: " + Arrays.toString(learnRateSpace));
// Check that cardinality of grid
Model[] ms = grid.getModels();
Integer numModels = ms.length;
System.out.println("Grid consists of " + numModels + " models");
assertTrue(numModels == ntreesDim * maxDepthDim * learnRateDim);
// Pick a random model from the grid
HashMap<String, Object[]> randomHyperParms = new HashMap<>();
randomHyperParms.put("_distribution", new DistributionFamily[] {DistributionFamily.gaussian});
Integer ntreeVal = ntreesSpace[rng.nextInt(ntreesSpace.length)];
randomHyperParms.put("_ntrees", new Integer[] {ntreeVal});
Integer maxDepthVal = maxDepthSpace[rng.nextInt(maxDepthSpace.length)];
randomHyperParms.put("_max_depth", maxDepthSpace);
Double learnRateVal = learnRateSpace[rng.nextInt(learnRateSpace.length)];
randomHyperParms.put("_learn_rate", learnRateSpace);
// TODO: GBMModel gbmFromGrid = (GBMModel) g2.model(randomHyperParms).get();
// Rebuild it with it's parameters
params._distribution = DistributionFamily.gaussian;
params._ntrees = ntreeVal;
params._max_depth = maxDepthVal;
params._learn_rate = learnRateVal;
GBM gbm = new GBM(params);
gbmRebuilt = gbm.trainModel().get();
assertTrue(gbm.isStopped());
// Make sure the MSE metrics match
// double fromGridMSE = gbmFromGrid._output._scored_train[gbmFromGrid._output._ntrees]._mse;
double rebuiltMSE = gbmRebuilt._output._scored_train[gbmRebuilt._output._ntrees]._mse;
// System.out.println("The random grid model's MSE: " + fromGridMSE);
System.out.println("The rebuilt model's MSE: " + rebuiltMSE);
// assertEquals(fromGridMSE, rebuiltMSE);
} finally {
if (old != null) old.remove();
if (fr != null) fr.remove();
if (grid != null) grid.remove();
if (gbmRebuilt != null) gbmRebuilt.remove();
}
}
@Test
public void testCarsGrid() {
Grid<GBMModel.GBMParameters> grid = null;
Frame fr = null;
Vec old = null;
try {
fr = parse_test_file("smalldata/junit/cars.csv");
fr.remove("name").remove(); // Remove unique id
old = fr.remove("cylinders");
fr.add("cylinders", old.toCategoricalVec()); // response to last column
DKV.put(fr);
// Setup hyperparameter search space
final Double[] legalLearnRateOpts = new Double[] {0.01, 0.1, 0.3};
final Double[] illegalLearnRateOpts = new Double[] {-1.0};
HashMap<String, Object[]> hyperParms =
new HashMap<String, Object[]>() {
{
put("_ntrees", new Integer[] {1, 2});
put("_distribution", new DistributionFamily[] {DistributionFamily.multinomial});
put("_max_depth", new Integer[] {1, 2, 5});
put("_learn_rate", ArrayUtils.join(legalLearnRateOpts, illegalLearnRateOpts));
}
};
// Name of used hyper parameters
String[] hyperParamNames = hyperParms.keySet().toArray(new String[hyperParms.size()]);
Arrays.sort(hyperParamNames);
int hyperSpaceSize = ArrayUtils.crossProductSize(hyperParms);
// Fire off a grid search
GBMModel.GBMParameters params = new GBMModel.GBMParameters();
params._train = fr._key;
params._response_column = "cylinders";
// Get the Grid for this modeling class and frame
Job<Grid> gs = GridSearch.startGridSearch(null, params, hyperParms);
grid = (Grid<GBMModel.GBMParameters>) gs.get();
// Make sure number of produced models match size of specified hyper space
Assert.assertEquals(
"Size of grid (models+failures) should match to size of hyper space",
hyperSpaceSize,
grid.getModelCount() + grid.getFailureCount());
//
// Make sure that names of used parameters match
//
String[] gridHyperNames = grid.getHyperNames();
Arrays.sort(gridHyperNames);
Assert.assertArrayEquals(
"Hyper parameters names should match!", hyperParamNames, gridHyperNames);
//
// Make sure that values of used parameters match as well to the specified values
//
Key<Model>[] mKeys = grid.getModelKeys();
Map<String, Set<Object>> usedHyperParams = GridTestUtils.initMap(hyperParamNames);
for (Key<Model> mKey : mKeys) {
GBMModel gbm = (GBMModel) mKey.get();
System.out.println(
gbm._output._scored_train[gbm._output._ntrees]._mse
+ " "
+ Arrays.deepToString(
ArrayUtils.zip(grid.getHyperNames(), grid.getHyperValues(gbm._parms))));
GridTestUtils.extractParams(usedHyperParams, gbm._parms, hyperParamNames);
}
// Remove illegal options
hyperParms.put("_learn_rate", legalLearnRateOpts);
GridTestUtils.assertParamsEqual(
"Grid models parameters have to cover specified hyper space",
hyperParms,
usedHyperParams);
// Verify model failure
Map<String, Set<Object>> failedHyperParams = GridTestUtils.initMap(hyperParamNames);
;
for (Model.Parameters failedParams : grid.getFailedParameters()) {
GridTestUtils.extractParams(failedHyperParams, failedParams, hyperParamNames);
}
hyperParms.put("_learn_rate", illegalLearnRateOpts);
GridTestUtils.assertParamsEqual(
"Failed model parameters have to correspond to specified hyper space",
hyperParms,
failedHyperParams);
} finally {
if (old != null) {
old.remove();
}
if (fr != null) {
fr.remove();
}
if (grid != null) {
grid.remove();
}
}
}
public void remove() {
remove(new Futures());
}