protected void testKeyValues(
Key k, double n1, double n2, double n3, double nx3, double nx2, double nx1) {
ValueArray v = ValueArray.value(k);
assertEquals(v.datad(0, 0), n1, 0.0);
assertEquals(v.datad(1, 0), n2, 0.0);
assertEquals(v.datad(2, 0), n3, 0.0);
assertEquals(v.datad(v.numRows() - 3, 0), nx3, 0.0);
assertEquals(v.datad(v.numRows() - 2, 0), nx2, 0.0);
assertEquals(v.datad(v.numRows() - 1, 0), nx1, 0.0);
}
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);
}
/**
* 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;
}
public void testDataFrameStructure(Key k, int rows, int cols) {
ValueArray v = ValueArray.value(k);
assertEquals(v.numRows(), rows);
assertEquals(v.numCols(), cols);
}
