[jvm-packages] Scala/Java interface for Fast Histogram Algorithm (#1966)

* add back train method but mark as deprecated * fix scalastyle error * first commit in scala binding for fast histo * java test * add missed scala tests * spark training * add back train method but mark as deprecated * fix scalastyle error * local change * first commit in scala binding for fast histo * local change * fix df frame test
2017-03-04 15:37:24 -08:00
parent ac30a0aff5
commit ab13fd72bd
10 changed files with 400 additions and 37 deletions
--- a/jvm-packages/xgboost4j/src/test/java/ml/dmlc/xgboost4j/java/BoosterImplTest.java
+++ b/jvm-packages/xgboost4j/src/test/java/ml/dmlc/xgboost4j/java/BoosterImplTest.java
@@ -26,7 +26,6 @@ import java.util.HashMap;
 import java.util.Map;

 import junit.framework.TestCase;
-import ml.dmlc.xgboost4j.java.*;
 import org.apache.commons.logging.Log;
 import org.apache.commons.logging.LogFactory;
 import org.junit.Test;
@@ -151,6 +150,130 @@ public class BoosterImplTest {
    TestCase.assertTrue("loadedPredictErr:" + loadedPredictError, loadedPredictError < 0.1f);
  }

+  private void testWithFastHisto(DMatrix trainingSet, Map<String, DMatrix> watches, int round,
+                                      Map<String, Object> paramMap, float threshold) throws XGBoostError {
+    float[][] metrics = new float[watches.size()][round];
+    Booster booster = XGBoost.train(trainingSet, paramMap, round, watches,
+            metrics, null, null);
+    for (int i = 0; i < metrics.length; i++)
+      for (int j = 1; j < metrics[i].length; j++) {
+        TestCase.assertTrue(metrics[i][j] >= metrics[i][j - 1]);
+      }
+    for (int i = 0; i < metrics.length; i++)
+      for (int j = 0; j < metrics[i].length; j++) {
+      TestCase.assertTrue(metrics[i][j] >= threshold);
+      }
+    booster.dispose();
+  }
+
+  @Test
+  public void testFastHistoDepthWise() throws XGBoostError {
+    DMatrix trainMat = new DMatrix("../../demo/data/agaricus.txt.train");
+    DMatrix testMat = new DMatrix("../../demo/data/agaricus.txt.test");
+    // testBoosterWithFastHistogram(trainMat, testMat);
+    Map<String, Object> paramMap = new HashMap<String, Object>() {
+      {
+        put("max_depth", 3);
+        put("silent", 1);
+        put("objective", "binary:logistic");
+        put("tree_method", "hist");
+        put("grow_policy", "depthwise");
+        put("eval_metric", "auc");
+      }
+    };
+    Map<String, DMatrix> watches = new HashMap<>();
+    watches.put("training", trainMat);
+    watches.put("test", testMat);
+    testWithFastHisto(trainMat, watches, 10, paramMap, 0.0f);
+  }
+
+  @Test
+  public void testFastHistoLossGuide() throws XGBoostError {
+    DMatrix trainMat = new DMatrix("../../demo/data/agaricus.txt.train");
+    DMatrix testMat = new DMatrix("../../demo/data/agaricus.txt.test");
+    // testBoosterWithFastHistogram(trainMat, testMat);
+    Map<String, Object> paramMap = new HashMap<String, Object>() {
+      {
+        put("max_depth", 0);
+        put("silent", 1);
+        put("objective", "binary:logistic");
+        put("tree_method", "hist");
+        put("grow_policy", "lossguide");
+        put("max_leaves", 8);
+        put("eval_metric", "auc");
+      }
+    };
+    Map<String, DMatrix> watches = new HashMap<>();
+    watches.put("training", trainMat);
+    watches.put("test", testMat);
+    testWithFastHisto(trainMat, watches, 10, paramMap, 0.0f);
+  }
+
+  @Test
+  public void testFastHistoLossGuideMaxBin() throws XGBoostError {
+    DMatrix trainMat = new DMatrix("../../demo/data/agaricus.txt.train");
+    DMatrix testMat = new DMatrix("../../demo/data/agaricus.txt.test");
+    // testBoosterWithFastHistogram(trainMat, testMat);
+    Map<String, Object> paramMap = new HashMap<String, Object>() {
+      {
+        put("max_depth", 0);
+        put("silent", 1);
+        put("objective", "binary:logistic");
+        put("tree_method", "hist");
+        put("grow_policy", "lossguide");
+        put("max_leaves", 8);
+        put("max_bins", 16);
+        put("eval_metric", "auc");
+      }
+    };
+    Map<String, DMatrix> watches = new HashMap<>();
+    watches.put("training", trainMat);
+    testWithFastHisto(trainMat, watches, 10, paramMap, 0.0f);
+  }
+
+  @Test
+  public void testFastHistoDepthwiseMaxDepth() throws XGBoostError {
+    DMatrix trainMat = new DMatrix("../../demo/data/agaricus.txt.train");
+    DMatrix testMat = new DMatrix("../../demo/data/agaricus.txt.test");
+    // testBoosterWithFastHistogram(trainMat, testMat);
+    Map<String, Object> paramMap = new HashMap<String, Object>() {
+      {
+        put("max_depth", 3);
+        put("silent", 1);
+        put("objective", "binary:logistic");
+        put("tree_method", "hist");
+        put("max_depth", 2);
+        put("grow_policy", "depthwise");
+        put("eval_metric", "auc");
+      }
+    };
+    Map<String, DMatrix> watches = new HashMap<>();
+    watches.put("training", trainMat);
+    testWithFastHisto(trainMat, watches, 10, paramMap, 0.85f);
+  }
+
+  @Test
+  public void testFastHistoDepthwiseMaxDepthMaxBin() throws XGBoostError {
+    DMatrix trainMat = new DMatrix("../../demo/data/agaricus.txt.train");
+    DMatrix testMat = new DMatrix("../../demo/data/agaricus.txt.test");
+    // testBoosterWithFastHistogram(trainMat, testMat);
+    Map<String, Object> paramMap = new HashMap<String, Object>() {
+      {
+        put("max_depth", 3);
+        put("silent", 1);
+        put("objective", "binary:logistic");
+        put("tree_method", "hist");
+        put("max_depth", 2);
+        put("max_bin", 2);
+        put("grow_policy", "depthwise");
+        put("eval_metric", "auc");
+      }
+    };
+    Map<String, DMatrix> watches = new HashMap<>();
+    watches.put("training", trainMat);
+    testWithFastHisto(trainMat, watches, 10, paramMap, 0.85f);
+  }
+
  /**
   * test cross valiation
   *
--- a/jvm-packages/xgboost4j/src/test/scala/ml/dmlc/xgboost4j/scala/ScalaBoosterImplSuite.scala
+++ b/jvm-packages/xgboost4j/src/test/scala/ml/dmlc/xgboost4j/scala/ScalaBoosterImplSuite.scala
@@ -77,6 +77,23 @@ class ScalaBoosterImplSuite extends FunSuite {
    XGBoost.train(trainMat, paramMap, round, watches, null, null)
  }

+  private def trainBoosterWithFastHisto(
+      trainMat: DMatrix,
+      watches: Map[String, DMatrix],
+      round: Int,
+      paramMap: Map[String, String],
+      threshold: Float): Booster = {
+    val metrics = Array.fill(watches.size, round)(0.0f)
+    val booster = XGBoost.train(trainMat, paramMap, round, watches, metrics, null, null)
+    for (i <- 0 until watches.size; j <- 1 until metrics(i).length) {
+      assert(metrics(i)(j) >= metrics(i)(j - 1))
+    }
+    for (metricsArray <- metrics; m <- metricsArray) {
+      assert(m >= threshold)
+    }
+    booster
+  }
+
  test("basic operation of booster") {
    val trainMat = new DMatrix("../../demo/data/agaricus.txt.train")
    val testMat = new DMatrix("../../demo/data/agaricus.txt.test")
@@ -128,4 +145,57 @@ class ScalaBoosterImplSuite extends FunSuite {
    val nfold = 5
    XGBoost.crossValidation(trainMat, params, round, nfold, null, null, null)
  }
+
+  test("test with fast histo depthwise") {
+    val trainMat = new DMatrix("../../demo/data/agaricus.txt.train")
+    val testMat = new DMatrix("../../demo/data/agaricus.txt.test")
+    val paramMap = List("max_depth" -> "3", "silent" -> "0",
+      "objective" -> "binary:logistic", "tree_method" -> "hist",
+      "grow_policy" -> "depthwise", "eval_metric" -> "auc").toMap
+    trainBoosterWithFastHisto(trainMat, Map("training" -> trainMat, "test" -> testMat),
+      round = 10, paramMap, 0.0f)
+  }
+
+  test("test with fast histo lossguide") {
+    val trainMat = new DMatrix("../../demo/data/agaricus.txt.train")
+    val testMat = new DMatrix("../../demo/data/agaricus.txt.test")
+    val paramMap = List("max_depth" -> "0", "silent" -> "0",
+      "objective" -> "binary:logistic", "tree_method" -> "hist",
+      "grow_policy" -> "lossguide", "max_leaves" -> "8", "eval_metric" -> "auc").toMap
+    trainBoosterWithFastHisto(trainMat, Map("training" -> trainMat, "test" -> testMat),
+      round = 10, paramMap, 0.0f)
+  }
+
+  test("test with fast histo lossguide with max bin") {
+    val trainMat = new DMatrix("../../demo/data/agaricus.txt.train")
+    val testMat = new DMatrix("../../demo/data/agaricus.txt.test")
+    val paramMap = List("max_depth" -> "0", "silent" -> "0",
+      "objective" -> "binary:logistic", "tree_method" -> "hist",
+      "grow_policy" -> "lossguide", "max_leaves" -> "8", "max_bin" -> "16",
+      "eval_metric" -> "auc").toMap
+    trainBoosterWithFastHisto(trainMat, Map("training" -> trainMat),
+      round = 10, paramMap, 0.0f)
+  }
+
+  test("test with fast histo depthwidth with max depth") {
+    val trainMat = new DMatrix("../../demo/data/agaricus.txt.train")
+    val testMat = new DMatrix("../../demo/data/agaricus.txt.test")
+    val paramMap = List("max_depth" -> "0", "silent" -> "0",
+      "objective" -> "binary:logistic", "tree_method" -> "hist",
+      "grow_policy" -> "depthwise", "max_leaves" -> "8", "max_depth" -> "2",
+      "eval_metric" -> "auc").toMap
+    trainBoosterWithFastHisto(trainMat, Map("training" -> trainMat),
+      round = 10, paramMap, 0.85f)
+  }
+
+  test("test with fast histo depthwidth with max depth and max bin") {
+    val trainMat = new DMatrix("../../demo/data/agaricus.txt.train")
+    val testMat = new DMatrix("../../demo/data/agaricus.txt.test")
+    val paramMap = List("max_depth" -> "0", "silent" -> "0",
+      "objective" -> "binary:logistic", "tree_method" -> "hist",
+      "grow_policy" -> "depthwise", "max_depth" -> "2", "max_bin" -> "2",
+      "eval_metric" -> "auc").toMap
+    trainBoosterWithFastHisto(trainMat, Map("training" -> trainMat),
+      round = 10, paramMap, 0.85f)
+  }
 }