You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@ignite.apache.org by ch...@apache.org on 2018/08/30 16:29:06 UTC
[3/3] ignite git commit: IGNITE-9237: [ML] Random forest optimization
IGNITE-9237: [ML] Random forest optimization
this closes #4612
Project: http://git-wip-us.apache.org/repos/asf/ignite/repo
Commit: http://git-wip-us.apache.org/repos/asf/ignite/commit/78328fe4
Tree: http://git-wip-us.apache.org/repos/asf/ignite/tree/78328fe4
Diff: http://git-wip-us.apache.org/repos/asf/ignite/diff/78328fe4
Branch: refs/heads/master
Commit: 78328fe491e6b73b5a9d581af51846badbec287b
Parents: 2bf48e5
Author: Alexey Platonov <ap...@gmail.com>
Authored: Thu Aug 30 19:28:34 2018 +0300
Committer: Yury Babak <yb...@gridgain.com>
Committed: Thu Aug 30 19:28:34 2018 +0300
----------------------------------------------------------------------
.../RandomForestClassificationExample.java | 386 ++++++++++---------
.../RandomForestRegressionExample.java | 26 +-
modules/ml/pom.xml | 13 +-
.../WeightedPredictionsAggregator.java | 2 +-
.../ignite/ml/dataset/feature/BucketMeta.java | 88 +++++
.../dataset/feature/DistributionComputer.java | 32 ++
.../ignite/ml/dataset/feature/FeatureMeta.java | 65 ++++
.../ignite/ml/dataset/feature/Histogram.java | 64 +++
.../ml/dataset/feature/ObjectHistogram.java | 129 +++++++
.../ignite/ml/dataset/feature/package-info.java | 24 ++
.../BootstrappedDatasetBuilder.java | 90 +++++
.../BootstrappedDatasetPartition.java | 68 ++++
.../impl/bootstrapping/BootstrappedVector.java | 87 +++++
.../impl/bootstrapping/package-info.java | 23 ++
.../RandomForestClassifierTrainer.java | 117 +++---
.../RandomForestRegressionTrainer.java | 82 ++--
.../tree/randomforest/RandomForestTrainer.java | 372 ++++++++++++++++--
.../data/FeaturesCountSelectionStrategies.java | 47 +++
.../ml/tree/randomforest/data/NodeId.java | 55 +++
.../ml/tree/randomforest/data/NodeSplit.java | 79 ++++
.../ml/tree/randomforest/data/TreeNode.java | 200 ++++++++++
.../ml/tree/randomforest/data/TreeRoot.java | 86 +++++
.../data/impurity/GiniHistogram.java | 225 +++++++++++
.../data/impurity/GiniHistogramsComputer.java | 46 +++
.../data/impurity/ImpurityComputer.java | 38 ++
.../data/impurity/ImpurityHistogram.java | 74 ++++
.../impurity/ImpurityHistogramsComputer.java | 211 ++++++++++
.../data/impurity/MSEHistogram.java | 235 +++++++++++
.../data/impurity/MSEHistogramComputer.java | 33 ++
.../data/impurity/package-info.java | 22 ++
.../ml/tree/randomforest/data/package-info.java | 22 ++
.../ClassifierLeafValuesComputer.java | 82 ++++
.../data/statistics/LeafValuesComputer.java | 158 ++++++++
.../data/statistics/MeanValueStatistic.java | 72 ++++
.../NormalDistributionStatistics.java | 112 ++++++
.../NormalDistributionStatisticsComputer.java | 119 ++++++
.../RegressionLeafValuesComputer.java | 62 +++
.../data/statistics/package-info.java | 22 ++
.../ignite/ml/dataset/DatasetTestSuite.java | 4 +-
.../ml/dataset/feature/ObjectHistogramTest.java | 170 ++++++++
.../ml/environment/EnvironmentTestSuite.java | 1 -
.../ml/environment/LearningEnvironmentTest.java | 187 ---------
.../ignite/ml/tree/DecisionTreeTestSuite.java | 6 +-
.../RandomForestClassifierTrainerTest.java | 26 +-
.../RandomForestRegressionTrainerTest.java | 17 +-
.../ml/tree/randomforest/RandomForestTest.java | 78 ++++
.../randomforest/RandomForestTreeTestSuite.java | 39 ++
.../ml/tree/randomforest/data/TreeNodeTest.java | 79 ++++
.../data/impurity/GiniFeatureHistogramTest.java | 254 ++++++++++++
.../data/impurity/ImpurityHistogramTest.java | 69 ++++
.../data/impurity/MSEHistogramTest.java | 135 +++++++
...ormalDistributionStatisticsComputerTest.java | 130 +++++++
52 files changed, 4309 insertions(+), 554 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/ignite/blob/78328fe4/examples/src/main/java/org/apache/ignite/examples/ml/tree/randomforest/RandomForestClassificationExample.java
----------------------------------------------------------------------
diff --git a/examples/src/main/java/org/apache/ignite/examples/ml/tree/randomforest/RandomForestClassificationExample.java b/examples/src/main/java/org/apache/ignite/examples/ml/tree/randomforest/RandomForestClassificationExample.java
index 09c1e4f..4ea471c 100644
--- a/examples/src/main/java/org/apache/ignite/examples/ml/tree/randomforest/RandomForestClassificationExample.java
+++ b/examples/src/main/java/org/apache/ignite/examples/ml/tree/randomforest/RandomForestClassificationExample.java
@@ -18,6 +18,9 @@
package org.apache.ignite.examples.ml.tree.randomforest;
import java.util.Arrays;
+import java.util.concurrent.atomic.AtomicInteger;
+import java.util.stream.Collectors;
+import java.util.stream.IntStream;
import javax.cache.Cache;
import org.apache.ignite.Ignite;
import org.apache.ignite.IgniteCache;
@@ -26,18 +29,20 @@ import org.apache.ignite.cache.query.QueryCursor;
import org.apache.ignite.cache.query.ScanQuery;
import org.apache.ignite.examples.ml.util.TestCache;
import org.apache.ignite.ml.composition.ModelsComposition;
+import org.apache.ignite.ml.dataset.feature.FeatureMeta;
import org.apache.ignite.ml.math.primitives.vector.VectorUtils;
import org.apache.ignite.ml.tree.randomforest.RandomForestClassifierTrainer;
import org.apache.ignite.ml.tree.randomforest.RandomForestTrainer;
+import org.apache.ignite.ml.tree.randomforest.data.FeaturesCountSelectionStrategies;
import org.apache.ignite.thread.IgniteThread;
/**
- * Example represents a solution for the task of wine classification based on RandomForest
- * implementation for multi-classification. It shows an initialization of {@link RandomForestTrainer} with
- * thread pool for multi-thread learning, initialization of Ignite Cache,
- * learning step and evaluation of accuracy of model.
+ * Example represents a solution for the task of wine classification based on RandomForestTrainer implementation for
+ * multi-classification. It shows an initialization of {@link RandomForestTrainer} with thread pool for multi-thread
+ * learning, initialization of Ignite Cache, learning step and evaluation of accuracy of model.
*
* Dataset url: https://archive.ics.uci.edu/ml/machine-learning-databases/wine/
+ *
* @see RandomForestClassifierTrainer
*/
public class RandomForestClassificationExample {
@@ -55,11 +60,18 @@ public class RandomForestClassificationExample {
RandomForestClassificationExample.class.getSimpleName(), () -> {
IgniteCache<Integer, double[]> dataCache = new TestCache(ignite).fillCacheWith(data);
- RandomForestClassifierTrainer trainer = new RandomForestClassifierTrainer(13, 4, 101, 0.3, 2, 0);
+ AtomicInteger indx = new AtomicInteger(0);
+ RandomForestClassifierTrainer classifier = new RandomForestClassifierTrainer(
+ IntStream.range(0, 13).mapToObj(x -> new FeatureMeta("", indx.getAndIncrement(), false)).collect(Collectors.toList()))
+ .withCountOfTrees(101)
+ .withFeaturesCountSelectionStrgy(FeaturesCountSelectionStrategies.SQRT)
+ .withMaxDepth(3)
+ .withMinImpurityDelta(0.)
+ .withSubsampleSize(0.3);
- ModelsComposition randomForest = trainer.fit(ignite, dataCache,
- (k, v) -> VectorUtils.of(Arrays.copyOfRange(v, 1, v.length)),
- (k, v) -> v[0]
+ ModelsComposition randomForest = classifier.fit(ignite, dataCache,
+ (k, v) -> VectorUtils.of(Arrays.copyOfRange(v, 1, v.length)),
+ (k, v) -> v[0]
);
int amountOfErrors = 0;
@@ -80,7 +92,7 @@ public class RandomForestClassificationExample {
}
System.out.println("\n>>> Absolute amount of errors " + amountOfErrors);
- System.out.println("\n>>> Accuracy " + (1 - amountOfErrors / (double) totalAmount));
+ System.out.println("\n>>> Accuracy " + (1 - amountOfErrors / (double)totalAmount));
}
});
@@ -93,183 +105,183 @@ public class RandomForestClassificationExample {
* The Wine dataset.
*/
private static final double[][] data = {
- {1, 14.23, 1.71, 2.43, 15.6, 127, 2.8, 3.06, .28, 2.29, 5.64, 1.04, 3.92, 1065},
- {1, 13.2, 1.78, 2.14, 11.2, 100, 2.65, 2.76, .26, 1.28, 4.38, 1.05, 3.4, 1050},
- {1, 13.16, 2.36, 2.67, 18.6, 101, 2.8, 3.24, .3, 2.81, 5.68, 1.03, 3.17, 1185},
- {1, 14.37, 1.95, 2.5, 16.8, 113, 3.85, 3.49, .24, 2.18, 7.8, .86, 3.45, 1480},
- {1, 13.24, 2.59, 2.87, 21, 118, 2.8, 2.69, .39, 1.82, 4.32, 1.04, 2.93, 735},
- {1, 14.2, 1.76, 2.45, 15.2, 112, 3.27, 3.39, .34, 1.97, 6.75, 1.05, 2.85, 1450},
- {1, 14.39, 1.87, 2.45, 14.6, 96, 2.5, 2.52, .3, 1.98, 5.25, 1.02, 3.58, 1290},
- {1, 14.06, 2.15, 2.61, 17.6, 121, 2.6, 2.51, .31, 1.25, 5.05, 1.06, 3.58, 1295},
- {1, 14.83, 1.64, 2.17, 14, 97, 2.8, 2.98, .29, 1.98, 5.2, 1.08, 2.85, 1045},
- {1, 13.86, 1.35, 2.27, 16, 98, 2.98, 3.15, .22, 1.85, 7.22, 1.01, 3.55, 1045},
- {1, 14.1, 2.16, 2.3, 18, 105, 2.95, 3.32, .22, 2.38, 5.75, 1.25, 3.17, 1510},
- {1, 14.12, 1.48, 2.32, 16.8, 95, 2.2, 2.43, .26, 1.57, 5, 1.17, 2.82, 1280},
- {1, 13.75, 1.73, 2.41, 16, 89, 2.6, 2.76, .29, 1.81, 5.6, 1.15, 2.9, 1320},
- {1, 14.75, 1.73, 2.39, 11.4, 91, 3.1, 3.69, .43, 2.81, 5.4, 1.25, 2.73, 1150},
- {1, 14.38, 1.87, 2.38, 12, 102, 3.3, 3.64, .29, 2.96, 7.5, 1.2, 3, 1547},
- {1, 13.63, 1.81, 2.7, 17.2, 112, 2.85, 2.91, .3, 1.46, 7.3, 1.28, 2.88, 1310},
- {1, 14.3, 1.92, 2.72, 20, 120, 2.8, 3.14, .33, 1.97, 6.2, 1.07, 2.65, 1280},
- {1, 13.83, 1.57, 2.62, 20, 115, 2.95, 3.4, .4, 1.72, 6.6, 1.13, 2.57, 1130},
- {1, 14.19, 1.59, 2.48, 16.5, 108, 3.3, 3.93, .32, 1.86, 8.7, 1.23, 2.82, 1680},
- {1, 13.64, 3.1, 2.56, 15.2, 116, 2.7, 3.03, .17, 1.66, 5.1, .96, 3.36, 845},
- {1, 14.06, 1.63, 2.28, 16, 126, 3, 3.17, .24, 2.1, 5.65, 1.09, 3.71, 780},
- {1, 12.93, 3.8, 2.65, 18.6, 102, 2.41, 2.41, .25, 1.98, 4.5, 1.03, 3.52, 770},
- {1, 13.71, 1.86, 2.36, 16.6, 101, 2.61, 2.88, .27, 1.69, 3.8, 1.11, 4, 1035},
- {1, 12.85, 1.6, 2.52, 17.8, 95, 2.48, 2.37, .26, 1.46, 3.93, 1.09, 3.63, 1015},
- {1, 13.5, 1.81, 2.61, 20, 96, 2.53, 2.61, .28, 1.66, 3.52, 1.12, 3.82, 845},
- {1, 13.05, 2.05, 3.22, 25, 124, 2.63, 2.68, .47, 1.92, 3.58, 1.13, 3.2, 830},
- {1, 13.39, 1.77, 2.62, 16.1, 93, 2.85, 2.94, .34, 1.45, 4.8, .92, 3.22, 1195},
- {1, 13.3, 1.72, 2.14, 17, 94, 2.4, 2.19, .27, 1.35, 3.95, 1.02, 2.77, 1285},
- {1, 13.87, 1.9, 2.8, 19.4, 107, 2.95, 2.97, .37, 1.76, 4.5, 1.25, 3.4, 915},
- {1, 14.02, 1.68, 2.21, 16, 96, 2.65, 2.33, .26, 1.98, 4.7, 1.04, 3.59, 1035},
- {1, 13.73, 1.5, 2.7, 22.5, 101, 3, 3.25, .29, 2.38, 5.7, 1.19, 2.71, 1285},
- {1, 13.58, 1.66, 2.36, 19.1, 106, 2.86, 3.19, .22, 1.95, 6.9, 1.09, 2.88, 1515},
- {1, 13.68, 1.83, 2.36, 17.2, 104, 2.42, 2.69, .42, 1.97, 3.84, 1.23, 2.87, 990},
- {1, 13.76, 1.53, 2.7, 19.5, 132, 2.95, 2.74, .5, 1.35, 5.4, 1.25, 3, 1235},
- {1, 13.51, 1.8, 2.65, 19, 110, 2.35, 2.53, .29, 1.54, 4.2, 1.1, 2.87, 1095},
- {1, 13.48, 1.81, 2.41, 20.5, 100, 2.7, 2.98, .26, 1.86, 5.1, 1.04, 3.47, 920},
- {1, 13.28, 1.64, 2.84, 15.5, 110, 2.6, 2.68, .34, 1.36, 4.6, 1.09, 2.78, 880},
- {1, 13.05, 1.65, 2.55, 18, 98, 2.45, 2.43, .29, 1.44, 4.25, 1.12, 2.51, 1105},
- {1, 13.07, 1.5, 2.1, 15.5, 98, 2.4, 2.64, .28, 1.37, 3.7, 1.18, 2.69, 1020},
- {1, 14.22, 3.99, 2.51, 13.2, 128, 3, 3.04, .2, 2.08, 5.1, .89, 3.53, 760},
- {1, 13.56, 1.71, 2.31, 16.2, 117, 3.15, 3.29, .34, 2.34, 6.13, .95, 3.38, 795},
- {1, 13.41, 3.84, 2.12, 18.8, 90, 2.45, 2.68, .27, 1.48, 4.28, .91, 3, 1035},
- {1, 13.88, 1.89, 2.59, 15, 101, 3.25, 3.56, .17, 1.7, 5.43, .88, 3.56, 1095},
- {1, 13.24, 3.98, 2.29, 17.5, 103, 2.64, 2.63, .32, 1.66, 4.36, .82, 3, 680},
- {1, 13.05, 1.77, 2.1, 17, 107, 3, 3, .28, 2.03, 5.04, .88, 3.35, 885},
- {1, 14.21, 4.04, 2.44, 18.9, 111, 2.85, 2.65, .3, 1.25, 5.24, .87, 3.33, 1080},
- {1, 14.38, 3.59, 2.28, 16, 102, 3.25, 3.17, .27, 2.19, 4.9, 1.04, 3.44, 1065},
- {1, 13.9, 1.68, 2.12, 16, 101, 3.1, 3.39, .21, 2.14, 6.1, .91, 3.33, 985},
- {1, 14.1, 2.02, 2.4, 18.8, 103, 2.75, 2.92, .32, 2.38, 6.2, 1.07, 2.75, 1060},
- {1, 13.94, 1.73, 2.27, 17.4, 108, 2.88, 3.54, .32, 2.08, 8.90, 1.12, 3.1, 1260},
- {1, 13.05, 1.73, 2.04, 12.4, 92, 2.72, 3.27, .17, 2.91, 7.2, 1.12, 2.91, 1150},
- {1, 13.83, 1.65, 2.6, 17.2, 94, 2.45, 2.99, .22, 2.29, 5.6, 1.24, 3.37, 1265},
- {1, 13.82, 1.75, 2.42, 14, 111, 3.88, 3.74, .32, 1.87, 7.05, 1.01, 3.26, 1190},
- {1, 13.77, 1.9, 2.68, 17.1, 115, 3, 2.79, .39, 1.68, 6.3, 1.13, 2.93, 1375},
- {1, 13.74, 1.67, 2.25, 16.4, 118, 2.6, 2.9, .21, 1.62, 5.85, .92, 3.2, 1060},
- {1, 13.56, 1.73, 2.46, 20.5, 116, 2.96, 2.78, .2, 2.45, 6.25, .98, 3.03, 1120},
- {1, 14.22, 1.7, 2.3, 16.3, 118, 3.2, 3, .26, 2.03, 6.38, .94, 3.31, 970},
- {1, 13.29, 1.97, 2.68, 16.8, 102, 3, 3.23, .31, 1.66, 6, 1.07, 2.84, 1270},
- {1, 13.72, 1.43, 2.5, 16.7, 108, 3.4, 3.67, .19, 2.04, 6.8, .89, 2.87, 1285},
- {2, 12.37, .94, 1.36, 10.6, 88, 1.98, .57, .28, .42, 1.95, 1.05, 1.82, 520},
- {2, 12.33, 1.1, 2.28, 16, 101, 2.05, 1.09, .63, .41, 3.27, 1.25, 1.67, 680},
- {2, 12.64, 1.36, 2.02, 16.8, 100, 2.02, 1.41, .53, .62, 5.75, .98, 1.59, 450},
- {2, 13.67, 1.25, 1.92, 18, 94, 2.1, 1.79, .32, .73, 3.8, 1.23, 2.46, 630},
- {2, 12.37, 1.13, 2.16, 19, 87, 3.5, 3.1, .19, 1.87, 4.45, 1.22, 2.87, 420},
- {2, 12.17, 1.45, 2.53, 19, 104, 1.89, 1.75, .45, 1.03, 2.95, 1.45, 2.23, 355},
- {2, 12.37, 1.21, 2.56, 18.1, 98, 2.42, 2.65, .37, 2.08, 4.6, 1.19, 2.3, 678},
- {2, 13.11, 1.01, 1.7, 15, 78, 2.98, 3.18, .26, 2.28, 5.3, 1.12, 3.18, 502},
- {2, 12.37, 1.17, 1.92, 19.6, 78, 2.11, 2, .27, 1.04, 4.68, 1.12, 3.48, 510},
- {2, 13.34, .94, 2.36, 17, 110, 2.53, 1.3, .55, .42, 3.17, 1.02, 1.93, 750},
- {2, 12.21, 1.19, 1.75, 16.8, 151, 1.85, 1.28, .14, 2.5, 2.85, 1.28, 3.07, 718},
- {2, 12.29, 1.61, 2.21, 20.4, 103, 1.1, 1.02, .37, 1.46, 3.05, .906, 1.82, 870},
- {2, 13.86, 1.51, 2.67, 25, 86, 2.95, 2.86, .21, 1.87, 3.38, 1.36, 3.16, 410},
- {2, 13.49, 1.66, 2.24, 24, 87, 1.88, 1.84, .27, 1.03, 3.74, .98, 2.78, 472},
- {2, 12.99, 1.67, 2.6, 30, 139, 3.3, 2.89, .21, 1.96, 3.35, 1.31, 3.5, 985},
- {2, 11.96, 1.09, 2.3, 21, 101, 3.38, 2.14, .13, 1.65, 3.21, .99, 3.13, 886},
- {2, 11.66, 1.88, 1.92, 16, 97, 1.61, 1.57, .34, 1.15, 3.8, 1.23, 2.14, 428},
- {2, 13.03, .9, 1.71, 16, 86, 1.95, 2.03, .24, 1.46, 4.6, 1.19, 2.48, 392},
- {2, 11.84, 2.89, 2.23, 18, 112, 1.72, 1.32, .43, .95, 2.65, .96, 2.52, 500},
- {2, 12.33, .99, 1.95, 14.8, 136, 1.9, 1.85, .35, 2.76, 3.4, 1.06, 2.31, 750},
- {2, 12.7, 3.87, 2.4, 23, 101, 2.83, 2.55, .43, 1.95, 2.57, 1.19, 3.13, 463},
- {2, 12, .92, 2, 19, 86, 2.42, 2.26, .3, 1.43, 2.5, 1.38, 3.12, 278},
- {2, 12.72, 1.81, 2.2, 18.8, 86, 2.2, 2.53, .26, 1.77, 3.9, 1.16, 3.14, 714},
- {2, 12.08, 1.13, 2.51, 24, 78, 2, 1.58, .4, 1.4, 2.2, 1.31, 2.72, 630},
- {2, 13.05, 3.86, 2.32, 22.5, 85, 1.65, 1.59, .61, 1.62, 4.8, .84, 2.01, 515},
- {2, 11.84, .89, 2.58, 18, 94, 2.2, 2.21, .22, 2.35, 3.05, .79, 3.08, 520},
- {2, 12.67, .98, 2.24, 18, 99, 2.2, 1.94, .3, 1.46, 2.62, 1.23, 3.16, 450},
- {2, 12.16, 1.61, 2.31, 22.8, 90, 1.78, 1.69, .43, 1.56, 2.45, 1.33, 2.26, 495},
- {2, 11.65, 1.67, 2.62, 26, 88, 1.92, 1.61, .4, 1.34, 2.6, 1.36, 3.21, 562},
- {2, 11.64, 2.06, 2.46, 21.6, 84, 1.95, 1.69, .48, 1.35, 2.8, 1, 2.75, 680},
- {2, 12.08, 1.33, 2.3, 23.6, 70, 2.2, 1.59, .42, 1.38, 1.74, 1.07, 3.21, 625},
- {2, 12.08, 1.83, 2.32, 18.5, 81, 1.6, 1.5, .52, 1.64, 2.4, 1.08, 2.27, 480},
- {2, 12, 1.51, 2.42, 22, 86, 1.45, 1.25, .5, 1.63, 3.6, 1.05, 2.65, 450},
- {2, 12.69, 1.53, 2.26, 20.7, 80, 1.38, 1.46, .58, 1.62, 3.05, .96, 2.06, 495},
- {2, 12.29, 2.83, 2.22, 18, 88, 2.45, 2.25, .25, 1.99, 2.15, 1.15, 3.3, 290},
- {2, 11.62, 1.99, 2.28, 18, 98, 3.02, 2.26, .17, 1.35, 3.25, 1.16, 2.96, 345},
- {2, 12.47, 1.52, 2.2, 19, 162, 2.5, 2.27, .32, 3.28, 2.6, 1.16, 2.63, 937},
- {2, 11.81, 2.12, 2.74, 21.5, 134, 1.6, .99, .14, 1.56, 2.5, .95, 2.26, 625},
- {2, 12.29, 1.41, 1.98, 16, 85, 2.55, 2.5, .29, 1.77, 2.9, 1.23, 2.74, 428},
- {2, 12.37, 1.07, 2.1, 18.5, 88, 3.52, 3.75, .24, 1.95, 4.5, 1.04, 2.77, 660},
- {2, 12.29, 3.17, 2.21, 18, 88, 2.85, 2.99, .45, 2.81, 2.3, 1.42, 2.83, 406},
- {2, 12.08, 2.08, 1.7, 17.5, 97, 2.23, 2.17, .26, 1.4, 3.3, 1.27, 2.96, 710},
- {2, 12.6, 1.34, 1.9, 18.5, 88, 1.45, 1.36, .29, 1.35, 2.45, 1.04, 2.77, 562},
- {2, 12.34, 2.45, 2.46, 21, 98, 2.56, 2.11, .34, 1.31, 2.8, .8, 3.38, 438},
- {2, 11.82, 1.72, 1.88, 19.5, 86, 2.5, 1.64, .37, 1.42, 2.06, .94, 2.44, 415},
- {2, 12.51, 1.73, 1.98, 20.5, 85, 2.2, 1.92, .32, 1.48, 2.94, 1.04, 3.57, 672},
- {2, 12.42, 2.55, 2.27, 22, 90, 1.68, 1.84, .66, 1.42, 2.7, .86, 3.3, 315},
- {2, 12.25, 1.73, 2.12, 19, 80, 1.65, 2.03, .37, 1.63, 3.4, 1, 3.17, 510},
- {2, 12.72, 1.75, 2.28, 22.5, 84, 1.38, 1.76, .48, 1.63, 3.3, .88, 2.42, 488},
- {2, 12.22, 1.29, 1.94, 19, 92, 2.36, 2.04, .39, 2.08, 2.7, .86, 3.02, 312},
- {2, 11.61, 1.35, 2.7, 20, 94, 2.74, 2.92, .29, 2.49, 2.65, .96, 3.26, 680},
- {2, 11.46, 3.74, 1.82, 19.5, 107, 3.18, 2.58, .24, 3.58, 2.9, .75, 2.81, 562},
- {2, 12.52, 2.43, 2.17, 21, 88, 2.55, 2.27, .26, 1.22, 2, .9, 2.78, 325},
- {2, 11.76, 2.68, 2.92, 20, 103, 1.75, 2.03, .6, 1.05, 3.8, 1.23, 2.5, 607},
- {2, 11.41, .74, 2.5, 21, 88, 2.48, 2.01, .42, 1.44, 3.08, 1.1, 2.31, 434},
- {2, 12.08, 1.39, 2.5, 22.5, 84, 2.56, 2.29, .43, 1.04, 2.9, .93, 3.19, 385},
- {2, 11.03, 1.51, 2.2, 21.5, 85, 2.46, 2.17, .52, 2.01, 1.9, 1.71, 2.87, 407},
- {2, 11.82, 1.47, 1.99, 20.8, 86, 1.98, 1.6, .3, 1.53, 1.95, .95, 3.33, 495},
- {2, 12.42, 1.61, 2.19, 22.5, 108, 2, 2.09, .34, 1.61, 2.06, 1.06, 2.96, 345},
- {2, 12.77, 3.43, 1.98, 16, 80, 1.63, 1.25, .43, .83, 3.4, .7, 2.12, 372},
- {2, 12, 3.43, 2, 19, 87, 2, 1.64, .37, 1.87, 1.28, .93, 3.05, 564},
- {2, 11.45, 2.4, 2.42, 20, 96, 2.9, 2.79, .32, 1.83, 3.25, .8, 3.39, 625},
- {2, 11.56, 2.05, 3.23, 28.5, 119, 3.18, 5.08, .47, 1.87, 6, .93, 3.69, 465},
- {2, 12.42, 4.43, 2.73, 26.5, 102, 2.2, 2.13, .43, 1.71, 2.08, .92, 3.12, 365},
- {2, 13.05, 5.8, 2.13, 21.5, 86, 2.62, 2.65, .3, 2.01, 2.6, .73, 3.1, 380},
- {2, 11.87, 4.31, 2.39, 21, 82, 2.86, 3.03, .21, 2.91, 2.8, .75, 3.64, 380},
- {2, 12.07, 2.16, 2.17, 21, 85, 2.6, 2.65, .37, 1.35, 2.76, .86, 3.28, 378},
- {2, 12.43, 1.53, 2.29, 21.5, 86, 2.74, 3.15, .39, 1.77, 3.94, .69, 2.84, 352},
- {2, 11.79, 2.13, 2.78, 28.5, 92, 2.13, 2.24, .58, 1.76, 3, .97, 2.44, 466},
- {2, 12.37, 1.63, 2.3, 24.5, 88, 2.22, 2.45, .4, 1.9, 2.12, .89, 2.78, 342},
- {2, 12.04, 4.3, 2.38, 22, 80, 2.1, 1.75, .42, 1.35, 2.6, .79, 2.57, 580},
- {3, 12.86, 1.35, 2.32, 18, 122, 1.51, 1.25, .21, .94, 4.1, .76, 1.29, 630},
- {3, 12.88, 2.99, 2.4, 20, 104, 1.3, 1.22, .24, .83, 5.4, .74, 1.42, 530},
- {3, 12.81, 2.31, 2.4, 24, 98, 1.15, 1.09, .27, .83, 5.7, .66, 1.36, 560},
- {3, 12.7, 3.55, 2.36, 21.5, 106, 1.7, 1.2, .17, .84, 5, .78, 1.29, 600},
- {3, 12.51, 1.24, 2.25, 17.5, 85, 2, .58, .6, 1.25, 5.45, .75, 1.51, 650},
- {3, 12.6, 2.46, 2.2, 18.5, 94, 1.62, .66, .63, .94, 7.1, .73, 1.58, 695},
- {3, 12.25, 4.72, 2.54, 21, 89, 1.38, .47, .53, .8, 3.85, .75, 1.27, 720},
- {3, 12.53, 5.51, 2.64, 25, 96, 1.79, .6, .63, 1.1, 5, .82, 1.69, 515},
- {3, 13.49, 3.59, 2.19, 19.5, 88, 1.62, .48, .58, .88, 5.7, .81, 1.82, 580},
- {3, 12.84, 2.96, 2.61, 24, 101, 2.32, .6, .53, .81, 4.92, .89, 2.15, 590},
- {3, 12.93, 2.81, 2.7, 21, 96, 1.54, .5, .53, .75, 4.6, .77, 2.31, 600},
- {3, 13.36, 2.56, 2.35, 20, 89, 1.4, .5, .37, .64, 5.6, .7, 2.47, 780},
- {3, 13.52, 3.17, 2.72, 23.5, 97, 1.55, .52, .5, .55, 4.35, .89, 2.06, 520},
- {3, 13.62, 4.95, 2.35, 20, 92, 2, .8, .47, 1.02, 4.4, .91, 2.05, 550},
- {3, 12.25, 3.88, 2.2, 18.5, 112, 1.38, .78, .29, 1.14, 8.21, .65, 2, 855},
- {3, 13.16, 3.57, 2.15, 21, 102, 1.5, .55, .43, 1.3, 4, .6, 1.68, 830},
- {3, 13.88, 5.04, 2.23, 20, 80, .98, .34, .4, .68, 4.9, .58, 1.33, 415},
- {3, 12.87, 4.61, 2.48, 21.5, 86, 1.7, .65, .47, .86, 7.65, .54, 1.86, 625},
- {3, 13.32, 3.24, 2.38, 21.5, 92, 1.93, .76, .45, 1.25, 8.42, .55, 1.62, 650},
- {3, 13.08, 3.9, 2.36, 21.5, 113, 1.41, 1.39, .34, 1.14, 9.40, .57, 1.33, 550},
- {3, 13.5, 3.12, 2.62, 24, 123, 1.4, 1.57, .22, 1.25, 8.60, .59, 1.3, 500},
- {3, 12.79, 2.67, 2.48, 22, 112, 1.48, 1.36, .24, 1.26, 10.8, .48, 1.47, 480},
- {3, 13.11, 1.9, 2.75, 25.5, 116, 2.2, 1.28, .26, 1.56, 7.1, .61, 1.33, 425},
- {3, 13.23, 3.3, 2.28, 18.5, 98, 1.8, .83, .61, 1.87, 10.52, .56, 1.51, 675},
- {3, 12.58, 1.29, 2.1, 20, 103, 1.48, .58, .53, 1.4, 7.6, .58, 1.55, 640},
- {3, 13.17, 5.19, 2.32, 22, 93, 1.74, .63, .61, 1.55, 7.9, .6, 1.48, 725},
- {3, 13.84, 4.12, 2.38, 19.5, 89, 1.8, .83, .48, 1.56, 9.01, .57, 1.64, 480},
- {3, 12.45, 3.03, 2.64, 27, 97, 1.9, .58, .63, 1.14, 7.5, .67, 1.73, 880},
- {3, 14.34, 1.68, 2.7, 25, 98, 2.8, 1.31, .53, 2.7, 13, .57, 1.96, 660},
- {3, 13.48, 1.67, 2.64, 22.5, 89, 2.6, 1.1, .52, 2.29, 11.75, .57, 1.78, 620},
- {3, 12.36, 3.83, 2.38, 21, 88, 2.3, .92, .5, 1.04, 7.65, .56, 1.58, 520},
- {3, 13.69, 3.26, 2.54, 20, 107, 1.83, .56, .5, .8, 5.88, .96, 1.82, 680},
- {3, 12.85, 3.27, 2.58, 22, 106, 1.65, .6, .6, .96, 5.58, .87, 2.11, 570},
- {3, 12.96, 3.45, 2.35, 18.5, 106, 1.39, .7, .4, .94, 5.28, .68, 1.75, 675},
- {3, 13.78, 2.76, 2.3, 22, 90, 1.35, .68, .41, 1.03, 9.58, .7, 1.68, 615},
- {3, 13.73, 4.36, 2.26, 22.5, 88, 1.28, .47, .52, 1.15, 6.62, .78, 1.75, 520},
- {3, 13.45, 3.7, 2.6, 23, 111, 1.7, .92, .43, 1.46, 10.68, .85, 1.56, 695},
- {3, 12.82, 3.37, 2.3, 19.5, 88, 1.48, .66, .4, .97, 10.26, .72, 1.75, 685},
- {3, 13.58, 2.58, 2.69, 24.5, 105, 1.55, .84, .39, 1.54, 8.66, .74, 1.8, 750},
- {3, 13.4, 4.6, 2.86, 25, 112, 1.98, .96, .27, 1.11, 8.5, .67, 1.92, 630},
- {3, 12.2, 3.03, 2.32, 19, 96, 1.25, .49, .4, .73, 5.5, .66, 1.83, 510},
- {3, 12.77, 2.39, 2.28, 19.5, 86, 1.39, .51, .48, .64, 9.899999, .57, 1.63, 470},
- {3, 14.16, 2.51, 2.48, 20, 91, 1.68, .7, .44, 1.24, 9.7, .62, 1.71, 660},
- {3, 13.71, 5.65, 2.45, 20.5, 95, 1.68, .61, .52, 1.06, 7.7, .64, 1.74, 740},
- {3, 13.4, 3.91, 2.48, 23, 102, 1.8, .75, .43, 1.41, 7.3, .7, 1.56, 750},
- {3, 13.27, 4.28, 2.26, 20, 120, 1.59, .69, .43, 1.35, 10.2, .59, 1.56, 835},
- {3, 13.17, 2.59, 2.37, 20, 120, 1.65, .68, .53, 1.46, 9.3, .6, 1.62, 840},
- {3, 14.13, 4.1, 2.74, 24.5, 96, 2.05, .76, .56, 1.35, 9.2, .61, 1.6, 560}
+ {1, 14.23, 1.71, 2.43, 15.6, 127, 2.8, 3.06, .28, 2.29, 5.64, 1.04, 3.92, 1065},
+ {1, 13.2, 1.78, 2.14, 11.2, 100, 2.65, 2.76, .26, 1.28, 4.38, 1.05, 3.4, 1050},
+ {1, 13.16, 2.36, 2.67, 18.6, 101, 2.8, 3.24, .3, 2.81, 5.68, 1.03, 3.17, 1185},
+ {1, 14.37, 1.95, 2.5, 16.8, 113, 3.85, 3.49, .24, 2.18, 7.8, .86, 3.45, 1480},
+ {1, 13.24, 2.59, 2.87, 21, 118, 2.8, 2.69, .39, 1.82, 4.32, 1.04, 2.93, 735},
+ {1, 14.2, 1.76, 2.45, 15.2, 112, 3.27, 3.39, .34, 1.97, 6.75, 1.05, 2.85, 1450},
+ {1, 14.39, 1.87, 2.45, 14.6, 96, 2.5, 2.52, .3, 1.98, 5.25, 1.02, 3.58, 1290},
+ {1, 14.06, 2.15, 2.61, 17.6, 121, 2.6, 2.51, .31, 1.25, 5.05, 1.06, 3.58, 1295},
+ {1, 14.83, 1.64, 2.17, 14, 97, 2.8, 2.98, .29, 1.98, 5.2, 1.08, 2.85, 1045},
+ {1, 13.86, 1.35, 2.27, 16, 98, 2.98, 3.15, .22, 1.85, 7.22, 1.01, 3.55, 1045},
+ {1, 14.1, 2.16, 2.3, 18, 105, 2.95, 3.32, .22, 2.38, 5.75, 1.25, 3.17, 1510},
+ {1, 14.12, 1.48, 2.32, 16.8, 95, 2.2, 2.43, .26, 1.57, 5, 1.17, 2.82, 1280},
+ {1, 13.75, 1.73, 2.41, 16, 89, 2.6, 2.76, .29, 1.81, 5.6, 1.15, 2.9, 1320},
+ {1, 14.75, 1.73, 2.39, 11.4, 91, 3.1, 3.69, .43, 2.81, 5.4, 1.25, 2.73, 1150},
+ {1, 14.38, 1.87, 2.38, 12, 102, 3.3, 3.64, .29, 2.96, 7.5, 1.2, 3, 1547},
+ {1, 13.63, 1.81, 2.7, 17.2, 112, 2.85, 2.91, .3, 1.46, 7.3, 1.28, 2.88, 1310},
+ {1, 14.3, 1.92, 2.72, 20, 120, 2.8, 3.14, .33, 1.97, 6.2, 1.07, 2.65, 1280},
+ {1, 13.83, 1.57, 2.62, 20, 115, 2.95, 3.4, .4, 1.72, 6.6, 1.13, 2.57, 1130},
+ {1, 14.19, 1.59, 2.48, 16.5, 108, 3.3, 3.93, .32, 1.86, 8.7, 1.23, 2.82, 1680},
+ {1, 13.64, 3.1, 2.56, 15.2, 116, 2.7, 3.03, .17, 1.66, 5.1, .96, 3.36, 845},
+ {1, 14.06, 1.63, 2.28, 16, 126, 3, 3.17, .24, 2.1, 5.65, 1.09, 3.71, 780},
+ {1, 12.93, 3.8, 2.65, 18.6, 102, 2.41, 2.41, .25, 1.98, 4.5, 1.03, 3.52, 770},
+ {1, 13.71, 1.86, 2.36, 16.6, 101, 2.61, 2.88, .27, 1.69, 3.8, 1.11, 4, 1035},
+ {1, 12.85, 1.6, 2.52, 17.8, 95, 2.48, 2.37, .26, 1.46, 3.93, 1.09, 3.63, 1015},
+ {1, 13.5, 1.81, 2.61, 20, 96, 2.53, 2.61, .28, 1.66, 3.52, 1.12, 3.82, 845},
+ {1, 13.05, 2.05, 3.22, 25, 124, 2.63, 2.68, .47, 1.92, 3.58, 1.13, 3.2, 830},
+ {1, 13.39, 1.77, 2.62, 16.1, 93, 2.85, 2.94, .34, 1.45, 4.8, .92, 3.22, 1195},
+ {1, 13.3, 1.72, 2.14, 17, 94, 2.4, 2.19, .27, 1.35, 3.95, 1.02, 2.77, 1285},
+ {1, 13.87, 1.9, 2.8, 19.4, 107, 2.95, 2.97, .37, 1.76, 4.5, 1.25, 3.4, 915},
+ {1, 14.02, 1.68, 2.21, 16, 96, 2.65, 2.33, .26, 1.98, 4.7, 1.04, 3.59, 1035},
+ {1, 13.73, 1.5, 2.7, 22.5, 101, 3, 3.25, .29, 2.38, 5.7, 1.19, 2.71, 1285},
+ {1, 13.58, 1.66, 2.36, 19.1, 106, 2.86, 3.19, .22, 1.95, 6.9, 1.09, 2.88, 1515},
+ {1, 13.68, 1.83, 2.36, 17.2, 104, 2.42, 2.69, .42, 1.97, 3.84, 1.23, 2.87, 990},
+ {1, 13.76, 1.53, 2.7, 19.5, 132, 2.95, 2.74, .5, 1.35, 5.4, 1.25, 3, 1235},
+ {1, 13.51, 1.8, 2.65, 19, 110, 2.35, 2.53, .29, 1.54, 4.2, 1.1, 2.87, 1095},
+ {1, 13.48, 1.81, 2.41, 20.5, 100, 2.7, 2.98, .26, 1.86, 5.1, 1.04, 3.47, 920},
+ {1, 13.28, 1.64, 2.84, 15.5, 110, 2.6, 2.68, .34, 1.36, 4.6, 1.09, 2.78, 880},
+ {1, 13.05, 1.65, 2.55, 18, 98, 2.45, 2.43, .29, 1.44, 4.25, 1.12, 2.51, 1105},
+ {1, 13.07, 1.5, 2.1, 15.5, 98, 2.4, 2.64, .28, 1.37, 3.7, 1.18, 2.69, 1020},
+ {1, 14.22, 3.99, 2.51, 13.2, 128, 3, 3.04, .2, 2.08, 5.1, .89, 3.53, 760},
+ {1, 13.56, 1.71, 2.31, 16.2, 117, 3.15, 3.29, .34, 2.34, 6.13, .95, 3.38, 795},
+ {1, 13.41, 3.84, 2.12, 18.8, 90, 2.45, 2.68, .27, 1.48, 4.28, .91, 3, 1035},
+ {1, 13.88, 1.89, 2.59, 15, 101, 3.25, 3.56, .17, 1.7, 5.43, .88, 3.56, 1095},
+ {1, 13.24, 3.98, 2.29, 17.5, 103, 2.64, 2.63, .32, 1.66, 4.36, .82, 3, 680},
+ {1, 13.05, 1.77, 2.1, 17, 107, 3, 3, .28, 2.03, 5.04, .88, 3.35, 885},
+ {1, 14.21, 4.04, 2.44, 18.9, 111, 2.85, 2.65, .3, 1.25, 5.24, .87, 3.33, 1080},
+ {1, 14.38, 3.59, 2.28, 16, 102, 3.25, 3.17, .27, 2.19, 4.9, 1.04, 3.44, 1065},
+ {1, 13.9, 1.68, 2.12, 16, 101, 3.1, 3.39, .21, 2.14, 6.1, .91, 3.33, 985},
+ {1, 14.1, 2.02, 2.4, 18.8, 103, 2.75, 2.92, .32, 2.38, 6.2, 1.07, 2.75, 1060},
+ {1, 13.94, 1.73, 2.27, 17.4, 108, 2.88, 3.54, .32, 2.08, 8.90, 1.12, 3.1, 1260},
+ {1, 13.05, 1.73, 2.04, 12.4, 92, 2.72, 3.27, .17, 2.91, 7.2, 1.12, 2.91, 1150},
+ {1, 13.83, 1.65, 2.6, 17.2, 94, 2.45, 2.99, .22, 2.29, 5.6, 1.24, 3.37, 1265},
+ {1, 13.82, 1.75, 2.42, 14, 111, 3.88, 3.74, .32, 1.87, 7.05, 1.01, 3.26, 1190},
+ {1, 13.77, 1.9, 2.68, 17.1, 115, 3, 2.79, .39, 1.68, 6.3, 1.13, 2.93, 1375},
+ {1, 13.74, 1.67, 2.25, 16.4, 118, 2.6, 2.9, .21, 1.62, 5.85, .92, 3.2, 1060},
+ {1, 13.56, 1.73, 2.46, 20.5, 116, 2.96, 2.78, .2, 2.45, 6.25, .98, 3.03, 1120},
+ {1, 14.22, 1.7, 2.3, 16.3, 118, 3.2, 3, .26, 2.03, 6.38, .94, 3.31, 970},
+ {1, 13.29, 1.97, 2.68, 16.8, 102, 3, 3.23, .31, 1.66, 6, 1.07, 2.84, 1270},
+ {1, 13.72, 1.43, 2.5, 16.7, 108, 3.4, 3.67, .19, 2.04, 6.8, .89, 2.87, 1285},
+ {2, 12.37, .94, 1.36, 10.6, 88, 1.98, .57, .28, .42, 1.95, 1.05, 1.82, 520},
+ {2, 12.33, 1.1, 2.28, 16, 101, 2.05, 1.09, .63, .41, 3.27, 1.25, 1.67, 680},
+ {2, 12.64, 1.36, 2.02, 16.8, 100, 2.02, 1.41, .53, .62, 5.75, .98, 1.59, 450},
+ {2, 13.67, 1.25, 1.92, 18, 94, 2.1, 1.79, .32, .73, 3.8, 1.23, 2.46, 630},
+ {2, 12.37, 1.13, 2.16, 19, 87, 3.5, 3.1, .19, 1.87, 4.45, 1.22, 2.87, 420},
+ {2, 12.17, 1.45, 2.53, 19, 104, 1.89, 1.75, .45, 1.03, 2.95, 1.45, 2.23, 355},
+ {2, 12.37, 1.21, 2.56, 18.1, 98, 2.42, 2.65, .37, 2.08, 4.6, 1.19, 2.3, 678},
+ {2, 13.11, 1.01, 1.7, 15, 78, 2.98, 3.18, .26, 2.28, 5.3, 1.12, 3.18, 502},
+ {2, 12.37, 1.17, 1.92, 19.6, 78, 2.11, 2, .27, 1.04, 4.68, 1.12, 3.48, 510},
+ {2, 13.34, .94, 2.36, 17, 110, 2.53, 1.3, .55, .42, 3.17, 1.02, 1.93, 750},
+ {2, 12.21, 1.19, 1.75, 16.8, 151, 1.85, 1.28, .14, 2.5, 2.85, 1.28, 3.07, 718},
+ {2, 12.29, 1.61, 2.21, 20.4, 103, 1.1, 1.02, .37, 1.46, 3.05, .906, 1.82, 870},
+ {2, 13.86, 1.51, 2.67, 25, 86, 2.95, 2.86, .21, 1.87, 3.38, 1.36, 3.16, 410},
+ {2, 13.49, 1.66, 2.24, 24, 87, 1.88, 1.84, .27, 1.03, 3.74, .98, 2.78, 472},
+ {2, 12.99, 1.67, 2.6, 30, 139, 3.3, 2.89, .21, 1.96, 3.35, 1.31, 3.5, 985},
+ {2, 11.96, 1.09, 2.3, 21, 101, 3.38, 2.14, .13, 1.65, 3.21, .99, 3.13, 886},
+ {2, 11.66, 1.88, 1.92, 16, 97, 1.61, 1.57, .34, 1.15, 3.8, 1.23, 2.14, 428},
+ {2, 13.03, .9, 1.71, 16, 86, 1.95, 2.03, .24, 1.46, 4.6, 1.19, 2.48, 392},
+ {2, 11.84, 2.89, 2.23, 18, 112, 1.72, 1.32, .43, .95, 2.65, .96, 2.52, 500},
+ {2, 12.33, .99, 1.95, 14.8, 136, 1.9, 1.85, .35, 2.76, 3.4, 1.06, 2.31, 750},
+ {2, 12.7, 3.87, 2.4, 23, 101, 2.83, 2.55, .43, 1.95, 2.57, 1.19, 3.13, 463},
+ {2, 12, .92, 2, 19, 86, 2.42, 2.26, .3, 1.43, 2.5, 1.38, 3.12, 278},
+ {2, 12.72, 1.81, 2.2, 18.8, 86, 2.2, 2.53, .26, 1.77, 3.9, 1.16, 3.14, 714},
+ {2, 12.08, 1.13, 2.51, 24, 78, 2, 1.58, .4, 1.4, 2.2, 1.31, 2.72, 630},
+ {2, 13.05, 3.86, 2.32, 22.5, 85, 1.65, 1.59, .61, 1.62, 4.8, .84, 2.01, 515},
+ {2, 11.84, .89, 2.58, 18, 94, 2.2, 2.21, .22, 2.35, 3.05, .79, 3.08, 520},
+ {2, 12.67, .98, 2.24, 18, 99, 2.2, 1.94, .3, 1.46, 2.62, 1.23, 3.16, 450},
+ {2, 12.16, 1.61, 2.31, 22.8, 90, 1.78, 1.69, .43, 1.56, 2.45, 1.33, 2.26, 495},
+ {2, 11.65, 1.67, 2.62, 26, 88, 1.92, 1.61, .4, 1.34, 2.6, 1.36, 3.21, 562},
+ {2, 11.64, 2.06, 2.46, 21.6, 84, 1.95, 1.69, .48, 1.35, 2.8, 1, 2.75, 680},
+ {2, 12.08, 1.33, 2.3, 23.6, 70, 2.2, 1.59, .42, 1.38, 1.74, 1.07, 3.21, 625},
+ {2, 12.08, 1.83, 2.32, 18.5, 81, 1.6, 1.5, .52, 1.64, 2.4, 1.08, 2.27, 480},
+ {2, 12, 1.51, 2.42, 22, 86, 1.45, 1.25, .5, 1.63, 3.6, 1.05, 2.65, 450},
+ {2, 12.69, 1.53, 2.26, 20.7, 80, 1.38, 1.46, .58, 1.62, 3.05, .96, 2.06, 495},
+ {2, 12.29, 2.83, 2.22, 18, 88, 2.45, 2.25, .25, 1.99, 2.15, 1.15, 3.3, 290},
+ {2, 11.62, 1.99, 2.28, 18, 98, 3.02, 2.26, .17, 1.35, 3.25, 1.16, 2.96, 345},
+ {2, 12.47, 1.52, 2.2, 19, 162, 2.5, 2.27, .32, 3.28, 2.6, 1.16, 2.63, 937},
+ {2, 11.81, 2.12, 2.74, 21.5, 134, 1.6, .99, .14, 1.56, 2.5, .95, 2.26, 625},
+ {2, 12.29, 1.41, 1.98, 16, 85, 2.55, 2.5, .29, 1.77, 2.9, 1.23, 2.74, 428},
+ {2, 12.37, 1.07, 2.1, 18.5, 88, 3.52, 3.75, .24, 1.95, 4.5, 1.04, 2.77, 660},
+ {2, 12.29, 3.17, 2.21, 18, 88, 2.85, 2.99, .45, 2.81, 2.3, 1.42, 2.83, 406},
+ {2, 12.08, 2.08, 1.7, 17.5, 97, 2.23, 2.17, .26, 1.4, 3.3, 1.27, 2.96, 710},
+ {2, 12.6, 1.34, 1.9, 18.5, 88, 1.45, 1.36, .29, 1.35, 2.45, 1.04, 2.77, 562},
+ {2, 12.34, 2.45, 2.46, 21, 98, 2.56, 2.11, .34, 1.31, 2.8, .8, 3.38, 438},
+ {2, 11.82, 1.72, 1.88, 19.5, 86, 2.5, 1.64, .37, 1.42, 2.06, .94, 2.44, 415},
+ {2, 12.51, 1.73, 1.98, 20.5, 85, 2.2, 1.92, .32, 1.48, 2.94, 1.04, 3.57, 672},
+ {2, 12.42, 2.55, 2.27, 22, 90, 1.68, 1.84, .66, 1.42, 2.7, .86, 3.3, 315},
+ {2, 12.25, 1.73, 2.12, 19, 80, 1.65, 2.03, .37, 1.63, 3.4, 1, 3.17, 510},
+ {2, 12.72, 1.75, 2.28, 22.5, 84, 1.38, 1.76, .48, 1.63, 3.3, .88, 2.42, 488},
+ {2, 12.22, 1.29, 1.94, 19, 92, 2.36, 2.04, .39, 2.08, 2.7, .86, 3.02, 312},
+ {2, 11.61, 1.35, 2.7, 20, 94, 2.74, 2.92, .29, 2.49, 2.65, .96, 3.26, 680},
+ {2, 11.46, 3.74, 1.82, 19.5, 107, 3.18, 2.58, .24, 3.58, 2.9, .75, 2.81, 562},
+ {2, 12.52, 2.43, 2.17, 21, 88, 2.55, 2.27, .26, 1.22, 2, .9, 2.78, 325},
+ {2, 11.76, 2.68, 2.92, 20, 103, 1.75, 2.03, .6, 1.05, 3.8, 1.23, 2.5, 607},
+ {2, 11.41, .74, 2.5, 21, 88, 2.48, 2.01, .42, 1.44, 3.08, 1.1, 2.31, 434},
+ {2, 12.08, 1.39, 2.5, 22.5, 84, 2.56, 2.29, .43, 1.04, 2.9, .93, 3.19, 385},
+ {2, 11.03, 1.51, 2.2, 21.5, 85, 2.46, 2.17, .52, 2.01, 1.9, 1.71, 2.87, 407},
+ {2, 11.82, 1.47, 1.99, 20.8, 86, 1.98, 1.6, .3, 1.53, 1.95, .95, 3.3423, 495},
+ {2, 12.42, 1.61, 2.19, 22.5, 108, 2, 2.09, .34, 1.61, 2.06, 1.06, 2.96, 345},
+ {2, 12.77, 3.43, 1.98, 16, 80, 1.63, 1.25, .43, .83, 3.4, .7, 2.12, 372},
+ {2, 12, 3.43, 2, 19, 87, 2, 1.64, .37, 1.87, 1.28, .93, 3.05, 564},
+ {2, 11.45, 2.4, 2.42, 20, 96, 2.9, 2.79, .32, 1.83, 3.25, .8, 3.39, 625},
+ {2, 11.56, 2.05, 3.23, 28.5, 119, 3.18, 5.08, .47, 1.87, 6, .93, 3.69, 465},
+ {2, 12.42, 4.43, 2.73, 26.5, 102, 2.2, 2.13, .43, 1.71, 2.08, .92, 3.12, 365},
+ {2, 13.05, 5.8, 2.13, 21.5, 86, 2.62, 2.65, .3, 2.01, 2.6, .73, 3.1, 380},
+ {2, 11.87, 4.31, 2.39, 21, 82, 2.86, 3.03, .21, 2.91, 2.8, .75, 3.64, 380},
+ {2, 12.07, 2.16, 2.17, 21, 85, 2.6, 2.65, .37, 1.35, 2.76, .86, 3.28, 378},
+ {2, 12.43, 1.53, 2.29, 21.5, 86, 2.74, 3.15, .39, 1.77, 3.94, .69, 2.84, 352},
+ {2, 11.79, 2.13, 2.78, 28.5, 92, 2.13, 2.24, .58, 1.76, 3, .97, 2.44, 466},
+ {2, 12.37, 1.63, 2.3, 24.5, 88, 2.22, 2.45, .4, 1.9, 2.12, .89, 2.78, 342},
+ {2, 12.04, 4.3, 2.38, 22, 80, 2.1, 1.75, .42, 1.35, 2.6, .79, 2.57, 580},
+ {3, 12.86, 1.35, 2.32, 18, 122, 1.51, 1.25, .21, .94, 4.1, .76, 1.29, 630},
+ {3, 12.88, 2.99, 2.4, 20, 104, 1.3, 1.22, .24, .83, 5.4, .74, 1.42, 530},
+ {3, 12.81, 2.31, 2.4, 24, 98, 1.15, 1.09, .27, .83, 5.7, .66, 1.36, 560},
+ {3, 12.7, 3.55, 2.36, 21.5, 106, 1.7, 1.2, .17, .84, 5, .78, 1.29, 600},
+ {3, 12.51, 1.24, 2.25, 17.5, 85, 2, .58, .6, 1.25, 5.45, .75, 1.51, 650},
+ {3, 12.6, 2.46, 2.2, 18.5, 94, 1.62, .66, .63, .94, 7.1, .73, 1.58, 695},
+ {3, 12.25, 4.72, 2.54, 21, 89, 1.38, .47, .53, .8, 3.85, .75, 1.27, 720},
+ {3, 12.53, 5.51, 2.64, 25, 96, 1.79, .6, .63, 1.1, 5, .82, 1.69, 515},
+ {3, 13.49, 3.59, 2.19, 19.5, 88, 1.62, .48, .58, .88, 5.7, .81, 1.82, 580},
+ {3, 12.84, 2.96, 2.61, 24, 101, 2.32, .6, .53, .81, 4.92, .89, 2.15, 590},
+ {3, 12.93, 2.81, 2.7, 21, 96, 1.54, .5, .53, .75, 4.6, .77, 2.31, 600},
+ {3, 13.36, 2.56, 2.35, 20, 89, 1.4, .5, .37, .64, 5.6, .7, 2.47, 780},
+ {3, 13.52, 3.17, 2.72, 23.5, 97, 1.55, .52, .5, .55, 4.35, .89, 2.06, 520},
+ {3, 13.62, 4.95, 2.35, 20, 92, 2, .8, .47, 1.02, 4.4, .91, 2.05, 550},
+ {3, 12.25, 3.88, 2.2, 18.5, 112, 1.38, .78, .29, 1.14, 8.21, .65, 2, 855},
+ {3, 13.16, 3.57, 2.15, 21, 102, 1.5, .55, .43, 1.3, 4, .6, 1.68, 830},
+ {3, 13.88, 5.04, 2.23, 20, 80, .98, .34, .4, .68, 4.9, .58, 1.33, 415},
+ {3, 12.87, 4.61, 2.48, 21.5, 86, 1.7, .65, .47, .86, 7.65, .54, 1.86, 625},
+ {3, 13.32, 3.24, 2.38, 21.5, 92, 1.93, .76, .45, 1.25, 8.42, .55, 1.62, 650},
+ {3, 13.08, 3.9, 2.36, 21.5, 113, 1.41, 1.39, .34, 1.14, 9.40, .57, 1.33, 550},
+ {3, 13.5, 3.12, 2.62, 24, 123, 1.4, 1.57, .22, 1.25, 8.60, .59, 1.3, 500},
+ {3, 12.79, 2.67, 2.48, 22, 112, 1.48, 1.36, .24, 1.26, 10.8, .48, 1.47, 480},
+ {3, 13.11, 1.9, 2.75, 25.5, 116, 2.2, 1.28, .26, 1.56, 7.1, .61, 1.33, 425},
+ {3, 13.23, 3.3, 2.28, 18.5, 98, 1.8, .83, .61, 1.87, 10.52, .56, 1.51, 675},
+ {3, 12.58, 1.29, 2.1, 20, 103, 1.48, .58, .53, 1.4, 7.6, .58, 1.55, 640},
+ {3, 13.17, 5.19, 2.32, 22, 93, 1.74, .63, .61, 1.55, 7.9, .6, 1.48, 725},
+ {3, 13.84, 4.12, 2.38, 19.5, 89, 1.8, .83, .48, 1.56, 9.01, .57, 1.64, 480},
+ {3, 12.45, 3.03, 2.64, 27, 97, 1.9, .58, .63, 1.14, 7.5, .67, 1.73, 880},
+ {3, 14.34, 1.68, 2.7, 25, 98, 2.8, 1.31, .53, 2.7, 13, .57, 1.96, 660},
+ {3, 13.48, 1.67, 2.64, 22.5, 89, 2.6, 1.1, .52, 2.29, 11.75, .57, 1.78, 620},
+ {3, 12.36, 3.83, 2.38, 21, 88, 2.3, .92, .5, 1.04, 7.65, .56, 1.58, 520},
+ {3, 13.69, 3.26, 2.54, 20, 107, 1.83, .56, .5, .8, 5.88, .96, 1.82, 680},
+ {3, 12.85, 3.27, 2.58, 22, 106, 1.65, .6, .6, .96, 5.58, .87, 2.11, 570},
+ {3, 12.96, 3.45, 2.35, 18.5, 106, 1.39, .7, .4, .94, 5.28, .68, 1.75, 675},
+ {3, 13.78, 2.76, 2.3, 22, 90, 1.35, .68, .41, 1.03, 9.58, .7, 1.68, 615},
+ {3, 13.73, 4.36, 2.26, 22.5, 88, 1.28, .47, .52, 1.15, 6.62, .78, 1.75, 520},
+ {3, 13.45, 3.7, 2.6, 23, 111, 1.7, .92, .43, 1.46, 10.68, .85, 1.56, 695},
+ {3, 12.82, 3.37, 2.3, 19.5, 88, 1.48, .66, .4, .97, 10.26, .72, 1.75, 685},
+ {3, 13.58, 2.58, 2.69, 24.5, 105, 1.55, .84, .39, 1.54, 8.66, .74, 1.8, 750},
+ {3, 13.4, 4.6, 2.86, 25, 112, 1.98, .96, .27, 1.11, 8.5, .67, 1.92, 630},
+ {3, 12.2, 3.03, 2.32, 19, 96, 1.25, .49, .4, .73, 5.5, .66, 1.83, 510},
+ {3, 12.77, 2.39, 2.28, 19.5, 86, 1.39, .51, .48, .64, 9.899999, .57, 1.63, 470},
+ {3, 14.16, 2.51, 2.48, 20, 91, 1.68, .7, .44, 1.24, 9.7, .62, 1.71, 660},
+ {3, 13.71, 5.65, 2.45, 20.5, 95, 1.68, .61, .52, 1.06, 7.7, .64, 1.74, 740},
+ {3, 13.4, 3.91, 2.48, 23, 102, 1.8, .75, .43, 1.41, 7.3, .7, 1.56, 750},
+ {3, 13.27, 4.28, 2.26, 20, 120, 1.59, .69, .43, 1.35, 10.2, .59, 1.56, 835},
+ {3, 13.17, 2.59, 2.37, 20, 120, 1.65, .68, .53, 1.46, 9.3, .6, 1.62, 840},
+ {3, 14.13, 4.1, 2.74, 24.5, 96, 2.05, .76, .56, 1.35, 9.2, .61, 1.6, 560}
};
}
http://git-wip-us.apache.org/repos/asf/ignite/blob/78328fe4/examples/src/main/java/org/apache/ignite/examples/ml/tree/randomforest/RandomForestRegressionExample.java
----------------------------------------------------------------------
diff --git a/examples/src/main/java/org/apache/ignite/examples/ml/tree/randomforest/RandomForestRegressionExample.java b/examples/src/main/java/org/apache/ignite/examples/ml/tree/randomforest/RandomForestRegressionExample.java
index b83d526..96a87c2 100644
--- a/examples/src/main/java/org/apache/ignite/examples/ml/tree/randomforest/RandomForestRegressionExample.java
+++ b/examples/src/main/java/org/apache/ignite/examples/ml/tree/randomforest/RandomForestRegressionExample.java
@@ -18,6 +18,9 @@
package org.apache.ignite.examples.ml.tree.randomforest;
import java.util.Arrays;
+import java.util.concurrent.atomic.AtomicInteger;
+import java.util.stream.Collectors;
+import java.util.stream.IntStream;
import javax.cache.Cache;
import org.apache.ignite.Ignite;
import org.apache.ignite.IgniteCache;
@@ -26,17 +29,15 @@ import org.apache.ignite.cache.query.QueryCursor;
import org.apache.ignite.cache.query.ScanQuery;
import org.apache.ignite.examples.ml.util.TestCache;
import org.apache.ignite.ml.composition.ModelsComposition;
-import org.apache.ignite.ml.environment.LearningEnvironment;
-import org.apache.ignite.ml.environment.logging.ConsoleLogger;
-import org.apache.ignite.ml.environment.logging.MLLogger;
-import org.apache.ignite.ml.environment.parallelism.ParallelismStrategy;
+import org.apache.ignite.ml.dataset.feature.FeatureMeta;
import org.apache.ignite.ml.math.primitives.vector.VectorUtils;
import org.apache.ignite.ml.tree.randomforest.RandomForestRegressionTrainer;
import org.apache.ignite.ml.tree.randomforest.RandomForestTrainer;
+import org.apache.ignite.ml.tree.randomforest.data.FeaturesCountSelectionStrategies;
import org.apache.ignite.thread.IgniteThread;
/**
- * Example represents a solution for the task of price predictions for houses in Boston based on RandomForest
+ * Example represents a solution for the task of price predictions for houses in Boston based on RandomForestTrainer
* implementation for regression. It shows an initialization of {@link RandomForestTrainer}, +initialization of Ignite
* Cache, learning step and evaluation of model quality in terms of Mean Squared Error (MSE) and Mean Absolute Error
* (MAE).
@@ -60,12 +61,15 @@ public class RandomForestRegressionExample {
RandomForestRegressionExample.class.getSimpleName(), () -> {
IgniteCache<Integer, double[]> dataCache = new TestCache(ignite).fillCacheWith(data);
- RandomForestRegressionTrainer trainer = new RandomForestRegressionTrainer(13, 4, 101, 0.3, 2, 0);
- trainer.setEnvironment(LearningEnvironment.builder()
- .withParallelismStrategy(ParallelismStrategy.Type.ON_DEFAULT_POOL)
- .withLoggingFactory(ConsoleLogger.factory(MLLogger.VerboseLevel.LOW))
- .build()
- );
+ AtomicInteger indx = new AtomicInteger(0);
+ RandomForestRegressionTrainer trainer = new RandomForestRegressionTrainer(
+ IntStream.range(0, data[0].length - 1).mapToObj(x -> new FeatureMeta("", indx.getAndIncrement(), false)).collect(Collectors.toList())
+ ).withCountOfTrees(101)
+ .withFeaturesCountSelectionStrgy(FeaturesCountSelectionStrategies.ONE_THIRD)
+ .withMaxDepth(4)
+ .withMinImpurityDelta(0.)
+ .withSubsampleSize(0.3)
+ .withSeed(0);
ModelsComposition randomForest = trainer.fit(ignite, dataCache,
(k, v) -> VectorUtils.of(Arrays.copyOfRange(v, 0, v.length - 1)),
http://git-wip-us.apache.org/repos/asf/ignite/blob/78328fe4/modules/ml/pom.xml
----------------------------------------------------------------------
diff --git a/modules/ml/pom.xml b/modules/ml/pom.xml
index fac5ab4..ad31da2 100644
--- a/modules/ml/pom.xml
+++ b/modules/ml/pom.xml
@@ -21,6 +21,9 @@
-->
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
+ <properties>
+ <commons.math.version>3.6.1</commons.math.version>
+ </properties>
<parent>
<artifactId>ignite-parent</artifactId>
@@ -47,7 +50,7 @@
<type>test-jar</type>
<scope>test</scope>
</dependency>
-
+
<dependency>
<groupId>org.apache.ignite</groupId>
<artifactId>ignite-indexing</artifactId>
@@ -60,7 +63,7 @@
<artifactId>ignite-spring</artifactId>
<version>${project.version}</version>
</dependency>
-
+
<dependency>
<groupId>it.unimi.dsi</groupId>
<artifactId>fastutil</artifactId>
@@ -118,6 +121,12 @@
<version>${mockito.version}</version>
<scope>test</scope>
</dependency>
+
+ <dependency>
+ <groupId>org.apache.commons</groupId>
+ <artifactId>commons-math3</artifactId>
+ <version>${commons.math.version}</version>
+ </dependency>
</dependencies>
<profiles>
http://git-wip-us.apache.org/repos/asf/ignite/blob/78328fe4/modules/ml/src/main/java/org/apache/ignite/ml/composition/predictionsaggregator/WeightedPredictionsAggregator.java
----------------------------------------------------------------------
diff --git a/modules/ml/src/main/java/org/apache/ignite/ml/composition/predictionsaggregator/WeightedPredictionsAggregator.java b/modules/ml/src/main/java/org/apache/ignite/ml/composition/predictionsaggregator/WeightedPredictionsAggregator.java
index c37fdf7..8a369ad 100644
--- a/modules/ml/src/main/java/org/apache/ignite/ml/composition/predictionsaggregator/WeightedPredictionsAggregator.java
+++ b/modules/ml/src/main/java/org/apache/ignite/ml/composition/predictionsaggregator/WeightedPredictionsAggregator.java
@@ -20,7 +20,7 @@ package org.apache.ignite.ml.composition.predictionsaggregator;
import org.apache.ignite.internal.util.typedef.internal.A;
/**
- * Predictions aggregator returning weighted sum of predictions.
+ * Predictions aggregator returning weighted plus of predictions.
* result(p1, ..., pn) = bias + p1*w1 + ... + pn*wn
*/
public class WeightedPredictionsAggregator implements PredictionsAggregator {
http://git-wip-us.apache.org/repos/asf/ignite/blob/78328fe4/modules/ml/src/main/java/org/apache/ignite/ml/dataset/feature/BucketMeta.java
----------------------------------------------------------------------
diff --git a/modules/ml/src/main/java/org/apache/ignite/ml/dataset/feature/BucketMeta.java b/modules/ml/src/main/java/org/apache/ignite/ml/dataset/feature/BucketMeta.java
new file mode 100644
index 0000000..4ac9adb
--- /dev/null
+++ b/modules/ml/src/main/java/org/apache/ignite/ml/dataset/feature/BucketMeta.java
@@ -0,0 +1,88 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.ignite.ml.dataset.feature;
+
+import java.io.Serializable;
+
+/**
+ * Bucket meta-information for feature histogram.
+ */
+public class BucketMeta implements Serializable {
+ /** Feature meta. */
+ private final FeatureMeta featureMeta;
+
+ /** Bucket size. */
+ private double bucketSize;
+
+ /** Min value of feature. */
+ private double minVal;
+
+ /**
+ * Creates an instance of BucketMeta.
+ *
+ * @param featureMeta Feature meta.
+ */
+ public BucketMeta(FeatureMeta featureMeta) {
+ this.featureMeta = featureMeta;
+ }
+
+ /**
+ * Returns bucket id for feature value.
+ *
+ * @param val Value.
+ * @return bucket id.
+ */
+ public int getBucketId(Double val) {
+ if(featureMeta.isCategoricalFeature())
+ return (int) Math.rint(val);
+
+ return (int) Math.rint((val - minVal) / bucketSize);
+ }
+
+ /**
+ * Returns mean value by bucket id.
+ *
+ * @param bucketId Bucket id.
+ * @return mean value of feature.
+ */
+ public double bucketIdToValue(int bucketId) {
+ if(featureMeta.isCategoricalFeature())
+ return (double) bucketId;
+
+ return minVal + (bucketId + 0.5) * bucketSize;
+ }
+
+ /**
+ * @param minVal Min value.
+ */
+ public void setMinVal(double minVal) {
+ this.minVal = minVal;
+ }
+
+ /**
+ * @param bucketSize Bucket size.
+ */
+ public void setBucketSize(double bucketSize) {
+ this.bucketSize = bucketSize;
+ }
+
+ /** */
+ public FeatureMeta getFeatureMeta() {
+ return featureMeta;
+ }
+}
http://git-wip-us.apache.org/repos/asf/ignite/blob/78328fe4/modules/ml/src/main/java/org/apache/ignite/ml/dataset/feature/DistributionComputer.java
----------------------------------------------------------------------
diff --git a/modules/ml/src/main/java/org/apache/ignite/ml/dataset/feature/DistributionComputer.java b/modules/ml/src/main/java/org/apache/ignite/ml/dataset/feature/DistributionComputer.java
new file mode 100644
index 0000000..7582da0
--- /dev/null
+++ b/modules/ml/src/main/java/org/apache/ignite/ml/dataset/feature/DistributionComputer.java
@@ -0,0 +1,32 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.ignite.ml.dataset.feature;
+
+import java.util.TreeMap;
+
+/**
+ * Interface specifies an object that can compute some discrete distribution.
+ */
+public interface DistributionComputer {
+ /**
+ * Compute distribution function.
+ *
+ * @return Map represents discrete distribution function.
+ */
+ public TreeMap<Integer, Double> computeDistributionFunction();
+}
http://git-wip-us.apache.org/repos/asf/ignite/blob/78328fe4/modules/ml/src/main/java/org/apache/ignite/ml/dataset/feature/FeatureMeta.java
----------------------------------------------------------------------
diff --git a/modules/ml/src/main/java/org/apache/ignite/ml/dataset/feature/FeatureMeta.java b/modules/ml/src/main/java/org/apache/ignite/ml/dataset/feature/FeatureMeta.java
new file mode 100644
index 0000000..a7d846f
--- /dev/null
+++ b/modules/ml/src/main/java/org/apache/ignite/ml/dataset/feature/FeatureMeta.java
@@ -0,0 +1,65 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.ignite.ml.dataset.feature;
+
+import java.io.Serializable;
+
+/**
+ * Feature meta class.
+ */
+public class FeatureMeta implements Serializable {
+ /** Serial version uid. */
+ private static final long serialVersionUID = -2990950807063111877L;
+
+ /** Name. */
+ private final String name;
+
+ /** Id of feature in feature vector. */
+ private final int featureId;
+
+ /** Is categorical feature flag. */
+ private final boolean isCategoricalFeature;
+
+ /**
+ * Create an instance of Feature meta.
+ *
+ * @param name Feature name.
+ * @param featureId Feature id.
+ * @param isCategoricalFeature Is categorical feature.
+ */
+ public FeatureMeta(String name, int featureId, boolean isCategoricalFeature) {
+ this.name = name;
+ this.featureId = featureId;
+ this.isCategoricalFeature = isCategoricalFeature;
+ }
+
+ /** */
+ public int getFeatureId() {
+ return featureId;
+ }
+
+ /** */
+ public boolean isCategoricalFeature() {
+ return isCategoricalFeature;
+ }
+
+ /** */
+ public String getName() {
+ return name;
+ }
+}
http://git-wip-us.apache.org/repos/asf/ignite/blob/78328fe4/modules/ml/src/main/java/org/apache/ignite/ml/dataset/feature/Histogram.java
----------------------------------------------------------------------
diff --git a/modules/ml/src/main/java/org/apache/ignite/ml/dataset/feature/Histogram.java b/modules/ml/src/main/java/org/apache/ignite/ml/dataset/feature/Histogram.java
new file mode 100644
index 0000000..6784af1
--- /dev/null
+++ b/modules/ml/src/main/java/org/apache/ignite/ml/dataset/feature/Histogram.java
@@ -0,0 +1,64 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.ignite.ml.dataset.feature;
+
+import java.io.Serializable;
+import java.util.Optional;
+import java.util.Set;
+
+/**
+ * Interface of histogram over type T.
+ *
+ * @param <T> Type of object for histogram.
+ * @param <H> Type of histogram that can be used in math operations with this histogram.
+ */
+public interface Histogram<T, H extends Histogram<T, H>> extends Serializable {
+ /**
+ * Add object to histogram.
+ *
+ * @param val Value.
+ */
+ public void addElement(T val);
+
+ /**
+ *
+ * @return bucket ids.
+ */
+ public Set<Integer> buckets();
+
+ /**
+ *
+ * @param bucketId Bucket id.
+ * @return value in according to bucket id.
+ */
+ public Optional<Double> getValue(Integer bucketId);
+
+ /**
+ * @param other Other histogram.
+ * @return sum of this and other histogram.
+ */
+ public H plus(H other);
+
+ /**
+ * Compares histogram with other and returns true if they are equals
+ *
+ * @param other Other histogram.
+ * @return true if histograms are equal.
+ */
+ public boolean isEqualTo(H other);
+}
http://git-wip-us.apache.org/repos/asf/ignite/blob/78328fe4/modules/ml/src/main/java/org/apache/ignite/ml/dataset/feature/ObjectHistogram.java
----------------------------------------------------------------------
diff --git a/modules/ml/src/main/java/org/apache/ignite/ml/dataset/feature/ObjectHistogram.java b/modules/ml/src/main/java/org/apache/ignite/ml/dataset/feature/ObjectHistogram.java
new file mode 100644
index 0000000..d894c3f
--- /dev/null
+++ b/modules/ml/src/main/java/org/apache/ignite/ml/dataset/feature/ObjectHistogram.java
@@ -0,0 +1,129 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.ignite.ml.dataset.feature;
+
+import java.util.HashSet;
+import java.util.Map;
+import java.util.Optional;
+import java.util.Set;
+import java.util.TreeMap;
+import org.apache.ignite.ml.math.functions.IgniteFunction;
+
+/**
+ * Basic implementation of {@link Histogram} that implements also {@link DistributionComputer}.
+ *
+ * @param <T> Type of object for histogram.
+ */
+public class ObjectHistogram<T> implements Histogram<T, ObjectHistogram<T>>, DistributionComputer {
+ /** Serial version uid. */
+ private static final long serialVersionUID = -2708731174031404487L;
+
+ /** Bucket mapping. */
+ private final IgniteFunction<T, Integer> bucketMapping;
+
+ /** Mapping to counter. */
+ private final IgniteFunction<T, Double> mappingToCntr;
+
+ /** Histogram. */
+ private final Map<Integer, Double> hist;
+
+ /**
+ * Create an instance of ObjectHistogram.
+ *
+ * @param bucketMapping Bucket mapping.
+ * @param mappingToCntr Mapping to counter.
+ */
+ public ObjectHistogram(IgniteFunction<T, Integer> bucketMapping,
+ IgniteFunction<T, Double> mappingToCntr) {
+
+ this.bucketMapping = bucketMapping;
+ this.mappingToCntr = mappingToCntr;
+ this.hist = new TreeMap<>(Integer::compareTo);
+ }
+
+ /** {@inheritDoc} */
+ @Override public void addElement(T val) {
+ Integer bucket = bucketMapping.apply(val);
+ Double cntrVal = mappingToCntr.apply(val);
+
+ assert cntrVal >= 0;
+ Double bucketVal = hist.getOrDefault(bucket, 0.0);
+ hist.put(bucket, bucketVal + cntrVal);
+ }
+
+ /** {@inheritDoc} */
+ @Override public Set<Integer> buckets() {
+ return hist.keySet();
+ }
+
+ /** {@inheritDoc} */
+ @Override public Optional<Double> getValue(Integer bucketId) {
+ return Optional.ofNullable(hist.get(bucketId));
+ }
+
+ /** {@inheritDoc} */
+ @Override public TreeMap<Integer, Double> computeDistributionFunction() {
+ TreeMap<Integer, Double> res = new TreeMap<>();
+
+ double accum = 0.0;
+ for (Integer bucket : hist.keySet()) {
+ accum += hist.get(bucket);
+ res.put(bucket, accum);
+ }
+
+ return res;
+ }
+
+ /** {@inheritDoc} */
+ @Override public ObjectHistogram<T> plus(ObjectHistogram<T> other) {
+ ObjectHistogram<T> res = new ObjectHistogram<>(bucketMapping, mappingToCntr);
+ addTo(this.hist, res.hist);
+ addTo(other.hist, res.hist);
+ return res;
+ }
+
+ /**
+ * Adds bucket values to target histogram.
+ *
+ * @param from From.
+ * @param to To.
+ */
+ private void addTo(Map<Integer, Double> from, Map<Integer, Double> to) {
+ from.forEach((bucket, value) -> {
+ Double putVal = to.getOrDefault(bucket, 0.0);
+ to.put(bucket, putVal + value);
+ });
+ }
+
+ /** {@inheritDoc} */
+ public boolean isEqualTo(ObjectHistogram<T> other) {
+ Set<Integer> totalBuckets = new HashSet<>(buckets());
+ totalBuckets.addAll(other.buckets());
+ if(totalBuckets.size() != buckets().size())
+ return false;
+
+ for(Integer bucketId : totalBuckets) {
+ double leftVal = hist.get(bucketId);
+ double rightVal = other.hist.get(bucketId);
+ if(Math.abs(leftVal - rightVal) > 0.001)
+ return false;
+ }
+
+ return true;
+ }
+}
http://git-wip-us.apache.org/repos/asf/ignite/blob/78328fe4/modules/ml/src/main/java/org/apache/ignite/ml/dataset/feature/package-info.java
----------------------------------------------------------------------
diff --git a/modules/ml/src/main/java/org/apache/ignite/ml/dataset/feature/package-info.java b/modules/ml/src/main/java/org/apache/ignite/ml/dataset/feature/package-info.java
new file mode 100644
index 0000000..a0c346b
--- /dev/null
+++ b/modules/ml/src/main/java/org/apache/ignite/ml/dataset/feature/package-info.java
@@ -0,0 +1,24 @@
+/*
+
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+/**
+ * <!-- Package description. -->
+ * Package for helper classes over features such as {@link org.apache.ignite.ml.dataset.feature.ObjectHistogram} or
+ * {@link org.apache.ignite.ml.dataset.feature.FeatureMeta}.
+ */
+package org.apache.ignite.ml.dataset.feature;
http://git-wip-us.apache.org/repos/asf/ignite/blob/78328fe4/modules/ml/src/main/java/org/apache/ignite/ml/dataset/impl/bootstrapping/BootstrappedDatasetBuilder.java
----------------------------------------------------------------------
diff --git a/modules/ml/src/main/java/org/apache/ignite/ml/dataset/impl/bootstrapping/BootstrappedDatasetBuilder.java b/modules/ml/src/main/java/org/apache/ignite/ml/dataset/impl/bootstrapping/BootstrappedDatasetBuilder.java
new file mode 100644
index 0000000..8707e3a
--- /dev/null
+++ b/modules/ml/src/main/java/org/apache/ignite/ml/dataset/impl/bootstrapping/BootstrappedDatasetBuilder.java
@@ -0,0 +1,90 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.ignite.ml.dataset.impl.bootstrapping;
+
+import java.util.Arrays;
+import java.util.Iterator;
+import org.apache.commons.math3.distribution.PoissonDistribution;
+import org.apache.ignite.ml.dataset.PartitionDataBuilder;
+import org.apache.ignite.ml.dataset.UpstreamEntry;
+import org.apache.ignite.ml.dataset.primitive.context.EmptyContext;
+import org.apache.ignite.ml.math.functions.IgniteBiFunction;
+import org.apache.ignite.ml.math.primitives.vector.Vector;
+
+/**
+ * Builder for bootstrapped dataset. Bootstrapped dataset consist of several subsamples created in according to random
+ * sampling with replacements selection of vectors from original dataset. This realization uses
+ * {@link BootstrappedVector} containing each vector from original sample with counters of repetitions
+ * for each subsample. As heuristic this implementation uses Poisson Distribution for generating counter values.
+ *
+ * @param <K> Type of a key in {@code upstream} data.
+ * @param <V> Type of a value in {@code upstream} data.
+ */
+public class BootstrappedDatasetBuilder<K,V> implements PartitionDataBuilder<K,V, EmptyContext, BootstrappedDatasetPartition> {
+ /** Serial version uid. */
+ private static final long serialVersionUID = 8146220902914010559L;
+
+ /** Feature extractor. */
+ private final IgniteBiFunction<K, V, Vector> featureExtractor;
+
+ /** Label extractor. */
+ private final IgniteBiFunction<K, V, Double> lbExtractor;
+
+ /** Samples count. */
+ private final int samplesCnt;
+
+ /** Subsample size. */
+ private final double subsampleSize;
+
+ /**
+ * Creates an instance of BootstrappedDatasetBuilder.
+ *
+ * @param featureExtractor Feature extractor.
+ * @param lbExtractor Label extractor.
+ * @param samplesCnt Samples count.
+ * @param subsampleSize Subsample size.
+ */
+ public BootstrappedDatasetBuilder(IgniteBiFunction<K, V, Vector> featureExtractor,
+ IgniteBiFunction<K, V, Double> lbExtractor, int samplesCnt, double subsampleSize) {
+
+ this.featureExtractor = featureExtractor;
+ this.lbExtractor = lbExtractor;
+ this.samplesCnt = samplesCnt;
+ this.subsampleSize = subsampleSize;
+ }
+
+ /** {@inheritDoc} */
+ @Override public BootstrappedDatasetPartition build(Iterator<UpstreamEntry<K, V>> upstreamData, long upstreamDataSize,
+ EmptyContext ctx) {
+
+ BootstrappedVector[] dataset = new BootstrappedVector[Math.toIntExact(upstreamDataSize)];
+
+ int cntr = 0;
+ PoissonDistribution poissonDistribution = new PoissonDistribution(subsampleSize);
+ while(upstreamData.hasNext()) {
+ UpstreamEntry<K, V> nextRow = upstreamData.next();
+ Vector features = featureExtractor.apply(nextRow.getKey(), nextRow.getValue());
+ Double lb = lbExtractor.apply(nextRow.getKey(), nextRow.getValue());
+ int[] repetitionCounters = new int[samplesCnt];
+ Arrays.setAll(repetitionCounters, i -> poissonDistribution.sample());
+ dataset[cntr++] = new BootstrappedVector(features, lb, repetitionCounters);
+ }
+
+ return new BootstrappedDatasetPartition(dataset);
+ }
+}
http://git-wip-us.apache.org/repos/asf/ignite/blob/78328fe4/modules/ml/src/main/java/org/apache/ignite/ml/dataset/impl/bootstrapping/BootstrappedDatasetPartition.java
----------------------------------------------------------------------
diff --git a/modules/ml/src/main/java/org/apache/ignite/ml/dataset/impl/bootstrapping/BootstrappedDatasetPartition.java b/modules/ml/src/main/java/org/apache/ignite/ml/dataset/impl/bootstrapping/BootstrappedDatasetPartition.java
new file mode 100644
index 0000000..2155d1a
--- /dev/null
+++ b/modules/ml/src/main/java/org/apache/ignite/ml/dataset/impl/bootstrapping/BootstrappedDatasetPartition.java
@@ -0,0 +1,68 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.ignite.ml.dataset.impl.bootstrapping;
+
+import java.util.Arrays;
+import java.util.Iterator;
+import org.jetbrains.annotations.NotNull;
+
+/**
+ * Partition of bootstrapped vectors.
+ */
+public class BootstrappedDatasetPartition implements AutoCloseable, Iterable<BootstrappedVector> {
+ /** Vectors. */
+ private final BootstrappedVector[] vectors;
+
+ /**
+ * Creates an instance of BootstrappedDatasetPartition.
+ *
+ * @param vectors Vectors.
+ */
+ public BootstrappedDatasetPartition(BootstrappedVector[] vectors) {
+ this.vectors = vectors;
+ }
+
+ /**
+ * Returns vector from dataset in according to row id.
+ *
+ * @param rowId Row id.
+ * @return Vector.
+ */
+ public BootstrappedVector getRow(int rowId) {
+ return vectors[rowId];
+ }
+
+ /**
+ * Returns rows count.
+ *
+ * @return rows count.
+ */
+ public int getRowsCount() {
+ return vectors.length;
+ }
+
+ /** {@inheritDoc} */
+ @NotNull @Override public Iterator<BootstrappedVector> iterator() {
+ return Arrays.stream(vectors).iterator();
+ }
+
+ /** {@inheritDoc} */
+ @Override public void close() throws Exception {
+ //NOP
+ }
+}
http://git-wip-us.apache.org/repos/asf/ignite/blob/78328fe4/modules/ml/src/main/java/org/apache/ignite/ml/dataset/impl/bootstrapping/BootstrappedVector.java
----------------------------------------------------------------------
diff --git a/modules/ml/src/main/java/org/apache/ignite/ml/dataset/impl/bootstrapping/BootstrappedVector.java b/modules/ml/src/main/java/org/apache/ignite/ml/dataset/impl/bootstrapping/BootstrappedVector.java
new file mode 100644
index 0000000..aedd0fd
--- /dev/null
+++ b/modules/ml/src/main/java/org/apache/ignite/ml/dataset/impl/bootstrapping/BootstrappedVector.java
@@ -0,0 +1,87 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.ignite.ml.dataset.impl.bootstrapping;
+
+import java.io.IOException;
+import java.io.ObjectInput;
+import java.io.ObjectOutput;
+import java.util.Arrays;
+import org.apache.ignite.ml.math.primitives.vector.Vector;
+import org.apache.ignite.ml.structures.LabeledVector;
+
+/**
+ * Represents vector with repetitions counters for subsamples in bootstrapped dataset.
+ * Each counter shows the number of repetitions of the vector for the n-th sample.
+ */
+public class BootstrappedVector extends LabeledVector<Vector, Double> {
+ /** Serial version uid. */
+ private static final long serialVersionUID = -4583008673032917259L;
+
+ /** Counters show the number of repetitions of the vector for the n-th sample. */
+ private int[] counters;
+
+ /**
+ * Creates an instance of BootstrappedVector.
+ *
+ * @param features Features.
+ * @param lb Label.
+ * @param counters Repetitions counters.
+ */
+ public BootstrappedVector(Vector features, double lb, int[] counters) {
+ super(features, lb);
+ this.counters = counters;
+ }
+
+ /**
+ * @return repetitions counters vector.
+ */
+ public int[] counters() {
+ return counters;
+ }
+
+ /** {@inheritDoc} */
+ @Override public boolean equals(Object o) {
+ if (this == o)
+ return true;
+ if (o == null || getClass() != o.getClass())
+ return false;
+ if (!super.equals(o))
+ return false;
+ BootstrappedVector vector = (BootstrappedVector)o;
+ return Arrays.equals(counters, vector.counters);
+ }
+
+ /** {@inheritDoc} */
+ @Override public int hashCode() {
+ int result = super.hashCode();
+ result = 31 * result + Arrays.hashCode(counters);
+ return result;
+ }
+
+ /** {@inheritDoc} */
+ @Override public void writeExternal(ObjectOutput out) throws IOException {
+ super.writeExternal(out);
+ out.writeObject(counters);
+ }
+
+ /** {@inheritDoc} */
+ @Override public void readExternal(ObjectInput in) throws IOException, ClassNotFoundException {
+ super.readExternal(in);
+ counters = (int[]) in.readObject();
+ }
+}
http://git-wip-us.apache.org/repos/asf/ignite/blob/78328fe4/modules/ml/src/main/java/org/apache/ignite/ml/dataset/impl/bootstrapping/package-info.java
----------------------------------------------------------------------
diff --git a/modules/ml/src/main/java/org/apache/ignite/ml/dataset/impl/bootstrapping/package-info.java b/modules/ml/src/main/java/org/apache/ignite/ml/dataset/impl/bootstrapping/package-info.java
new file mode 100644
index 0000000..5fcf629
--- /dev/null
+++ b/modules/ml/src/main/java/org/apache/ignite/ml/dataset/impl/bootstrapping/package-info.java
@@ -0,0 +1,23 @@
+/*
+
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+/**
+ * <!-- Package description. -->
+ * Base package for bootstrapped implementation of machine learning dataset.
+ */
+package org.apache.ignite.ml.dataset.impl.bootstrapping;
http://git-wip-us.apache.org/repos/asf/ignite/blob/78328fe4/modules/ml/src/main/java/org/apache/ignite/ml/tree/randomforest/RandomForestClassifierTrainer.java
----------------------------------------------------------------------
diff --git a/modules/ml/src/main/java/org/apache/ignite/ml/tree/randomforest/RandomForestClassifierTrainer.java b/modules/ml/src/main/java/org/apache/ignite/ml/tree/randomforest/RandomForestClassifierTrainer.java
index bbbb2a9..559dfff 100644
--- a/modules/ml/src/main/java/org/apache/ignite/ml/tree/randomforest/RandomForestClassifierTrainer.java
+++ b/modules/ml/src/main/java/org/apache/ignite/ml/tree/randomforest/RandomForestClassifierTrainer.java
@@ -17,72 +17,93 @@
package org.apache.ignite.ml.tree.randomforest;
+import java.util.HashMap;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Map;
+import java.util.Set;
+import org.apache.ignite.ml.composition.ModelsComposition;
import org.apache.ignite.ml.composition.predictionsaggregator.OnMajorityPredictionsAggregator;
-import org.apache.ignite.ml.composition.predictionsaggregator.PredictionsAggregator;
-import org.apache.ignite.ml.trainers.DatasetTrainer;
-import org.apache.ignite.ml.tree.DecisionTreeClassificationTrainer;
-import org.apache.ignite.ml.tree.DecisionTreeNode;
+import org.apache.ignite.ml.dataset.Dataset;
+import org.apache.ignite.ml.dataset.feature.FeatureMeta;
+import org.apache.ignite.ml.dataset.feature.ObjectHistogram;
+import org.apache.ignite.ml.dataset.impl.bootstrapping.BootstrappedDatasetPartition;
+import org.apache.ignite.ml.dataset.impl.bootstrapping.BootstrappedVector;
+import org.apache.ignite.ml.dataset.primitive.context.EmptyContext;
+import org.apache.ignite.ml.tree.randomforest.data.TreeRoot;
+import org.apache.ignite.ml.tree.randomforest.data.impurity.GiniHistogram;
+import org.apache.ignite.ml.tree.randomforest.data.impurity.GiniHistogramsComputer;
+import org.apache.ignite.ml.tree.randomforest.data.impurity.ImpurityHistogramsComputer;
+import org.apache.ignite.ml.tree.randomforest.data.statistics.ClassifierLeafValuesComputer;
+import org.apache.ignite.ml.tree.randomforest.data.statistics.LeafValuesComputer;
/**
- * Random forest classifier trainer.
+ * Classifier trainer based on RandomForest algorithm.
*/
-public class RandomForestClassifierTrainer extends RandomForestTrainer {
+public class RandomForestClassifierTrainer
+ extends RandomForestTrainer<ObjectHistogram<BootstrappedVector>, GiniHistogram, RandomForestClassifierTrainer> {
+ /** Label mapping. */
+ private Map<Double, Integer> lblMapping = new HashMap<>();
+
/**
- * Constructs new instance of RandomForestClassifierTrainer.
+ * Constructs an instance of RandomForestClassifierTrainer.
*
- * @param predictionsAggregator Predictions aggregator.
- * @param featureVectorSize Feature vector size.
- * @param maximumFeaturesCntPerMdl Number of features to draw from original features vector to train each model.
- * @param ensembleSize Ensemble size.
- * @param samplePartSizePerMdl Size of sample part in percent to train one model.
- * @param maxDeep Max decision tree deep.
- * @param minImpurityDecrease Min impurity decrease.
+ * @param meta Features meta.
*/
- public RandomForestClassifierTrainer(PredictionsAggregator predictionsAggregator,
- int featureVectorSize,
- int maximumFeaturesCntPerMdl,
- int ensembleSize,
- double samplePartSizePerMdl,
- int maxDeep,
- double minImpurityDecrease) {
+ public RandomForestClassifierTrainer(List<FeatureMeta> meta) {
+ super(meta);
+ }
- super(predictionsAggregator, featureVectorSize, maximumFeaturesCntPerMdl,
- ensembleSize, samplePartSizePerMdl, maxDeep, minImpurityDecrease);
+ /** {@inheritDoc} */
+ @Override protected RandomForestClassifierTrainer instance() {
+ return this;
}
/**
- * Constructs new instance of RandomForestClassifierTrainer.
+ * Aggregates all unique labels from dataset and assigns integer id value for each label.
+ * This id can be used as index in arrays or lists.
*
- * @param featureVectorSize Feature vector size.
- * @param maximumFeaturesCntPerMdl Number of features to draw from original features vector to train each model.
- * @param ensembleSize Ensemble size.
- * @param samplePartSizePerMdl Size of sample part in percent to train one model.
- * @param maxDeep Max decision tree deep.
- * @param minImpurityDecrease Min impurity decrease.
+ * @param dataset Dataset.
*/
- public RandomForestClassifierTrainer(int featureVectorSize,
- int maximumFeaturesCntPerMdl,
- int ensembleSize,
- double samplePartSizePerMdl,
- int maxDeep, double minImpurityDecrease) {
+ @Override protected void init(Dataset<EmptyContext, BootstrappedDatasetPartition> dataset) {
+ Set<Double> uniqLabels = dataset.compute(
+ x -> {
+ Set<Double> labels = new HashSet<>();
+ for (int i = 0; i < x.getRowsCount(); i++)
+ labels.add(x.getRow(i).label());
+ return labels;
+ },
+ (l, r) -> {
+ if (l == null)
+ return r;
+ if (r == null)
+ return l;
+ Set<Double> lbls = new HashSet<>();
+ lbls.addAll(l);
+ lbls.addAll(r);
+ return lbls;
+ }
+ );
- this(new OnMajorityPredictionsAggregator(), featureVectorSize, maximumFeaturesCntPerMdl,
- ensembleSize, samplePartSizePerMdl, maxDeep, minImpurityDecrease);
+ int i = 0;
+ for (Double label : uniqLabels)
+ lblMapping.put(label, i++);
+
+ super.init(dataset);
}
/** {@inheritDoc} */
- @Override protected DatasetTrainer<DecisionTreeNode, Double> buildDatasetTrainerForModel() {
- return new DecisionTreeClassificationTrainer(maxDeep, minImpurityDecrease).withUseIndex(useIndex);
+ @Override protected ModelsComposition buildComposition(List<TreeRoot> models) {
+ return new ModelsComposition(models, new OnMajorityPredictionsAggregator());
}
- /**
- * Sets useIndex parameter and returns trainer instance.
- *
- * @param useIndex Use index.
- * @return Decision tree trainer.
- */
- public RandomForestClassifierTrainer withUseIndex(boolean useIndex) {
- this.useIndex = useIndex;
- return this;
+ /** {@inheritDoc} */
+ @Override protected ImpurityHistogramsComputer<GiniHistogram> createImpurityHistogramsComputer() {
+ return new GiniHistogramsComputer(lblMapping);
+ }
+
+ /** {@inheritDoc} */
+ @Override protected LeafValuesComputer<ObjectHistogram<BootstrappedVector>> createLeafStatisticsAggregator() {
+ return new ClassifierLeafValuesComputer(lblMapping);
}
}
http://git-wip-us.apache.org/repos/asf/ignite/blob/78328fe4/modules/ml/src/main/java/org/apache/ignite/ml/tree/randomforest/RandomForestRegressionTrainer.java
----------------------------------------------------------------------
diff --git a/modules/ml/src/main/java/org/apache/ignite/ml/tree/randomforest/RandomForestRegressionTrainer.java b/modules/ml/src/main/java/org/apache/ignite/ml/tree/randomforest/RandomForestRegressionTrainer.java
index 009fff2..ab1d036 100644
--- a/modules/ml/src/main/java/org/apache/ignite/ml/tree/randomforest/RandomForestRegressionTrainer.java
+++ b/modules/ml/src/main/java/org/apache/ignite/ml/tree/randomforest/RandomForestRegressionTrainer.java
@@ -17,73 +17,49 @@
package org.apache.ignite.ml.tree.randomforest;
+import java.util.List;
+import org.apache.ignite.ml.composition.ModelsComposition;
import org.apache.ignite.ml.composition.predictionsaggregator.MeanValuePredictionsAggregator;
-import org.apache.ignite.ml.composition.predictionsaggregator.PredictionsAggregator;
-import org.apache.ignite.ml.trainers.DatasetTrainer;
-import org.apache.ignite.ml.tree.DecisionTreeNode;
-import org.apache.ignite.ml.tree.DecisionTreeRegressionTrainer;
+import org.apache.ignite.ml.dataset.feature.FeatureMeta;
+import org.apache.ignite.ml.tree.randomforest.data.TreeRoot;
+import org.apache.ignite.ml.tree.randomforest.data.impurity.ImpurityHistogramsComputer;
+import org.apache.ignite.ml.tree.randomforest.data.impurity.MSEHistogram;
+import org.apache.ignite.ml.tree.randomforest.data.impurity.MSEHistogramComputer;
+import org.apache.ignite.ml.tree.randomforest.data.statistics.LeafValuesComputer;
+import org.apache.ignite.ml.tree.randomforest.data.statistics.MeanValueStatistic;
+import org.apache.ignite.ml.tree.randomforest.data.statistics.RegressionLeafValuesComputer;
/**
- * Random forest regression trainer.
+ * Regression trainer based on RandomForest algorithm.
*/
-public class RandomForestRegressionTrainer extends RandomForestTrainer {
+public class RandomForestRegressionTrainer
+ extends RandomForestTrainer<MeanValueStatistic, MSEHistogram, RandomForestRegressionTrainer> {
/**
- * Constructs new instance of RandomForestRegressionTrainer.
+ * Constructs an instance of RandomForestRegressionTrainer.
*
- * @param predictionsAggregator Predictions aggregator.
- * @param featureVectorSize Feature vector size.
- * @param maximumFeaturesCntPerMdl Number of features to draw from original features vector to train each model.
- * @param ensembleSize Ensemble size.
- * @param samplePartSizePerMdl Size of sample part in percent to train one model.
- * @param maxDeep Max decision tree deep.
- * @param minImpurityDecrease Min impurity decrease.
+ * @param meta Features meta.
*/
- public RandomForestRegressionTrainer(PredictionsAggregator predictionsAggregator,
- int featureVectorSize,
- int maximumFeaturesCntPerMdl,
- int ensembleSize,
- double samplePartSizePerMdl,
- int maxDeep,
- double minImpurityDecrease) {
-
- super(predictionsAggregator, featureVectorSize, maximumFeaturesCntPerMdl,
- ensembleSize, samplePartSizePerMdl, maxDeep, minImpurityDecrease);
+ public RandomForestRegressionTrainer(List<FeatureMeta> meta) {
+ super(meta);
}
- /**
- * Constructs new instance of RandomForestRegressionTrainer.
- *
- * @param featureVectorSize Feature vector size.
- * @param maximumFeaturesCntPerMdl Number of features to draw from original features vector to train each model.
- * @param ensembleSize Ensemble size.
- * @param samplePartSizePerMdl Size of sample part in percent to train one model.
- * @param maxDeep Max decision tree deep.
- * @param minImpurityDecrease Min impurity decrease.
- */
- public RandomForestRegressionTrainer(int featureVectorSize,
- int maximumFeaturesCntPerMdl,
- int ensembleSize,
- double samplePartSizePerMdl,
- int maxDeep,
- double minImpurityDecrease) {
+ /** {@inheritDoc} */
+ @Override protected RandomForestRegressionTrainer instance() {
+ return this;
+ }
- this(new MeanValuePredictionsAggregator(), featureVectorSize, maximumFeaturesCntPerMdl,
- ensembleSize, samplePartSizePerMdl, maxDeep, minImpurityDecrease);
+ /** {@inheritDoc} */
+ @Override protected ModelsComposition buildComposition(List<TreeRoot> models) {
+ return new ModelsComposition(models, new MeanValuePredictionsAggregator());
}
/** {@inheritDoc} */
- @Override protected DatasetTrainer<DecisionTreeNode, Double> buildDatasetTrainerForModel() {
- return new DecisionTreeRegressionTrainer(maxDeep, minImpurityDecrease).withUseIndex(useIndex);
+ @Override protected ImpurityHistogramsComputer<MSEHistogram> createImpurityHistogramsComputer() {
+ return new MSEHistogramComputer();
}
- /**
- * Sets useIndex parameter and returns trainer instance.
- *
- * @param useIndex Use index.
- * @return Decision tree trainer.
- */
- public RandomForestRegressionTrainer withUseIndex(boolean useIndex) {
- this.useIndex = useIndex;
- return this;
+ /** {@inheritDoc} */
+ @Override protected LeafValuesComputer<MeanValueStatistic> createLeafStatisticsAggregator() {
+ return new RegressionLeafValuesComputer();
}
}