-
Notifications
You must be signed in to change notification settings - Fork 17
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
v1.1.0 - added 6 optimised algorithms (#18)
Add Kmeans、DecisionTree、LinearRegression、LogisticRegression、PCA and SVD testcase
- Loading branch information
1 parent
92288c1
commit 36e654a
Showing
58 changed files
with
7,040 additions
and
130 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
26 changes: 3 additions & 23 deletions
26
ml-accelerator/src/main/scala/breeze/optimize/FirstOrderMinimizerX.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
27 changes: 9 additions & 18 deletions
27
ml-accelerator/src/main/scala/breeze/optimize/OWLQNX.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
154 changes: 154 additions & 0 deletions
154
...ccelerator/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,154 @@ | ||
| /* | ||
| * 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.spark.ml.classification | ||
|
|
||
| import org.apache.spark.annotation.Since | ||
| import org.apache.spark.ml.feature.LabeledPoint | ||
| import org.apache.spark.ml.linalg.Vector | ||
| import org.apache.spark.ml.param.ParamMap | ||
| import org.apache.spark.ml.tree._ | ||
| import org.apache.spark.ml.tree.impl.DecisionForest | ||
| import org.apache.spark.ml.util._ | ||
| import org.apache.spark.mllib.tree.configuration.{Algo => OldAlgo, Strategy => OldStrategy} | ||
| import org.apache.spark.rdd.RDD | ||
| import org.apache.spark.sql.Dataset | ||
|
|
||
|
|
||
| /** | ||
| * Decision tree learning algorithm (http://en.wikipedia.org/wiki/Decision_tree_learning) | ||
| * for classification. | ||
| * It supports both binary and multiclass labels, as well as both continuous and categorical | ||
| * features. | ||
| */ | ||
| @Since("1.4.0") | ||
| class DecisionTreeClassifier @Since("1.4.0") ( | ||
| @Since("1.4.0") override val uid: String) | ||
| extends ProbabilisticClassifier[Vector, DecisionTreeClassifier, DecisionTreeClassificationModel] | ||
| with DecisionTreeClassifierParams with DefaultParamsWritable { | ||
|
|
||
| @Since("1.4.0") | ||
| def this() = this(Identifiable.randomUID("dtc")) | ||
|
|
||
| // Override parameter setters from parent trait for Java API compatibility. | ||
|
|
||
| /** @group setParam */ | ||
| @Since("1.4.0") | ||
| override def setMaxDepth(value: Int): this.type = set(maxDepth, value) | ||
|
|
||
| /** @group setParam */ | ||
| @Since("1.4.0") | ||
| override def setMaxBins(value: Int): this.type = set(maxBins, value) | ||
|
|
||
| /** @group setParam */ | ||
| @Since("1.4.0") | ||
| override def setMinInstancesPerNode(value: Int): this.type = set(minInstancesPerNode, value) | ||
|
|
||
| /** @group setParam */ | ||
| @Since("1.4.0") | ||
| override def setMinInfoGain(value: Double): this.type = set(minInfoGain, value) | ||
|
|
||
| /** @group expertSetParam */ | ||
| @Since("1.4.0") | ||
| override def setMaxMemoryInMB(value: Int): this.type = set(maxMemoryInMB, value) | ||
|
|
||
| /** @group expertSetParam */ | ||
| @Since("1.4.0") | ||
| override def setCacheNodeIds(value: Boolean): this.type = set(cacheNodeIds, value) | ||
|
|
||
| /** | ||
| * Specifies how often to checkpoint the cached node IDs. | ||
| * E.g. 10 means that the cache will get checkpointed every 10 iterations. | ||
| * This is only used if cacheNodeIds is true and if the checkpoint directory is set in | ||
| * [[org.apache.spark.SparkContext]]. | ||
| * Must be at least 1. | ||
| * (default = 10) | ||
| * @group setParam | ||
| */ | ||
| @Since("1.4.0") | ||
| override def setCheckpointInterval(value: Int): this.type = set(checkpointInterval, value) | ||
|
|
||
| /** @group setParam */ | ||
| @Since("1.4.0") | ||
| override def setImpurity(value: String): this.type = set(impurity, value) | ||
|
|
||
| /** @group setParam */ | ||
| @Since("1.6.0") | ||
| override def setSeed(value: Long): this.type = set(seed, value) | ||
|
|
||
| override protected def train(dataset: Dataset[_]): DecisionTreeClassificationModel = { | ||
| val categoricalFeatures: Map[Int, Int] = | ||
| MetadataUtils.getCategoricalFeatures(dataset.schema($(featuresCol))) | ||
| val numClasses: Int = getNumClasses(dataset) | ||
|
|
||
| if (isDefined(thresholds)) { | ||
| require($(thresholds).length == numClasses, this.getClass.getSimpleName + | ||
| ".train() called with non-matching numClasses and thresholds.length." + | ||
| s" numClasses=$numClasses, but thresholds has length ${$(thresholds).length}") | ||
| } | ||
|
|
||
| val oldDataset: RDD[LabeledPoint] = extractLabeledPoints(dataset, numClasses) | ||
| val strategy = getOldStrategy(categoricalFeatures, numClasses) | ||
|
|
||
| val instr = Instrumentation.create(this, oldDataset) | ||
| instr.logParams(params: _*) | ||
|
|
||
| val trees = DecisionForest.run(oldDataset, strategy, numTrees = 1, | ||
| featureSubsetStrategy = "all", | ||
| seed = $(seed), instr = Some(instr), parentUID = Some(uid)) | ||
|
|
||
| val m = trees.head.asInstanceOf[DecisionTreeClassificationModel] | ||
| instr.logSuccess(m) | ||
| m | ||
| } | ||
|
|
||
| /** (private[ml]) Train a decision tree on an RDD */ | ||
| private[ml] def train(data: RDD[LabeledPoint], | ||
| oldStrategy: OldStrategy): DecisionTreeClassificationModel = { | ||
| val instr = Instrumentation.create(this, data) | ||
| instr.logParams(params: _*) | ||
|
|
||
| val trees = DecisionForest.run(data, oldStrategy, numTrees = 1, | ||
| featureSubsetStrategy = "all", | ||
| seed = 0L, instr = Some(instr), parentUID = Some(uid)) | ||
|
|
||
| val m = trees.head.asInstanceOf[DecisionTreeClassificationModel] | ||
| instr.logSuccess(m) | ||
| m | ||
| } | ||
|
|
||
| /** (private[ml]) Create a Strategy instance to use with the old API. */ | ||
| private[ml] def getOldStrategy( | ||
| categoricalFeatures: Map[Int, Int], | ||
| numClasses: Int): OldStrategy = { | ||
| super.getOldStrategy(categoricalFeatures, numClasses, OldAlgo.Classification, getOldImpurity, | ||
| subsamplingRate = 1.0) | ||
| } | ||
|
|
||
| @Since("1.4.1") | ||
| override def copy(extra: ParamMap): DecisionTreeClassifier = defaultCopy(extra) | ||
| } | ||
|
|
||
| @Since("1.4.0") | ||
| object DecisionTreeClassifier extends DefaultParamsReadable[DecisionTreeClassifier] { | ||
| /** Accessor for supported impurities: entropy, gini */ | ||
| @Since("1.4.0") | ||
| final val supportedImpurities: Array[String] = TreeClassifierParams.supportedImpurities | ||
|
|
||
| @Since("2.0.0") | ||
| override def load(path: String): DecisionTreeClassifier = super.load(path) | ||
| } |
Empty file modified
0
ml-accelerator/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala
100755 → 100644
Empty file.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.