Github user tillrohrmann commented on a diff in the pull request:
https://github.com/apache/flink/pull/579#discussion_r28412522
--- Diff:
flink-staging/flink-ml/src/main/scala/org/apache/flink/ml/preprocessing/StandardScaler.scala
---
@@ -0,0 +1,178 @@
+/*
+ * 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.flink.ml.preprocessing
+
+import java.lang.Iterable
+import breeze.linalg
+import breeze.linalg.DenseVector
+import breeze.numerics.sqrt
+import breeze.numerics.sqrt._
+import org.apache.flink.api.common.functions._
+import org.apache.flink.api.scala._
+import org.apache.flink.configuration.Configuration
+import org.apache.flink.ml.common.{Parameter, ParameterMap, Transformer}
+import org.apache.flink.ml.math.Breeze._
+import org.apache.flink.ml.math.Vector
+import org.apache.flink.ml.preprocessing.StandardScaler.{Mean, Std}
+import org.apache.flink.util.Collector
+
+/** Scales observations, so that all features have mean equal to zero
+ * and standard deviation equal to one
+ *
+ * This transformer takes a a Vector of values and maps it into the
+ * scaled Vector that each feature has a user-specified mean and standard
deviation.
+ *
+ * This transformer can be prepended to all [[Transformer]] and
+ * [[org.apache.flink.ml.common.Learner]] implementations which expect an
input of
+ * [[Vector]].
+ *
+ * @example
+ * {{{
+ * val trainingDS: DataSet[Vector] =
env.fromCollection(data)
+ *
+ * val transformer =
StandardScaler().setMean(10.0).setStd(2.0)
+ *
+ * transformer.transform(trainingDS)
+ * }}}
+ *
+ * =Parameters=
+ *
+ * - [[StandardScaler.Mean]]: The mean value of transformed data set; by
default equal to 0
+ * - [[StandardScaler.Std]]: The standard deviation of the transformed
data set; by default
+ * equal to 1
+ */
+class StandardScaler extends Transformer[Vector, Vector] with Serializable
{
+
+ def setMean(mu: Double): StandardScaler = {
+ parameters.add(Mean, mu)
+ this
+ }
+
+ def setStd(std: Double): StandardScaler = {
+ parameters.add(Std, std)
+ this
+ }
+
+ override def transform(input: DataSet[Vector], parameters: ParameterMap):
+ DataSet[Vector] = {
+ val resultingParameters = this.parameters ++ parameters
+ val mean = resultingParameters(Mean)
+ val std = resultingParameters(Std)
+
+ val featureMetrics = extractFeatureMetrics(input)
+
+ input.map(new RichMapFunction[Vector, Vector]() {
+
+ var broadcastMeanSet: Vector = null
+ var broadcastStdSet: Vector = null
+
+ override def open(parameters: Configuration): Unit = {
+ val broadcastedMetrics =
getRuntimeContext().getBroadcastVariable[(Vector,
+ Vector)]("broadcastedMetrics").get(0)
+ broadcastMeanSet = broadcastedMetrics._1
+ broadcastStdSet = broadcastedMetrics._2
+ }
+
+ override def map(vector: Vector): Vector = {
+ var myVector = vector.asBreeze
+
+ myVector :-= broadcastMeanSet.asBreeze
+ myVector :/= broadcastStdSet.asBreeze
+ myVector = (myVector :* std) :+ mean
+ return myVector.fromBreeze
+ }
+ }).withBroadcastSet(featureMetrics, "broadcastedMetrics")
+ }
+
+ /** Calculates in one pass over the data the features' mean and standard
deviation.
+ * For the calculation of the Standard deviation with one pas over the
data,
+ * the Youngs & Cramer algorithm was used
--- End diff --
Maybe we can put the link
http://www.cs.yale.edu/publications/techreports/tr222.pdf here, too.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
