Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/1207#discussion_r15733205
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/feature/StandardScaler.scala ---
@@ -0,0 +1,94 @@
+/*
+ * 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.mllib.feature
+
+import breeze.linalg.{DenseVector => BDV}
+
+import org.apache.spark.annotation.DeveloperApi
+import org.apache.spark.mllib.linalg.distributed.RowMatrix
+import org.apache.spark.mllib.linalg.{Vector, Vectors}
+import org.apache.spark.rdd.RDD
+
+/**
+ * :: DeveloperApi ::
+ * Standardizes features by removing the mean and scaling to unit variance
using column summary
+ * statistics on the samples in the training set.
+ *
+ * @param withMean True by default. Centers the data with mean before
scaling. It will build a dense
+ * output, so this does not work on sparse input and will
raise an exception.
+ * @param withStd True by default. Scales the data to unit standard
deviation.
+ */
+@DeveloperApi
+class StandardScaler(withMean: Boolean, withStd: Boolean)
+ extends VectorTransformer with Serializable {
+
+ def this() = this(true, true)
+
+ var mean: Vector = _
+ var variance: Vector = _
+
+ /**
+ * Computes the mean and variance and stores as a model to be used for
later scaling.
+ *
+ * @param data The data used to compute the mean and variance to build
the transformation model.
+ * @return This StandardScalar object.
+ */
+ def fit(data: RDD[Vector]): this.type = {
+ val summary = new RowMatrix(data).computeColumnSummaryStatistics
+ this.mean = summary.mean
+ this.variance = summary.variance
+ require(mean.toBreeze.length == variance.toBreeze.length)
+ this
+ }
+
+ /**
+ * Applies standardization transformation on a vector.
+ *
+ * @param vector Vector to be standardized.
+ * @return Standardized vector. If the variance of a column is zero, it
will return default `0.0`
+ * for the column with zero variance.
+ */
+ override def transform(vector: Vector): Vector = {
+ require(mean != null || variance != null, s"Please `fit` the model
with training set first.")
+ require(vector.toBreeze.length == mean.toBreeze.length)
+
+ if (withMean) {
+ vector.toBreeze match {
+ case dv: BDV[Double] => // pass
+ case v: Any =>
+ throw new IllegalArgumentException("Do not support vector type "
+ v.getClass)
+ }
+ }
+
+ val output = vector.toBreeze.copy
+ output.activeIterator.foreach {
+ case (i, value) => {
+ val shift = if (withMean) mean(i) else 0.0
+ if (variance(i) != 0.0 && withStd) {
+ output(i) = (value - shift) / Math.sqrt(variance(i))
--- End diff --
ditto: same issue with random access
---
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.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
