Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/10939#discussion_r53747506
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/feature/MaxAbsScaler.scala ---
@@ -0,0 +1,175 @@
+/*
+ * 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.feature
+
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.ml.{Estimator, Model}
+import org.apache.spark.ml.param.{ParamMap, Params}
+import org.apache.spark.ml.param.shared.{HasInputCol, HasOutputCol}
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.{Vector, Vectors, VectorUDT}
+import org.apache.spark.mllib.stat.Statistics
+import org.apache.spark.sql._
+import org.apache.spark.sql.functions._
+import org.apache.spark.sql.types.{StructField, StructType}
+
+/**
+ * Params for [[MaxAbsScaler]] and [[MaxAbsScalerModel]].
+ */
+private[feature] trait MaxAbsScalerParams extends Params with HasInputCol
with HasOutputCol {
+
+ /** Validates and transforms the input schema. */
+ protected def validateAndTransformSchema(schema: StructType): StructType
= {
+ validateParams()
+ val inputType = schema($(inputCol)).dataType
+ require(inputType.isInstanceOf[VectorUDT],
+ s"Input column ${$(inputCol)} must be a vector column")
+ require(!schema.fieldNames.contains($(outputCol)),
+ s"Output column ${$(outputCol)} already exists.")
+ val outputFields = schema.fields :+ StructField($(outputCol), new
VectorUDT, false)
+ StructType(outputFields)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Rescale each feature individually to range [-1, 1] by dividing through
the largest maximum
+ * absolute value in each feature. It does not shift/center the data, and
thus does not destroy
+ * any sparsity.
+ */
+@Experimental
+class MaxAbsScaler(override val uid: String)
+ extends Estimator[MaxAbsScalerModel] with MaxAbsScalerParams with
DefaultParamsWritable {
+
+ def this() = this(Identifiable.randomUID("maxAbsScal"))
+
+ /** @group setParam */
+ def setInputCol(value: String): this.type = set(inputCol, value)
+
+ /** @group setParam */
+ def setOutputCol(value: String): this.type = set(outputCol, value)
+
+ override def fit(dataset: DataFrame): MaxAbsScalerModel = {
+ transformSchema(dataset.schema, logging = true)
+ val input = dataset.select($(inputCol)).map { case Row(v: Vector) => v
}
+ val summary = Statistics.colStats(input)
+ val maxAbs = summary.min.toArray.zip(summary.max.toArray).map { case
(min, max) =>
--- End diff --
This is not very efficient because `zip` creates a new array with many
small objects. Try the following:
~~~scala
val minVals = summary.min.toArray
val maxVals = summary.max.toArray
val maxAbs = Array.fill(n) { i => math.max(math.abs(minVals(i)),
math.abs(maxVals(i)))) }
~~~
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
