Github user mateiz commented on a diff in the pull request:
https://github.com/apache/spark/pull/3099#discussion_r20116846
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala ---
@@ -0,0 +1,100 @@
+/*
+ * 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.spark.ml._
+import org.apache.spark.ml.param._
+import org.apache.spark.mllib.feature
+import org.apache.spark.mllib.linalg.{Vector, VectorUDT}
+import org.apache.spark.sql._
+import org.apache.spark.sql.catalyst.analysis.Star
+import org.apache.spark.sql.catalyst.dsl._
+
+/**
+ * Params for [[StandardScaler]] and [[StandardScalerModel]].
+ */
+private[feature] trait StandardScalerParams extends Params with
HasInputCol with HasOutputCol
+
+/**
+ * Standardizes features by removing the mean and scaling to unit variance
using column summary
+ * statistics on the samples in the training set.
+ */
+class StandardScaler extends Estimator[StandardScalerModel] with
StandardScalerParams {
+
+ def setInputCol(value: String): this.type = { set(inputCol, value); this
}
+ def setOutputCol(value: String): this.type = { set(outputCol, value);
this }
+
+ override def fit(dataset: SchemaRDD, paramMap: ParamMap):
StandardScalerModel = {
+ transform(dataset.schema, paramMap, logging = true)
+ import dataset.sqlContext._
+ val map = this.paramMap ++ paramMap
+ val input = dataset.select(map(inputCol).attr)
+ .map { case Row(v: Vector) =>
+ v
+ }
+ val scaler = new feature.StandardScaler().fit(input)
+ val model = new StandardScalerModel(this, map, scaler)
+ Params.copyValues(this, model)
+ model
+ }
+
+ override def transform(schema: StructType, paramMap: ParamMap):
StructType = {
+ val map = this.paramMap ++ paramMap
+ val inputType = schema(map(inputCol)).dataType
+ require(inputType.isInstanceOf[VectorUDT],
+ s"Input column ${map(inputCol)} must be a vector column")
+ require(!schema.fieldNames.contains(map(outputCol)),
+ s"Output column ${map(outputCol)} already exists.")
+ val outputFields = schema.fields :+ StructField(map(outputCol), new
VectorUDT, false)
+ StructType(outputFields)
+ }
+}
+
+/**
+ * Model fitted by [[StandardScaler]].
+ */
+class StandardScalerModel private[ml] (
+ override val parent: StandardScaler,
+ override val fittingParamMap: ParamMap,
+ scaler: feature.StandardScalerModel) extends Model[StandardScalerModel]
--- End diff --
Code style nit: in these cases move extends to a separate line; see the
second example in http://docs.scala-lang.org/style/declarations.html
(applies to other places 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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
