Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/5779#discussion_r30535320
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/feature/QuantileDiscretizer.scala ---
@@ -0,0 +1,141 @@
+/*
+ * 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 scala.collection.mutable
+
+import org.apache.spark.annotation.AlphaComponent
+import org.apache.spark.ml._
+import org.apache.spark.ml.attribute.NominalAttribute
+import org.apache.spark.ml.param.shared.{HasInputCol, HasOutputCol}
+import org.apache.spark.ml.param.{IntParam, _}
+import org.apache.spark.ml.util._
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.types.{DoubleType, StructType}
+import org.apache.spark.sql.{DataFrame, Row}
+import org.apache.spark.util.random.XORShiftRandom
+
+/**
+ * Params for [[QuantileDiscretizer]].
+ */
+private[feature] trait QuantileDiscretizerBase extends Params with
HasInputCol with HasOutputCol {
+
+ /**
+ * Number of buckets to collect data points, which should be a positive
integer.
+ * @group param
+ */
+ val numBuckets = new IntParam(this, "numBuckets",
+ "Number of buckets to collect data points, which should be a positive
integer.",
+ ParamValidators.gtEq(2))
+ setDefault(numBuckets -> 2)
+
+ /** @group getParam */
+ def getNumBuckets: Int = getOrDefault(numBuckets)
+}
+
+/**
+ * :: AlphaComponent ::
+ * `QuantileDiscretizer` takes a column with continuous features and
outputs a column with binned
+ * categorical features.
+ */
+@AlphaComponent
+final class QuantileDiscretizer(override val uid: String)
+ extends Estimator[Bucketizer] with QuantileDiscretizerBase {
+
+ def this() = this(Identifiable.randomUID("QuantileDiscretizer"))
+
+ /** @group setParam */
+ def setNumBuckets(value: Int): this.type = set(numBuckets, value)
+
+ /** @group setParam */
+ def setInputCol(value: String): this.type = set(inputCol, value)
+
+ /** @group setParam */
+ def setOutputCol(value: String): this.type = set(outputCol, value)
+
+ override def transformSchema(schema: StructType): StructType = {
+ SchemaUtils.checkColumnType(schema, $(inputCol), DoubleType)
+ val inputFields = schema.fields
+ require(inputFields.forall(_.name != $(outputCol)),
+ s"Output column ${$(outputCol)} already exists.")
+ val attr = NominalAttribute.defaultAttr.withName($(outputCol))
+ val outputFields = inputFields :+ attr.toStructField()
+ StructType(outputFields)
+ }
+
+ override def fit(dataset: DataFrame): Bucketizer = {
+ val input = dataset.select($(inputCol)).map { case Row(feature:
Double) => feature }
--- End diff --
It will be better to keep input as a DataFrame and use DataFrame.sample
within getSampledInput. That will let Catalyst optimize stuff.
---
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]
