Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/5980#discussion_r29912960
--- Diff: mllib/src/main/scala/org/apache/spark/ml/feature/Bucketizer.scala
---
@@ -0,0 +1,158 @@
+/*
+ * 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.annotation.AlphaComponent
+import org.apache.spark.ml.attribute.NominalAttribute
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared.{HasInputCol, HasOutputCol}
+import org.apache.spark.ml.util.SchemaUtils
+import org.apache.spark.ml.{Estimator, Model}
+import org.apache.spark.sql._
+import org.apache.spark.sql.functions._
+import org.apache.spark.sql.types.{DoubleType, StructField, StructType}
+
+/**
+ * :: AlphaComponent ::
+ * `Bucketizer` maps a column of continuous features to a column of
feature buckets.
+ */
+@AlphaComponent
+private[ml] final class Bucketizer(override val parent:
Estimator[Bucketizer])
+ extends Model[Bucketizer] with HasInputCol with HasOutputCol {
+
+ def this() = this(null)
+
+ /**
+ * Parameter for mapping continuous features into buckets. With n
splits, there are n+1 buckets.
+ * A bucket defined by splits x,y holds values in the range [x,y).
+ * @group param
+ */
+ val splits: Param[Array[Double]] = new Param[Array[Double]](this,
"splits",
+ "Split points for mapping continuous features into buckets. With n
splits, there are n+1" +
+ " buckets. A bucket defined by splits x,y holds values in the range
[x,y).",
+ Bucketizer.checkSplits)
+
+ /** @group getParam */
+ def getSplits: Array[Double] = $(splits)
+
+ /** @group setParam */
+ def setSplits(value: Array[Double]): this.type = set(splits, value)
+
+ /** @group Param */
+ val lowerInclusive: BooleanParam = new BooleanParam(this,
"lowerInclusive",
+ "An indicator of the inclusiveness of negative infinite.")
+ setDefault(lowerInclusive -> true)
+
+ /** @group getParam */
+ def getLowerInclusive: Boolean = $(lowerInclusive)
+
+ /** @group setParam */
+ def setLowerInclusive(value: Boolean): this.type = set(lowerInclusive,
value)
+
+ /** @group Param */
+ val upperInclusive: BooleanParam = new BooleanParam(this,
"upperInclusive",
+ "An indicator of the inclusiveness of positive infinite.")
--- End diff --
Ditto: Please make clearer, e.g.:
```
"If true, then use implicit bin [getSplits.last, inf). If false, then
throw exception if values > getSplits.last are encountered."
```
Also, please copy this doc to the Scala doc comment.
---
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]
