spark-reviews mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From mengxr <...@git.apache.org>
Subject [GitHub] spark pull request: [SPARK-5895] [ML] Add VectorSlicer - updated
Date Wed, 05 Aug 2015 22:35:53 GMT
Github user mengxr commented on a diff in the pull request:

    https://github.com/apache/spark/pull/7972#discussion_r36363033
  
    --- Diff: mllib/src/main/scala/org/apache/spark/ml/feature/VectorSlicer.scala ---
    @@ -0,0 +1,182 @@
    +/*
    + * 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.Experimental
    +import org.apache.spark.ml.Transformer
    +import org.apache.spark.ml.attribute.{Attribute, AttributeGroup}
    +import org.apache.spark.ml.param.shared.{HasInputCol, HasOutputCol}
    +import org.apache.spark.ml.param.{IntArrayParam, ParamMap, StringArrayParam}
    +import org.apache.spark.ml.util.{Identifiable, SchemaUtils}
    +import org.apache.spark.mllib.linalg._
    +import org.apache.spark.sql.DataFrame
    +import org.apache.spark.sql.functions._
    +import org.apache.spark.sql.types.StructType
    +
    +/**
    + * :: Experimental ::
    + * This class takes a feature vector and outputs a new feature vector with a subarray
of the
    + * original features.
    + * The subset of features can be specified with either indices ([[setSelectedIndices()]])
    + * or names ([[setSelectedNames()]]).  At least one feature must be selected.
    + * The output vector will order features with the selected indices first (in the order
given),
    + * followed by the selected names (in the order given).
    + */
    +@Experimental
    +final class VectorSlicer(override val uid: String)
    +  extends Transformer with HasInputCol with HasOutputCol {
    +
    +  def this() = this(Identifiable.randomUID("vectorSlicer"))
    +
    +  /**
    +   * An array of indices to select features from a vector column.
    +   * There can be no overlap with [[selectedNames]].
    +   * @group param
    +   */
    +  val selectedIndices = new IntArrayParam(this, "selectedIndices",
    +    "An array of indices to select features from a vector column." +
    +      " There can be no overlap with selectedNames.", VectorSlicer.validIndices)
    +
    +  setDefault(selectedIndices -> Array.empty[Int])
    +
    +  /** @group getParam */
    +  def getSelectedIndices: Array[Int] = getOrDefault(selectedIndices)
    --- End diff --
    
    `getOrDefault` -> `$`


---
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 infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org


Mime
View raw message