spark-reviews mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From petro-rudenko <...@git.apache.org>
Subject [GitHub] spark pull request: [SPARK-5885][MLLIB] Add VectorAssembler as a f...
Date Fri, 03 Apr 2015 16:48:15 GMT
Github user petro-rudenko commented on a diff in the pull request:

    https://github.com/apache/spark/pull/5196#discussion_r27739585
  
    --- Diff: mllib/src/main/scala/org/apache/spark/ml/feature/VectorAssembler.scala ---
    @@ -0,0 +1,101 @@
    +/*
    + * 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.ArrayBuilder
    +
    +import org.apache.spark.SparkException
    +import org.apache.spark.annotation.AlphaComponent
    +import org.apache.spark.ml.Transformer
    +import org.apache.spark.ml.param.{HasInputCols, HasOutputCol, ParamMap}
    +import org.apache.spark.mllib.linalg.{Vector, VectorUDT, Vectors}
    +import org.apache.spark.sql.{Column, DataFrame, Row}
    +import org.apache.spark.sql.catalyst.analysis.UnresolvedAttribute
    +import org.apache.spark.sql.catalyst.expressions.CreateStruct
    +import org.apache.spark.sql.functions._
    +import org.apache.spark.sql.types._
    +
    +/**
    + * :: AlphaComponent ::
    + * A feature transformer than merge multiple columns into a vector column.
    + */
    +@AlphaComponent
    +class VectorAssembler extends Transformer with HasInputCols with HasOutputCol {
    +
    +  /** @group setParam */
    +  def setInputCols(value: Array[String]): this.type = set(inputCols, value)
    +
    +  /** @group setParam */
    +  def setOutputCol(value: String): this.type = set(outputCol, value)
    +
    +  override def transform(dataset: DataFrame, paramMap: ParamMap): DataFrame = {
    +    val map = this.paramMap ++ paramMap
    +    val assembleFunc = udf { r: Row =>
    +      VectorAssembler.assemble(r.toSeq: _*)
    +    }
    +    val args = map(inputCols).map(c => UnresolvedAttribute(c))
    +    dataset.select(col("*"), assembleFunc(new Column(CreateStruct(args))).as(map(outputCol)))
    +  }
    +
    +  override def transformSchema(schema: StructType, paramMap: ParamMap): StructType =
{
    +    val map = this.paramMap ++ paramMap
    +    val inputColNames = map(inputCols)
    +    val outputColName = map(outputCol)
    +    val inputDataTypes = inputColNames.map(name => schema(name).dataType)
    +    for (dataType <- inputDataTypes) {
    +      if (!(dataType == DoubleType || dataType.isInstanceOf[VectorUDT])) {
    +        throw new IllegalArgumentException(s"Data type $dataType is not supported.")
    +      }
    +    }
    +    if (schema.fieldNames.contains(outputColName)) {
    +      throw new IllegalArgumentException(s"Output column $outputColName already exists.")
    +    }
    +    StructType(schema.fields :+ new StructField(outputColName, new VectorUDT, false))
    +  }
    +}
    +
    +@AlphaComponent
    +object VectorAssembler {
    +
    +  private[feature] def assemble(vv: Any*): Vector = {
    +    val indices = ArrayBuilder.make[Int]
    +    val values = ArrayBuilder.make[Double]
    +    var cur = 0
    +    vv.foreach {
    +      case v: Double =>
    --- End diff --
    
    Would be good to support Integers also and just convert them to double.


---
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