spark Normalizer 源码

spark Normalizer 代码

文件路径：/mllib/src/main/scala/org/apache/spark/ml/feature/Normalizer.scala

/*
 * 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.Since
import org.apache.spark.ml.UnaryTransformer
import org.apache.spark.ml.attribute.AttributeGroup
import org.apache.spark.ml.linalg.{Vector, VectorUDT}
import org.apache.spark.ml.param.{DoubleParam, ParamValidators}
import org.apache.spark.ml.util._
import org.apache.spark.mllib.feature
import org.apache.spark.mllib.linalg.{Vectors => OldVectors}
import org.apache.spark.sql.types._

/**
 * Normalize a vector to have unit norm using the given p-norm.
 */
@Since("1.4.0")
class Normalizer @Since("1.4.0") (@Since("1.4.0") override val uid: String)
  extends UnaryTransformer[Vector, Vector, Normalizer] with DefaultParamsWritable {

  @Since("1.4.0")
  def this() = this(Identifiable.randomUID("normalizer"))

  /**
   * Normalization in L^p^ space. Must be greater than equal to 1.
   * (default: p = 2)
   * @group param
   */
  @Since("1.4.0")
  val p = new DoubleParam(this, "p", "the p norm value", ParamValidators.gtEq(1))

  setDefault(p -> 2.0)

  /** @group getParam */
  @Since("1.4.0")
  def getP: Double = $(p)

  /** @group setParam */
  @Since("1.4.0")
  def setP(value: Double): this.type = set(p, value)

  override protected def createTransformFunc: Vector => Vector = {
    val normalizer = new feature.Normalizer($(p))
    vector => normalizer.transform(OldVectors.fromML(vector)).asML
  }

  override protected def validateInputType(inputType: DataType): Unit = {
    require(inputType.isInstanceOf[VectorUDT],
      s"Input type must be ${(new VectorUDT).catalogString} but got ${inputType.catalogString}.")
  }

  override protected def outputDataType: DataType = new VectorUDT()

  @Since("1.4.0")
  override def transformSchema(schema: StructType): StructType = {
    var outputSchema = super.transformSchema(schema)
    if ($(inputCol).nonEmpty && $(outputCol).nonEmpty) {
      val size = AttributeGroup.fromStructField(schema($(inputCol))).size
      if (size >= 0) {
        outputSchema = SchemaUtils.updateAttributeGroupSize(outputSchema,
          $(outputCol), size)
      }
    }
    outputSchema
  }

  @Since("3.0.0")
  override def toString: String = {
    s"Normalizer: uid=$uid, p=${$(p)}"
  }
}

@Since("1.6.0")
object Normalizer extends DefaultParamsReadable[Normalizer] {

  @Since("1.6.0")
  override def load(path: String): Normalizer = super.load(path)
}

相关信息

spark 源码目录

相关文章

spark Binarizer 源码

spark BucketedRandomProjectionLSH 源码

spark Bucketizer 源码

spark ChiSqSelector 源码

spark CountVectorizer 源码

spark DCT 源码

spark ElementwiseProduct 源码

spark FeatureHasher 源码

spark HashingTF 源码

spark IDF 源码