spark RWrapperUtils 源码

2022-10-20
浏览 (231)

spark RWrapperUtils 代码

文件路径：/mllib/src/main/scala/org/apache/spark/ml/r/RWrapperUtils.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.r

import org.apache.spark.internal.Logging
import org.apache.spark.ml.attribute.{Attribute, AttributeGroup, NominalAttribute}
import org.apache.spark.ml.feature.{RFormula, RFormulaModel}
import org.apache.spark.ml.util.Identifiable
import org.apache.spark.sql.Dataset

private[r] object RWrapperUtils extends Logging {

  /**
   * DataFrame column check.
   * When loading libsvm data, default columns "features" and "label" will be added.
   * And "features" would conflict with RFormula default feature column names.
   * Here is to change the column name to avoid "column already exists" error.
   *
   * @param rFormula RFormula instance
   * @param data Input dataset
   */
  def checkDataColumns(rFormula: RFormula, data: Dataset[_]): Unit = {
    if (data.schema.fieldNames.contains(rFormula.getFeaturesCol)) {
      val newFeaturesName = s"${Identifiable.randomUID(rFormula.getFeaturesCol)}"
      logInfo(s"data containing ${rFormula.getFeaturesCol} column, " +
        s"using new name $newFeaturesName instead")
      rFormula.setFeaturesCol(newFeaturesName)
    }

    if (rFormula.getForceIndexLabel && data.schema.fieldNames.contains(rFormula.getLabelCol)) {
      val newLabelName = s"${Identifiable.randomUID(rFormula.getLabelCol)}"
      logInfo(s"data containing ${rFormula.getLabelCol} column and we force to index label, " +
        s"using new name $newLabelName instead")
      rFormula.setLabelCol(newLabelName)
    }
  }

  /**
   * Get the feature names and original labels from the schema
   * of DataFrame transformed by RFormulaModel.
   *
   * @param rFormulaModel The RFormulaModel instance.
   * @param data Input dataset.
   * @return The feature names and original labels.
   */
  def getFeaturesAndLabels(
      rFormulaModel: RFormulaModel,
      data: Dataset[_]): (Array[String], Array[String]) = {
    val schema = rFormulaModel.transform(data).schema
    val featureAttrs = AttributeGroup.fromStructField(schema(rFormulaModel.getFeaturesCol))
      .attributes.get
    val features = featureAttrs.map(_.name.get)
    val labelAttr = Attribute.fromStructField(schema(rFormulaModel.getLabelCol))
      .asInstanceOf[NominalAttribute]
    val labels = labelAttr.values.get
    (features, labels)
  }
}

相关信息

spark 源码目录

相关文章

spark AFTSurvivalRegressionWrapper 源码

spark ALSWrapper 源码

spark BisectingKMeansWrapper 源码

spark DecisionTreeClassifierWrapper 源码

spark DecisionTreeRegressorWrapper 源码

spark FMClassifierWrapper 源码

spark FMRegressorWrapper 源码

spark FPGrowthWrapper 源码

spark GBTClassifierWrapper 源码

spark GBTRegressorWrapper 源码

0 赞

所属分类： 前端技术
本文标签：
版权声明： 原创文章如转载，请注明本文链接: https://www.seaxiang.com/blog/6fc2919f8b5a43cc9de92790d0d43419

热门推荐

1、直接访问google.com
2、 - 优质文章
3、 gate.io
4、 harmony 鸿蒙hdc使用指导
5、 harmony 鸿蒙ArkUI组件（ArkTS）开发常见问题
6、 harmony 鸿蒙初识ArkTS语言
7、 golang
8、 flink kafka connector scan.startup.mode 的几个选项
9、 openharmony
10、 Vue中input框自动聚焦

Loading...