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-8518] [ML] Log-linear models for surviv...
Date Tue, 15 Sep 2015 16:30:04 GMT
Github user mengxr commented on a diff in the pull request:

    https://github.com/apache/spark/pull/8611#discussion_r39532370
  
    --- Diff: mllib/src/main/scala/org/apache/spark/ml/regression/AFTSurvivalRegression.scala
---
    @@ -0,0 +1,400 @@
    +/*
    + * 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.regression
    +
    +import scala.collection.mutable
    +
    +import breeze.linalg.{DenseVector => BDV}
    +import breeze.optimize.{CachedDiffFunction, DiffFunction, LBFGS => BreezeLBFGS}
    +
    +import org.apache.spark.{SparkException, Logging}
    +import org.apache.spark.annotation.Experimental
    +import org.apache.spark.ml.{Model, Estimator}
    +import org.apache.spark.ml.param._
    +import org.apache.spark.ml.param.shared._
    +import org.apache.spark.ml.util.{SchemaUtils, Identifiable}
    +import org.apache.spark.mllib.linalg.{Vector, Vectors, VectorUDT}
    +import org.apache.spark.rdd.RDD
    +import org.apache.spark.sql.{Row, DataFrame}
    +import org.apache.spark.sql.functions._
    +import org.apache.spark.sql.types.{DoubleType, StructType}
    +import org.apache.spark.storage.StorageLevel
    +
    +/**
    + * Params for Accelerated Failure Time regression.
    + */
    +private[regression] trait AFTSurvivalRegressionParams extends Params
    +  with HasFeaturesCol with HasLabelCol with HasPredictionCol with HasMaxIter
    +  with HasTol with HasFitIntercept {
    +
    +  /**
    +   * Param for censored column name.
    +   * @group param
    +   */
    +  final val censorCol: Param[String] = new Param[String](this, "censorCol", "censored
column name")
    +
    +  /** @group getParam */
    +  final def getCensorCol: String = $(censorCol)
    +
    +  /**
    +   * Param for quantile vector.
    +   * @group param
    +   */
    +  final val quantile: Param[Vector] = new Param[Vector](this,
    +    "quantileCol", "quantile column name")
    +
    +  /** @group getParam */
    +  final def getQuantile: Vector = $(quantile)
    +
    +  /** Checks whether the input has quantile vector. */
    +  protected[ml] def hasQuantile: Boolean = {
    +    isDefined(quantile) && $(quantile).size != 0
    +  }
    +
    +  /**
    +   * Validates and transforms the input schema with the provided param map.
    +   * @param schema input schema
    +   * @param fitting whether this is in fitting or prediction
    +   * @return output schema
    +   */
    +  protected def validateAndTransformSchema(
    +      schema: StructType,
    +      fitting: Boolean): StructType = {
    +    SchemaUtils.checkColumnType(schema, $(featuresCol), new VectorUDT)
    +    if (fitting) {
    +      SchemaUtils.checkColumnType(schema, $(censorCol), DoubleType)
    +      SchemaUtils.checkColumnType(schema, $(labelCol), DoubleType)
    +    }
    +    SchemaUtils.appendColumn(schema, $(predictionCol), DoubleType)
    +  }
    +}
    +
    +/**
    + * :: Experimental ::
    + * Fit a parametric survival regression model named Accelerated failure time model
    + * ([[https://en.wikipedia.org/wiki/Accelerated_failure_time_model]])
    + * based on the Weibull distribution of the survival time.
    + */
    +@Experimental
    +class AFTSurvivalRegression(override val uid: String)
    +  extends Estimator[AFTSurvivalRegressionModel] with AFTSurvivalRegressionParams with
Logging {
    +
    +  def this() = this(Identifiable.randomUID("aftReg"))
    +
    +  /** @group setParam */
    +  def setFeaturesCol(value: String): this.type = set(featuresCol, value)
    +
    +  /** @group setParam */
    +  def setLabelCol(value: String): this.type = set(labelCol, value)
    +
    +  /** @group setParam */
    +  def setCensorCol(value: String): this.type = set(censorCol, value)
    +  setDefault(censorCol -> "censored")
    +
    +  /** @group setParam */
    +  def setPredictionCol(value: String): this.type = set(predictionCol, value)
    +
    +  /**
    +   * Set if we should fit the intercept
    +   * Default is true.
    +   * @group setParam
    +   */
    +  def setFitIntercept(value: Boolean): this.type = set(fitIntercept, value)
    +  setDefault(fitIntercept -> true)
    +
    +  /**
    +   * Set the maximum number of iterations.
    +   * Default is 100.
    +   * @group setParam
    +   */
    +  def setMaxIter(value: Int): this.type = set(maxIter, value)
    +  setDefault(maxIter -> 100)
    +
    +  /**
    +   * Set the convergence tolerance of iterations.
    +   * Smaller value will lead to higher accuracy with the cost of more iterations.
    +   * Default is 1E-6.
    +   * @group setParam
    +   */
    +  def setTol(value: Double): this.type = set(tol, value)
    +  setDefault(tol -> 1E-6)
    --- End diff --
    
    Use the same tolerance as in linear regression, `1e-3`?


---
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