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-3530][MLLIB] pipeline and parameters wi...
Date Mon, 10 Nov 2014 23:48:27 GMT
Github user mengxr commented on a diff in the pull request:

    https://github.com/apache/spark/pull/3099#discussion_r20122957
  
    --- Diff: mllib/src/main/scala/org/apache/spark/ml/Pipeline.scala ---
    @@ -0,0 +1,136 @@
    +/*
    + * 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
    +
    +import scala.collection.mutable.ListBuffer
    +
    +import org.apache.spark.Logging
    +import org.apache.spark.ml.param.{Param, ParamMap}
    +import org.apache.spark.sql.{SchemaRDD, StructType}
    +
    +/**
    + * A stage in a pipeline, either an Estimator or an Transformer.
    + */
    +abstract class PipelineStage extends Serializable with Logging {
    +
    +  /**
    +   * Derives the output schema from the input schema and parameters.
    +   */
    +  def transform(schema: StructType, paramMap: ParamMap): StructType
    +
    +  /**
    +   * Drives the output schema from the input schema and parameters, optionally with logging.
    +   */
    +  protected def transform(schema: StructType, paramMap: ParamMap, logging: Boolean):
StructType = {
    +    if (logging) {
    +      logDebug(s"Input schema: ${schema.json}")
    +    }
    +    val outputSchema = transform(schema, paramMap)
    +    if (logging) {
    +      logDebug(s"Expected output schema: ${outputSchema.json}")
    +    }
    +    outputSchema
    +  }
    +}
    +
    +/**
    + * A simple pipeline, which acts as an estimator.
    --- End diff --
    
    done.


---
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