diff options
author | Xiangrui Meng <meng@databricks.com> | 2015-05-21 22:57:33 -0700 |
---|---|---|
committer | Xiangrui Meng <meng@databricks.com> | 2015-05-21 22:57:33 -0700 |
commit | 8f11c6116bf8c7246682cbb2d6f27bf0f1531c6d (patch) | |
tree | 144b7d5b9ec1215e88d05539f51e042a6d39470c /mllib/src/main | |
parent | e4136ea6c457bc74cee312aa14974498ab4633eb (diff) | |
download | spark-8f11c6116bf8c7246682cbb2d6f27bf0f1531c6d.tar.gz spark-8f11c6116bf8c7246682cbb2d6f27bf0f1531c6d.tar.bz2 spark-8f11c6116bf8c7246682cbb2d6f27bf0f1531c6d.zip |
[SPARK-7535] [.0] [MLLIB] Audit the pipeline APIs for 1.4
Some changes to the pipeilne APIs:
1. Estimator/Transformer/ doesn’t need to extend Params since PipelineStage already does.
1. Move Evaluator to ml.evaluation.
1. Mention larger metric values are better.
1. PipelineModel doc. “compiled” -> “fitted”
1. Hide object PolynomialExpansion.
1. Hide object VectorAssembler.
1. Word2Vec.minCount (and other) -> group param
1. ParamValidators -> DeveloperApi
1. Hide MetadataUtils/SchemaUtils.
jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes #6322 from mengxr/SPARK-7535.0 and squashes the following commits:
9e9c7da [Xiangrui Meng] move JavaEvaluator to ml.evaluation as well
e179480 [Xiangrui Meng] move Evaluation to ml.evaluation in PySpark
08ef61f [Xiangrui Meng] update pipieline APIs
Diffstat (limited to 'mllib/src/main')
12 files changed, 20 insertions, 19 deletions
diff --git a/mllib/src/main/scala/org/apache/spark/ml/Estimator.scala b/mllib/src/main/scala/org/apache/spark/ml/Estimator.scala index 7f3f3262a6..9e16e60270 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/Estimator.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/Estimator.scala @@ -28,7 +28,7 @@ import org.apache.spark.sql.DataFrame * Abstract class for estimators that fit models to data. */ @AlphaComponent -abstract class Estimator[M <: Model[M]] extends PipelineStage with Params { +abstract class Estimator[M <: Model[M]] extends PipelineStage { /** * Fits a single model to the input data with optional parameters. diff --git a/mllib/src/main/scala/org/apache/spark/ml/Pipeline.scala b/mllib/src/main/scala/org/apache/spark/ml/Pipeline.scala index fac54188f9..43bee1b770 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/Pipeline.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/Pipeline.scala @@ -170,7 +170,7 @@ class Pipeline(override val uid: String) extends Estimator[PipelineModel] { /** * :: AlphaComponent :: - * Represents a compiled pipeline. + * Represents a fitted pipeline. */ @AlphaComponent class PipelineModel private[ml] ( diff --git a/mllib/src/main/scala/org/apache/spark/ml/Transformer.scala b/mllib/src/main/scala/org/apache/spark/ml/Transformer.scala index d96b54e511..38bb6a5a53 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/Transformer.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/Transformer.scala @@ -32,7 +32,7 @@ import org.apache.spark.sql.types._ * Abstract class for transformers that transform one dataset into another. */ @AlphaComponent -abstract class Transformer extends PipelineStage with Params { +abstract class Transformer extends PipelineStage { /** * Transforms the dataset with optional parameters diff --git a/mllib/src/main/scala/org/apache/spark/ml/evaluation/BinaryClassificationEvaluator.scala b/mllib/src/main/scala/org/apache/spark/ml/evaluation/BinaryClassificationEvaluator.scala index c1af09c969..ddbdd00ceb 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/evaluation/BinaryClassificationEvaluator.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/evaluation/BinaryClassificationEvaluator.scala @@ -18,7 +18,7 @@ package org.apache.spark.ml.evaluation import org.apache.spark.annotation.AlphaComponent -import org.apache.spark.ml.Evaluator +import org.apache.spark.ml.evaluation.Evaluator import org.apache.spark.ml.param._ import org.apache.spark.ml.param.shared._ import org.apache.spark.ml.util.{Identifiable, SchemaUtils} diff --git a/mllib/src/main/scala/org/apache/spark/ml/Evaluator.scala b/mllib/src/main/scala/org/apache/spark/ml/evaluation/Evaluator.scala index 5f2f8c94e9..cabd1c97c0 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/Evaluator.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/evaluation/Evaluator.scala @@ -15,7 +15,7 @@ * limitations under the License. */ -package org.apache.spark.ml +package org.apache.spark.ml.evaluation import org.apache.spark.annotation.AlphaComponent import org.apache.spark.ml.param.{ParamMap, Params} @@ -29,7 +29,7 @@ import org.apache.spark.sql.DataFrame abstract class Evaluator extends Params { /** - * Evaluates the output. + * Evaluates model output and returns a scalar metric (larger is better). * * @param dataset a dataset that contains labels/observations and predictions. * @param paramMap parameter map that specifies the input columns and output metrics diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala index 41564410e4..8ddf9d6a1e 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala @@ -75,7 +75,7 @@ class PolynomialExpansion(override val uid: String) * To handle sparsity, if c is zero, we can skip all monomials that contain it. We remember the * current index and increment it properly for sparse input. */ -object PolynomialExpansion { +private[feature] object PolynomialExpansion { private def choose(n: Int, k: Int): Int = { Range(n, n - k, -1).product / Range(k, 1, -1).product diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/VectorAssembler.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/VectorAssembler.scala index 1c00094769..181b62f46f 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/feature/VectorAssembler.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/feature/VectorAssembler.scala @@ -78,8 +78,7 @@ class VectorAssembler(override val uid: String) } } -@AlphaComponent -object VectorAssembler { +private object VectorAssembler { private[feature] def assemble(vv: Any*): Vector = { val indices = ArrayBuilder.make[Int] diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala index 90f0be76df..ed03266922 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala @@ -37,6 +37,7 @@ private[feature] trait Word2VecBase extends Params /** * The dimension of the code that you want to transform from words. + * @group param */ final val vectorSize = new IntParam( this, "vectorSize", "the dimension of codes after transforming from words") @@ -47,6 +48,7 @@ private[feature] trait Word2VecBase extends Params /** * Number of partitions for sentences of words. + * @group param */ final val numPartitions = new IntParam( this, "numPartitions", "number of partitions for sentences of words") @@ -58,6 +60,7 @@ private[feature] trait Word2VecBase extends Params /** * The minimum number of times a token must appear to be included in the word2vec model's * vocabulary. + * @group param */ final val minCount = new IntParam(this, "minCount", "the minimum number of times a token must " + "appear to be included in the word2vec model's vocabulary") diff --git a/mllib/src/main/scala/org/apache/spark/ml/param/params.scala b/mllib/src/main/scala/org/apache/spark/ml/param/params.scala index 94abfcda5c..12fc5b561f 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/param/params.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/param/params.scala @@ -24,7 +24,7 @@ import scala.annotation.varargs import scala.collection.mutable import scala.collection.JavaConverters._ -import org.apache.spark.annotation.AlphaComponent +import org.apache.spark.annotation.{DeveloperApi, AlphaComponent} import org.apache.spark.ml.util.Identifiable /** @@ -92,9 +92,11 @@ class Param[T](val parent: String, val name: String, val doc: String, val isVali } /** + * :: DeveloperApi :: * Factory methods for common validation functions for [[Param.isValid]]. * The numerical methods only support Int, Long, Float, and Double. */ +@DeveloperApi object ParamValidators { /** (private[param]) Default validation always return true */ @@ -529,11 +531,13 @@ trait Params extends Identifiable with Serializable { } /** + * :: DeveloperApi :: * Java-friendly wrapper for [[Params]]. * Java developers who need to extend [[Params]] should use this class instead. * If you need to extend a abstract class which already extends [[Params]], then that abstract * class should be Java-friendly as well. */ +@DeveloperApi abstract class JavaParams extends Params /** diff --git a/mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala b/mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala index 5c6ff2dda3..e21ff94a20 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala @@ -22,6 +22,7 @@ import com.github.fommil.netlib.F2jBLAS import org.apache.spark.Logging import org.apache.spark.annotation.AlphaComponent import org.apache.spark.ml._ +import org.apache.spark.ml.evaluation.Evaluator import org.apache.spark.ml.param._ import org.apache.spark.ml.util.Identifiable import org.apache.spark.mllib.util.MLUtils diff --git a/mllib/src/main/scala/org/apache/spark/ml/util/MetadataUtils.scala b/mllib/src/main/scala/org/apache/spark/ml/util/MetadataUtils.scala index 56075c9a6b..2a1db90f2c 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/util/MetadataUtils.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/util/MetadataUtils.scala @@ -19,18 +19,14 @@ package org.apache.spark.ml.util import scala.collection.immutable.HashMap -import org.apache.spark.annotation.Experimental import org.apache.spark.ml.attribute._ import org.apache.spark.sql.types.StructField /** - * :: Experimental :: - * * Helper utilities for tree-based algorithms */ -@Experimental -object MetadataUtils { +private[spark] object MetadataUtils { /** * Examine a schema to identify the number of classes in a label column. diff --git a/mllib/src/main/scala/org/apache/spark/ml/util/SchemaUtils.scala b/mllib/src/main/scala/org/apache/spark/ml/util/SchemaUtils.scala index 11592b77eb..7cd53c6d7e 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/util/SchemaUtils.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/util/SchemaUtils.scala @@ -17,15 +17,13 @@ package org.apache.spark.ml.util -import org.apache.spark.annotation.DeveloperApi import org.apache.spark.sql.types.{DataType, StructField, StructType} + /** - * :: DeveloperApi :: * Utils for handling schemas. */ -@DeveloperApi -object SchemaUtils { +private[spark] object SchemaUtils { // TODO: Move the utility methods to SQL. |