Repository: spark Updated Branches: refs/heads/master 83cdfd84f -> a1894422a
[SPARK-7715] [MLLIB] [ML] [DOC] Updated MLlib programming guide for release 1.4 Reorganized docs a bit. Added migration guides. **Q**: Do we want to say more for the 1.3 -> 1.4 migration guide for ```spark.ml```? It would be a lot. CC: mengxr Author: Joseph K. Bradley <[email protected]> Closes #6897 from jkbradley/ml-guide-1.4 and squashes the following commits: 4bf26d6 [Joseph K. Bradley] tiny fix 8085067 [Joseph K. Bradley] fixed spacing/layout issues in ml guide from previous commit in this PR 6cd5c78 [Joseph K. Bradley] Updated MLlib programming guide for release 1.4 Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/a1894422 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/a1894422 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/a1894422 Branch: refs/heads/master Commit: a1894422ad6b3335c84c73ba9466da6677d893cb Parents: 83cdfd8 Author: Joseph K. Bradley <[email protected]> Authored: Sun Jun 21 16:25:25 2015 -0700 Committer: Xiangrui Meng <[email protected]> Committed: Sun Jun 21 16:25:25 2015 -0700 ---------------------------------------------------------------------- docs/ml-guide.md | 32 ++++++++++++++---------- docs/mllib-feature-extraction.md | 3 ++- docs/mllib-guide.md | 47 +++++++++++++++++++++-------------- docs/mllib-migration-guides.md | 16 ++++++++++++ 4 files changed, 65 insertions(+), 33 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/a1894422/docs/ml-guide.md ---------------------------------------------------------------------- diff --git a/docs/ml-guide.md b/docs/ml-guide.md index 4eb622d..c74cb1f 100644 --- a/docs/ml-guide.md +++ b/docs/ml-guide.md @@ -3,10 +3,10 @@ layout: global title: Spark ML Programming Guide --- -`spark.ml` is a new package introduced in Spark 1.2, which aims to provide a uniform set of +Spark 1.2 introduced a new package called `spark.ml`, which aims to provide a uniform set of high-level APIs that help users create and tune practical machine learning pipelines. -It is currently an alpha component, and we would like to hear back from the community about -how it fits real-world use cases and how it could be improved. + +*Graduated from Alpha!* The Pipelines API is no longer an alpha component, although many elements of it are still `Experimental` or `DeveloperApi`. Note that we will keep supporting and adding features to `spark.mllib` along with the development of `spark.ml`. @@ -14,6 +14,12 @@ Users should be comfortable using `spark.mllib` features and expect more feature Developers should contribute new algorithms to `spark.mllib` and can optionally contribute to `spark.ml`. +Guides for sub-packages of `spark.ml` include: + +* [Feature Extraction, Transformation, and Selection](ml-features.html): Details on transformers supported in the Pipelines API, including a few not in the lower-level `spark.mllib` API +* [Ensembles](ml-ensembles.html): Details on ensemble learning methods in the Pipelines API + + **Table of Contents** * This will become a table of contents (this text will be scraped). @@ -148,16 +154,6 @@ Parameters belong to specific instances of `Estimator`s and `Transformer`s. For example, if we have two `LogisticRegression` instances `lr1` and `lr2`, then we can build a `ParamMap` with both `maxIter` parameters specified: `ParamMap(lr1.maxIter -> 10, lr2.maxIter -> 20)`. This is useful if there are two algorithms with the `maxIter` parameter in a `Pipeline`. -# Algorithm Guides - -There are now several algorithms in the Pipelines API which are not in the lower-level MLlib API, so we link to documentation for them here. These algorithms are mostly feature transformers, which fit naturally into the `Transformer` abstraction in Pipelines, and ensembles, which fit naturally into the `Estimator` abstraction in the Pipelines. - -**Pipelines API Algorithm Guides** - -* [Feature Extraction, Transformation, and Selection](ml-features.html) -* [Ensembles](ml-ensembles.html) - - # Code Examples This section gives code examples illustrating the functionality discussed above. @@ -783,6 +779,16 @@ Spark ML also depends upon Spark SQL, but the relevant parts of Spark SQL do not # Migration Guide +## From 1.3 to 1.4 + +Several major API changes occurred, including: +* `Param` and other APIs for specifying parameters +* `uid` unique IDs for Pipeline components +* Reorganization of certain classes +Since the `spark.ml` API was an Alpha Component in Spark 1.3, we do not list all changes here. + +However, now that `spark.ml` is no longer an Alpha Component, we will provide details on any API changes for future releases. + ## From 1.2 to 1.3 The main API changes are from Spark SQL. We list the most important changes here: http://git-wip-us.apache.org/repos/asf/spark/blob/a1894422/docs/mllib-feature-extraction.md ---------------------------------------------------------------------- diff --git a/docs/mllib-feature-extraction.md b/docs/mllib-feature-extraction.md index 1197dbb..83e9376 100644 --- a/docs/mllib-feature-extraction.md +++ b/docs/mllib-feature-extraction.md @@ -576,8 +576,9 @@ parsedData = data.map(lambda x: [float(t) for t in x.split(" ")]) transformingVector = Vectors.dense([0.0, 1.0, 2.0]) transformer = ElementwiseProduct(transformingVector) -# Batch transform. +# Batch transform transformedData = transformer.transform(parsedData) +# Single-row transform transformedData2 = transformer.transform(parsedData.first()) {% endhighlight %} http://git-wip-us.apache.org/repos/asf/spark/blob/a1894422/docs/mllib-guide.md ---------------------------------------------------------------------- diff --git a/docs/mllib-guide.md b/docs/mllib-guide.md index de7d66f..d2d1cc9 100644 --- a/docs/mllib-guide.md +++ b/docs/mllib-guide.md @@ -7,7 +7,19 @@ description: MLlib machine learning library overview for Spark SPARK_VERSION_SHO MLlib is Spark's scalable machine learning library consisting of common learning algorithms and utilities, including classification, regression, clustering, collaborative -filtering, dimensionality reduction, as well as underlying optimization primitives, as outlined below: +filtering, dimensionality reduction, as well as underlying optimization primitives. +Guides for individual algorithms are listed below. + +The API is divided into 2 parts: + +* [The original `spark.mllib` API](mllib-guide.html#mllib-types-algorithms-and-utilities) is the primary API. +* [The "Pipelines" `spark.ml` API](mllib-guide.html#sparkml-high-level-apis-for-ml-pipelines) is a higher-level API for constructing ML workflows. + +We list major functionality from both below, with links to detailed guides. + +# MLlib types, algorithms and utilities + +This lists functionality included in `spark.mllib`, the main MLlib API. * [Data types](mllib-data-types.html) * [Basic statistics](mllib-statistics.html) @@ -49,8 +61,8 @@ and the migration guide below will explain all changes between releases. Spark 1.2 introduced a new package called `spark.ml`, which aims to provide a uniform set of high-level APIs that help users create and tune practical machine learning pipelines. -It is currently an alpha component, and we would like to hear back from the community about -how it fits real-world use cases and how it could be improved. + +*Graduated from Alpha!* The Pipelines API is no longer an alpha component, although many elements of it are still `Experimental` or `DeveloperApi`. Note that we will keep supporting and adding features to `spark.mllib` along with the development of `spark.ml`. @@ -58,7 +70,11 @@ Users should be comfortable using `spark.mllib` features and expect more feature Developers should contribute new algorithms to `spark.mllib` and can optionally contribute to `spark.ml`. -See the **[spark.ml programming guide](ml-guide.html)** for more information on this package. +More detailed guides for `spark.ml` include: + +* **[spark.ml programming guide](ml-guide.html)**: overview of the Pipelines API and major concepts +* [Feature transformers](ml-features.html): Details on transformers supported in the Pipelines API, including a few not in the lower-level `spark.mllib` API +* [Ensembles](ml-ensembles.html): Details on ensemble learning methods in the Pipelines API # Dependencies @@ -90,21 +106,14 @@ version 1.4 or newer. For the `spark.ml` package, please see the [spark.ml Migration Guide](ml-guide.html#migration-guide). -## From 1.2 to 1.3 - -In the `spark.mllib` package, there were several breaking changes. The first change (in `ALS`) is the only one in a component not marked as Alpha or Experimental. - -* *(Breaking change)* In [`ALS`](api/scala/index.html#org.apache.spark.mllib.recommendation.ALS), the extraneous method `solveLeastSquares` has been removed. The `DeveloperApi` method `analyzeBlocks` was also removed. -* *(Breaking change)* [`StandardScalerModel`](api/scala/index.html#org.apache.spark.mllib.feature.StandardScalerModel) remains an Alpha component. In it, the `variance` method has been replaced with the `std` method. To compute the column variance values returned by the original `variance` method, simply square the standard deviation values returned by `std`. -* *(Breaking change)* [`StreamingLinearRegressionWithSGD`](api/scala/index.html#org.apache.spark.mllib.regression.StreamingLinearRegressionWithSGD) remains an Experimental component. In it, there were two changes: - * The constructor taking arguments was removed in favor of a builder patten using the default constructor plus parameter setter methods. - * Variable `model` is no longer public. -* *(Breaking change)* [`DecisionTree`](api/scala/index.html#org.apache.spark.mllib.tree.DecisionTree) remains an Experimental component. In it and its associated classes, there were several changes: - * In `DecisionTree`, the deprecated class method `train` has been removed. (The object/static `train` methods remain.) - * In `Strategy`, the `checkpointDir` parameter has been removed. Checkpointing is still supported, but the checkpoint directory must be set before calling tree and tree ensemble training. -* `PythonMLlibAPI` (the interface between Scala/Java and Python for MLlib) was a public API but is now private, declared `private[python]`. This was never meant for external use. -* In linear regression (including Lasso and ridge regression), the squared loss is now divided by 2. - So in order to produce the same result as in 1.2, the regularization parameter needs to be divided by 2 and the step size needs to be multiplied by 2. +## From 1.3 to 1.4 + +In the `spark.mllib` package, there were several breaking changes, but all in `DeveloperApi` or `Experimental` APIs: + +* Gradient-Boosted Trees + * *(Breaking change)* The signature of the [`Loss.gradient`](api/scala/index.html#org.apache.spark.mllib.tree.loss.Loss) method was changed. This is only an issues for users who wrote their own losses for GBTs. + * *(Breaking change)* The `apply` and `copy` methods for the case class [`BoostingStrategy`](api/scala/index.html#org.apache.spark.mllib.tree.configuration.BoostingStrategy) have been changed because of a modification to the case class fields. This could be an issue for users who use `BoostingStrategy` to set GBT parameters. +* *(Breaking change)* The return value of [`LDA.run`](api/scala/index.html#org.apache.spark.mllib.clustering.LDA) has changed. It now returns an abstract class `LDAModel` instead of the concrete class `DistributedLDAModel`. The object of type `LDAModel` can still be cast to the appropriate concrete type, which depends on the optimization algorithm. ## Previous Spark Versions http://git-wip-us.apache.org/repos/asf/spark/blob/a1894422/docs/mllib-migration-guides.md ---------------------------------------------------------------------- diff --git a/docs/mllib-migration-guides.md b/docs/mllib-migration-guides.md index 4de2d94..8df68d8 100644 --- a/docs/mllib-migration-guides.md +++ b/docs/mllib-migration-guides.md @@ -7,6 +7,22 @@ description: MLlib migration guides from before Spark SPARK_VERSION_SHORT The migration guide for the current Spark version is kept on the [MLlib Programming Guide main page](mllib-guide.html#migration-guide). +## From 1.2 to 1.3 + +In the `spark.mllib` package, there were several breaking changes. The first change (in `ALS`) is the only one in a component not marked as Alpha or Experimental. + +* *(Breaking change)* In [`ALS`](api/scala/index.html#org.apache.spark.mllib.recommendation.ALS), the extraneous method `solveLeastSquares` has been removed. The `DeveloperApi` method `analyzeBlocks` was also removed. +* *(Breaking change)* [`StandardScalerModel`](api/scala/index.html#org.apache.spark.mllib.feature.StandardScalerModel) remains an Alpha component. In it, the `variance` method has been replaced with the `std` method. To compute the column variance values returned by the original `variance` method, simply square the standard deviation values returned by `std`. +* *(Breaking change)* [`StreamingLinearRegressionWithSGD`](api/scala/index.html#org.apache.spark.mllib.regression.StreamingLinearRegressionWithSGD) remains an Experimental component. In it, there were two changes: + * The constructor taking arguments was removed in favor of a builder pattern using the default constructor plus parameter setter methods. + * Variable `model` is no longer public. +* *(Breaking change)* [`DecisionTree`](api/scala/index.html#org.apache.spark.mllib.tree.DecisionTree) remains an Experimental component. In it and its associated classes, there were several changes: + * In `DecisionTree`, the deprecated class method `train` has been removed. (The object/static `train` methods remain.) + * In `Strategy`, the `checkpointDir` parameter has been removed. Checkpointing is still supported, but the checkpoint directory must be set before calling tree and tree ensemble training. +* `PythonMLlibAPI` (the interface between Scala/Java and Python for MLlib) was a public API but is now private, declared `private[python]`. This was never meant for external use. +* In linear regression (including Lasso and ridge regression), the squared loss is now divided by 2. + So in order to produce the same result as in 1.2, the regularization parameter needs to be divided by 2 and the step size needs to be multiplied by 2. + ## From 1.1 to 1.2 The only API changes in MLlib v1.2 are in --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
