diff options
Diffstat (limited to 'docs')
31 files changed, 149 insertions, 1793 deletions
diff --git a/docs/_data/menu-ml.yaml b/docs/_data/menu-ml.yaml index fe37d0573e..2eea9a917a 100644 --- a/docs/_data/menu-ml.yaml +++ b/docs/_data/menu-ml.yaml @@ -1,5 +1,5 @@ - text: "Overview: estimators, transformers and pipelines" - url: ml-intro.html + url: ml-guide.html - text: Extracting, transforming and selecting features url: ml-features.html - text: Classification and Regression diff --git a/docs/_includes/nav-left-wrapper-ml.html b/docs/_includes/nav-left-wrapper-ml.html index 0103e890cc..e2d7eda027 100644 --- a/docs/_includes/nav-left-wrapper-ml.html +++ b/docs/_includes/nav-left-wrapper-ml.html @@ -1,8 +1,8 @@ <div class="left-menu-wrapper"> <div class="left-menu"> - <h3>spark.ml package</h3> + <h3><a href="ml-guide.html">spark.ml package</a></h3> {% include nav-left.html nav=include.nav-ml %} - <h3>spark.mllib package</h3> + <h3><a href="mllib-guide.html">spark.mllib package</a></h3> {% include nav-left.html nav=include.nav-mllib %} </div> </div>
\ No newline at end of file diff --git a/docs/ml-advanced.md b/docs/ml-advanced.md index b005633e56..91731d78a2 100644 --- a/docs/ml-advanced.md +++ b/docs/ml-advanced.md @@ -1,7 +1,7 @@ --- layout: global title: Advanced topics - spark.ml -displayTitle: Advanced topics +displayTitle: Advanced topics - spark.ml --- # Optimization of linear methods diff --git a/docs/ml-ann.md b/docs/ml-ann.md new file mode 100644 index 0000000000..c2d9bd200f --- /dev/null +++ b/docs/ml-ann.md @@ -0,0 +1,8 @@ +--- +layout: global +title: Multilayer perceptron classifier - spark.ml +displayTitle: Multilayer perceptron classifier - spark.ml +--- + + > This section has been moved into the + [classification and regression section](ml-classification-regression.html#multilayer-perceptron-classifier). diff --git a/docs/ml-classification-regression.md b/docs/ml-classification-regression.md index 3663ffee32..d63438bf74 100644 --- a/docs/ml-classification-regression.md +++ b/docs/ml-classification-regression.md @@ -1,7 +1,7 @@ --- layout: global title: Classification and regression - spark.ml -displayTitle: Classification and regression in spark.ml +displayTitle: Classification and regression - spark.ml --- @@ -27,10 +27,10 @@ displayTitle: Classification and regression in spark.ml * This will become a table of contents (this text will be scraped). {:toc} -In MLlib, we implement popular linear methods such as logistic +In `spark.ml`, we implement popular linear methods such as logistic regression and linear least squares with $L_1$ or $L_2$ regularization. Refer to [the linear methods in mllib](mllib-linear-methods.html) for -details. In `spark.ml`, we also include Pipelines API for [Elastic +details about implementation and tuning. We also include a DataFrame API for [Elastic net](http://en.wikipedia.org/wiki/Elastic_net_regularization), a hybrid of $L_1$ and $L_2$ regularization proposed in [Zou et al, Regularization and variable selection via the elastic @@ -86,7 +86,7 @@ $\alpha$ and `regParam` corresponds to $\lambda$. The `spark.ml` implementation of logistic regression also supports extracting a summary of the model over the training set. Note that the -predictions and metrics which are stored as `Dataframe` in +predictions and metrics which are stored as `DataFrame` in `BinaryLogisticRegressionSummary` are annotated `@transient` and hence only available on the driver. @@ -523,7 +523,7 @@ feature scaling, and are able to capture non-linearities and feature interaction algorithms such as random forests and boosting are among the top performers for classification and regression tasks. -MLlib supports decision trees for binary and multiclass classification and for regression, +The `spark.ml` implementation supports decision trees for binary and multiclass classification and for regression, using both continuous and categorical features. The implementation partitions data by rows, allowing distributed training with millions or even billions of instances. @@ -611,24 +611,25 @@ All output columns are optional; to exclude an output column, set its correspond # Tree Ensembles -The Pipelines API supports two major tree ensemble algorithms: [Random Forests](http://en.wikipedia.org/wiki/Random_forest) and [Gradient-Boosted Trees (GBTs)](http://en.wikipedia.org/wiki/Gradient_boosting). -Both use [MLlib decision trees](ml-decision-tree.html) as their base models. +The DataFrame API supports two major tree ensemble algorithms: [Random Forests](http://en.wikipedia.org/wiki/Random_forest) and [Gradient-Boosted Trees (GBTs)](http://en.wikipedia.org/wiki/Gradient_boosting). +Both use [`spark.ml` decision trees](ml-classification-regression.html#decision-trees) as their base models. -Users can find more information about ensemble algorithms in the [MLlib Ensemble guide](mllib-ensembles.html). In this section, we demonstrate the Pipelines API for ensembles. +Users can find more information about ensemble algorithms in the [MLlib Ensemble guide](mllib-ensembles.html). +In this section, we demonstrate the DataFrame API for ensembles. The main differences between this API and the [original MLlib ensembles API](mllib-ensembles.html) are: -* support for ML Pipelines +* support for DataFrames and ML Pipelines * separation of classification vs. regression * use of DataFrame metadata to distinguish continuous and categorical features -* a bit more functionality for random forests: estimates of feature importance, as well as the predicted probability of each class (a.k.a. class conditional probabilities) for classification. +* more functionality for random forests: estimates of feature importance, as well as the predicted probability of each class (a.k.a. class conditional probabilities) for classification. ## Random Forests [Random forests](http://en.wikipedia.org/wiki/Random_forest) are ensembles of [decision trees](ml-decision-tree.html). Random forests combine many decision trees in order to reduce the risk of overfitting. -MLlib supports random forests for binary and multiclass classification and for regression, +The `spark.ml` implementation supports random forests for binary and multiclass classification and for regression, using both continuous and categorical features. For more information on the algorithm itself, please see the [`spark.mllib` documentation on random forests](mllib-ensembles.html). @@ -709,7 +710,7 @@ All output columns are optional; to exclude an output column, set its correspond [Gradient-Boosted Trees (GBTs)](http://en.wikipedia.org/wiki/Gradient_boosting) are ensembles of [decision trees](ml-decision-tree.html). GBTs iteratively train decision trees in order to minimize a loss function. -MLlib supports GBTs for binary classification and for regression, +The `spark.ml` implementation supports GBTs for binary classification and for regression, using both continuous and categorical features. For more information on the algorithm itself, please see the [`spark.mllib` documentation on GBTs](mllib-ensembles.html). diff --git a/docs/ml-clustering.md b/docs/ml-clustering.md index 697777714b..a59f7e3005 100644 --- a/docs/ml-clustering.md +++ b/docs/ml-clustering.md @@ -1,7 +1,7 @@ --- layout: global -title: Clustering - ML -displayTitle: <a href="ml-guide.html">ML</a> - Clustering +title: Clustering - spark.ml +displayTitle: Clustering - spark.ml --- In this section, we introduce the pipeline API for [clustering in mllib](mllib-clustering.html). diff --git a/docs/ml-decision-tree.md b/docs/ml-decision-tree.md index 2bfac6f6c8..a721d55bc6 100644 --- a/docs/ml-decision-tree.md +++ b/docs/ml-decision-tree.md @@ -1,171 +1,8 @@ --- layout: global -title: Decision Trees - SparkML -displayTitle: <a href="ml-guide.html">ML</a> - Decision Trees +title: Decision trees - spark.ml +displayTitle: Decision trees - spark.ml --- -**Table of Contents** - -* This will become a table of contents (this text will be scraped). -{:toc} - - -# Overview - -[Decision trees](http://en.wikipedia.org/wiki/Decision_tree_learning) -and their ensembles are popular methods for the machine learning tasks of -classification and regression. Decision trees are widely used since they are easy to interpret, -handle categorical features, extend to the multiclass classification setting, do not require -feature scaling, and are able to capture non-linearities and feature interactions. Tree ensemble -algorithms such as random forests and boosting are among the top performers for classification and -regression tasks. - -MLlib supports decision trees for binary and multiclass classification and for regression, -using both continuous and categorical features. The implementation partitions data by rows, -allowing distributed training with millions or even billions of instances. - -Users can find more information about the decision tree algorithm in the [MLlib Decision Tree guide](mllib-decision-tree.html). In this section, we demonstrate the Pipelines API for Decision Trees. - -The Pipelines API for Decision Trees offers a bit more functionality than the original API. In particular, for classification, users can get the predicted probability of each class (a.k.a. class conditional probabilities). - -Ensembles of trees (Random Forests and Gradient-Boosted Trees) are described in the [Ensembles guide](ml-ensembles.html). - -# Inputs and Outputs - -We list the input and output (prediction) column types here. -All output columns are optional; to exclude an output column, set its corresponding Param to an empty string. - -## Input Columns - -<table class="table"> - <thead> - <tr> - <th align="left">Param name</th> - <th align="left">Type(s)</th> - <th align="left">Default</th> - <th align="left">Description</th> - </tr> - </thead> - <tbody> - <tr> - <td>labelCol</td> - <td>Double</td> - <td>"label"</td> - <td>Label to predict</td> - </tr> - <tr> - <td>featuresCol</td> - <td>Vector</td> - <td>"features"</td> - <td>Feature vector</td> - </tr> - </tbody> -</table> - -## Output Columns - -<table class="table"> - <thead> - <tr> - <th align="left">Param name</th> - <th align="left">Type(s)</th> - <th align="left">Default</th> - <th align="left">Description</th> - <th align="left">Notes</th> - </tr> - </thead> - <tbody> - <tr> - <td>predictionCol</td> - <td>Double</td> - <td>"prediction"</td> - <td>Predicted label</td> - <td></td> - </tr> - <tr> - <td>rawPredictionCol</td> - <td>Vector</td> - <td>"rawPrediction"</td> - <td>Vector of length # classes, with the counts of training instance labels at the tree node which makes the prediction</td> - <td>Classification only</td> - </tr> - <tr> - <td>probabilityCol</td> - <td>Vector</td> - <td>"probability"</td> - <td>Vector of length # classes equal to rawPrediction normalized to a multinomial distribution</td> - <td>Classification only</td> - </tr> - </tbody> -</table> - -# Examples - -The below examples demonstrate the Pipelines API for Decision Trees. The main differences between this API and the [original MLlib Decision Tree API](mllib-decision-tree.html) are: - -* support for ML Pipelines -* separation of Decision Trees for classification vs. regression -* use of DataFrame metadata to distinguish continuous and categorical features - - -## Classification - -The following examples load a dataset in LibSVM format, split it into training and test sets, train on the first dataset, and then evaluate on the held-out test set. -We use two feature transformers to prepare the data; these help index categories for the label and categorical features, adding metadata to the `DataFrame` which the Decision Tree algorithm can recognize. - -<div class="codetabs"> -<div data-lang="scala" markdown="1"> - -More details on parameters can be found in the [Scala API documentation](api/scala/index.html#org.apache.spark.ml.classification.DecisionTreeClassifier). - -{% include_example scala/org/apache/spark/examples/ml/DecisionTreeClassificationExample.scala %} - -</div> - -<div data-lang="java" markdown="1"> - -More details on parameters can be found in the [Java API documentation](api/java/org/apache/spark/ml/classification/DecisionTreeClassifier.html). - -{% include_example java/org/apache/spark/examples/ml/JavaDecisionTreeClassificationExample.java %} - -</div> - -<div data-lang="python" markdown="1"> - -More details on parameters can be found in the [Python API documentation](api/python/pyspark.ml.html#pyspark.ml.classification.DecisionTreeClassifier). - -{% include_example python/ml/decision_tree_classification_example.py %} - -</div> - -</div> - - -## Regression - -The following examples load a dataset in LibSVM format, split it into training and test sets, train on the first dataset, and then evaluate on the held-out test set. -We use a feature transformer to index categorical features, adding metadata to the `DataFrame` which the Decision Tree algorithm can recognize. - -<div class="codetabs"> -<div data-lang="scala" markdown="1"> - -More details on parameters can be found in the [Scala API documentation](api/scala/index.html#org.apache.spark.ml.regression.DecisionTreeRegressor). - -{% include_example scala/org/apache/spark/examples/ml/DecisionTreeRegressionExample.scala %} -</div> - -<div data-lang="java" markdown="1"> - -More details on parameters can be found in the [Java API documentation](api/java/org/apache/spark/ml/regression/DecisionTreeRegressor.html). - -{% include_example java/org/apache/spark/examples/ml/JavaDecisionTreeRegressionExample.java %} -</div> - -<div data-lang="python" markdown="1"> - -More details on parameters can be found in the [Python API documentation](api/python/pyspark.ml.html#pyspark.ml.regression.DecisionTreeRegressor). - -{% include_example python/ml/decision_tree_regression_example.py %} -</div> - -</div> + > This section has been moved into the + [classification and regression section](ml-classification-regression.html#decision-trees). diff --git a/docs/ml-ensembles.md b/docs/ml-ensembles.md index 14fef76f26..303773e803 100644 --- a/docs/ml-ensembles.md +++ b/docs/ml-ensembles.md @@ -1,319 +1,8 @@ --- layout: global -title: Ensembles -displayTitle: <a href="ml-guide.html">ML</a> - Ensembles +title: Tree ensemble methods - spark.ml +displayTitle: Tree ensemble methods - spark.ml --- -**Table of Contents** - -* This will become a table of contents (this text will be scraped). -{:toc} - -An [ensemble method](http://en.wikipedia.org/wiki/Ensemble_learning) -is a learning algorithm which creates a model composed of a set of other base models. - -## Tree Ensembles - -The Pipelines API supports two major tree ensemble algorithms: [Random Forests](http://en.wikipedia.org/wiki/Random_forest) and [Gradient-Boosted Trees (GBTs)](http://en.wikipedia.org/wiki/Gradient_boosting). -Both use [MLlib decision trees](ml-decision-tree.html) as their base models. - -Users can find more information about ensemble algorithms in the [MLlib Ensemble guide](mllib-ensembles.html). In this section, we demonstrate the Pipelines API for ensembles. - -The main differences between this API and the [original MLlib ensembles API](mllib-ensembles.html) are: - -* support for ML Pipelines -* separation of classification vs. regression -* use of DataFrame metadata to distinguish continuous and categorical features -* a bit more functionality for random forests: estimates of feature importance, as well as the predicted probability of each class (a.k.a. class conditional probabilities) for classification. - -### Random Forests - -[Random forests](http://en.wikipedia.org/wiki/Random_forest) -are ensembles of [decision trees](ml-decision-tree.html). -Random forests combine many decision trees in order to reduce the risk of overfitting. -MLlib supports random forests for binary and multiclass classification and for regression, -using both continuous and categorical features. - -This section gives examples of using random forests with the Pipelines API. -For more information on the algorithm, please see the [main MLlib docs on random forests](mllib-ensembles.html). - -#### Inputs and Outputs - -We list the input and output (prediction) column types here. -All output columns are optional; to exclude an output column, set its corresponding Param to an empty string. - -##### Input Columns - -<table class="table"> - <thead> - <tr> - <th align="left">Param name</th> - <th align="left">Type(s)</th> - <th align="left">Default</th> - <th align="left">Description</th> - </tr> - </thead> - <tbody> - <tr> - <td>labelCol</td> - <td>Double</td> - <td>"label"</td> - <td>Label to predict</td> - </tr> - <tr> - <td>featuresCol</td> - <td>Vector</td> - <td>"features"</td> - <td>Feature vector</td> - </tr> - </tbody> -</table> - -##### Output Columns (Predictions) - -<table class="table"> - <thead> - <tr> - <th align="left">Param name</th> - <th align="left">Type(s)</th> - <th align="left">Default</th> - <th align="left">Description</th> - <th align="left">Notes</th> - </tr> - </thead> - <tbody> - <tr> - <td>predictionCol</td> - <td>Double</td> - <td>"prediction"</td> - <td>Predicted label</td> - <td></td> - </tr> - <tr> - <td>rawPredictionCol</td> - <td>Vector</td> - <td>"rawPrediction"</td> - <td>Vector of length # classes, with the counts of training instance labels at the tree node which makes the prediction</td> - <td>Classification only</td> - </tr> - <tr> - <td>probabilityCol</td> - <td>Vector</td> - <td>"probability"</td> - <td>Vector of length # classes equal to rawPrediction normalized to a multinomial distribution</td> - <td>Classification only</td> - </tr> - </tbody> -</table> - -#### Example: Classification - -The following examples load a dataset in LibSVM format, split it into training and test sets, train on the first dataset, and then evaluate on the held-out test set. -We use two feature transformers to prepare the data; these help index categories for the label and categorical features, adding metadata to the `DataFrame` which the tree-based algorithms can recognize. - -<div class="codetabs"> -<div data-lang="scala" markdown="1"> - -Refer to the [Scala API docs](api/scala/index.html#org.apache.spark.ml.classification.RandomForestClassifier) for more details. - -{% include_example scala/org/apache/spark/examples/ml/RandomForestClassifierExample.scala %} -</div> - -<div data-lang="java" markdown="1"> - -Refer to the [Java API docs](api/java/org/apache/spark/ml/classification/RandomForestClassifier.html) for more details. - -{% include_example java/org/apache/spark/examples/ml/JavaRandomForestClassifierExample.java %} -</div> - -<div data-lang="python" markdown="1"> - -Refer to the [Python API docs](api/python/pyspark.ml.html#pyspark.ml.classification.RandomForestClassifier) for more details. - -{% include_example python/ml/random_forest_classifier_example.py %} -</div> -</div> - -#### Example: Regression - -The following examples load a dataset in LibSVM format, split it into training and test sets, train on the first dataset, and then evaluate on the held-out test set. -We use a feature transformer to index categorical features, adding metadata to the `DataFrame` which the tree-based algorithms can recognize. - -<div class="codetabs"> -<div data-lang="scala" markdown="1"> - -Refer to the [Scala API docs](api/scala/index.html#org.apache.spark.ml.regression.RandomForestRegressor) for more details. - -{% include_example scala/org/apache/spark/examples/ml/RandomForestRegressorExample.scala %} -</div> - -<div data-lang="java" markdown="1"> - -Refer to the [Java API docs](api/java/org/apache/spark/ml/regression/RandomForestRegressor.html) for more details. - -{% include_example java/org/apache/spark/examples/ml/JavaRandomForestRegressorExample.java %} -</div> - -<div data-lang="python" markdown="1"> - -Refer to the [Python API docs](api/python/pyspark.ml.html#pyspark.ml.regression.RandomForestRegressor) for more details. - -{% include_example python/ml/random_forest_regressor_example.py %} -</div> -</div> - -### Gradient-Boosted Trees (GBTs) - -[Gradient-Boosted Trees (GBTs)](http://en.wikipedia.org/wiki/Gradient_boosting) -are ensembles of [decision trees](ml-decision-tree.html). -GBTs iteratively train decision trees in order to minimize a loss function. -MLlib supports GBTs for binary classification and for regression, -using both continuous and categorical features. - -This section gives examples of using GBTs with the Pipelines API. -For more information on the algorithm, please see the [main MLlib docs on GBTs](mllib-ensembles.html). - -#### Inputs and Outputs - -We list the input and output (prediction) column types here. -All output columns are optional; to exclude an output column, set its corresponding Param to an empty string. - -##### Input Columns - -<table class="table"> - <thead> - <tr> - <th align="left">Param name</th> - <th align="left">Type(s)</th> - <th align="left">Default</th> - <th align="left">Description</th> - </tr> - </thead> - <tbody> - <tr> - <td>labelCol</td> - <td>Double</td> - <td>"label"</td> - <td>Label to predict</td> - </tr> - <tr> - <td>featuresCol</td> - <td>Vector</td> - <td>"features"</td> - <td>Feature vector</td> - </tr> - </tbody> -</table> - -Note that `GBTClassifier` currently only supports binary labels. - -##### Output Columns (Predictions) - -<table class="table"> - <thead> - <tr> - <th align="left">Param name</th> - <th align="left">Type(s)</th> - <th align="left">Default</th> - <th align="left">Description</th> - <th align="left">Notes</th> - </tr> - </thead> - <tbody> - <tr> - <td>predictionCol</td> - <td>Double</td> - <td>"prediction"</td> - <td>Predicted label</td> - <td></td> - </tr> - </tbody> -</table> - -In the future, `GBTClassifier` will also output columns for `rawPrediction` and `probability`, just as `RandomForestClassifier` does. - -#### Example: Classification - -The following examples load a dataset in LibSVM format, split it into training and test sets, train on the first dataset, and then evaluate on the held-out test set. -We use two feature transformers to prepare the data; these help index categories for the label and categorical features, adding metadata to the `DataFrame` which the tree-based algorithms can recognize. - -<div class="codetabs"> -<div data-lang="scala" markdown="1"> - -Refer to the [Scala API docs](api/scala/index.html#org.apache.spark.ml.classification.GBTClassifier) for more details. - -{% include_example scala/org/apache/spark/examples/ml/GradientBoostedTreeClassifierExample.scala %} -</div> - -<div data-lang="java" markdown="1"> - -Refer to the [Java API docs](api/java/org/apache/spark/ml/classification/GBTClassifier.html) for more details. - -{% include_example java/org/apache/spark/examples/ml/JavaGradientBoostedTreeClassifierExample.java %} -</div> - -<div data-lang="python" markdown="1"> - -Refer to the [Python API docs](api/python/pyspark.ml.html#pyspark.ml.classification.GBTClassifier) for more details. - -{% include_example python/ml/gradient_boosted_tree_classifier_example.py %} -</div> -</div> - -#### Example: Regression - -Note: For this example dataset, `GBTRegressor` actually only needs 1 iteration, but that will not -be true in general. - -<div class="codetabs"> -<div data-lang="scala" markdown="1"> - -Refer to the [Scala API docs](api/scala/index.html#org.apache.spark.ml.regression.GBTRegressor) for more details. - -{% include_example scala/org/apache/spark/examples/ml/GradientBoostedTreeRegressorExample.scala %} -</div> - -<div data-lang="java" markdown="1"> - -Refer to the [Java API docs](api/java/org/apache/spark/ml/regression/GBTRegressor.html) for more details. - -{% include_example java/org/apache/spark/examples/ml/JavaGradientBoostedTreeRegressorExample.java %} -</div> - -<div data-lang="python" markdown="1"> - -Refer to the [Python API docs](api/python/pyspark.ml.html#pyspark.ml.regression.GBTRegressor) for more details. - -{% include_example python/ml/gradient_boosted_tree_regressor_example.py %} -</div> -</div> - - -## One-vs-Rest (a.k.a. One-vs-All) - -[OneVsRest](http://en.wikipedia.org/wiki/Multiclass_classification#One-vs.-rest) is an example of a machine learning reduction for performing multiclass classification given a base classifier that can perform binary classification efficiently. It is also known as "One-vs-All." - -`OneVsRest` is implemented as an `Estimator`. For the base classifier it takes instances of `Classifier` and creates a binary classification problem for each of the k classes. The classifier for class i is trained to predict whether the label is i or not, distinguishing class i from all other classes. - -Predictions are done by evaluating each binary classifier and the index of the most confident classifier is output as label. - -### Example - -The example below demonstrates how to load the -[Iris dataset](http://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/multiclass/iris.scale), parse it as a DataFrame and perform multiclass classification using `OneVsRest`. The test error is calculated to measure the algorithm accuracy. - -<div class="codetabs"> -<div data-lang="scala" markdown="1"> - -Refer to the [Scala API docs](api/scala/index.html#org.apache.spark.ml.classifier.OneVsRest) for more details. - -{% include_example scala/org/apache/spark/examples/ml/OneVsRestExample.scala %} -</div> - -<div data-lang="java" markdown="1"> - -Refer to the [Java API docs](api/java/org/apache/spark/ml/classification/OneVsRest.html) for more details. - -{% include_example java/org/apache/spark/examples/ml/JavaOneVsRestExample.java %} -</div> -</div> + > This section has been moved into the + [classification and regression section](ml-classification-regression.html#tree-ensembles). diff --git a/docs/ml-features.md b/docs/ml-features.md index 7ad7c4eb7e..6494fed0a0 100644 --- a/docs/ml-features.md +++ b/docs/ml-features.md @@ -1,7 +1,7 @@ --- layout: global -title: Extracting, transforming and selecting features -displayTitle: Extracting, transforming and selecting features +title: Extracting, transforming and selecting features - spark.ml +displayTitle: Extracting, transforming and selecting features - spark.ml --- This section covers algorithms for working with features, roughly divided into these groups: diff --git a/docs/ml-guide.md b/docs/ml-guide.md index 6f35b30c3d..5c96c2b7d5 100644 --- a/docs/ml-guide.md +++ b/docs/ml-guide.md @@ -1,8 +1,10 @@ --- layout: global -title: Spark ML Programming Guide +title: "Overview: estimators, transformers and pipelines - spark.ml" +displayTitle: "Overview: estimators, transformers and pipelines - spark.ml" --- + `\[ \newcommand{\R}{\mathbb{R}} \newcommand{\E}{\mathbb{E}} @@ -32,21 +34,6 @@ See the [algorithm guides](#algorithm-guides) section below for guides on sub-pa * This will become a table of contents (this text will be scraped). {:toc} -# Algorithm guides - -We provide several algorithm guides specific to the Pipelines API. -Several of these algorithms, such as certain feature transformers, are not in the `spark.mllib` API. -Also, some algorithms have additional capabilities in the `spark.ml` API; e.g., random forests -provide class probabilities, and linear models provide model summaries. - -* [Feature extraction, transformation, and selection](ml-features.html) -* [Clustering](ml-clustering.html) -* [Decision Trees for classification and regression](ml-decision-tree.html) -* [Ensembles](ml-ensembles.html) -* [Linear methods with elastic net regularization](ml-linear-methods.html) -* [Multilayer perceptron classifier](ml-ann.html) -* [Survival Regression](ml-survival-regression.html) - # Main concepts in Pipelines diff --git a/docs/ml-intro.md b/docs/ml-intro.md deleted file mode 100644 index d95a66ba23..0000000000 --- a/docs/ml-intro.md +++ /dev/null @@ -1,941 +0,0 @@ ---- -layout: global -title: "Overview: estimators, transformers and pipelines - spark.ml" -displayTitle: "Overview: estimators, transformers and pipelines" ---- - - -`\[ -\newcommand{\R}{\mathbb{R}} -\newcommand{\E}{\mathbb{E}} -\newcommand{\x}{\mathbf{x}} -\newcommand{\y}{\mathbf{y}} -\newcommand{\wv}{\mathbf{w}} -\newcommand{\av}{\mathbf{\alpha}} -\newcommand{\bv}{\mathbf{b}} -\newcommand{\N}{\mathbb{N}} -\newcommand{\id}{\mathbf{I}} -\newcommand{\ind}{\mathbf{1}} -\newcommand{\0}{\mathbf{0}} -\newcommand{\unit}{\mathbf{e}} -\newcommand{\one}{\mathbf{1}} -\newcommand{\zero}{\mathbf{0}} -\]` - - -The `spark.ml` package aims to provide a uniform set of high-level APIs built on top of -[DataFrames](sql-programming-guide.html#dataframes) that help users create and tune practical -machine learning pipelines. -See the [algorithm guides](#algorithm-guides) section below for guides on sub-packages of -`spark.ml`, including feature transformers unique to the Pipelines API, ensembles, and more. - -**Table of contents** - -* This will become a table of contents (this text will be scraped). -{:toc} - - -# Main concepts in Pipelines - -Spark ML standardizes APIs for machine learning algorithms to make it easier to combine multiple -algorithms into a single pipeline, or workflow. -This section covers the key concepts introduced by the Spark ML API, where the pipeline concept is -mostly inspired by the [scikit-learn](http://scikit-learn.org/) project. - -* **[`DataFrame`](ml-guide.html#dataframe)**: Spark ML uses `DataFrame` from Spark SQL as an ML - dataset, which can hold a variety of data types. - E.g., a `DataFrame` could have different columns storing text, feature vectors, true labels, and predictions. - -* **[`Transformer`](ml-guide.html#transformers)**: A `Transformer` is an algorithm which can transform one `DataFrame` into another `DataFrame`. -E.g., an ML model is a `Transformer` which transforms `DataFrame` with features into a `DataFrame` with predictions. - -* **[`Estimator`](ml-guide.html#estimators)**: An `Estimator` is an algorithm which can be fit on a `DataFrame` to produce a `Transformer`. -E.g., a learning algorithm is an `Estimator` which trains on a `DataFrame` and produces a model. - -* **[`Pipeline`](ml-guide.html#pipeline)**: A `Pipeline` chains multiple `Transformer`s and `Estimator`s together to specify an ML workflow. - -* **[`Parameter`](ml-guide.html#parameters)**: All `Transformer`s and `Estimator`s now share a common API for specifying parameters. - -## DataFrame - -Machine learning can be applied to a wide variety of data types, such as vectors, text, images, and structured data. -Spark ML adopts the `DataFrame` from Spark SQL in order to support a variety of data types. - -`DataFrame` supports many basic and structured types; see the [Spark SQL datatype reference](sql-programming-guide.html#spark-sql-datatype-reference) for a list of supported types. -In addition to the types listed in the Spark SQL guide, `DataFrame` can use ML [`Vector`](mllib-data-types.html#local-vector) types. - -A `DataFrame` can be created either implicitly or explicitly from a regular `RDD`. See the code examples below and the [Spark SQL programming guide](sql-programming-guide.html) for examples. - -Columns in a `DataFrame` are named. The code examples below use names such as "text," "features," and "label." - -## Pipeline components - -### Transformers - -A `Transformer` is an abstraction that includes feature transformers and learned models. -Technically, a `Transformer` implements a method `transform()`, which converts one `DataFrame` into -another, generally by appending one or more columns. -For example: - -* A feature transformer might take a `DataFrame`, read a column (e.g., text), map it into a new - column (e.g., feature vectors), and output a new `DataFrame` with the mapped column appended. -* A learning model might take a `DataFrame`, read the column containing feature vectors, predict the - label for each feature vector, and output a new `DataFrame` with predicted labels appended as a - column. - -### Estimators - -An `Estimator` abstracts the concept of a learning algorithm or any algorithm that fits or trains on -data. -Technically, an `Estimator` implements a method `fit()`, which accepts a `DataFrame` and produces a -`Model`, which is a `Transformer`. -For example, a learning algorithm such as `LogisticRegression` is an `Estimator`, and calling -`fit()` trains a `LogisticRegressionModel`, which is a `Model` and hence a `Transformer`. - -### Properties of pipeline components - -`Transformer.transform()`s and `Estimator.fit()`s are both stateless. In the future, stateful algorithms may be supported via alternative concepts. - -Each instance of a `Transformer` or `Estimator` has a unique ID, which is useful in specifying parameters (discussed below). - -## Pipeline - -In machine learning, it is common to run a sequence of algorithms to process and learn from data. -E.g., a simple text document processing workflow might include several stages: - -* Split each document's text into words. -* Convert each document's words into a numerical feature vector. -* Learn a prediction model using the feature vectors and labels. - -Spark ML represents such a workflow as a `Pipeline`, which consists of a sequence of -`PipelineStage`s (`Transformer`s and `Estimator`s) to be run in a specific order. -We will use this simple workflow as a running example in this section. - -### How it works - -A `Pipeline` is specified as a sequence of stages, and each stage is either a `Transformer` or an `Estimator`. -These stages are run in order, and the input `DataFrame` is transformed as it passes through each stage. -For `Transformer` stages, the `transform()` method is called on the `DataFrame`. -For `Estimator` stages, the `fit()` method is called to produce a `Transformer` (which becomes part of the `PipelineModel`, or fitted `Pipeline`), and that `Transformer`'s `transform()` method is called on the `DataFrame`. - -We illustrate this for the simple text document workflow. The figure below is for the *training time* usage of a `Pipeline`. - -<p style="text-align: center;"> - <img - src="img/ml-Pipeline.png" - title="Spark ML Pipeline Example" - alt="Spark ML Pipeline Example" - width="80%" - /> -</p> - -Above, the top row represents a `Pipeline` with three stages. -The first two (`Tokenizer` and `HashingTF`) are `Transformer`s (blue), and the third (`LogisticRegression`) is an `Estimator` (red). -The bottom row represents data flowing through the pipeline, where cylinders indicate `DataFrame`s. -The `Pipeline.fit()` method is called on the original `DataFrame`, which has raw text documents and labels. -The `Tokenizer.transform()` method splits the raw text documents into words, adding a new column with words to the `DataFrame`. -The `HashingTF.transform()` method converts the words column into feature vectors, adding a new column with those vectors to the `DataFrame`. -Now, since `LogisticRegression` is an `Estimator`, the `Pipeline` first calls `LogisticRegression.fit()` to produce a `LogisticRegressionModel`. -If the `Pipeline` had more stages, it would call the `LogisticRegressionModel`'s `transform()` -method on the `DataFrame` before passing the `DataFrame` to the next stage. - -A `Pipeline` is an `Estimator`. -Thus, after a `Pipeline`'s `fit()` method runs, it produces a `PipelineModel`, which is a -`Transformer`. -This `PipelineModel` is used at *test time*; the figure below illustrates this usage. - -<p style="text-align: center;"> - <img - src="img/ml-PipelineModel.png" - title="Spark ML PipelineModel Example" - alt="Spark ML PipelineModel Example" - width="80%" - /> -</p> - -In the figure above, the `PipelineModel` has the same number of stages as the original `Pipeline`, but all `Estimator`s in the original `Pipeline` have become `Transformer`s. -When the `PipelineModel`'s `transform()` method is called on a test dataset, the data are passed -through the fitted pipeline in order. -Each stage's `transform()` method updates the dataset and passes it to the next stage. - -`Pipeline`s and `PipelineModel`s help to ensure that training and test data go through identical feature processing steps. - -### Details - -*DAG `Pipeline`s*: A `Pipeline`'s stages are specified as an ordered array. The examples given here are all for linear `Pipeline`s, i.e., `Pipeline`s in which each stage uses data produced by the previous stage. It is possible to create non-linear `Pipeline`s as long as the data flow graph forms a Directed Acyclic Graph (DAG). This graph is currently specified implicitly based on the input and output column names of each stage (generally specified as parameters). If the `Pipeline` forms a DAG, then the stages must be specified in topological order. - -*Runtime checking*: Since `Pipeline`s can operate on `DataFrame`s with varied types, they cannot use -compile-time type checking. -`Pipeline`s and `PipelineModel`s instead do runtime checking before actually running the `Pipeline`. -This type checking is done using the `DataFrame` *schema*, a description of the data types of columns in the `DataFrame`. - -*Unique Pipeline stages*: A `Pipeline`'s stages should be unique instances. E.g., the same instance -`myHashingTF` should not be inserted into the `Pipeline` twice since `Pipeline` stages must have -unique IDs. However, different instances `myHashingTF1` and `myHashingTF2` (both of type `HashingTF`) -can be put into the same `Pipeline` since different instances will be created with different IDs. - -## Parameters - -Spark ML `Estimator`s and `Transformer`s use a uniform API for specifying parameters. - -A `Param` is a named parameter with self-contained documentation. -A `ParamMap` is a set of (parameter, value) pairs. - -There are two main ways to pass parameters to an algorithm: - -1. Set parameters for an instance. E.g., if `lr` is an instance of `LogisticRegression`, one could - call `lr.setMaxIter(10)` to make `lr.fit()` use at most 10 iterations. - This API resembles the API used in `spark.mllib` package. -2. Pass a `ParamMap` to `fit()` or `transform()`. Any parameters in the `ParamMap` will override parameters previously specified via setter methods. - -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`. - -# Code examples - -This section gives code examples illustrating the functionality discussed above. -For more info, please refer to the API documentation -([Scala](api/scala/index.html#org.apache.spark.ml.package), -[Java](api/java/org/apache/spark/ml/package-summary.html), -and [Python](api/python/pyspark.ml.html)). -Some Spark ML algorithms are wrappers for `spark.mllib` algorithms, and the -[MLlib programming guide](mllib-guide.html) has details on specific algorithms. - -## Example: Estimator, Transformer, and Param - -This example covers the concepts of `Estimator`, `Transformer`, and `Param`. - -<div class="codetabs"> - -<div data-lang="scala"> -{% highlight scala %} -import org.apache.spark.ml.classification.LogisticRegression -import org.apache.spark.ml.param.ParamMap -import org.apache.spark.mllib.linalg.{Vector, Vectors} -import org.apache.spark.sql.Row - -// Prepare training data from a list of (label, features) tuples. -val training = sqlContext.createDataFrame(Seq( - (1.0, Vectors.dense(0.0, 1.1, 0.1)), - (0.0, Vectors.dense(2.0, 1.0, -1.0)), - (0.0, Vectors.dense(2.0, 1.3, 1.0)), - (1.0, Vectors.dense(0.0, 1.2, -0.5)) -)).toDF("label", "features") - -// Create a LogisticRegression instance. This instance is an Estimator. -val lr = new LogisticRegression() -// Print out the parameters, documentation, and any default values. -println("LogisticRegression parameters:\n" + lr.explainParams() + "\n") - -// We may set parameters using setter methods. -lr.setMaxIter(10) - .setRegParam(0.01) - -// Learn a LogisticRegression model. This uses the parameters stored in lr. -val model1 = lr.fit(training) -// Since model1 is a Model (i.e., a Transformer produced by an Estimator), -// we can view the parameters it used during fit(). -// This prints the parameter (name: value) pairs, where names are unique IDs for this -// LogisticRegression instance. -println("Model 1 was fit using parameters: " + model1.parent.extractParamMap) - -// We may alternatively specify parameters using a ParamMap, -// which supports several methods for specifying parameters. -val paramMap = ParamMap(lr.maxIter -> 20) - .put(lr.maxIter, 30) // Specify 1 Param. This overwrites the original maxIter. - .put(lr.regParam -> 0.1, lr.threshold -> 0.55) // Specify multiple Params. - -// One can also combine ParamMaps. -val paramMap2 = ParamMap(lr.probabilityCol -> "myProbability") // Change output column name -val paramMapCombined = paramMap ++ paramMap2 - -// Now learn a new model using the paramMapCombined parameters. -// paramMapCombined overrides all parameters set earlier via lr.set* methods. -val model2 = lr.fit(training, paramMapCombined) -println("Model 2 was fit using parameters: " + model2.parent.extractParamMap) - -// Prepare test data. -val test = sqlContext.createDataFrame(Seq( - (1.0, Vectors.dense(-1.0, 1.5, 1.3)), - (0.0, Vectors.dense(3.0, 2.0, -0.1)), - (1.0, Vectors.dense(0.0, 2.2, -1.5)) -)).toDF("label", "features") - -// Make predictions on test data using the Transformer.transform() method. -// LogisticRegression.transform will only use the 'features' column. -// Note that model2.transform() outputs a 'myProbability' column instead of the usual -// 'probability' column since we renamed the lr.probabilityCol parameter previously. -model2.transform(test) - .select("features", "label", "myProbability", "prediction") - .collect() - .foreach { case Row(features: Vector, label: Double, prob: Vector, prediction: Double) => - println(s"($features, $label) -> prob=$prob, prediction=$prediction") - } - -{% endhighlight %} -</div> - -<div data-lang="java"> -{% highlight java %} -import java.util.Arrays; -import java.util.List; - -import org.apache.spark.ml.classification.LogisticRegressionModel; -import org.apache.spark.ml.param.ParamMap; -import org.apache.spark.ml.classification.LogisticRegression; -import org.apache.spark.mllib.linalg.Vectors; -import org.apache.spark.mllib.regression.LabeledPoint; -import org.apache.spark.sql.DataFrame; -import org.apache.spark.sql.Row; - -// Prepare training data. -// We use LabeledPoint, which is a JavaBean. Spark SQL can convert RDDs of JavaBeans -// into DataFrames, where it uses the bean metadata to infer the schema. -DataFrame training = sqlContext.createDataFrame(Arrays.asList( - new LabeledPoint(1.0, Vectors.dense(0.0, 1.1, 0.1)), - new LabeledPoint(0.0, Vectors.dense(2.0, 1.0, -1.0)), - new LabeledPoint(0.0, Vectors.dense(2.0, 1.3, 1.0)), - new LabeledPoint(1.0, Vectors.dense(0.0, 1.2, -0.5)) -), LabeledPoint.class); - -// Create a LogisticRegression instance. This instance is an Estimator. -LogisticRegression lr = new LogisticRegression(); -// Print out the parameters, documentation, and any default values. -System.out.println("LogisticRegression parameters:\n" + lr.explainParams() + "\n"); - -// We may set parameters using setter methods. -lr.setMaxIter(10) - .setRegParam(0.01); - -// Learn a LogisticRegression model. This uses the parameters stored in lr. -LogisticRegressionModel model1 = lr.fit(training); -// Since model1 is a Model (i.e., a Transformer produced by an Estimator), -// we can view the parameters it used during fit(). -// This prints the parameter (name: value) pairs, where names are unique IDs for this -// LogisticRegression instance. -System.out.println("Model 1 was fit using parameters: " + model1.parent().extractParamMap()); - -// We may alternatively specify parameters using a ParamMap. -ParamMap paramMap = new ParamMap() - .put(lr.maxIter().w(20)) // Specify 1 Param. - .put(lr.maxIter(), 30) // This overwrites the original maxIter. - .put(lr.regParam().w(0.1), lr.threshold().w(0.55)); // Specify multiple Params. - -// One can also combine ParamMaps. -ParamMap paramMap2 = new ParamMap() - .put(lr.probabilityCol().w("myProbability")); // Change output column name -ParamMap paramMapCombined = paramMap.$plus$plus(paramMap2); - -// Now learn a new model using the paramMapCombined parameters. -// paramMapCombined overrides all parameters set earlier via lr.set* methods. -LogisticRegressionModel model2 = lr.fit(training, paramMapCombined); -System.out.println("Model 2 was fit using parameters: " + model2.parent().extractParamMap()); - -// Prepare test documents. -DataFrame test = sqlContext.createDataFrame(Arrays.asList( - new LabeledPoint(1.0, Vectors.dense(-1.0, 1.5, 1.3)), - new LabeledPoint(0.0, Vectors.dense(3.0, 2.0, -0.1)), - new LabeledPoint(1.0, Vectors.dense(0.0, 2.2, -1.5)) -), LabeledPoint.class); - -// Make predictions on test documents using the Transformer.transform() method. -// LogisticRegression.transform will only use the 'features' column. -// Note that model2.transform() outputs a 'myProbability' column instead of the usual -// 'probability' column since we renamed the lr.probabilityCol parameter previously. -DataFrame results = model2.transform(test); -for (Row r: results.select("features", "label", "myProbability", "prediction").collect()) { - System.out.println("(" + r.get(0) + ", " + r.get(1) + ") -> prob=" + r.get(2) - + ", prediction=" + r.get(3)); -} - -{% endhighlight %} -</div> - -<div data-lang="python"> -{% highlight python %} -from pyspark.mllib.linalg import Vectors -from pyspark.ml.classification import LogisticRegression -from pyspark.ml.param import Param, Params - -# Prepare training data from a list of (label, features) tuples. -training = sqlContext.createDataFrame([ - (1.0, Vectors.dense([0.0, 1.1, 0.1])), - (0.0, Vectors.dense([2.0, 1.0, -1.0])), - (0.0, Vectors.dense([2.0, 1.3, 1.0])), - (1.0, Vectors.dense([0.0, 1.2, -0.5]))], ["label", "features"]) - -# Create a LogisticRegression instance. This instance is an Estimator. -lr = LogisticRegression(maxIter=10, regParam=0.01) -# Print out the parameters, documentation, and any default values. -print "LogisticRegression parameters:\n" + lr.explainParams() + "\n" - -# Learn a LogisticRegression model. This uses the parameters stored in lr. -model1 = lr.fit(training) - -# Since model1 is a Model (i.e., a transformer produced by an Estimator), -# we can view the parameters it used during fit(). -# This prints the parameter (name: value) pairs, where names are unique IDs for this -# LogisticRegression instance. -print "Model 1 was fit using parameters: " -print model1.extractParamMap() - -# We may alternatively specify parameters using a Python dictionary as a paramMap -paramMap = {lr.maxIter: 20} -paramMap[lr.maxIter] = 30 # Specify 1 Param, overwriting the original maxIter. -paramMap.update({lr.regParam: 0.1, lr.threshold: 0.55}) # Specify multiple Params. - -# You can combine paramMaps, which are python dictionaries. -paramMap2 = {lr.probabilityCol: "myProbability"} # Change output column name -paramMapCombined = paramMap.copy() -paramMapCombined.update(paramMap2) - -# Now learn a new model using the paramMapCombined parameters. -# paramMapCombined overrides all parameters set earlier via lr.set* methods. -model2 = lr.fit(training, paramMapCombined) -print "Model 2 was fit using parameters: " -print model2.extractParamMap() - -# Prepare test data -test = sqlContext.createDataFrame([ - (1.0, Vectors.dense([-1.0, 1.5, 1.3])), - (0.0, Vectors.dense([3.0, 2.0, -0.1])), - (1.0, Vectors.dense([0.0, 2.2, -1.5]))], ["label", "features"]) - -# Make predictions on test data using the Transformer.transform() method. -# LogisticRegression.transform will only use the 'features' column. -# Note that model2.transform() outputs a "myProbability" column instead of the usual -# 'probability' column since we renamed the lr.probabilityCol parameter previously. -prediction = model2.transform(test) -selected = prediction.select("features", "label", "myProbability", "prediction") -for row in selected.collect(): - print row - -{% endhighlight %} -</div> - -</div> - -## Example: Pipeline - -This example follows the simple text document `Pipeline` illustrated in the figures above. - -<div class="codetabs"> - -<div data-lang="scala"> -{% highlight scala %} -import org.apache.spark.ml.Pipeline -import org.apache.spark.ml.classification.LogisticRegression -import org.apache.spark.ml.feature.{HashingTF, Tokenizer} -import org.apache.spark.mllib.linalg.Vector -import org.apache.spark.sql.Row - -// Prepare training documents from a list of (id, text, label) tuples. -val training = sqlContext.createDataFrame(Seq( - (0L, "a b c d e spark", 1.0), - (1L, "b d", 0.0), - (2L, "spark f g h", 1.0), - (3L, "hadoop mapreduce", 0.0) -)).toDF("id", "text", "label") - -// Configure an ML pipeline, which consists of three stages: tokenizer, hashingTF, and lr. -val tokenizer = new Tokenizer() - .setInputCol("text") - .setOutputCol("words") -val hashingTF = new HashingTF() - .setNumFeatures(1000) - .setInputCol(tokenizer.getOutputCol) - .setOutputCol("features") -val lr = new LogisticRegression() - .setMaxIter(10) - .setRegParam(0.01) -val pipeline = new Pipeline() - .setStages(Array(tokenizer, hashingTF, lr)) - -// Fit the pipeline to training documents. -val model = pipeline.fit(training) - -// Prepare test documents, which are unlabeled (id, text) tuples. -val test = sqlContext.createDataFrame(Seq( - (4L, "spark i j k"), - (5L, "l m n"), - (6L, "mapreduce spark"), - (7L, "apache hadoop") -)).toDF("id", "text") - -// Make predictions on test documents. -model.transform(test) - .select("id", "text", "probability", "prediction") - .collect() - .foreach { case Row(id: Long, text: String, prob: Vector, prediction: Double) => - println(s"($id, $text) --> prob=$prob, prediction=$prediction") - } - -{% endhighlight %} -</div> - -<div data-lang="java"> -{% highlight java %} -import java.util.Arrays; -import java.util.List; - -import org.apache.spark.ml.Pipeline; -import org.apache.spark.ml.PipelineModel; -import org.apache.spark.ml.PipelineStage; -import org.apache.spark.ml.classification.LogisticRegression; -import org.apache.spark.ml.feature.HashingTF; -import org.apache.spark.ml.feature.Tokenizer; -import org.apache.spark.sql.DataFrame; -import org.apache.spark.sql.Row; - -// Labeled and unlabeled instance types. -// Spark SQL can infer schema from Java Beans. -public class Document implements Serializable { - private long id; - private String text; - - public Document(long id, String text) { - this.id = id; - this.text = text; - } - - public long getId() { return this.id; } - public void setId(long id) { this.id = id; } - - public String getText() { return this.text; } - public void setText(String text) { this.text = text; } -} - -public class LabeledDocument extends Document implements Serializable { - private double label; - - public LabeledDocument(long id, String text, double label) { - super(id, text); - this.label = label; - } - - public double getLabel() { return this.label; } - public void setLabel(double label) { this.label = label; } -} - -// Prepare training documents, which are labeled. -DataFrame training = sqlContext.createDataFrame(Arrays.asList( - new LabeledDocument(0L, "a b c d e spark", 1.0), - new LabeledDocument(1L, "b d", 0.0), - new LabeledDocument(2L, "spark f g h", 1.0), - new LabeledDocument(3L, "hadoop mapreduce", 0.0) -), LabeledDocument.class); - -// Configure an ML pipeline, which consists of three stages: tokenizer, hashingTF, and lr. -Tokenizer tokenizer = new Tokenizer() - .setInputCol("text") - .setOutputCol("words"); -HashingTF hashingTF = new HashingTF() - .setNumFeatures(1000) - .setInputCol(tokenizer.getOutputCol()) - .setOutputCol("features"); -LogisticRegression lr = new LogisticRegression() - .setMaxIter(10) - .setRegParam(0.01); -Pipeline pipeline = new Pipeline() - .setStages(new PipelineStage[] {tokenizer, hashingTF, lr}); - -// Fit the pipeline to training documents. -PipelineModel model = pipeline.fit(training); - -// Prepare test documents, which are unlabeled. -DataFrame test = sqlContext.createDataFrame(Arrays.asList( - new Document(4L, "spark i j k"), - new Document(5L, "l m n"), - new Document(6L, "mapreduce spark"), - new Document(7L, "apache hadoop") -), Document.class); - -// Make predictions on test documents. -DataFrame predictions = model.transform(test); -for (Row r: predictions.select("id", "text", "probability", "prediction").collect()) { - System.out.println("(" + r.get(0) + ", " + r.get(1) + ") --> prob=" + r.get(2) - + ", prediction=" + r.get(3)); -} - -{% endhighlight %} -</div> - -<div data-lang="python"> -{% highlight python %} -from pyspark.ml import Pipeline -from pyspark.ml.classification import LogisticRegression -from pyspark.ml.feature import HashingTF, Tokenizer -from pyspark.sql import Row - -# Prepare training documents from a list of (id, text, label) tuples. -LabeledDocument = Row("id", "text", "label") -training = sqlContext.createDataFrame([ - (0L, "a b c d e spark", 1.0), - (1L, "b d", 0.0), - (2L, "spark f g h", 1.0), - (3L, "hadoop mapreduce", 0.0)], ["id", "text", "label"]) - -# Configure an ML pipeline, which consists of tree stages: tokenizer, hashingTF, and lr. -tokenizer = Tokenizer(inputCol="text", outputCol="words") -hashingTF = HashingTF(inputCol=tokenizer.getOutputCol(), outputCol="features") -lr = LogisticRegression(maxIter=10, regParam=0.01) -pipeline = Pipeline(stages=[tokenizer, hashingTF, lr]) - -# Fit the pipeline to training documents. -model = pipeline.fit(training) - -# Prepare test documents, which are unlabeled (id, text) tuples. -test = sqlContext.createDataFrame([ - (4L, "spark i j k"), - (5L, "l m n"), - (6L, "mapreduce spark"), - (7L, "apache hadoop")], ["id", "text"]) - -# Make predictions on test documents and print columns of interest. -prediction = model.transform(test) -selected = prediction.select("id", "text", "prediction") -for row in selected.collect(): - print(row) - -{% endhighlight %} -</div> - -</div> - -## Example: model selection via cross-validation - -An important task in ML is *model selection*, or using data to find the best model or parameters for a given task. This is also called *tuning*. -`Pipeline`s facilitate model selection by making it easy to tune an entire `Pipeline` at once, rather than tuning each element in the `Pipeline` separately. - -Currently, `spark.ml` supports model selection using the [`CrossValidator`](api/scala/index.html#org.apache.spark.ml.tuning.CrossValidator) class, which takes an `Estimator`, a set of `ParamMap`s, and an [`Evaluator`](api/scala/index.html#org.apache.spark.ml.evaluation.Evaluator). -`CrossValidator` begins by splitting the dataset into a set of *folds* which are used as separate training and test datasets; e.g., with `$k=3$` folds, `CrossValidator` will generate 3 (training, test) dataset pairs, each of which uses 2/3 of the data for training and 1/3 for testing. -`CrossValidator` iterates through the set of `ParamMap`s. For each `ParamMap`, it trains the given `Estimator` and evaluates it using the given `Evaluator`. - -The `Evaluator` can be a [`RegressionEvaluator`](api/scala/index.html#org.apache.spark.ml.evaluation.RegressionEvaluator) -for regression problems, a [`BinaryClassificationEvaluator`](api/scala/index.html#org.apache.spark.ml.evaluation.BinaryClassificationEvaluator) -for binary data, or a [`MultiClassClassificationEvaluator`](api/scala/index.html#org.apache.spark.ml.evaluation.MultiClassClassificationEvaluator) -for multiclass problems. The default metric used to choose the best `ParamMap` can be overriden by the `setMetric` -method in each of these evaluators. - -The `ParamMap` which produces the best evaluation metric (averaged over the `$k$` folds) is selected as the best model. -`CrossValidator` finally fits the `Estimator` using the best `ParamMap` and the entire dataset. - -The following example demonstrates using `CrossValidator` to select from a grid of parameters. -To help construct the parameter grid, we use the [`ParamGridBuilder`](api/scala/index.html#org.apache.spark.ml.tuning.ParamGridBuilder) utility. - -Note that cross-validation over a grid of parameters is expensive. -E.g., in the example below, the parameter grid has 3 values for `hashingTF.numFeatures` and 2 values for `lr.regParam`, and `CrossValidator` uses 2 folds. This multiplies out to `$(3 \times 2) \times 2 = 12$` different models being trained. -In realistic settings, it can be common to try many more parameters and use more folds (`$k=3$` and `$k=10$` are common). -In other words, using `CrossValidator` can be very expensive. -However, it is also a well-established method for choosing parameters which is more statistically sound than heuristic hand-tuning. - -<div class="codetabs"> - -<div data-lang="scala"> -{% highlight scala %} -import org.apache.spark.ml.Pipeline -import org.apache.spark.ml.classification.LogisticRegression -import org.apache.spark.ml.evaluation.BinaryClassificationEvaluator -import org.apache.spark.ml.feature.{HashingTF, Tokenizer} -import org.apache.spark.ml.tuning.{ParamGridBuilder, CrossValidator} -import org.apache.spark.mllib.linalg.Vector -import org.apache.spark.sql.Row - -// Prepare training data from a list of (id, text, label) tuples. -val training = sqlContext.createDataFrame(Seq( - (0L, "a b c d e spark", 1.0), - (1L, "b d", 0.0), - (2L, "spark f g h", 1.0), - (3L, "hadoop mapreduce", 0.0), - (4L, "b spark who", 1.0), - (5L, "g d a y", 0.0), - (6L, "spark fly", 1.0), - (7L, "was mapreduce", 0.0), - (8L, "e spark program", 1.0), - (9L, "a e c l", 0.0), - (10L, "spark compile", 1.0), - (11L, "hadoop software", 0.0) -)).toDF("id", "text", "label") - -// Configure an ML pipeline, which consists of three stages: tokenizer, hashingTF, and lr. -val tokenizer = new Tokenizer() - .setInputCol("text") - .setOutputCol("words") -val hashingTF = new HashingTF() - .setInputCol(tokenizer.getOutputCol) - .setOutputCol("features") -val lr = new LogisticRegression() - .setMaxIter(10) -val pipeline = new Pipeline() - .setStages(Array(tokenizer, hashingTF, lr)) - -// We use a ParamGridBuilder to construct a grid of parameters to search over. -// With 3 values for hashingTF.numFeatures and 2 values for lr.regParam, -// this grid will have 3 x 2 = 6 parameter settings for CrossValidator to choose from. -val paramGrid = new ParamGridBuilder() - .addGrid(hashingTF.numFeatures, Array(10, 100, 1000)) - .addGrid(lr.regParam, Array(0.1, 0.01)) - .build() - -// We now treat the Pipeline as an Estimator, wrapping it in a CrossValidator instance. -// This will allow us to jointly choose parameters for all Pipeline stages. -// A CrossValidator requires an Estimator, a set of Estimator ParamMaps, and an Evaluator. -// Note that the evaluator here is a BinaryClassificationEvaluator and its default metric -// is areaUnderROC. -val cv = new CrossValidator() - .setEstimator(pipeline) - .setEvaluator(new BinaryClassificationEvaluator) - .setEstimatorParamMaps(paramGrid) - .setNumFolds(2) // Use 3+ in practice - -// Run cross-validation, and choose the best set of parameters. -val cvModel = cv.fit(training) - -// Prepare test documents, which are unlabeled (id, text) tuples. -val test = sqlContext.createDataFrame(Seq( - (4L, "spark i j k"), - (5L, "l m n"), - (6L, "mapreduce spark"), - (7L, "apache hadoop") -)).toDF("id", "text") - -// Make predictions on test documents. cvModel uses the best model found (lrModel). -cvModel.transform(test) - .select("id", "text", "probability", "prediction") - .collect() - .foreach { case Row(id: Long, text: String, prob: Vector, prediction: Double) => - println(s"($id, $text) --> prob=$prob, prediction=$prediction") - } - -{% endhighlight %} -</div> - -<div data-lang="java"> -{% highlight java %} -import java.util.Arrays; -import java.util.List; - -import org.apache.spark.ml.Pipeline; -import org.apache.spark.ml.PipelineStage; -import org.apache.spark.ml.classification.LogisticRegression; -import org.apache.spark.ml.evaluation.BinaryClassificationEvaluator; -import org.apache.spark.ml.feature.HashingTF; -import org.apache.spark.ml.feature.Tokenizer; -import org.apache.spark.ml.param.ParamMap; -import org.apache.spark.ml.tuning.CrossValidator; -import org.apache.spark.ml.tuning.CrossValidatorModel; -import org.apache.spark.ml.tuning.ParamGridBuilder; -import org.apache.spark.sql.DataFrame; -import org.apache.spark.sql.Row; - -// Labeled and unlabeled instance types. -// Spark SQL can infer schema from Java Beans. -public class Document implements Serializable { - private long id; - private String text; - - public Document(long id, String text) { - this.id = id; - this.text = text; - } - - public long getId() { return this.id; } - public void setId(long id) { this.id = id; } - - public String getText() { return this.text; } - public void setText(String text) { this.text = text; } -} - -public class LabeledDocument extends Document implements Serializable { - private double label; - - public LabeledDocument(long id, String text, double label) { - super(id, text); - this.label = label; - } - - public double getLabel() { return this.label; } - public void setLabel(double label) { this.label = label; } -} - - -// Prepare training documents, which are labeled. -DataFrame training = sqlContext.createDataFrame(Arrays.asList( - new LabeledDocument(0L, "a b c d e spark", 1.0), - new LabeledDocument(1L, "b d", 0.0), - new LabeledDocument(2L, "spark f g h", 1.0), - new LabeledDocument(3L, "hadoop mapreduce", 0.0), - new LabeledDocument(4L, "b spark who", 1.0), - new LabeledDocument(5L, "g d a y", 0.0), - new LabeledDocument(6L, "spark fly", 1.0), - new LabeledDocument(7L, "was mapreduce", 0.0), - new LabeledDocument(8L, "e spark program", 1.0), - new LabeledDocument(9L, "a e c l", 0.0), - new LabeledDocument(10L, "spark compile", 1.0), - new LabeledDocument(11L, "hadoop software", 0.0) -), LabeledDocument.class); - -// Configure an ML pipeline, which consists of three stages: tokenizer, hashingTF, and lr. -Tokenizer tokenizer = new Tokenizer() - .setInputCol("text") - .setOutputCol("words"); -HashingTF hashingTF = new HashingTF() - .setNumFeatures(1000) - .setInputCol(tokenizer.getOutputCol()) - .setOutputCol("features"); -LogisticRegression lr = new LogisticRegression() - .setMaxIter(10) - .setRegParam(0.01); -Pipeline pipeline = new Pipeline() - .setStages(new PipelineStage[] {tokenizer, hashingTF, lr}); - -// We use a ParamGridBuilder to construct a grid of parameters to search over. -// With 3 values for hashingTF.numFeatures and 2 values for lr.regParam, -// this grid will have 3 x 2 = 6 parameter settings for CrossValidator to choose from. -ParamMap[] paramGrid = new ParamGridBuilder() - .addGrid(hashingTF.numFeatures(), new int[]{10, 100, 1000}) - .addGrid(lr.regParam(), new double[]{0.1, 0.01}) - .build(); - -// We now treat the Pipeline as an Estimator, wrapping it in a CrossValidator instance. -// This will allow us to jointly choose parameters for all Pipeline stages. -// A CrossValidator requires an Estimator, a set of Estimator ParamMaps, and an Evaluator. -// Note that the evaluator here is a BinaryClassificationEvaluator and its default metric -// is areaUnderROC. -CrossValidator cv = new CrossValidator() - .setEstimator(pipeline) - .setEvaluator(new BinaryClassificationEvaluator()) - .setEstimatorParamMaps(paramGrid) - .setNumFolds(2); // Use 3+ in practice - -// Run cross-validation, and choose the best set of parameters. -CrossValidatorModel cvModel = cv.fit(training); - -// Prepare test documents, which are unlabeled. -DataFrame test = sqlContext.createDataFrame(Arrays.asList( - new Document(4L, "spark i j k"), - new Document(5L, "l m n"), - new Document(6L, "mapreduce spark"), - new Document(7L, "apache hadoop") -), Document.class); - -// Make predictions on test documents. cvModel uses the best model found (lrModel). -DataFrame predictions = cvModel.transform(test); -for (Row r: predictions.select("id", "text", "probability", "prediction").collect()) { - System.out.println("(" + r.get(0) + ", " + r.get(1) + ") --> prob=" + r.get(2) - + ", prediction=" + r.get(3)); -} - -{% endhighlight %} -</div> - -</div> - -## Example: model selection via train validation split -In addition to `CrossValidator` Spark also offers `TrainValidationSplit` for hyper-parameter tuning. -`TrainValidationSplit` only evaluates each combination of parameters once as opposed to k times in - case of `CrossValidator`. It is therefore less expensive, - but will not produce as reliable results when the training dataset is not sufficiently large. - -`TrainValidationSplit` takes an `Estimator`, a set of `ParamMap`s provided in the `estimatorParamMaps` parameter, -and an `Evaluator`. -It begins by splitting the dataset into two parts using `trainRatio` parameter -which are used as separate training and test datasets. For example with `$trainRatio=0.75$` (default), -`TrainValidationSplit` will generate a training and test dataset pair where 75% of the data is used for training and 25% for validation. -Similar to `CrossValidator`, `TrainValidationSplit` also iterates through the set of `ParamMap`s. -For each combination of parameters, it trains the given `Estimator` and evaluates it using the given `Evaluator`. -The `ParamMap` which produces the best evaluation metric is selected as the best option. -`TrainValidationSplit` finally fits the `Estimator` using the best `ParamMap` and the entire dataset. - -<div class="codetabs"> - -<div data-lang="scala" markdown="1"> -{% highlight scala %} -import org.apache.spark.ml.evaluation.RegressionEvaluator -import org.apache.spark.ml.regression.LinearRegression -import org.apache.spark.ml.tuning.{ParamGridBuilder, TrainValidationSplit} - -// Prepare training and test data. -val data = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt") -val Array(training, test) = data.randomSplit(Array(0.9, 0.1), seed = 12345) - -val lr = new LinearRegression() - -// We use a ParamGridBuilder to construct a grid of parameters to search over. -// TrainValidationSplit will try all combinations of values and determine best model using -// the evaluator. -val paramGrid = new ParamGridBuilder() - .addGrid(lr.regParam, Array(0.1, 0.01)) - .addGrid(lr.fitIntercept) - .addGrid(lr.elasticNetParam, Array(0.0, 0.5, 1.0)) - .build() - -// In this case the estimator is simply the linear regression. -// A TrainValidationSplit requires an Estimator, a set of Estimator ParamMaps, and an Evaluator. -val trainValidationSplit = new TrainValidationSplit() - .setEstimator(lr) - .setEvaluator(new RegressionEvaluator) - .setEstimatorParamMaps(paramGrid) - // 80% of the data will be used for training and the remaining 20% for validation. - .setTrainRatio(0.8) - -// Run train validation split, and choose the best set of parameters. -val model = trainValidationSplit.fit(training) - -// Make predictions on test data. model is the model with combination of parameters -// that performed best. -model.transform(test) - .select("features", "label", "prediction") - .show() - -{% endhighlight %} -</div> - -<div data-lang="java" markdown="1"> -{% highlight java %} -import org.apache.spark.ml.evaluation.RegressionEvaluator; -import org.apache.spark.ml.param.ParamMap; -import org.apache.spark.ml.regression.LinearRegression; -import org.apache.spark.ml.tuning.*; -import org.apache.spark.sql.DataFrame; - -DataFrame data = jsql.read().format("libsvm").load("data/mllib/sample_libsvm_data.txt"); - -// Prepare training and test data. -DataFrame[] splits = data.randomSplit(new double[] {0.9, 0.1}, 12345); -DataFrame training = splits[0]; -DataFrame test = splits[1]; - -LinearRegression lr = new LinearRegression(); - -// We use a ParamGridBuilder to construct a grid of parameters to search over. -// TrainValidationSplit will try all combinations of values and determine best model using -// the evaluator. -ParamMap[] paramGrid = new ParamGridBuilder() - .addGrid(lr.regParam(), new double[] {0.1, 0.01}) - .addGrid(lr.fitIntercept()) - .addGrid(lr.elasticNetParam(), new double[] {0.0, 0.5, 1.0}) - .build(); - -// In this case the estimator is simply the linear regression. -// A TrainValidationSplit requires an Estimator, a set of Estimator ParamMaps, and an Evaluator. -TrainValidationSplit trainValidationSplit = new TrainValidationSplit() - .setEstimator(lr) - .setEvaluator(new RegressionEvaluator()) - .setEstimatorParamMaps(paramGrid) - .setTrainRatio(0.8); // 80% for training and the remaining 20% for validation - -// Run train validation split, and choose the best set of parameters. -TrainValidationSplitModel model = trainValidationSplit.fit(training); - -// Make predictions on test data. model is the model with combination of parameters -// that performed best. -model.transform(test) - .select("features", "label", "prediction") - .show(); - -{% endhighlight %} -</div> - -</div>
\ No newline at end of file diff --git a/docs/ml-linear-methods.md b/docs/ml-linear-methods.md index 0c13d7d0c8..a8754835ca 100644 --- a/docs/ml-linear-methods.md +++ b/docs/ml-linear-methods.md @@ -1,148 +1,8 @@ --- layout: global -title: Linear Methods - ML -displayTitle: <a href="ml-guide.html">ML</a> - Linear Methods +title: Linear methods - spark.ml +displayTitle: Linear methods - spark.ml --- - -`\[ -\newcommand{\R}{\mathbb{R}} -\newcommand{\E}{\mathbb{E}} -\newcommand{\x}{\mathbf{x}} -\newcommand{\y}{\mathbf{y}} -\newcommand{\wv}{\mathbf{w}} -\newcommand{\av}{\mathbf{\alpha}} -\newcommand{\bv}{\mathbf{b}} -\newcommand{\N}{\mathbb{N}} -\newcommand{\id}{\mathbf{I}} -\newcommand{\ind}{\mathbf{1}} -\newcommand{\0}{\mathbf{0}} -\newcommand{\unit}{\mathbf{e}} -\newcommand{\one}{\mathbf{1}} -\newcommand{\zero}{\mathbf{0}} -\]` - - -In MLlib, we implement popular linear methods such as logistic -regression and linear least squares with $L_1$ or $L_2$ regularization. -Refer to [the linear methods in mllib](mllib-linear-methods.html) for -details. In `spark.ml`, we also include Pipelines API for [Elastic -net](http://en.wikipedia.org/wiki/Elastic_net_regularization), a hybrid -of $L_1$ and $L_2$ regularization proposed in [Zou et al, Regularization -and variable selection via the elastic -net](http://users.stat.umn.edu/~zouxx019/Papers/elasticnet.pdf). -Mathematically, it is defined as a convex combination of the $L_1$ and -the $L_2$ regularization terms: -`\[ -\alpha \left( \lambda \|\wv\|_1 \right) + (1-\alpha) \left( \frac{\lambda}{2}\|\wv\|_2^2 \right) , \alpha \in [0, 1], \lambda \geq 0 -\]` -By setting $\alpha$ properly, elastic net contains both $L_1$ and $L_2$ -regularization as special cases. For example, if a [linear -regression](https://en.wikipedia.org/wiki/Linear_regression) model is -trained with the elastic net parameter $\alpha$ set to $1$, it is -equivalent to a -[Lasso](http://en.wikipedia.org/wiki/Least_squares#Lasso_method) model. -On the other hand, if $\alpha$ is set to $0$, the trained model reduces -to a [ridge -regression](http://en.wikipedia.org/wiki/Tikhonov_regularization) model. -We implement Pipelines API for both linear regression and logistic -regression with elastic net regularization. - -## Example: Logistic Regression - -The following example shows how to train a logistic regression model -with elastic net regularization. `elasticNetParam` corresponds to -$\alpha$ and `regParam` corresponds to $\lambda$. - -<div class="codetabs"> - -<div data-lang="scala" markdown="1"> -{% include_example scala/org/apache/spark/examples/ml/LogisticRegressionWithElasticNetExample.scala %} -</div> - -<div data-lang="java" markdown="1"> -{% include_example java/org/apache/spark/examples/ml/JavaLogisticRegressionWithElasticNetExample.java %} -</div> - -<div data-lang="python" markdown="1"> -{% include_example python/ml/logistic_regression_with_elastic_net.py %} -</div> - -</div> - -The `spark.ml` implementation of logistic regression also supports -extracting a summary of the model over the training set. Note that the -predictions and metrics which are stored as `Dataframe` in -`BinaryLogisticRegressionSummary` are annotated `@transient` and hence -only available on the driver. - -<div class="codetabs"> - -<div data-lang="scala" markdown="1"> - -[`LogisticRegressionTrainingSummary`](api/scala/index.html#org.apache.spark.ml.classification.LogisticRegressionTrainingSummary) -provides a summary for a -[`LogisticRegressionModel`](api/scala/index.html#org.apache.spark.ml.classification.LogisticRegressionModel). -Currently, only binary classification is supported and the -summary must be explicitly cast to -[`BinaryLogisticRegressionTrainingSummary`](api/scala/index.html#org.apache.spark.ml.classification.BinaryLogisticRegressionTrainingSummary). -This will likely change when multiclass classification is supported. - -Continuing the earlier example: - -{% include_example scala/org/apache/spark/examples/ml/LogisticRegressionSummaryExample.scala %} -</div> - -<div data-lang="java" markdown="1"> -[`LogisticRegressionTrainingSummary`](api/java/org/apache/spark/ml/classification/LogisticRegressionTrainingSummary.html) -provides a summary for a -[`LogisticRegressionModel`](api/java/org/apache/spark/ml/classification/LogisticRegressionModel.html). -Currently, only binary classification is supported and the -summary must be explicitly cast to -[`BinaryLogisticRegressionTrainingSummary`](api/java/org/apache/spark/ml/classification/BinaryLogisticRegressionTrainingSummary.html). -This will likely change when multiclass classification is supported. - -Continuing the earlier example: - -{% include_example java/org/apache/spark/examples/ml/JavaLogisticRegressionSummaryExample.java %} -</div> - -<!--- TODO: Add python model summaries once implemented --> -<div data-lang="python" markdown="1"> -Logistic regression model summary is not yet supported in Python. -</div> - -</div> - -## Example: Linear Regression - -The interface for working with linear regression models and model -summaries is similar to the logistic regression case. The following -example demonstrates training an elastic net regularized linear -regression model and extracting model summary statistics. - -<div class="codetabs"> - -<div data-lang="scala" markdown="1"> -{% include_example scala/org/apache/spark/examples/ml/LinearRegressionWithElasticNetExample.scala %} -</div> - -<div data-lang="java" markdown="1"> -{% include_example java/org/apache/spark/examples/ml/JavaLinearRegressionWithElasticNetExample.java %} -</div> - -<div data-lang="python" markdown="1"> -<!--- TODO: Add python model summaries once implemented --> -{% include_example python/ml/linear_regression_with_elastic_net.py %} -</div> - -</div> - -# Optimization - -The optimization algorithm underlying the implementation is called -[Orthant-Wise Limited-memory -QuasiNewton](http://research-srv.microsoft.com/en-us/um/people/jfgao/paper/icml07scalable.pdf) -(OWL-QN). It is an extension of L-BFGS that can effectively handle L1 -regularization and elastic net. - + > This section has been moved into the + [classification and regression section](ml-classification-regression.html). diff --git a/docs/ml-survival-regression.md b/docs/ml-survival-regression.md index ab275213b9..856ceb2f4e 100644 --- a/docs/ml-survival-regression.md +++ b/docs/ml-survival-regression.md @@ -1,96 +1,8 @@ --- layout: global -title: Survival Regression - ML -displayTitle: <a href="ml-guide.html">ML</a> - Survival Regression +title: Survival Regression - spark.ml +displayTitle: Survival Regression - spark.ml --- - -`\[ -\newcommand{\R}{\mathbb{R}} -\newcommand{\E}{\mathbb{E}} -\newcommand{\x}{\mathbf{x}} -\newcommand{\y}{\mathbf{y}} -\newcommand{\wv}{\mathbf{w}} -\newcommand{\av}{\mathbf{\alpha}} -\newcommand{\bv}{\mathbf{b}} -\newcommand{\N}{\mathbb{N}} -\newcommand{\id}{\mathbf{I}} -\newcommand{\ind}{\mathbf{1}} -\newcommand{\0}{\mathbf{0}} -\newcommand{\unit}{\mathbf{e}} -\newcommand{\one}{\mathbf{1}} -\newcommand{\zero}{\mathbf{0}} -\]` - - -In `spark.ml`, we implement the [Accelerated failure time (AFT)](https://en.wikipedia.org/wiki/Accelerated_failure_time_model) -model which is a parametric survival regression model for censored data. -It describes a model for the log of survival time, so it's often called -log-linear model for survival analysis. Different from -[Proportional hazards](https://en.wikipedia.org/wiki/Proportional_hazards_model) model -designed for the same purpose, the AFT model is more easily to parallelize -because each instance contribute to the objective function independently. - -Given the values of the covariates $x^{'}$, for random lifetime $t_{i}$ of -subjects i = 1, ..., n, with possible right-censoring, -the likelihood function under the AFT model is given as: -`\[ -L(\beta,\sigma)=\prod_{i=1}^n[\frac{1}{\sigma}f_{0}(\frac{\log{t_{i}}-x^{'}\beta}{\sigma})]^{\delta_{i}}S_{0}(\frac{\log{t_{i}}-x^{'}\beta}{\sigma})^{1-\delta_{i}} -\]` -Where $\delta_{i}$ is the indicator of the event has occurred i.e. uncensored or not. -Using $\epsilon_{i}=\frac{\log{t_{i}}-x^{'}\beta}{\sigma}$, the log-likelihood function -assumes the form: -`\[ -\iota(\beta,\sigma)=\sum_{i=1}^{n}[-\delta_{i}\log\sigma+\delta_{i}\log{f_{0}}(\epsilon_{i})+(1-\delta_{i})\log{S_{0}(\epsilon_{i})}] -\]` -Where $S_{0}(\epsilon_{i})$ is the baseline survivor function, -and $f_{0}(\epsilon_{i})$ is corresponding density function. - -The most commonly used AFT model is based on the Weibull distribution of the survival time. -The Weibull distribution for lifetime corresponding to extreme value distribution for -log of the lifetime, and the $S_{0}(\epsilon)$ function is: -`\[ -S_{0}(\epsilon_{i})=\exp(-e^{\epsilon_{i}}) -\]` -the $f_{0}(\epsilon_{i})$ function is: -`\[ -f_{0}(\epsilon_{i})=e^{\epsilon_{i}}\exp(-e^{\epsilon_{i}}) -\]` -The log-likelihood function for AFT model with Weibull distribution of lifetime is: -`\[ -\iota(\beta,\sigma)= -\sum_{i=1}^n[\delta_{i}\log\sigma-\delta_{i}\epsilon_{i}+e^{\epsilon_{i}}] -\]` -Due to minimizing the negative log-likelihood equivalent to maximum a posteriori probability, -the loss function we use to optimize is $-\iota(\beta,\sigma)$. -The gradient functions for $\beta$ and $\log\sigma$ respectively are: -`\[ -\frac{\partial (-\iota)}{\partial \beta}=\sum_{1=1}^{n}[\delta_{i}-e^{\epsilon_{i}}]\frac{x_{i}}{\sigma} -\]` -`\[ -\frac{\partial (-\iota)}{\partial (\log\sigma)}=\sum_{i=1}^{n}[\delta_{i}+(\delta_{i}-e^{\epsilon_{i}})\epsilon_{i}] -\]` - -The AFT model can be formulated as a convex optimization problem, -i.e. the task of finding a minimizer of a convex function $-\iota(\beta,\sigma)$ -that depends coefficients vector $\beta$ and the log of scale parameter $\log\sigma$. -The optimization algorithm underlying the implementation is L-BFGS. -The implementation matches the result from R's survival function -[survreg](https://stat.ethz.ch/R-manual/R-devel/library/survival/html/survreg.html) - -## Example: - -<div class="codetabs"> - -<div data-lang="scala" markdown="1"> -{% include_example scala/org/apache/spark/examples/ml/AFTSurvivalRegressionExample.scala %} -</div> - -<div data-lang="java" markdown="1"> -{% include_example java/org/apache/spark/examples/ml/JavaAFTSurvivalRegressionExample.java %} -</div> - -<div data-lang="python" markdown="1"> -{% include_example python/ml/aft_survival_regression.py %} -</div> - -</div>
\ No newline at end of file + > This section has been moved into the + [classification and regression section](ml-classification-regression.html#survival-regression). diff --git a/docs/mllib-classification-regression.md b/docs/mllib-classification-regression.md index 0210950b89..aaf8bd465c 100644 --- a/docs/mllib-classification-regression.md +++ b/docs/mllib-classification-regression.md @@ -1,10 +1,10 @@ --- layout: global -title: Classification and Regression - MLlib -displayTitle: <a href="mllib-guide.html">MLlib</a> - Classification and Regression +title: Classification and Regression - spark.mllib +displayTitle: Classification and Regression - spark.mllib --- -MLlib supports various methods for +The `spark.mllib` package supports various methods for [binary classification](http://en.wikipedia.org/wiki/Binary_classification), [multiclass classification](http://en.wikipedia.org/wiki/Multiclass_classification), and diff --git a/docs/mllib-clustering.md b/docs/mllib-clustering.md index 8fbced6c87..48d64cd402 100644 --- a/docs/mllib-clustering.md +++ b/docs/mllib-clustering.md @@ -1,7 +1,7 @@ --- layout: global -title: Clustering - MLlib -displayTitle: <a href="mllib-guide.html">MLlib</a> - Clustering +title: Clustering - spark.mllib +displayTitle: Clustering - spark.mllib --- [Clustering](https://en.wikipedia.org/wiki/Cluster_analysis) is an unsupervised learning problem whereby we aim to group subsets @@ -10,19 +10,19 @@ often used for exploratory analysis and/or as a component of a hierarchical [supervised learning](https://en.wikipedia.org/wiki/Supervised_learning) pipeline (in which distinct classifiers or regression models are trained for each cluster). -MLlib supports the following models: +The `spark.mllib` package supports the following models: * Table of contents {:toc} ## K-means -[k-means](http://en.wikipedia.org/wiki/K-means_clustering) is one of the +[K-means](http://en.wikipedia.org/wiki/K-means_clustering) is one of the most commonly used clustering algorithms that clusters the data points into a -predefined number of clusters. The MLlib implementation includes a parallelized +predefined number of clusters. The `spark.mllib` implementation includes a parallelized variant of the [k-means++](http://en.wikipedia.org/wiki/K-means%2B%2B) method called [kmeans||](http://theory.stanford.edu/~sergei/papers/vldb12-kmpar.pdf). -The implementation in MLlib has the following parameters: +The implementation in `spark.mllib` has the following parameters: * *k* is the number of desired clusters. * *maxIterations* is the maximum number of iterations to run. @@ -171,7 +171,7 @@ sameModel = KMeansModel.load(sc, "myModelPath") A [Gaussian Mixture Model](http://en.wikipedia.org/wiki/Mixture_model#Multivariate_Gaussian_mixture_model) represents a composite distribution whereby points are drawn from one of *k* Gaussian sub-distributions, -each with its own probability. The MLlib implementation uses the +each with its own probability. The `spark.mllib` implementation uses the [expectation-maximization](http://en.wikipedia.org/wiki/Expectation%E2%80%93maximization_algorithm) algorithm to induce the maximum-likelihood model given a set of samples. The implementation has the following parameters: @@ -308,13 +308,13 @@ graph given pairwise similarties as edge properties, described in [Lin and Cohen, Power Iteration Clustering](http://www.icml2010.org/papers/387.pdf). It computes a pseudo-eigenvector of the normalized affinity matrix of the graph via [power iteration](http://en.wikipedia.org/wiki/Power_iteration) and uses it to cluster vertices. -MLlib includes an implementation of PIC using GraphX as its backend. +`spark.mllib` includes an implementation of PIC using GraphX as its backend. It takes an `RDD` of `(srcId, dstId, similarity)` tuples and outputs a model with the clustering assignments. The similarities must be nonnegative. PIC assumes that the similarity measure is symmetric. A pair `(srcId, dstId)` regardless of the ordering should appear at most once in the input data. If a pair is missing from input, their similarity is treated as zero. -MLlib's PIC implementation takes the following (hyper-)parameters: +`spark.mllib`'s PIC implementation takes the following (hyper-)parameters: * `k`: number of clusters * `maxIterations`: maximum number of power iterations @@ -323,7 +323,7 @@ MLlib's PIC implementation takes the following (hyper-)parameters: **Examples** -In the following, we show code snippets to demonstrate how to use PIC in MLlib. +In the following, we show code snippets to demonstrate how to use PIC in `spark.mllib`. <div class="codetabs"> <div data-lang="scala" markdown="1"> @@ -493,7 +493,7 @@ checkpointing can help reduce shuffle file sizes on disk and help with failure recovery. -All of MLlib's LDA models support: +All of `spark.mllib`'s LDA models support: * `describeTopics`: Returns topics as arrays of most important terms and term weights @@ -721,7 +721,7 @@ sameModel = LDAModel.load(sc, "myModelPath") ## Streaming k-means When data arrive in a stream, we may want to estimate clusters dynamically, -updating them as new data arrive. MLlib provides support for streaming k-means clustering, +updating them as new data arrive. `spark.mllib` provides support for streaming k-means clustering, with parameters to control the decay (or "forgetfulness") of the estimates. The algorithm uses a generalization of the mini-batch k-means update rule. For each batch of data, we assign all points to their nearest cluster, compute new cluster centers, then update each cluster using: diff --git a/docs/mllib-collaborative-filtering.md b/docs/mllib-collaborative-filtering.md index 7cd1b894e7..1ebb4654ae 100644 --- a/docs/mllib-collaborative-filtering.md +++ b/docs/mllib-collaborative-filtering.md @@ -1,7 +1,7 @@ --- layout: global -title: Collaborative Filtering - MLlib -displayTitle: <a href="mllib-guide.html">MLlib</a> - Collaborative Filtering +title: Collaborative Filtering - spark.mllib +displayTitle: Collaborative Filtering - spark.mllib --- * Table of contents @@ -11,12 +11,12 @@ displayTitle: <a href="mllib-guide.html">MLlib</a> - Collaborative Filtering [Collaborative filtering](http://en.wikipedia.org/wiki/Recommender_system#Collaborative_filtering) is commonly used for recommender systems. These techniques aim to fill in the -missing entries of a user-item association matrix. MLlib currently supports +missing entries of a user-item association matrix. `spark.mllib` currently supports model-based collaborative filtering, in which users and products are described by a small set of latent factors that can be used to predict missing entries. -MLlib uses the [alternating least squares +`spark.mllib` uses the [alternating least squares (ALS)](http://dl.acm.org/citation.cfm?id=1608614) -algorithm to learn these latent factors. The implementation in MLlib has the +algorithm to learn these latent factors. The implementation in `spark.mllib` has the following parameters: * *numBlocks* is the number of blocks used to parallelize computation (set to -1 to auto-configure). @@ -34,7 +34,7 @@ The standard approach to matrix factorization based collaborative filtering trea the entries in the user-item matrix as *explicit* preferences given by the user to the item. It is common in many real-world use cases to only have access to *implicit feedback* (e.g. views, -clicks, purchases, likes, shares etc.). The approach used in MLlib to deal with such data is taken +clicks, purchases, likes, shares etc.). The approach used in `spark.mllib` to deal with such data is taken from [Collaborative Filtering for Implicit Feedback Datasets](http://dx.doi.org/10.1109/ICDM.2008.22). Essentially instead of trying to model the matrix of ratings directly, this approach treats the data @@ -119,4 +119,4 @@ a dependency. ## Tutorial The [training exercises](https://databricks-training.s3.amazonaws.com/index.html) from the Spark Summit 2014 include a hands-on tutorial for -[personalized movie recommendation with MLlib](https://databricks-training.s3.amazonaws.com/movie-recommendation-with-mllib.html). +[personalized movie recommendation with `spark.mllib`](https://databricks-training.s3.amazonaws.com/movie-recommendation-with-mllib.html). diff --git a/docs/mllib-data-types.md b/docs/mllib-data-types.md index 3c0c047967..363dc7c13b 100644 --- a/docs/mllib-data-types.md +++ b/docs/mllib-data-types.md @@ -1,7 +1,7 @@ --- layout: global title: Data Types - MLlib -displayTitle: <a href="mllib-guide.html">MLlib</a> - Data Types +displayTitle: Data Types - MLlib --- * Table of contents diff --git a/docs/mllib-decision-tree.md b/docs/mllib-decision-tree.md index 77ce34e91a..a8612b6c84 100644 --- a/docs/mllib-decision-tree.md +++ b/docs/mllib-decision-tree.md @@ -1,7 +1,7 @@ --- layout: global -title: Decision Trees - MLlib -displayTitle: <a href="mllib-guide.html">MLlib</a> - Decision Trees +title: Decision Trees - spark.mllib +displayTitle: Decision Trees - spark.mllib --- * Table of contents @@ -15,7 +15,7 @@ feature scaling, and are able to capture non-linearities and feature interaction algorithms such as random forests and boosting are among the top performers for classification and regression tasks. -MLlib supports decision trees for binary and multiclass classification and for regression, +`spark.mllib` supports decision trees for binary and multiclass classification and for regression, using both continuous and categorical features. The implementation partitions data by rows, allowing distributed training with millions of instances. diff --git a/docs/mllib-dimensionality-reduction.md b/docs/mllib-dimensionality-reduction.md index ac3526908a..11d8e0bd1d 100644 --- a/docs/mllib-dimensionality-reduction.md +++ b/docs/mllib-dimensionality-reduction.md @@ -1,7 +1,7 @@ --- layout: global -title: Dimensionality Reduction - MLlib -displayTitle: <a href="mllib-guide.html">MLlib</a> - Dimensionality Reduction +title: Dimensionality Reduction - spark.mllib +displayTitle: Dimensionality Reduction - spark.mllib --- * Table of contents @@ -11,7 +11,7 @@ displayTitle: <a href="mllib-guide.html">MLlib</a> - Dimensionality Reduction of reducing the number of variables under consideration. It can be used to extract latent features from raw and noisy features or compress data while maintaining the structure. -MLlib provides support for dimensionality reduction on the <a href="mllib-data-types.html#rowmatrix">RowMatrix</a> class. +`spark.mllib` provides support for dimensionality reduction on the <a href="mllib-data-types.html#rowmatrix">RowMatrix</a> class. ## Singular value decomposition (SVD) @@ -57,7 +57,7 @@ passes, $O(n)$ storage on each executor, and $O(n k)$ storage on the driver. ### SVD Example -MLlib provides SVD functionality to row-oriented matrices, provided in the +`spark.mllib` provides SVD functionality to row-oriented matrices, provided in the <a href="mllib-data-types.html#rowmatrix">RowMatrix</a> class. <div class="codetabs"> @@ -141,7 +141,7 @@ statistical method to find a rotation such that the first coordinate has the lar possible, and each succeeding coordinate in turn has the largest variance possible. The columns of the rotation matrix are called principal components. PCA is used widely in dimensionality reduction. -MLlib supports PCA for tall-and-skinny matrices stored in row-oriented format and any Vectors. +`spark.mllib` supports PCA for tall-and-skinny matrices stored in row-oriented format and any Vectors. <div class="codetabs"> <div data-lang="scala" markdown="1"> diff --git a/docs/mllib-ensembles.md b/docs/mllib-ensembles.md index 50450e05d2..2416b6fa0a 100644 --- a/docs/mllib-ensembles.md +++ b/docs/mllib-ensembles.md @@ -1,7 +1,7 @@ --- layout: global -title: Ensembles - MLlib -displayTitle: <a href="mllib-guide.html">MLlib</a> - Ensembles +title: Ensembles - spark.mllib +displayTitle: Ensembles - spark.mllib --- * Table of contents @@ -9,7 +9,7 @@ displayTitle: <a href="mllib-guide.html">MLlib</a> - Ensembles An [ensemble method](http://en.wikipedia.org/wiki/Ensemble_learning) is a learning algorithm which creates a model composed of a set of other base models. -MLlib supports two major ensemble algorithms: [`GradientBoostedTrees`](api/scala/index.html#org.apache.spark.mllib.tree.GradientBoostedTrees) and [`RandomForest`](api/scala/index.html#org.apache.spark.mllib.tree.RandomForest). +`spark.mllib` supports two major ensemble algorithms: [`GradientBoostedTrees`](api/scala/index.html#org.apache.spark.mllib.tree.GradientBoostedTrees) and [`RandomForest`](api/scala/index.html#org.apache.spark.mllib.tree.RandomForest). Both use [decision trees](mllib-decision-tree.html) as their base models. ## Gradient-Boosted Trees vs. Random Forests @@ -33,9 +33,9 @@ Like decision trees, random forests handle categorical features, extend to the multiclass classification setting, do not require feature scaling, and are able to capture non-linearities and feature interactions. -MLlib supports random forests for binary and multiclass classification and for regression, +`spark.mllib` supports random forests for binary and multiclass classification and for regression, using both continuous and categorical features. -MLlib implements random forests using the existing [decision tree](mllib-decision-tree.html) +`spark.mllib` implements random forests using the existing [decision tree](mllib-decision-tree.html) implementation. Please see the decision tree guide for more information on trees. ### Basic algorithm @@ -155,9 +155,9 @@ Like decision trees, GBTs handle categorical features, extend to the multiclass classification setting, do not require feature scaling, and are able to capture non-linearities and feature interactions. -MLlib supports GBTs for binary classification and for regression, +`spark.mllib` supports GBTs for binary classification and for regression, using both continuous and categorical features. -MLlib implements GBTs using the existing [decision tree](mllib-decision-tree.html) implementation. Please see the decision tree guide for more information on trees. +`spark.mllib` implements GBTs using the existing [decision tree](mllib-decision-tree.html) implementation. Please see the decision tree guide for more information on trees. *Note*: GBTs do not yet support multiclass classification. For multiclass problems, please use [decision trees](mllib-decision-tree.html) or [Random Forests](mllib-ensembles.html#Random-Forest). @@ -171,7 +171,7 @@ The specific mechanism for re-labeling instances is defined by a loss function ( #### Losses -The table below lists the losses currently supported by GBTs in MLlib. +The table below lists the losses currently supported by GBTs in `spark.mllib`. Note that each loss is applicable to one of classification or regression, not both. Notation: $N$ = number of instances. $y_i$ = label of instance $i$. $x_i$ = features of instance $i$. $F(x_i)$ = model's predicted label for instance $i$. diff --git a/docs/mllib-evaluation-metrics.md b/docs/mllib-evaluation-metrics.md index 6924037b94..774826c270 100644 --- a/docs/mllib-evaluation-metrics.md +++ b/docs/mllib-evaluation-metrics.md @@ -1,20 +1,20 @@ --- layout: global -title: Evaluation Metrics - MLlib -displayTitle: <a href="mllib-guide.html">MLlib</a> - Evaluation Metrics +title: Evaluation Metrics - spark.mllib +displayTitle: Evaluation Metrics - spark.mllib --- * Table of contents {:toc} -Spark's MLlib comes with a number of machine learning algorithms that can be used to learn from and make predictions +`spark.mllib` comes with a number of machine learning algorithms that can be used to learn from and make predictions on data. When these algorithms are applied to build machine learning models, there is a need to evaluate the performance -of the model on some criteria, which depends on the application and its requirements. Spark's MLlib also provides a +of the model on some criteria, which depends on the application and its requirements. `spark.mllib` also provides a suite of metrics for the purpose of evaluating the performance of machine learning models. Specific machine learning algorithms fall under broader types of machine learning applications like classification, regression, clustering, etc. Each of these types have well established metrics for performance evaluation and those -metrics that are currently available in Spark's MLlib are detailed in this section. +metrics that are currently available in `spark.mllib` are detailed in this section. ## Classification model evaluation diff --git a/docs/mllib-feature-extraction.md b/docs/mllib-feature-extraction.md index 5bee170c61..7796bac697 100644 --- a/docs/mllib-feature-extraction.md +++ b/docs/mllib-feature-extraction.md @@ -1,7 +1,7 @@ --- layout: global -title: Feature Extraction and Transformation - MLlib -displayTitle: <a href="mllib-guide.html">MLlib</a> - Feature Extraction and Transformation +title: Feature Extraction and Transformation - spark.mllib +displayTitle: Feature Extraction and Transformation - spark.mllib --- * Table of contents @@ -31,7 +31,7 @@ The TF-IDF measure is simply the product of TF and IDF: TFIDF(t, d, D) = TF(t, d) \cdot IDF(t, D). \]` There are several variants on the definition of term frequency and document frequency. -In MLlib, we separate TF and IDF to make them flexible. +In `spark.mllib`, we separate TF and IDF to make them flexible. Our implementation of term frequency utilizes the [hashing trick](http://en.wikipedia.org/wiki/Feature_hashing). @@ -44,7 +44,7 @@ To reduce the chance of collision, we can increase the target feature dimension, the number of buckets of the hash table. The default feature dimension is `$2^{20} = 1,048,576$`. -**Note:** MLlib doesn't provide tools for text segmentation. +**Note:** `spark.mllib` doesn't provide tools for text segmentation. We refer users to the [Stanford NLP Group](http://nlp.stanford.edu/) and [scalanlp/chalk](https://github.com/scalanlp/chalk). @@ -86,7 +86,7 @@ val idf = new IDF().fit(tf) val tfidf: RDD[Vector] = idf.transform(tf) {% endhighlight %} -MLlib's IDF implementation provides an option for ignoring terms which occur in less than a +`spark.mllib`'s IDF implementation provides an option for ignoring terms which occur in less than a minimum number of documents. In such cases, the IDF for these terms is set to 0. This feature can be used by passing the `minDocFreq` value to the IDF constructor. @@ -134,7 +134,7 @@ idf = IDF().fit(tf) tfidf = idf.transform(tf) {% endhighlight %} -MLLib's IDF implementation provides an option for ignoring terms which occur in less than a +`spark.mllib`'s IDF implementation provides an option for ignoring terms which occur in less than a minimum number of documents. In such cases, the IDF for these terms is set to 0. This feature can be used by passing the `minDocFreq` value to the IDF constructor. diff --git a/docs/mllib-frequent-pattern-mining.md b/docs/mllib-frequent-pattern-mining.md index fe42896a05..2c8a8f2361 100644 --- a/docs/mllib-frequent-pattern-mining.md +++ b/docs/mllib-frequent-pattern-mining.md @@ -1,7 +1,7 @@ --- layout: global -title: Frequent Pattern Mining - MLlib -displayTitle: <a href="mllib-guide.html">MLlib</a> - Frequent Pattern Mining +title: Frequent Pattern Mining - spark.mllib +displayTitle: Frequent Pattern Mining - spark.mllib --- Mining frequent items, itemsets, subsequences, or other substructures is usually among the @@ -9,7 +9,7 @@ first steps to analyze a large-scale dataset, which has been an active research data mining for years. We refer users to Wikipedia's [association rule learning](http://en.wikipedia.org/wiki/Association_rule_learning) for more information. -MLlib provides a parallel implementation of FP-growth, +`spark.mllib` provides a parallel implementation of FP-growth, a popular algorithm to mining frequent itemsets. ## FP-growth @@ -22,13 +22,13 @@ Different from [Apriori-like](http://en.wikipedia.org/wiki/Apriori_algorithm) al the second step of FP-growth uses a suffix tree (FP-tree) structure to encode transactions without generating candidate sets explicitly, which are usually expensive to generate. After the second step, the frequent itemsets can be extracted from the FP-tree. -In MLlib, we implemented a parallel version of FP-growth called PFP, +In `spark.mllib`, we implemented a parallel version of FP-growth called PFP, as described in [Li et al., PFP: Parallel FP-growth for query recommendation](http://dx.doi.org/10.1145/1454008.1454027). PFP distributes the work of growing FP-trees based on the suffices of transactions, and hence more scalable than a single-machine implementation. We refer users to the papers for more details. -MLlib's FP-growth implementation takes the following (hyper-)parameters: +`spark.mllib`'s FP-growth implementation takes the following (hyper-)parameters: * `minSupport`: the minimum support for an itemset to be identified as frequent. For example, if an item appears 3 out of 5 transactions, it has a support of 3/5=0.6. @@ -126,7 +126,7 @@ PrefixSpan Approach](http://dx.doi.org/10.1109%2FTKDE.2004.77). We refer the reader to the referenced paper for formalizing the sequential pattern mining problem. -MLlib's PrefixSpan implementation takes the following parameters: +`spark.mllib`'s PrefixSpan implementation takes the following parameters: * `minSupport`: the minimum support required to be considered a frequent sequential pattern. diff --git a/docs/mllib-guide.md b/docs/mllib-guide.md index 3bc2b78060..7fef6b5c61 100644 --- a/docs/mllib-guide.md +++ b/docs/mllib-guide.md @@ -66,7 +66,7 @@ We list major functionality from both below, with links to detailed guides. # spark.ml: high-level APIs for ML pipelines -* [Overview: estimators, transformers and pipelines](ml-intro.html) +* [Overview: estimators, transformers and pipelines](ml-guide.html) * [Extracting, transforming and selecting features](ml-features.html) * [Classification and regression](ml-classification-regression.html) * [Clustering](ml-clustering.html) diff --git a/docs/mllib-isotonic-regression.md b/docs/mllib-isotonic-regression.md index 85f9226b43..8ede4407d5 100644 --- a/docs/mllib-isotonic-regression.md +++ b/docs/mllib-isotonic-regression.md @@ -1,7 +1,7 @@ --- layout: global -title: Isotonic regression - MLlib -displayTitle: <a href="mllib-guide.html">MLlib</a> - Regression +title: Isotonic regression - spark.mllib +displayTitle: Regression - spark.mllib --- ## Isotonic regression @@ -23,7 +23,7 @@ Essentially isotonic regression is a [monotonic function](http://en.wikipedia.org/wiki/Monotonic_function) best fitting the original data points. -MLlib supports a +`spark.mllib` supports a [pool adjacent violators algorithm](http://doi.org/10.1198/TECH.2010.10111) which uses an approach to [parallelizing isotonic regression](http://doi.org/10.1007/978-3-642-99789-1_10). diff --git a/docs/mllib-linear-methods.md b/docs/mllib-linear-methods.md index 132f8c354a..20b35612ca 100644 --- a/docs/mllib-linear-methods.md +++ b/docs/mllib-linear-methods.md @@ -1,7 +1,7 @@ --- layout: global -title: Linear Methods - MLlib -displayTitle: <a href="mllib-guide.html">MLlib</a> - Linear Methods +title: Linear Methods - spark.mllib +displayTitle: Linear Methods - spark.mllib --- * Table of contents @@ -41,7 +41,7 @@ the objective function is of the form Here the vectors `$\x_i\in\R^d$` are the training data examples, for `$1\le i\le n$`, and `$y_i\in\R$` are their corresponding labels, which we want to predict. We call the method *linear* if $L(\wv; \x, y)$ can be expressed as a function of $\wv^T x$ and $y$. -Several of MLlib's classification and regression algorithms fall into this category, +Several of `spark.mllib`'s classification and regression algorithms fall into this category, and are discussed here. The objective function `$f$` has two parts: @@ -55,7 +55,7 @@ training error) and minimizing model complexity (i.e., to avoid overfitting). ### Loss functions The following table summarizes the loss functions and their gradients or sub-gradients for the -methods MLlib supports: +methods `spark.mllib` supports: <table class="table"> <thead> @@ -83,7 +83,7 @@ methods MLlib supports: The purpose of the [regularizer](http://en.wikipedia.org/wiki/Regularization_(mathematics)) is to encourage simple models and avoid overfitting. We support the following -regularizers in MLlib: +regularizers in `spark.mllib`: <table class="table"> <thead> @@ -115,7 +115,10 @@ especially when the number of training examples is small. ### Optimization -Under the hood, linear methods use convex optimization methods to optimize the objective functions. MLlib uses two methods, SGD and L-BFGS, described in the [optimization section](mllib-optimization.html). Currently, most algorithm APIs support Stochastic Gradient Descent (SGD), and a few support L-BFGS. Refer to [this optimization section](mllib-optimization.html#Choosing-an-Optimization-Method) for guidelines on choosing between optimization methods. +Under the hood, linear methods use convex optimization methods to optimize the objective functions. +`spark.mllib` uses two methods, SGD and L-BFGS, described in the [optimization section](mllib-optimization.html). +Currently, most algorithm APIs support Stochastic Gradient Descent (SGD), and a few support L-BFGS. +Refer to [this optimization section](mllib-optimization.html#Choosing-an-Optimization-Method) for guidelines on choosing between optimization methods. ## Classification @@ -126,16 +129,16 @@ The most common classification type is categories, usually named positive and negative. If there are more than two categories, it is called [multiclass classification](http://en.wikipedia.org/wiki/Multiclass_classification). -MLlib supports two linear methods for classification: linear Support Vector Machines (SVMs) +`spark.mllib` supports two linear methods for classification: linear Support Vector Machines (SVMs) and logistic regression. Linear SVMs supports only binary classification, while logistic regression supports both binary and multiclass classification problems. -For both methods, MLlib supports L1 and L2 regularized variants. +For both methods, `spark.mllib` supports L1 and L2 regularized variants. The training data set is represented by an RDD of [LabeledPoint](mllib-data-types.html) in MLlib, where labels are class indices starting from zero: $0, 1, 2, \ldots$. Note that, in the mathematical formulation in this guide, a binary label $y$ is denoted as either $+1$ (positive) or $-1$ (negative), which is convenient for the formulation. -*However*, the negative label is represented by $0$ in MLlib instead of $-1$, to be consistent with +*However*, the negative label is represented by $0$ in `spark.mllib` instead of $-1$, to be consistent with multiclass labeling. ### Linear Support Vector Machines (SVMs) @@ -207,7 +210,7 @@ val sameModel = SVMModel.load(sc, "myModelPath") The `SVMWithSGD.train()` method by default performs L2 regularization with the regularization parameter set to 1.0. If we want to configure this algorithm, we can customize `SVMWithSGD` further by creating a new object directly and -calling setter methods. All other MLlib algorithms support customization in +calling setter methods. All other `spark.mllib` algorithms support customization in this way as well. For example, the following code produces an L1 regularized variant of SVMs with regularization parameter set to 0.1, and runs the training algorithm for 200 iterations. @@ -293,7 +296,7 @@ public class SVMClassifier { The `SVMWithSGD.train()` method by default performs L2 regularization with the regularization parameter set to 1.0. If we want to configure this algorithm, we can customize `SVMWithSGD` further by creating a new object directly and -calling setter methods. All other MLlib algorithms support customization in +calling setter methods. All other `spark.mllib` algorithms support customization in this way as well. For example, the following code produces an L1 regularized variant of SVMs with regularization parameter set to 0.1, and runs the training algorithm for 200 iterations. @@ -375,7 +378,7 @@ Binary logistic regression can be generalized into train and predict multiclass classification problems. For example, for $K$ possible outcomes, one of the outcomes can be chosen as a "pivot", and the other $K - 1$ outcomes can be separately regressed against the pivot outcome. -In MLlib, the first class $0$ is chosen as the "pivot" class. +In `spark.mllib`, the first class $0$ is chosen as the "pivot" class. See Section 4.4 of [The Elements of Statistical Learning](http://statweb.stanford.edu/~tibs/ElemStatLearn/) for references. @@ -726,7 +729,7 @@ a dependency. ###Streaming linear regression When data arrive in a streaming fashion, it is useful to fit regression models online, -updating the parameters of the model as new data arrives. MLlib currently supports +updating the parameters of the model as new data arrives. `spark.mllib` currently supports streaming linear regression using ordinary least squares. The fitting is similar to that performed offline, except fitting occurs on each batch of data, so that the model continually updates to reflect the data from the stream. @@ -852,7 +855,7 @@ will get better! # Implementation (developer) -Behind the scene, MLlib implements a simple distributed version of stochastic gradient descent +Behind the scene, `spark.mllib` implements a simple distributed version of stochastic gradient descent (SGD), building on the underlying gradient descent primitive (as described in the <a href="mllib-optimization.html">optimization</a> section). All provided algorithms take as input a regularization parameter (`regParam`) along with various parameters associated with stochastic diff --git a/docs/mllib-migration-guides.md b/docs/mllib-migration-guides.md index 774b85d1f7..73e4fddf67 100644 --- a/docs/mllib-migration-guides.md +++ b/docs/mllib-migration-guides.md @@ -1,7 +1,7 @@ --- layout: global -title: Old Migration Guides - MLlib -displayTitle: <a href="mllib-guide.html">MLlib</a> - Old Migration Guides +title: Old Migration Guides - spark.mllib +displayTitle: Old Migration Guides - spark.mllib description: MLlib migration guides from before Spark SPARK_VERSION_SHORT --- diff --git a/docs/mllib-naive-bayes.md b/docs/mllib-naive-bayes.md index 60ac6c7e5b..d0d594af6a 100644 --- a/docs/mllib-naive-bayes.md +++ b/docs/mllib-naive-bayes.md @@ -1,7 +1,7 @@ --- layout: global -title: Naive Bayes - MLlib -displayTitle: <a href="mllib-guide.html">MLlib</a> - Naive Bayes +title: Naive Bayes - spark.mllib +displayTitle: Naive Bayes - spark.mllib --- [Naive Bayes](http://en.wikipedia.org/wiki/Naive_Bayes_classifier) is a simple @@ -12,7 +12,7 @@ distribution of each feature given label, and then it applies Bayes' theorem to compute the conditional probability distribution of label given an observation and use it for prediction. -MLlib supports [multinomial naive +`spark.mllib` supports [multinomial naive Bayes](http://en.wikipedia.org/wiki/Naive_Bayes_classifier#Multinomial_naive_Bayes) and [Bernoulli naive Bayes](http://nlp.stanford.edu/IR-book/html/htmledition/the-bernoulli-model-1.html). These models are typically used for [document classification](http://nlp.stanford.edu/IR-book/html/htmledition/naive-bayes-text-classification-1.html). diff --git a/docs/mllib-optimization.md b/docs/mllib-optimization.md index ad7bcd9bfd..f90b66f8e2 100644 --- a/docs/mllib-optimization.md +++ b/docs/mllib-optimization.md @@ -1,7 +1,7 @@ --- layout: global -title: Optimization - MLlib -displayTitle: <a href="mllib-guide.html">MLlib</a> - Optimization +title: Optimization - spark.mllib +displayTitle: Optimization - spark.mllib --- * Table of contents @@ -87,7 +87,7 @@ in the `$t$`-th iteration, with the input parameter `$s=$ stepSize`. Note that s step-size for SGD methods can often be delicate in practice and is a topic of active research. **Gradients.** -A table of (sub)gradients of the machine learning methods implemented in MLlib, is available in +A table of (sub)gradients of the machine learning methods implemented in `spark.mllib`, is available in the <a href="mllib-classification-regression.html">classification and regression</a> section. @@ -140,7 +140,7 @@ other first-order optimization. ### Choosing an Optimization Method -[Linear methods](mllib-linear-methods.html) use optimization internally, and some linear methods in MLlib support both SGD and L-BFGS. +[Linear methods](mllib-linear-methods.html) use optimization internally, and some linear methods in `spark.mllib` support both SGD and L-BFGS. Different optimization methods can have different convergence guarantees depending on the properties of the objective function, and we cannot cover the literature here. In general, when L-BFGS is available, we recommend using it instead of SGD since L-BFGS tends to converge faster (in fewer iterations). diff --git a/docs/mllib-pmml-model-export.md b/docs/mllib-pmml-model-export.md index 615287125c..b532ad907d 100644 --- a/docs/mllib-pmml-model-export.md +++ b/docs/mllib-pmml-model-export.md @@ -1,21 +1,21 @@ --- layout: global -title: PMML model export - MLlib -displayTitle: <a href="mllib-guide.html">MLlib</a> - PMML model export +title: PMML model export - spark.mllib +displayTitle: PMML model export - spark.mllib --- * Table of contents {:toc} -## MLlib supported models +## `spark.mllib` supported models -MLlib supports model export to Predictive Model Markup Language ([PMML](http://en.wikipedia.org/wiki/Predictive_Model_Markup_Language)). +`spark.mllib` supports model export to Predictive Model Markup Language ([PMML](http://en.wikipedia.org/wiki/Predictive_Model_Markup_Language)). -The table below outlines the MLlib models that can be exported to PMML and their equivalent PMML model. +The table below outlines the `spark.mllib` models that can be exported to PMML and their equivalent PMML model. <table class="table"> <thead> - <tr><th>MLlib model</th><th>PMML model</th></tr> + <tr><th>`spark.mllib` model</th><th>PMML model</th></tr> </thead> <tbody> <tr> diff --git a/docs/mllib-statistics.md b/docs/mllib-statistics.md index de209f68e1..652d215fa8 100644 --- a/docs/mllib-statistics.md +++ b/docs/mllib-statistics.md @@ -1,7 +1,7 @@ --- layout: global -title: Basic Statistics - MLlib -displayTitle: <a href="mllib-guide.html">MLlib</a> - Basic Statistics +title: Basic Statistics - spark.mllib +displayTitle: Basic Statistics - spark.mllib --- * Table of contents @@ -112,7 +112,7 @@ print(summary.numNonzeros()) ## Correlations -Calculating the correlation between two series of data is a common operation in Statistics. In MLlib +Calculating the correlation between two series of data is a common operation in Statistics. In `spark.mllib` we provide the flexibility to calculate pairwise correlations among many series. The supported correlation methods are currently Pearson's and Spearman's correlation. @@ -209,7 +209,7 @@ print(Statistics.corr(data, method="pearson")) ## Stratified sampling -Unlike the other statistics functions, which reside in MLlib, stratified sampling methods, +Unlike the other statistics functions, which reside in `spark.mllib`, stratified sampling methods, `sampleByKey` and `sampleByKeyExact`, can be performed on RDD's of key-value pairs. For stratified sampling, the keys can be thought of as a label and the value as a specific attribute. For example the key can be man or woman, or document ids, and the respective values can be the list of ages @@ -294,12 +294,12 @@ approxSample = data.sampleByKey(False, fractions); ## Hypothesis testing Hypothesis testing is a powerful tool in statistics to determine whether a result is statistically -significant, whether this result occurred by chance or not. MLlib currently supports Pearson's +significant, whether this result occurred by chance or not. `spark.mllib` currently supports Pearson's chi-squared ( $\chi^2$) tests for goodness of fit and independence. The input data types determine whether the goodness of fit or the independence test is conducted. The goodness of fit test requires an input type of `Vector`, whereas the independence test requires a `Matrix` as input. -MLlib also supports the input type `RDD[LabeledPoint]` to enable feature selection via chi-squared +`spark.mllib` also supports the input type `RDD[LabeledPoint]` to enable feature selection via chi-squared independence tests. <div class="codetabs"> @@ -438,7 +438,7 @@ for i, result in enumerate(featureTestResults): </div> -Additionally, MLlib provides a 1-sample, 2-sided implementation of the Kolmogorov-Smirnov (KS) test +Additionally, `spark.mllib` provides a 1-sample, 2-sided implementation of the Kolmogorov-Smirnov (KS) test for equality of probability distributions. By providing the name of a theoretical distribution (currently solely supported for the normal distribution) and its parameters, or a function to calculate the cumulative distribution according to a given theoretical distribution, the user can @@ -522,7 +522,7 @@ print(testResult) # summary of the test including the p-value, test statistic, </div> ### Streaming Significance Testing -MLlib provides online implementations of some tests to support use cases +`spark.mllib` provides online implementations of some tests to support use cases like A/B testing. These tests may be performed on a Spark Streaming `DStream[(Boolean,Double)]` where the first element of each tuple indicates control group (`false`) or treatment group (`true`) and the @@ -550,7 +550,7 @@ provides streaming hypothesis testing. ## Random data generation Random data generation is useful for randomized algorithms, prototyping, and performance testing. -MLlib supports generating random RDDs with i.i.d. values drawn from a given distribution: +`spark.mllib` supports generating random RDDs with i.i.d. values drawn from a given distribution: uniform, standard normal, or Poisson. <div class="codetabs"> |