From dce43d73394a656a6cdff99bd0d68fdf16823f3e Mon Sep 17 00:00:00 2001 From: Ram Sriharsha Date: Fri, 22 May 2015 13:18:08 -0700 Subject: [PATCH] [SPARK-7574] [ML] [DOC] User guide for OneVsRest Including Iris Dataset (after shuffling and relabeling 3 -> 0 to confirm to 0 -> numClasses-1 labeling). Could not find an existing dataset in data/mllib for multiclass classification. Author: Ram Sriharsha Closes #6296 from harsha2010/SPARK-7574 and squashes the following commits: 645427c [Ram Sriharsha] cleanup 46c41b1 [Ram Sriharsha] cleanup 2f76295 [Ram Sriharsha] Code Review Fixes ebdf103 [Ram Sriharsha] Java Example c026613 [Ram Sriharsha] Code Review fixes 4b7d1a6 [Ram Sriharsha] minor cleanup 13bed9c [Ram Sriharsha] add wikipedia link bb9dbfa [Ram Sriharsha] Clean up naming 6f90db1 [Ram Sriharsha] [SPARK-7574][ml][doc] User guide for OneVsRest --- .../sample_multiclass_classification_data.txt | 150 ++++++++++++++++++ docs/ml-ensembles.md | 129 +++++++++++++++ docs/ml-guide.md | 3 +- 3 files changed, 281 insertions(+), 1 deletion(-) create mode 100644 data/mllib/sample_multiclass_classification_data.txt create mode 100644 docs/ml-ensembles.md diff --git a/data/mllib/sample_multiclass_classification_data.txt b/data/mllib/sample_multiclass_classification_data.txt new file mode 100644 index 0000000000000..a0d7f90113919 --- /dev/null +++ b/data/mllib/sample_multiclass_classification_data.txt @@ -0,0 +1,150 @@ +1 1:-0.222222 2:0.5 3:-0.762712 4:-0.833333 +1 1:-0.555556 2:0.25 3:-0.864407 4:-0.916667 +1 1:-0.722222 2:-0.166667 3:-0.864407 4:-0.833333 +1 1:-0.722222 2:0.166667 3:-0.694915 4:-0.916667 +0 1:0.166667 2:-0.416667 3:0.457627 4:0.5 +1 1:-0.833333 3:-0.864407 4:-0.916667 +2 1:-1.32455e-07 2:-0.166667 3:0.220339 4:0.0833333 +2 1:-1.32455e-07 2:-0.333333 3:0.0169491 4:-4.03573e-08 +1 1:-0.5 2:0.75 3:-0.830508 4:-1 +0 1:0.611111 3:0.694915 4:0.416667 +0 1:0.222222 2:-0.166667 3:0.423729 4:0.583333 +1 1:-0.722222 2:-0.166667 3:-0.864407 4:-1 +1 1:-0.5 2:0.166667 3:-0.864407 4:-0.916667 +2 1:-0.222222 2:-0.333333 3:0.0508474 4:-4.03573e-08 +2 1:-0.0555556 2:-0.833333 3:0.0169491 4:-0.25 +2 1:-0.166667 2:-0.416667 3:-0.0169491 4:-0.0833333 +1 1:-0.944444 3:-0.898305 4:-0.916667 +2 1:-0.277778 2:-0.583333 3:-0.0169491 4:-0.166667 +0 1:0.111111 2:-0.333333 3:0.38983 4:0.166667 +2 1:-0.222222 2:-0.166667 3:0.0847457 4:-0.0833333 +0 1:0.166667 2:-0.333333 3:0.559322 4:0.666667 +1 1:-0.611111 2:0.0833333 3:-0.864407 4:-0.916667 +2 1:-0.333333 2:-0.583333 3:0.0169491 4:-4.03573e-08 +0 1:0.555555 2:-0.166667 3:0.661017 4:0.666667 +2 1:0.166667 3:0.186441 4:0.166667 +2 1:0.111111 2:-0.75 3:0.152542 4:-4.03573e-08 +2 1:0.166667 2:-0.25 3:0.118644 4:-4.03573e-08 +0 1:-0.0555556 2:-0.833333 3:0.355932 4:0.166667 +0 1:-0.277778 2:-0.333333 3:0.322034 4:0.583333 +2 1:-0.222222 2:-0.5 3:-0.152542 4:-0.25 +2 1:-0.111111 3:0.288136 4:0.416667 +2 1:-0.0555556 2:-0.25 3:0.186441 4:0.166667 +2 1:0.333333 2:-0.166667 3:0.355932 4:0.333333 +1 1:-0.611111 2:0.25 3:-0.898305 4:-0.833333 +0 1:0.166667 2:-0.333333 3:0.559322 4:0.75 +0 1:0.111111 2:-0.25 3:0.559322 4:0.416667 +0 1:0.833333 2:-0.166667 3:0.898305 4:0.666667 +2 1:-0.277778 2:-0.166667 3:0.186441 4:0.166667 +0 1:-0.666667 2:-0.583333 3:0.186441 4:0.333333 +1 1:-0.666667 2:-0.0833334 3:-0.830508 4:-1 +1 1:-0.166667 2:0.666667 3:-0.932203 4:-0.916667 +0 1:0.0555554 2:-0.333333 3:0.288136 4:0.416667 +1 1:-0.666667 2:-0.0833334 3:-0.830508 4:-1 +1 1:-0.833333 2:0.166667 3:-0.864407 4:-0.833333 +0 1:0.0555554 2:0.166667 3:0.491525 4:0.833333 +0 1:0.722222 2:-0.333333 3:0.728813 4:0.5 +2 1:-0.166667 2:-0.416667 3:0.0508474 4:-0.25 +2 1:0.5 3:0.254237 4:0.0833333 +0 1:0.111111 2:-0.583333 3:0.355932 4:0.5 +1 1:-0.944444 2:-0.166667 3:-0.898305 4:-0.916667 +2 1:0.277778 2:-0.25 3:0.220339 4:-4.03573e-08 +0 1:0.666667 2:-0.25 3:0.79661 4:0.416667 +0 1:0.111111 2:0.0833333 3:0.694915 4:1 +0 1:0.444444 3:0.59322 4:0.833333 +2 1:-0.0555556 2:0.166667 3:0.186441 4:0.25 +1 1:-0.833333 2:0.333333 3:-1 4:-0.916667 +1 1:-0.555556 2:0.416667 3:-0.830508 4:-0.75 +2 1:-0.333333 2:-0.5 3:0.152542 4:-0.0833333 +1 1:-1 2:-0.166667 3:-0.966102 4:-1 +1 1:-0.333333 2:0.25 3:-0.898305 4:-0.916667 +2 1:0.388889 2:-0.333333 3:0.288136 4:0.0833333 +2 1:0.277778 2:-0.166667 3:0.152542 4:0.0833333 +0 1:0.333333 2:0.0833333 3:0.59322 4:0.666667 +1 1:-0.777778 3:-0.79661 4:-0.916667 +1 1:-0.444444 2:0.416667 3:-0.830508 4:-0.916667 +0 1:0.222222 2:-0.166667 3:0.627119 4:0.75 +1 1:-0.555556 2:0.5 3:-0.79661 4:-0.916667 +1 1:-0.555556 2:0.5 3:-0.694915 4:-0.75 +2 1:-1.32455e-07 2:-0.25 3:0.254237 4:0.0833333 +1 1:-0.5 2:0.25 3:-0.830508 4:-0.916667 +0 1:0.166667 3:0.457627 4:0.833333 +2 1:0.444444 2:-0.0833334 3:0.322034 4:0.166667 +0 1:0.111111 2:0.166667 3:0.559322 4:0.916667 +1 1:-0.611111 2:0.25 3:-0.79661 4:-0.583333 +0 1:0.388889 3:0.661017 4:0.833333 +1 1:-0.722222 2:0.166667 3:-0.79661 4:-0.916667 +1 1:-0.722222 2:-0.0833334 3:-0.79661 4:-0.916667 +1 1:-0.555556 2:0.166667 3:-0.830508 4:-0.916667 +2 1:-0.666667 2:-0.666667 3:-0.220339 4:-0.25 +2 1:-0.611111 2:-0.75 3:-0.220339 4:-0.25 +2 1:0.0555554 2:-0.833333 3:0.186441 4:0.166667 +0 1:-0.166667 2:-0.416667 3:0.38983 4:0.5 +0 1:0.611111 2:0.333333 3:0.728813 4:1 +2 1:0.0555554 2:-0.25 3:0.118644 4:-4.03573e-08 +1 1:-0.666667 2:-0.166667 3:-0.864407 4:-0.916667 +1 1:-0.833333 2:-0.0833334 3:-0.830508 4:-0.916667 +0 1:0.611111 2:-0.166667 3:0.627119 4:0.25 +0 1:0.888889 2:0.5 3:0.932203 4:0.75 +2 1:0.222222 2:-0.333333 3:0.220339 4:0.166667 +1 1:-0.555556 2:0.25 3:-0.864407 4:-0.833333 +0 1:-1.32455e-07 2:-0.166667 3:0.322034 4:0.416667 +0 1:-1.32455e-07 2:-0.5 3:0.559322 4:0.0833333 +1 1:-0.611111 3:-0.932203 4:-0.916667 +1 1:-0.333333 2:0.833333 3:-0.864407 4:-0.916667 +0 1:-0.166667 2:-0.333333 3:0.38983 4:0.916667 +2 1:-0.333333 2:-0.666667 3:-0.0847458 4:-0.25 +2 1:-0.0555556 2:-0.416667 3:0.38983 4:0.25 +1 1:-0.388889 2:0.416667 3:-0.830508 4:-0.916667 +0 1:0.444444 2:-0.0833334 3:0.38983 4:0.833333 +1 1:-0.611111 2:0.333333 3:-0.864407 4:-0.916667 +0 1:0.111111 2:-0.416667 3:0.322034 4:0.416667 +0 1:0.166667 2:-0.0833334 3:0.525424 4:0.416667 +2 1:0.333333 2:-0.0833334 3:0.152542 4:0.0833333 +0 1:-0.0555556 2:-0.166667 3:0.288136 4:0.416667 +0 1:-0.166667 2:-0.416667 3:0.38983 4:0.5 +1 1:-0.611111 2:0.166667 3:-0.830508 4:-0.916667 +0 1:0.888889 2:-0.166667 3:0.728813 4:0.833333 +2 1:-0.277778 2:-0.25 3:-0.118644 4:-4.03573e-08 +2 1:-0.222222 2:-0.333333 3:0.186441 4:-4.03573e-08 +0 1:0.333333 2:-0.583333 3:0.627119 4:0.416667 +0 1:0.444444 2:-0.0833334 3:0.491525 4:0.666667 +2 1:-0.222222 2:-0.25 3:0.0847457 4:-4.03573e-08 +1 1:-0.611111 2:0.166667 3:-0.79661 4:-0.75 +2 1:-0.277778 2:-0.166667 3:0.0508474 4:-4.03573e-08 +0 1:1 2:0.5 3:0.830508 4:0.583333 +2 1:-0.333333 2:-0.666667 3:-0.0508475 4:-0.166667 +2 1:-0.277778 2:-0.416667 3:0.0847457 4:-4.03573e-08 +0 1:0.888889 2:-0.333333 3:0.932203 4:0.583333 +2 1:-0.111111 2:-0.166667 3:0.0847457 4:0.166667 +2 1:0.111111 2:-0.583333 3:0.322034 4:0.166667 +0 1:0.333333 2:0.0833333 3:0.59322 4:1 +0 1:0.222222 2:-0.166667 3:0.525424 4:0.416667 +1 1:-0.555556 2:0.5 3:-0.830508 4:-0.833333 +0 1:-0.111111 2:-0.166667 3:0.38983 4:0.416667 +0 1:0.888889 2:-0.5 3:1 4:0.833333 +1 1:-0.388889 2:0.583333 3:-0.898305 4:-0.75 +2 1:0.111111 2:0.0833333 3:0.254237 4:0.25 +0 1:0.333333 2:-0.166667 3:0.423729 4:0.833333 +1 1:-0.388889 2:0.166667 3:-0.762712 4:-0.916667 +0 1:0.333333 2:-0.0833334 3:0.559322 4:0.916667 +2 1:-0.333333 2:-0.75 3:0.0169491 4:-4.03573e-08 +1 1:-0.222222 2:1 3:-0.830508 4:-0.75 +1 1:-0.388889 2:0.583333 3:-0.762712 4:-0.75 +2 1:-0.611111 2:-1 3:-0.152542 4:-0.25 +2 1:-1.32455e-07 2:-0.333333 3:0.254237 4:-0.0833333 +2 1:-0.5 2:-0.416667 3:-0.0169491 4:0.0833333 +1 1:-0.888889 2:-0.75 3:-0.898305 4:-0.833333 +1 1:-0.666667 2:-0.0833334 3:-0.830508 4:-1 +2 1:-0.555556 2:-0.583333 3:-0.322034 4:-0.166667 +2 1:-0.166667 2:-0.5 3:0.0169491 4:-0.0833333 +1 1:-0.555556 2:0.0833333 3:-0.762712 4:-0.666667 +1 1:-0.777778 3:-0.898305 4:-0.916667 +0 1:0.388889 2:-0.166667 3:0.525424 4:0.666667 +0 1:0.222222 3:0.38983 4:0.583333 +2 1:0.333333 2:-0.0833334 3:0.254237 4:0.166667 +2 1:-0.388889 2:-0.166667 3:0.186441 4:0.166667 +0 1:-0.222222 2:-0.583333 3:0.355932 4:0.583333 +1 1:-0.611111 2:-0.166667 3:-0.79661 4:-0.916667 +1 1:-0.944444 2:-0.25 3:-0.864407 4:-0.916667 +1 1:-0.388889 2:0.166667 3:-0.830508 4:-0.75 diff --git a/docs/ml-ensembles.md b/docs/ml-ensembles.md new file mode 100644 index 0000000000000..9ff50e95fc479 --- /dev/null +++ b/docs/ml-ensembles.md @@ -0,0 +1,129 @@ +--- +layout: global +title: Ensembles +displayTitle: ML - Ensembles +--- + +**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. +The Pipelines API supports the following ensemble algorithms: [`OneVsRest`](api/scala/index.html#org.apache.spark.ml.classifier.OneVsRest) + +## OneVsRest + +[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. + +`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. + +
+
+{% highlight scala %} +import org.apache.spark.ml.classification.{LogisticRegression, OneVsRest} +import org.apache.spark.mllib.evaluation.MulticlassMetrics +import org.apache.spark.mllib.util.MLUtils +import org.apache.spark.sql.{Row, SQLContext} + +val sqlContext = new SQLContext(sc) + +// parse data into dataframe +val data = MLUtils.loadLibSVMFile(sc, + "data/mllib/sample_multiclass_classification_data.txt") +val Array(train, test) = data.toDF().randomSplit(Array(0.7, 0.3)) + +// instantiate multiclass learner and train +val ovr = new OneVsRest().setClassifier(new LogisticRegression) + +val ovrModel = ovr.fit(train) + +// score model on test data +val predictions = ovrModel.transform(test).select("prediction", "label") +val predictionsAndLabels = predictions.map {case Row(p: Double, l: Double) => (p, l)} + +// compute confusion matrix +val metrics = new MulticlassMetrics(predictionsAndLabels) +println(metrics.confusionMatrix) + +// the Iris DataSet has three classes +val numClasses = 3 + +println("label\tfpr\n") +(0 until numClasses).foreach { index => + val label = index.toDouble + println(label + "\t" + metrics.falsePositiveRate(label)) +} +{% endhighlight %} +
+
+{% highlight java %} + +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.ml.classification.LogisticRegression; +import org.apache.spark.ml.classification.OneVsRest; +import org.apache.spark.ml.classification.OneVsRestModel; +import org.apache.spark.mllib.evaluation.MulticlassMetrics; +import org.apache.spark.mllib.linalg.Matrix; +import org.apache.spark.mllib.regression.LabeledPoint; +import org.apache.spark.mllib.util.MLUtils; +import org.apache.spark.rdd.RDD; +import org.apache.spark.sql.DataFrame; +import org.apache.spark.sql.SQLContext; + +SparkConf conf = new SparkConf().setAppName("JavaOneVsRestExample"); +JavaSparkContext jsc = new JavaSparkContext(conf); +SQLContext jsql = new SQLContext(jsc); + +RDD data = MLUtils.loadLibSVMFile(jsc.sc(), + "data/mllib/sample_multiclass_classification_data.txt"); + +DataFrame dataFrame = jsql.createDataFrame(data, LabeledPoint.class); +DataFrame[] splits = dataFrame.randomSplit(new double[]{0.7, 0.3}, 12345); +DataFrame train = splits[0]; +DataFrame test = splits[1]; + +// instantiate the One Vs Rest Classifier +OneVsRest ovr = new OneVsRest().setClassifier(new LogisticRegression()); + +// train the multiclass model +OneVsRestModel ovrModel = ovr.fit(train.cache()); + +// score the model on test data +DataFrame predictions = ovrModel + .transform(test) + .select("prediction", "label"); + +// obtain metrics +MulticlassMetrics metrics = new MulticlassMetrics(predictions); +Matrix confusionMatrix = metrics.confusionMatrix(); + +// output the Confusion Matrix +System.out.println("Confusion Matrix"); +System.out.println(confusionMatrix); + +// compute the false positive rate per label +System.out.println(); +System.out.println("label\tfpr\n"); + +// the Iris DataSet has three classes +int numClasses = 3; +for (int index = 0; index < numClasses; index++) { + double label = (double) index; + System.out.print(label); + System.out.print("\t"); + System.out.print(metrics.falsePositiveRate(label)); + System.out.println(); +} +{% endhighlight %} +
+
diff --git a/docs/ml-guide.md b/docs/ml-guide.md index cac705683c8bc..c5f50ed7990f1 100644 --- a/docs/ml-guide.md +++ b/docs/ml-guide.md @@ -150,11 +150,12 @@ This is useful if there are two algorithms with the `maxIter` parameter in a `Pi # Algorithm Guides -There are now several algorithms in the Pipelines API which are not in the lower-level MLlib API, so we link to documentation for them here. These algorithms are mostly feature transformers, which fit naturally into the `Transformer` abstraction in Pipelines. +There are now several algorithms in the Pipelines API which are not in the lower-level MLlib API, so we link to documentation for them here. These algorithms are mostly feature transformers, which fit naturally into the `Transformer` abstraction in Pipelines, and ensembles, which fit naturally into the `Estimator` abstraction in the Pipelines. **Pipelines API Algorithm Guides** * [Feature Extraction, Transformation, and Selection](ml-features.html) +* [Ensembles](ml-ensembles.html) # Code Examples