Repository: spark Updated Branches: refs/heads/master 184de91d1 -> 201291335
[SPARK-8308] [MLLIB] add missing save load for python example jira: https://issues.apache.org/jira/browse/SPARK-8308 1. add some missing save/load in python examples. , LogisticRegression, LinearRegression and NaiveBayes 2. tune down iterations for MatrixFactorization, since current number will trigger StackOverflow for default java configuration (>1M) Author: Yuhao Yang <hhb...@gmail.com> Closes #6760 from hhbyyh/docUpdate and squashes the following commits: 9bd3383 [Yuhao Yang] update scala example 8a44692 [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into docUpdate 077cbb8 [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into docUpdate 3e948dc [Yuhao Yang] add missing save load for python example Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/20129133 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/20129133 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/20129133 Branch: refs/heads/master Commit: 2012913355993e6516e4c81dbc92e579977131da Parents: 184de91 Author: Yuhao Yang <hhb...@gmail.com> Authored: Wed Jul 1 11:17:56 2015 -0700 Committer: Joseph K. Bradley <jos...@databricks.com> Committed: Wed Jul 1 11:17:56 2015 -0700 ---------------------------------------------------------------------- docs/mllib-collaborative-filtering.md | 6 +++--- docs/mllib-linear-methods.md | 12 ++++++++++-- docs/mllib-naive-bayes.md | 6 +++++- 3 files changed, 18 insertions(+), 6 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/20129133/docs/mllib-collaborative-filtering.md ---------------------------------------------------------------------- diff --git a/docs/mllib-collaborative-filtering.md b/docs/mllib-collaborative-filtering.md index dfdf621..eedc234 100644 --- a/docs/mllib-collaborative-filtering.md +++ b/docs/mllib-collaborative-filtering.md @@ -77,7 +77,7 @@ val ratings = data.map(_.split(',') match { case Array(user, item, rate) => // Build the recommendation model using ALS val rank = 10 -val numIterations = 20 +val numIterations = 10 val model = ALS.train(ratings, rank, numIterations, 0.01) // Evaluate the model on rating data @@ -149,7 +149,7 @@ public class CollaborativeFiltering { // Build the recommendation model using ALS int rank = 10; - int numIterations = 20; + int numIterations = 10; MatrixFactorizationModel model = ALS.train(JavaRDD.toRDD(ratings), rank, numIterations, 0.01); // Evaluate the model on rating data @@ -210,7 +210,7 @@ ratings = data.map(lambda l: l.split(',')).map(lambda l: Rating(int(l[0]), int(l # Build the recommendation model using Alternating Least Squares rank = 10 -numIterations = 20 +numIterations = 10 model = ALS.train(ratings, rank, numIterations) # Evaluate the model on training data http://git-wip-us.apache.org/repos/asf/spark/blob/20129133/docs/mllib-linear-methods.md ---------------------------------------------------------------------- diff --git a/docs/mllib-linear-methods.md b/docs/mllib-linear-methods.md index 2a2a7c1..3927d65 100644 --- a/docs/mllib-linear-methods.md +++ b/docs/mllib-linear-methods.md @@ -499,7 +499,7 @@ Note that the Python API does not yet support multiclass classification and mode will in the future. {% highlight python %} -from pyspark.mllib.classification import LogisticRegressionWithLBFGS +from pyspark.mllib.classification import LogisticRegressionWithLBFGS, LogisticRegressionModel from pyspark.mllib.regression import LabeledPoint from numpy import array @@ -518,6 +518,10 @@ model = LogisticRegressionWithLBFGS.train(parsedData) labelsAndPreds = parsedData.map(lambda p: (p.label, model.predict(p.features))) trainErr = labelsAndPreds.filter(lambda (v, p): v != p).count() / float(parsedData.count()) print("Training Error = " + str(trainErr)) + +# Save and load model +model.save(sc, "myModelPath") +sameModel = LogisticRegressionModel.load(sc, "myModelPath") {% endhighlight %} </div> </div> @@ -668,7 +672,7 @@ values. We compute the mean squared error at the end to evaluate Note that the Python API does not yet support model save/load but will in the future. {% highlight python %} -from pyspark.mllib.regression import LabeledPoint, LinearRegressionWithSGD +from pyspark.mllib.regression import LabeledPoint, LinearRegressionWithSGD, LinearRegressionModel from numpy import array # Load and parse the data @@ -686,6 +690,10 @@ model = LinearRegressionWithSGD.train(parsedData) valuesAndPreds = parsedData.map(lambda p: (p.label, model.predict(p.features))) MSE = valuesAndPreds.map(lambda (v, p): (v - p)**2).reduce(lambda x, y: x + y) / valuesAndPreds.count() print("Mean Squared Error = " + str(MSE)) + +# Save and load model +model.save(sc, "myModelPath") +sameModel = LinearRegressionModel.load(sc, "myModelPath") {% endhighlight %} </div> </div> http://git-wip-us.apache.org/repos/asf/spark/blob/20129133/docs/mllib-naive-bayes.md ---------------------------------------------------------------------- diff --git a/docs/mllib-naive-bayes.md b/docs/mllib-naive-bayes.md index bf6d124..e73bd30 100644 --- a/docs/mllib-naive-bayes.md +++ b/docs/mllib-naive-bayes.md @@ -119,7 +119,7 @@ used for evaluation and prediction. Note that the Python API does not yet support model save/load but will in the future. {% highlight python %} -from pyspark.mllib.classification import NaiveBayes +from pyspark.mllib.classification import NaiveBayes, NaiveBayesModel from pyspark.mllib.linalg import Vectors from pyspark.mllib.regression import LabeledPoint @@ -140,6 +140,10 @@ model = NaiveBayes.train(training, 1.0) # Make prediction and test accuracy. predictionAndLabel = test.map(lambda p : (model.predict(p.features), p.label)) accuracy = 1.0 * predictionAndLabel.filter(lambda (x, v): x == v).count() / test.count() + +# Save and load model +model.save(sc, "myModelPath") +sameModel = NaiveBayesModel.load(sc, "myModelPath") {% endhighlight %} </div> --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
