diff options
author | Joseph K. Bradley <joseph@databricks.com> | 2015-02-25 16:13:17 -0800 |
---|---|---|
committer | Xiangrui Meng <meng@databricks.com> | 2015-02-25 16:13:17 -0800 |
commit | d20559b157743981b9c09e286f2aaff8cbefab59 (patch) | |
tree | 6d92015c1ae6b05c725860685351f86b8c4ed6af /docs/mllib-decision-tree.md | |
parent | 46a044a36a2aff1306f7f677e952ce253ddbefac (diff) | |
download | spark-d20559b157743981b9c09e286f2aaff8cbefab59.tar.gz spark-d20559b157743981b9c09e286f2aaff8cbefab59.tar.bz2 spark-d20559b157743981b9c09e286f2aaff8cbefab59.zip |
[SPARK-5974] [SPARK-5980] [mllib] [python] [docs] Update ML guide with save/load, Python GBT
* Add GradientBoostedTrees Python examples to ML guide
* I ran these in the pyspark shell, and they worked.
* Add save/load to examples in ML guide
* Added note to python docs about predict,transform not working within RDD actions,transformations in some cases (See SPARK-5981)
CC: mengxr
Author: Joseph K. Bradley <joseph@databricks.com>
Closes #4750 from jkbradley/SPARK-5974 and squashes the following commits:
c410e38 [Joseph K. Bradley] Added note to LabeledPoint about attributes
bcae18b [Joseph K. Bradley] Added import of models for save/load examples in ml guide. Fixed line length for tree.py, feature.py (but not other ML Pyspark files yet).
6d81c3e [Joseph K. Bradley] completed python GBT examples
9903309 [Joseph K. Bradley] Added note to python docs about predict,transform not working within RDD actions,transformations in some cases
c7dfad8 [Joseph K. Bradley] Added model save/load to ML guide. Added GBT examples to ML guide
Diffstat (limited to 'docs/mllib-decision-tree.md')
-rw-r--r-- | docs/mllib-decision-tree.md | 20 |
1 files changed, 20 insertions, 0 deletions
diff --git a/docs/mllib-decision-tree.md b/docs/mllib-decision-tree.md index 6675133a81..4695d1cde4 100644 --- a/docs/mllib-decision-tree.md +++ b/docs/mllib-decision-tree.md @@ -194,6 +194,7 @@ maximum tree depth of 5. The test error is calculated to measure the algorithm a <div data-lang="scala"> {% highlight scala %} import org.apache.spark.mllib.tree.DecisionTree +import org.apache.spark.mllib.tree.model.DecisionTreeModel import org.apache.spark.mllib.util.MLUtils // Load and parse the data file. @@ -221,6 +222,9 @@ val labelAndPreds = testData.map { point => val testErr = labelAndPreds.filter(r => r._1 != r._2).count.toDouble / testData.count() println("Test Error = " + testErr) println("Learned classification tree model:\n" + model.toDebugString) + +model.save("myModelPath") +val sameModel = DecisionTreeModel.load("myModelPath") {% endhighlight %} </div> @@ -279,10 +283,16 @@ Double testErr = }).count() / testData.count(); System.out.println("Test Error: " + testErr); System.out.println("Learned classification tree model:\n" + model.toDebugString()); + +model.save("myModelPath"); +DecisionTreeModel sameModel = DecisionTreeModel.load("myModelPath"); {% endhighlight %} </div> <div data-lang="python"> + +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 from pyspark.mllib.tree import DecisionTree @@ -324,6 +334,7 @@ depth of 5. The Mean Squared Error (MSE) is computed at the end to evaluate <div data-lang="scala"> {% highlight scala %} import org.apache.spark.mllib.tree.DecisionTree +import org.apache.spark.mllib.tree.model.DecisionTreeModel import org.apache.spark.mllib.util.MLUtils // Load and parse the data file. @@ -350,6 +361,9 @@ val labelsAndPredictions = testData.map { point => val testMSE = labelsAndPredictions.map{ case(v, p) => math.pow((v - p), 2)}.mean() println("Test Mean Squared Error = " + testMSE) println("Learned regression tree model:\n" + model.toDebugString) + +model.save("myModelPath") +val sameModel = DecisionTreeModel.load("myModelPath") {% endhighlight %} </div> @@ -414,10 +428,16 @@ Double testMSE = }) / data.count(); System.out.println("Test Mean Squared Error: " + testMSE); System.out.println("Learned regression tree model:\n" + model.toDebugString()); + +model.save("myModelPath"); +DecisionTreeModel sameModel = DecisionTreeModel.load("myModelPath"); {% endhighlight %} </div> <div data-lang="python"> + +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 from pyspark.mllib.tree import DecisionTree |