Repository: spark Updated Branches: refs/heads/master 661c21049 -> e2ec32dab
[SPARK-15031][EXAMPLES][FOLLOW-UP] Make Python param example working with SparkSession ## What changes were proposed in this pull request? It seems most of Python examples were changed to use SparkSession by https://github.com/apache/spark/pull/12809. This PR said both examples below: - `simple_params_example.py` - `aft_survival_regression.py` are not changed because it dose not work. It seems `aft_survival_regression.py` is changed by https://github.com/apache/spark/pull/13050 but `simple_params_example.py` is not yet. This PR corrects the example and make this use SparkSession. In more detail, it seems `threshold` is replaced to `thresholds` here and there by https://github.com/apache/spark/commit/5a23213c148bfe362514f9c71f5273ebda0a848a. However, when it calls `lr.fit(training, paramMap)` this overwrites the values. So, `threshold` was 5 and `thresholds` becomes 5.5 (by `1 / (1 + thresholds(0) / thresholds(1)`). According to the comment below. this is not allowed, https://github.com/apache/spark/blob/354f8f11bd4b20fa99bd67a98da3525fd3d75c81/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala#L58-L61. So, in this PR, it sets the equivalent value so that this does not throw an exception. ## How was this patch tested? Manully (`mvn package -DskipTests && spark-submit simple_params_example.py`) Author: hyukjinkwon <gurwls...@gmail.com> Closes #13135 from HyukjinKwon/SPARK-15031. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/e2ec32da Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/e2ec32da Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/e2ec32da Branch: refs/heads/master Commit: e2ec32dab8530aa21ec95a27d60b1c22f3d1a18c Parents: 661c210 Author: hyukjinkwon <gurwls...@gmail.com> Authored: Thu May 19 08:52:41 2016 +0200 Committer: Nick Pentreath <ni...@za.ibm.com> Committed: Thu May 19 08:52:41 2016 +0200 ---------------------------------------------------------------------- .../examples/ml/JavaSimpleParamsExample.java | 2 +- .../src/main/python/ml/simple_params_example.py | 24 +++++++++----------- .../spark/examples/ml/SimpleParamsExample.scala | 2 +- 3 files changed, 13 insertions(+), 15 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/e2ec32da/examples/src/main/java/org/apache/spark/examples/ml/JavaSimpleParamsExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaSimpleParamsExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaSimpleParamsExample.java index ff1eb07..ca80d0d 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaSimpleParamsExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaSimpleParamsExample.java @@ -77,7 +77,7 @@ public class JavaSimpleParamsExample { ParamMap paramMap = new ParamMap(); paramMap.put(lr.maxIter().w(20)); // Specify 1 Param. paramMap.put(lr.maxIter(), 30); // This overwrites the original maxIter. - double[] thresholds = {0.45, 0.55}; + double[] thresholds = {0.5, 0.5}; paramMap.put(lr.regParam().w(0.1), lr.thresholds().w(thresholds)); // Specify multiple Params. // One can also combine ParamMaps. http://git-wip-us.apache.org/repos/asf/spark/blob/e2ec32da/examples/src/main/python/ml/simple_params_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/simple_params_example.py b/examples/src/main/python/ml/simple_params_example.py index 2d6d115..c57e59d 100644 --- a/examples/src/main/python/ml/simple_params_example.py +++ b/examples/src/main/python/ml/simple_params_example.py @@ -20,11 +20,10 @@ from __future__ import print_function import pprint import sys -from pyspark import SparkContext from pyspark.ml.classification import LogisticRegression from pyspark.mllib.linalg import DenseVector from pyspark.mllib.regression import LabeledPoint -from pyspark.sql import SQLContext +from pyspark.sql import SparkSession """ A simple example demonstrating ways to specify parameters for Estimators and Transformers. @@ -33,21 +32,20 @@ Run with: """ if __name__ == "__main__": - if len(sys.argv) > 1: - print("Usage: simple_params_example", file=sys.stderr) - exit(1) - sc = SparkContext(appName="PythonSimpleParamsExample") - sqlContext = SQLContext(sc) + spark = SparkSession \ + .builder \ + .appName("SimpleTextClassificationPipeline") \ + .getOrCreate() # prepare training data. # We create an RDD of LabeledPoints and convert them into a DataFrame. # A LabeledPoint is an Object with two fields named label and features # and Spark SQL identifies these fields and creates the schema appropriately. - training = sc.parallelize([ + training = spark.createDataFrame([ LabeledPoint(1.0, DenseVector([0.0, 1.1, 0.1])), LabeledPoint(0.0, DenseVector([2.0, 1.0, -1.0])), LabeledPoint(0.0, DenseVector([2.0, 1.3, 1.0])), - LabeledPoint(1.0, DenseVector([0.0, 1.2, -0.5]))]).toDF() + LabeledPoint(1.0, DenseVector([0.0, 1.2, -0.5]))]) # Create a LogisticRegression instance with maxIter = 10. # This instance is an Estimator. @@ -70,7 +68,7 @@ if __name__ == "__main__": # We may alternatively specify parameters using a parameter map. # paramMap overrides all lr parameters set earlier. - paramMap = {lr.maxIter: 20, lr.thresholds: [0.45, 0.55], lr.probabilityCol: "myProbability"} + paramMap = {lr.maxIter: 20, lr.thresholds: [0.5, 0.5], lr.probabilityCol: "myProbability"} # Now learn a new model using the new parameters. model2 = lr.fit(training, paramMap) @@ -78,10 +76,10 @@ if __name__ == "__main__": pprint.pprint(model2.extractParamMap()) # prepare test data. - test = sc.parallelize([ + test = spark.createDataFrame([ LabeledPoint(1.0, DenseVector([-1.0, 1.5, 1.3])), LabeledPoint(0.0, DenseVector([3.0, 2.0, -0.1])), - LabeledPoint(0.0, DenseVector([0.0, 2.2, -1.5]))]).toDF() + LabeledPoint(0.0, DenseVector([0.0, 2.2, -1.5]))]) # Make predictions on test data using the Transformer.transform() method. # LogisticRegressionModel.transform will only use the 'features' column. @@ -95,4 +93,4 @@ if __name__ == "__main__": print("features=%s,label=%s -> prob=%s, prediction=%s" % (row.features, row.label, row.myProbability, row.prediction)) - sc.stop() + spark.stop() http://git-wip-us.apache.org/repos/asf/spark/blob/e2ec32da/examples/src/main/scala/org/apache/spark/examples/ml/SimpleParamsExample.scala ---------------------------------------------------------------------- diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/SimpleParamsExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/SimpleParamsExample.scala index 3355c8f..29f1f50 100644 --- a/examples/src/main/scala/org/apache/spark/examples/ml/SimpleParamsExample.scala +++ b/examples/src/main/scala/org/apache/spark/examples/ml/SimpleParamsExample.scala @@ -70,7 +70,7 @@ object SimpleParamsExample { // which supports several methods for specifying parameters. val paramMap = ParamMap(lr.maxIter -> 20) paramMap.put(lr.maxIter, 30) // Specify 1 Param. This overwrites the original maxIter. - paramMap.put(lr.regParam -> 0.1, lr.thresholds -> Array(0.45, 0.55)) // Specify multiple Params. + paramMap.put(lr.regParam -> 0.1, lr.thresholds -> Array(0.5, 0.5)) // Specify multiple Params. // One can also combine ParamMaps. val paramMap2 = ParamMap(lr.probabilityCol -> "myProbability") // Change output column name --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
