From d614967b0bad1e6c5277d612602ec0a653a00258 Mon Sep 17 00:00:00 2001 From: Nicholas Chammas Date: Wed, 6 Aug 2014 12:58:24 -0700 Subject: [SPARK-2627] [PySpark] have the build enforce PEP 8 automatically As described in [SPARK-2627](https://issues.apache.org/jira/browse/SPARK-2627), we'd like Python code to automatically be checked for PEP 8 compliance by Jenkins. This pull request aims to do that. Notes: * We may need to install [`pep8`](https://pypi.python.org/pypi/pep8) on the build server. * I'm expecting tests to fail now that PEP 8 compliance is being checked as part of the build. I'm fine with cleaning up any remaining PEP 8 violations as part of this pull request. * I did not understand why the RAT and scalastyle reports are saved to text files. I did the same for the PEP 8 check, but only so that the console output style can match those for the RAT and scalastyle checks. The PEP 8 report is removed right after the check is complete. * Updates to the ["Contributing to Spark"](https://cwiki.apache.org/confluence/display/SPARK/Contributing+to+Spark) guide will be submitted elsewhere, as I don't believe that text is part of the Spark repo. Author: Nicholas Chammas Author: nchammas Closes #1744 from nchammas/master and squashes the following commits: 274b238 [Nicholas Chammas] [SPARK-2627] [PySpark] minor indentation changes 983d963 [nchammas] Merge pull request #5 from apache/master 1db5314 [nchammas] Merge pull request #4 from apache/master 0e0245f [Nicholas Chammas] [SPARK-2627] undo erroneous whitespace fixes bf30942 [Nicholas Chammas] [SPARK-2627] PEP8: comment spacing 6db9a44 [nchammas] Merge pull request #3 from apache/master 7b4750e [Nicholas Chammas] merge upstream changes 91b7584 [Nicholas Chammas] [SPARK-2627] undo unnecessary line breaks 44e3e56 [Nicholas Chammas] [SPARK-2627] use tox.ini to exclude files b09fae2 [Nicholas Chammas] don't wrap comments unnecessarily bfb9f9f [Nicholas Chammas] [SPARK-2627] keep up with the PEP 8 fixes 9da347f [nchammas] Merge pull request #2 from apache/master aa5b4b5 [Nicholas Chammas] [SPARK-2627] follow Spark bash style for if blocks d0a83b9 [Nicholas Chammas] [SPARK-2627] check that pep8 downloaded fine dffb5dd [Nicholas Chammas] [SPARK-2627] download pep8 at runtime a1ce7ae [Nicholas Chammas] [SPARK-2627] space out test report sections 21da538 [Nicholas Chammas] [SPARK-2627] it's PEP 8, not PEP8 6f4900b [Nicholas Chammas] [SPARK-2627] more misc PEP 8 fixes fe57ed0 [Nicholas Chammas] removing merge conflict backups 9c01d4c [nchammas] Merge pull request #1 from apache/master 9a66cb0 [Nicholas Chammas] resolving merge conflicts a31ccc4 [Nicholas Chammas] [SPARK-2627] miscellaneous PEP 8 fixes beaa9ac [Nicholas Chammas] [SPARK-2627] fail check on non-zero status 723ed39 [Nicholas Chammas] always delete the report file 0541ebb [Nicholas Chammas] [SPARK-2627] call Python linter from run-tests 12440fa [Nicholas Chammas] [SPARK-2627] add Scala linter 61c07b9 [Nicholas Chammas] [SPARK-2627] add Python linter 75ad552 [Nicholas Chammas] make check output style consistent --- python/pyspark/mllib/random.py | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'python/pyspark/mllib/random.py') diff --git a/python/pyspark/mllib/random.py b/python/pyspark/mllib/random.py index 36e710dbae..eb496688b6 100644 --- a/python/pyspark/mllib/random.py +++ b/python/pyspark/mllib/random.py @@ -24,7 +24,9 @@ from pyspark.rdd import RDD from pyspark.mllib._common import _deserialize_double, _deserialize_double_vector from pyspark.serializers import NoOpSerializer + class RandomRDDGenerators: + """ Generator methods for creating RDDs comprised of i.i.d samples from some distribution. @@ -53,7 +55,7 @@ class RandomRDDGenerators: True """ jrdd = sc._jvm.PythonMLLibAPI().uniformRDD(sc._jsc, size, numPartitions, seed) - uniform = RDD(jrdd, sc, NoOpSerializer()) + uniform = RDD(jrdd, sc, NoOpSerializer()) return uniform.map(lambda bytes: _deserialize_double(bytearray(bytes))) @staticmethod @@ -77,7 +79,7 @@ class RandomRDDGenerators: True """ jrdd = sc._jvm.PythonMLLibAPI().normalRDD(sc._jsc, size, numPartitions, seed) - normal = RDD(jrdd, sc, NoOpSerializer()) + normal = RDD(jrdd, sc, NoOpSerializer()) return normal.map(lambda bytes: _deserialize_double(bytearray(bytes))) @staticmethod @@ -98,7 +100,7 @@ class RandomRDDGenerators: True """ jrdd = sc._jvm.PythonMLLibAPI().poissonRDD(sc._jsc, mean, size, numPartitions, seed) - poisson = RDD(jrdd, sc, NoOpSerializer()) + poisson = RDD(jrdd, sc, NoOpSerializer()) return poisson.map(lambda bytes: _deserialize_double(bytearray(bytes))) @staticmethod @@ -118,7 +120,7 @@ class RandomRDDGenerators: """ jrdd = sc._jvm.PythonMLLibAPI() \ .uniformVectorRDD(sc._jsc, numRows, numCols, numPartitions, seed) - uniform = RDD(jrdd, sc, NoOpSerializer()) + uniform = RDD(jrdd, sc, NoOpSerializer()) return uniform.map(lambda bytes: _deserialize_double_vector(bytearray(bytes))) @staticmethod @@ -138,7 +140,7 @@ class RandomRDDGenerators: """ jrdd = sc._jvm.PythonMLLibAPI() \ .normalVectorRDD(sc._jsc, numRows, numCols, numPartitions, seed) - normal = RDD(jrdd, sc, NoOpSerializer()) + normal = RDD(jrdd, sc, NoOpSerializer()) return normal.map(lambda bytes: _deserialize_double_vector(bytearray(bytes))) @staticmethod @@ -161,7 +163,7 @@ class RandomRDDGenerators: """ jrdd = sc._jvm.PythonMLLibAPI() \ .poissonVectorRDD(sc._jsc, mean, numRows, numCols, numPartitions, seed) - poisson = RDD(jrdd, sc, NoOpSerializer()) + poisson = RDD(jrdd, sc, NoOpSerializer()) return poisson.map(lambda bytes: _deserialize_double_vector(bytearray(bytes))) -- cgit v1.2.3