diff options
| -rw-r--r-- | python/pyspark/sql/dataframe.py | 23 |
1 files changed, 20 insertions, 3 deletions
diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py index 841724095f..388033d385 100644 --- a/python/pyspark/sql/dataframe.py +++ b/python/pyspark/sql/dataframe.py @@ -244,8 +244,25 @@ class DataFrame(object): debugging purpose. If extended is False, only prints the physical plan. - """ - self._jdf.explain(extended) + + >>> df.explain() + PhysicalRDD [age#0,name#1], MapPartitionsRDD[...] at mapPartitions at SQLContext.scala:... + + >>> df.explain(True) + == Parsed Logical Plan == + ... + == Analyzed Logical Plan == + ... + == Optimized Logical Plan == + ... + == Physical Plan == + ... + == RDD == + """ + if extended: + print self._jdf.queryExecution().toString() + else: + print self._jdf.queryExecution().executedPlan().toString() def isLocal(self): """ @@ -1034,7 +1051,7 @@ def _test(): Row(name='Bob', age=5, height=85)]).toDF() (failure_count, test_count) = doctest.testmod( pyspark.sql.dataframe, globs=globs, - optionflags=doctest.ELLIPSIS | doctest.NORMALIZE_WHITESPACE) + optionflags=doctest.ELLIPSIS | doctest.NORMALIZE_WHITESPACE | doctest.REPORT_NDIFF) globs['sc'].stop() if failure_count: exit(-1) |