diff options
| author | Davies Liu <davies@databricks.com> | 2015-11-25 11:11:39 -0800 |
|---|---|---|
| committer | Davies Liu <davies.liu@gmail.com> | 2015-11-25 11:11:39 -0800 |
| commit | dc1d324fdf83e9f4b1debfb277533b002691d71f (patch) | |
| tree | d382bd678fa69c929ac3ca24e8d7e2f229d29256 /sql | |
| parent | 6b781576a15d8d5c5fbed8bef1c5bda95b3d44ac (diff) | |
| download | spark-dc1d324fdf83e9f4b1debfb277533b002691d71f.tar.gz spark-dc1d324fdf83e9f4b1debfb277533b002691d71f.tar.bz2 spark-dc1d324fdf83e9f4b1debfb277533b002691d71f.zip | |
[SPARK-11969] [SQL] [PYSPARK] visualization of SQL query for pyspark
Currently, we does not have visualization for SQL query from Python, this PR fix that.
cc zsxwing
Author: Davies Liu <davies@databricks.com>
Closes #9949 from davies/pyspark_sql_ui.
Diffstat (limited to 'sql')
| -rw-r--r-- | sql/core/src/main/scala/org/apache/spark/sql/DataFrame.scala | 7 | ||||
| -rw-r--r-- | sql/core/src/main/scala/org/apache/spark/sql/execution/python.scala | 12 |
2 files changed, 14 insertions, 5 deletions
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/DataFrame.scala b/sql/core/src/main/scala/org/apache/spark/sql/DataFrame.scala index d8319b9a97..6197f10813 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/DataFrame.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/DataFrame.scala @@ -29,6 +29,7 @@ import org.apache.commons.lang3.StringUtils import org.apache.spark.annotation.{DeveloperApi, Experimental} import org.apache.spark.api.java.JavaRDD +import org.apache.spark.api.python.PythonRDD import org.apache.spark.rdd.RDD import org.apache.spark.sql.catalyst.InternalRow import org.apache.spark.sql.catalyst.analysis._ @@ -1735,6 +1736,12 @@ class DataFrame private[sql]( EvaluatePython.javaToPython(rdd) } + protected[sql] def collectToPython(): Int = { + withNewExecutionId { + PythonRDD.collectAndServe(javaToPython.rdd) + } + } + //////////////////////////////////////////////////////////////////////////// //////////////////////////////////////////////////////////////////////////// // Deprecated methods diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/python.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/python.scala index d611b0011d..defcec95fb 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/python.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/python.scala @@ -121,11 +121,13 @@ object EvaluatePython { def takeAndServe(df: DataFrame, n: Int): Int = { registerPicklers() - val iter = new SerDeUtil.AutoBatchedPickler( - df.queryExecution.executedPlan.executeTake(n).iterator.map { row => - EvaluatePython.toJava(row, df.schema) - }) - PythonRDD.serveIterator(iter, s"serve-DataFrame") + df.withNewExecutionId { + val iter = new SerDeUtil.AutoBatchedPickler( + df.queryExecution.executedPlan.executeTake(n).iterator.map { row => + EvaluatePython.toJava(row, df.schema) + }) + PythonRDD.serveIterator(iter, s"serve-DataFrame") + } } /** |