Github user huaxingao commented on a diff in the pull request: https://github.com/apache/spark/pull/22295#discussion_r223165392 --- Diff: python/pyspark/sql/session.py --- @@ -252,6 +255,20 @@ def newSession(self): """ return self.__class__(self._sc, self._jsparkSession.newSession()) + @classmethod + @since(2.5) + def getActiveSession(cls): + """ + Returns the active SparkSession for the current thread, returned by the builder. + >>> s = SparkSession.getActiveSession() + >>> l = [('Alice', 1)] + >>> rdd = s.sparkContext.parallelize(l) + >>> df = s.createDataFrame(rdd, ['name', 'age']) + >>> df.select("age").collect() + [Row(age=1)] + """ + return cls._activeSession --- End diff -- @HyukjinKwon I am not sure if I follow your suggestion correctly. Does the following look right to you? session.py ``` @classmethod @since(3.0) def getActiveSession(cls): from pyspark.sql import functions return functions.getActiveSession() ``` functions.py ``` @since(3.0) def getActiveSession(): from pyspark.sql import SparkSession sc = SparkContext._active_spark_context if sc is None: sc = SparkContext() if sc._jvm.SparkSession.getActiveSession().isDefined(): SparkSession(sc, sc._jvm.SparkSession.getActiveSession().get()) return SparkSession._activeSession else: return None ```
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org