Github user holdenk commented on a diff in the pull request:
https://github.com/apache/spark/pull/13599#discussion_r122558038
--- Diff: python/pyspark/context.py ---
@@ -980,6 +996,33 @@ def getConf(self):
conf.setAll(self._conf.getAll())
return conf
+ def install_packages(self, packages, install_driver=True):
+ """
+ install python packages on all executors and driver through pip
+ :param packages: string for single package or a list of string for
multiple packages
+ :param install_driver: whether to install packages in client
+ """
+ if self._conf.get("spark.pyspark.virtualenv.enabled") != "true":
+ raise Exception("install_packages can only use called when "
+ "spark.pyspark.virtualenv.enabled set as true")
+ if isinstance(packages, basestring):
+ packages = [packages]
+ num_executors = int(self._conf.get("spark.executor.instances"))
+ dummyRDD = self.parallelize(range(num_executors), num_executors)
--- End diff --
This is not guaranteed to work, and overlooks the situation of having
executors added.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
