Bumping version to 0.0.16

Author: igorborgest

README.md

@@ -2,7 +2,7 @@
 
 > Utility belt to handle data on AWS.
 
-[![Release](https://img.shields.io/badge/release-0.0.15-brightgreen.svg)](https://pypi.org/project/awswrangler/)
+[![Release](https://img.shields.io/badge/release-0.0.16-brightgreen.svg)](https://pypi.org/project/awswrangler/)
 [![Downloads](https://img.shields.io/pypi/dm/awswrangler.svg)](https://pypi.org/project/awswrangler/)
 [![Python Version](https://img.shields.io/badge/python-3.6%20%7C%203.7-brightgreen.svg)](https://pypi.org/project/awswrangler/)
 [![Documentation Status](https://readthedocs.org/projects/aws-data-wrangler/badge/?version=latest)](https://aws-data-wrangler.readthedocs.io/en/latest/?badge=latest)
@@ -283,7 +283,10 @@ cluster_id = session.emr.create_cluster(
     spark_jars_path=[f"s3://...jar"],
     maximize_resource_allocation=True,
     keep_cluster_alive_when_no_steps=True,
-    termination_protected=False
+    termination_protected=False,
+    tags={
+        "foo": "boo"
+    }
 )
 print(cluster_id)
 ```

awswrangler/__version__.py

@@ -1,4 +1,4 @@
 __title__ = "awswrangler"
 __description__ = "Utility belt to handle data on AWS."
-__version__ = "0.0.15"
+__version__ = "0.0.16"
 __license__ = "Apache License 2.0"

awswrangler/emr.py

@@ -267,6 +267,10 @@ def _build_cluster_args(**pars):
                 }
             args["Instances"]["InstanceFleets"].append(fleet_task)
 
+        # Tags
+        if pars["tags"] is not None:
+            args["Tags"] = [{"Key": k, "Value": v} for k, v in pars["tags"].items()]
+
         logger.info(f"args: \n{json.dumps(args, default=str, indent=4)}")
         return args
 
@@ -318,7 +322,8 @@ def create_cluster(self,
                        maximize_resource_allocation: bool = False,
                        steps: Optional[List[Dict[str, Collection[str]]]] = None,
                        keep_cluster_alive_when_no_steps: bool = True,
-                       termination_protected: bool = False):
+                       termination_protected: bool = False,
+                       tags: Optional[Dict[str, str]] = None):
         """
         Create a EMR cluster with instance fleets configuration
         https://docs.aws.amazon.com/emr/latest/ManagementGuide/emr-instance-fleet.html
@@ -370,6 +375,7 @@ def create_cluster(self,
         :param steps: Steps definitions (Obs: Use EMR.build_step() to build that)
         :param keep_cluster_alive_when_no_steps: Specifies whether the cluster should remain available after completing all steps
         :param termination_protected: Specifies whether the Amazon EC2 instances in the cluster are protected from termination by API calls, user intervention, or in the event of a job-flow error.
+        :param tags: Key/Value collection to put on the Cluster. (e.g. {"foo": "boo", "bar": "xoo"})
         :return: Cluster ID (string)
         """
         args = EMR._build_cluster_args(**locals())

docs/source/examples.rst

@@ -244,7 +244,10 @@ Create EMR cluster
         spark_jars_path=[f"s3://...jar"],
         maximize_resource_allocation=True,
         keep_cluster_alive_when_no_steps=True,
-        termination_protected=False
+        termination_protected=False,
+        tags={
+            "foo": "boo"
+        }
     )
     print(cluster_id)
 

testing/test_awswrangler/test_emr.py

@@ -133,7 +133,11 @@ def test_cluster_single_node(session, bucket, cloudformation_outputs):
                                             spark_defaults={"spark.default.parallelism": "400"},
                                             maximize_resource_allocation=True,
                                             keep_cluster_alive_when_no_steps=False,
-                                            termination_protected=False)
+                                            termination_protected=False,
+                                            tags={
+                                                "foo": "boo",
+                                                "bar": "xoo"
+                                            })
     sleep(10)
     cluster_state = session.emr.get_cluster_state(cluster_id=cluster_id)
     print(f"cluster_state: {cluster_state}")