Elgato_dark/zeppelin
1
0
Fork 0
mirror of https://github.com/apache/zeppelin synced 2026-05-24 09:38:26 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

[ZEPPELIN-116] renamed add_mahout_interpreters.py and overwrite_existing feature

Browse source
This commit is contained in:
rawkintrevo 2016-11-06 07:54:14 -06:00
parent e7d4e120da
commit ed6eff0f26
3 changed files with 17 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
docs/interpreter/mahout.md
View file

@ -65,6 +65,11 @@ The `add_mahout.py` script contains several command line arguments for advanced
<td>This flag will force the script to re-download the binary even if it already exists. This is useful for previously failed downloads.</td>
<td>NA</td>
</tr>
<tr>
<td>--overwrite_existing</td>
<td>This flag will force the script to overwrite existing `%sparkMahout` and `%flinkMahout` interpreters. Useful when you want to just start over.</td>
<td>NA</td>
</tr>
</table>
__NOTE 1:__ Apache Mahout at this time only supports Spark 1.5 and Spark 1.6 and Scala 2.10. If the user is using another version of Spark (e.g. 2.0), the `%sparkMahout` will likely not work. The `%flinkMahout` interpreter will still work and the user is encouraged to develop with that engine as the code can be ported via copy and paste, as is evidenced by the tutorial notebook.

2
notebook/2BYEZ5EVK/note.json
View file

@ -119,7 +119,7 @@
},
{
"title": "Convenience Paragraph if you started Zeppelin by \u0027bin/zeppelin-daemon.sh start\u0027",
"text": "%sh\npython scripts/mahout/add_mahout.py",
"text": "%sh\npython scripts/mahout/add_mahout_interpreters.py",
"dateUpdated": "Sep 27, 2016 5:26:49 AM",
"config": {
"colWidth": 12.0,

15
scripts/mahout/add_mahout.py → scripts/mahout/add_mahout_interpreters.py
View file

@ -39,6 +39,7 @@ parser.add_argument("--force_download", help="force download Apache Mahout", act
parser.add_argument("--restart_later", help="force download Apache Mahout", action="store_true")
parser.add_argument("--zeppelin_home", help="path to ZEPPELIN_HOME")
parser.add_argument("--mahout_home", help="path to MAHOUT_HOME, use this if you have already installed Apache Mahout")
parser.add_argument("--overwrite_existing", help="if %sparkMahout or %flinkMahout exist, delete them and create new ones. Otherwise Fail.", action="store_true")
args = parser.parse_args()
@ -63,11 +64,17 @@ class ZeppelinTerpWrangler:
return False
return True
def createTerp(self, original_terp_name, new_terp_name ):
def createTerp(self, original_terp_name, new_terp_name, overwrite_existing=True ):
new_terp_id = new_terp_name
if self._terpExists(new_terp_name):
del self.interpreter_json['interpreterSettings'][self._getTerpID(new_terp_name)]
print "Found existing '%s' interpreter..." % new_terp_name
if overwrite_existing:
print "deleting %s from interpreter.json" %new_terp_name
del self.interpreter_json['interpreterSettings'][self._getTerpID(new_terp_name)]
else:
print "exiting program."
exit(1)
orig_terp_id = self._getTerpID(original_terp_name)
@ -235,8 +242,8 @@ else:
#######################################################################################################################
z._readTerpJson()
z.createTerp("spark", "sparkMahout")
z.createTerp("flink", "flinkMahout")
z.createTerp("spark", "sparkMahout", args.overwrite_existing)
z.createTerp("flink", "flinkMahout", args.overwrite_existing)
z.addMahoutConfig("sparkMahout", mahout_home, mahout_version)
z.addMahoutConfig("flinkMahout", mahout_home, mahout_version)
z._writeTerpJson()