Change ksonnet package path for tf-job-operator

[andreyvelich]

Fixes #1885
I Moved tf-job-operator component from kubeflow/core to kubeflow/tf-job-operator.

---

This change is 

[andreyvelich]

/assign @jlewi

[jlewi]

/assign @richardsliu

What do you think we should call the package? "tf-job-operator" just "tf-job"?

[jlewi]

It looks like we use "pytorch-job" so I think "tf-job" would be consistent.

[richardsliu]

Would "tf-job" be confusing since it is also the name of the custom resource?

I would prefer something like "tf-training".

[andreyvelich]

@richardsliu @jlewi
I changed package name to tf-training and kept prototype name to tf-job-operator.
We can install and generate this component like this:

ks pkg install kubeflow/tf-training
ks generate tf-job-operator tf-job-operator

[richardsliu]

@andreyvelich Looks like the minikube e2e test failed:

INFO|2018-11-07T09:44:10|util.py:41| Running: ks generate tf-job-operator tf-job-operator
cwd=/mnt/test-data-volume/kubeflow-presubmit-kubeflow-e2e-minikube-1920-34fe7c8-4250-117d/kubeflow-test-3657
INFO|2018-11-07T09:44:10|util.py:56| Subprocess output:
INFO|2018-11-07T09:44:10|util.py:62| level=error msg="no prototype names matched 'tf-job-operator'"
ERROR|2018-11-07T09:44:11|test_helper.py:101| Subprocess failed;
level=error msg="no prototype names matched 'tf-job-operator'"
Traceback (most recent call last):
 File "/mnt/test-data-volume/kubeflow-presubmit-kubeflow-e2e-minikube-1920-34fe7c8-4250-117d/src/kubeflow/testing/py/kubeflow/testing/test_helper.py", line 99, in wrap_test
   test_case.test_func(test_case)
 File "/mnt/test-data-volume/kubeflow-presubmit-kubeflow-e2e-minikube-1920-34fe7c8-4250-117d/src/kubeflow/kubeflow/testing/deploy_kubeflow.py", line 63, in deploy_kubeflow
   cwd=app_dir)
 File "/mnt/test-data-volume/kubeflow-presubmit-kubeflow-e2e-minikube-1920-34fe7c8-4250-117d/src/kubeflow/testing/py/kubeflow/testing/util.py", line 74, in run
   " ".join(command), process.returncode), "\n".join(output))
CalledProcessError: Command 'cmd: ks generate tf-job-operator tf-job-operator exited with code 1' returned non-zero exit status 1

[andreyvelich]

@richardsliu I fixed it.

[richardsliu]

Thanks for fixing this.
/lgtm
/approve

[k8s-ci-robot]

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: richardsliu

The full list of commands accepted by this bot can be found here.

The pull request process is described here

Needs approval from an approver in each of these files:

• OWNERS [richardsliu]

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment