def test_run_local():
if Path(ARTIFACTS_PATH).is_dir():
shutil.rmtree(ARTIFACTS_PATH)
task = new_task(name="task-feature-selection",
handler = feature_selection,
params={'k': 2,
'min_votes': 0.3,
'label_column': 'is_error'},
inputs={'df_artifact': 'data/metrics.pq'},
)
run_local(task=task,
artifact_path=os.path.join(os.path.abspath('./'), 'artifacts'))
_validate_paths({'feature_scores.parquet',
'selected_features.parquet'})
def test_run_local_handler():
spec = tag_test(base_spec, "test_run_local_handler")
spec.spec.handler = "my_func"
result = run_local(spec,
command=f"{examples_path}/handler.py",
workdir=examples_path)
verify_state(result)
def test_basics_hyper_parameters(self):
run_object = run_local(
self._basics_task.with_hyper_params({"p2": [5, 2, 3]}, "min.loss"),
command="training.py",
workdir=str(self.assets_path),
)
self._logger.debug("Finished running task",
run_object=run_object.to_dict())
run_uid = run_object.uid()
assert run_uid is not None
assert run_object.state() == "completed"
self._verify_run_outputs(
run_object.outputs,
uid=run_uid,
name="demo",
project=self.project_name,
output_path=self.results_path / run_uid,
accuracy=10,
loss=15,
best_iteration=1,
iteration_results=True,
)
def test_serialization():
spec = tag_test(base_spec, "test_serialization")
result = run_local(spec)
verify_state(result)
pprint(result.to_dict())
print(result.to_yaml())
pprint(result.to_json())
def test_run_local_handler():
spec = tag_test(base_spec, 'test_run_local_handler')
spec.spec.handler = 'my_func'
result = run_local(spec,
command='{}/handler.py'.format(examples_path),
workdir=examples_path)
verify_state(result)
def test_train():
spec = tag_test(base_spec, 'test_run_local_train')
result = run_local(spec,
command='../notebooks/functions/train.py',
workdir='./',
artifact_path='./faces/artifacts')
verify_state(result)
def test_describe_dask_local():
if Path(PLOTS_PATH).is_dir():
shutil.rmtree(PLOTS_PATH)
task = new_task(name="task-describe",
handler=summarize,
inputs={"table": DATA_URL},
params={
'update_dataset': True,
'label_column': 'label',
'dask_function': 'db://default/dask_tests'
})
run_local(task)
_validate_paths({
'corr.html', 'correlation-matrix.csv', 'hist.html', 'imbalance.html',
'imbalance-weights-vec.csv', 'violin.html'
})
def test_run_local_nb():
spec = tag_test(base_spec, 'test_run_local_handler')
spec.spec.handler = 'training'
result = run_local(spec,
command='{}/mlrun_jobs.ipynb'.format(examples_path),
workdir=examples_path)
verify_state(result)
def test_run_local_nb():
spec = tag_test(base_spec, "test_run_local_nb")
spec.spec.handler = "training"
result = run_local(spec,
command=f"{examples_path}/mlrun_jobs.ipynb",
workdir=examples_path)
verify_state(result)
def test_run_local_obj():
spec = tag_test(base_spec, 'test_run_local_handler')
spec.spec.handler = 'training'
nbpath = '{}/mlrun_jobs.ipynb'.format(examples_path)
ymlpath = path.join(out_path, 'nbyaml.yaml')
print('out path:', out_path, ymlpath)
fn = code_to_function(filename=nbpath, kind='job').export(ymlpath)
result = run_local(spec, command=fn, workdir=out_path)
verify_state(result)
def test_inline_code(self):
run_object = run_local(self._inline_task.with_params(p1=7))
self._logger.debug("Finished running task",
run_object=run_object.to_dict())
run_uid = run_object.uid()
assert run_uid is not None
assert run_object.state() == "completed"
def test_run_local_obj():
spec = tag_test(base_spec, "test_run_local_obj")
spec.spec.handler = "training"
nbpath = f"{examples_path}/mlrun_jobs.ipynb"
ymlpath = path.join(out_path, "nbyaml.yaml")
print("out path:", out_path, ymlpath)
fn = code_to_function(filename=nbpath, kind="job").export(ymlpath)
result = run_local(spec, command=fn, workdir=out_path)
verify_state(result)
def test_inline_code_with_param_file(self):
run_object = run_local(
self._inline_task.with_param_file(
str(self.assets_path / "params.csv"), "max.accuracy"))
self._logger.debug("Finished running task",
run_object=run_object.to_dict())
run_uid = run_object.uid()
assert run_uid is not None
assert run_object.state() == "completed"
def test_run_local():
if Path(PLOTS_PATH).is_dir():
shutil.rmtree(PLOTS_PATH)
task = new_task(
name="task-describe",
handler=summarize,
inputs={"table": DATA_URL},
params={
"update_dataset": True,
"label_column": "label"
},
)
run_local(task)
_validate_paths({
"corr.html",
"correlation-matrix.csv",
"hist.html",
"imbalance.html",
"imbalance-weights-vec.csv",
"violin.html",
})
def test_basics(self):
run_object = run_local(self._basics_task,
command="training.py",
workdir=str(self.assets_path))
self._logger.debug("Finished running task",
run_object=run_object.to_dict())
run_uid = run_object.uid()
assert run_uid is not None
self._verify_run_metadata(
run_object.to_dict()["metadata"],
uid=run_uid,
name="demo",
project=self.project_name,
labels={
"v3io_user": self._test_env["V3IO_USERNAME"],
"kind": "",
"owner": self._test_env["V3IO_USERNAME"],
"framework": "sklearn",
},
)
self._verify_run_spec(
run_object.to_dict()["spec"],
parameters={
"p1": 5,
"p2": "a-string"
},
inputs={"infile.txt": str(self.assets_path / "infile.txt")},
outputs=[],
output_path=str(self.results_path / run_uid),
secret_sources=[],
data_stores=[],
scrape_metrics=False,
)
assert run_object.state() == "completed"
self._verify_run_outputs(
run_object.outputs,
uid=run_uid,
name="demo",
project=self.project_name,
output_path=self.results_path / run_uid,
accuracy=10,
loss=15,
)
def test_run_local_with_uid_does_not_exist(monkeypatch):
"""
Mocking a scenario that happened in field in which getuser raised the same error as the mock
The problem was basically that the code was
environ.get("V3IO_USERNAME", getpass.getuser())
instead of
environ.get("V3IO_USERNAME") or getpass.getuser()
"""
def mock_getpwuid_raise(*args, **kwargs):
raise KeyError("getpwuid(): uid not found: 400")
environ["V3IO_USERNAME"] = "******"
monkeypatch.setattr(getpass, "getuser", mock_getpwuid_raise)
spec = tag_test(base_spec, "test_run_local")
result = run_local(spec,
command=f"{examples_path}/training.py",
workdir=examples_path)
verify_state(result)
def custom_setup(self):
self._logger.debug("Connecting to database")
self._logger.debug("Creating dummy task for db queries")
# {{run.uid}} will be substituted with the run id, so output will be written to different directories per run
output_path = str(self.results_path / "{{run.uid}}")
task = (new_task(name="demo",
params={
"p1": 5
},
artifact_path=output_path).with_secrets(
"file",
self.assets_path / "secrets.txt").set_label(
"type", "demo"))
self._logger.debug("Running dummy task")
run_object = run_local(task,
command="training.py",
workdir=str(self.assets_path))
self._logger.debug("Finished running dummy task",
run_object=run_object.to_dict())
self._run_uid = run_object.uid()
def test_db_commands(self):
self._logger.debug("Creating dummy task for db queries")
# {{run.uid}} will be substituted with the run id, so output will be written to different directories per run
output_path = str(self.results_path / "{{run.uid}}")
task = (new_task(name="demo",
params={
"p1": 5
},
artifact_path=output_path).with_secrets(
"file",
self.assets_path / "secrets.txt").set_label(
"type", "demo"))
runs_count_before_run = len(
self._run_db.list_runs(project=self.project_name))
artifacts_count_before_run = len(
self._run_db.list_artifacts(project=self.project_name, tag="*"))
self._logger.debug("Running dummy task")
run_object = run_local(task,
command="training.py",
workdir=str(self.assets_path))
self._logger.debug("Finished running dummy task",
run_object=run_object.to_dict())
self._run_uid = run_object.uid()
runs = self._run_db.list_runs(project=self.project_name)
assert len(runs) == runs_count_before_run + 1
self._verify_run_metadata(
runs[0]["metadata"],
uid=self._run_uid,
name="demo",
project=self.project_name,
labels={
"kind": "",
"framework": "sklearn"
},
)
self._verify_run_spec(
runs[0]["spec"],
parameters={
"p1": 5,
"p2": "a-string"
},
inputs={"infile.txt": str(self.assets_path / "infile.txt")},
outputs=[],
output_path=str(self.results_path / self._run_uid),
secret_sources=[],
data_stores=[],
)
artifacts = self._run_db.list_artifacts(project=self.project_name,
tag="*")
assert len(artifacts) == artifacts_count_before_run + 4
for artifact_key in ["chart", "html_result", "model", "mydf"]:
artifact_exists = False
for artifact in artifacts:
if artifact["key"] == artifact_key:
artifact_exists = True
break
assert artifact_exists
runtimes = self._run_db.list_runtimes()
assert len(runtimes) == len(
mlrun.runtimes.RuntimeKinds.runtime_with_handlers())
for runtime_kind in mlrun.runtimes.RuntimeKinds.runtime_with_handlers(
):
runtime_exists = False
for runtime in runtimes:
if runtime["kind"] == runtime_kind:
runtime_exists = True
break
assert runtime_exists
from os import path
out = mlconf.artifact_path or path.abspath('./data')
# {{run.uid}} will be substituted with the run id, so output will be written to different directoried per run
artifact_path = path.join(out, '{{run.uid}}')
# #### _running and linking multiple tasks_
# In this example we run two functions, ```training``` and ```validation``` and we pass the result from one to the other.
# We will see in the ```job``` example that linking works even when the tasks are run in a workflow on different processes or containers.
# ```run_local()``` will run our task on a local function:
# Run the training function. Functions can have multiple handlers/methods, here we call the ```training``` handler:
# In[ ]:
train_run = run_local(
NewTask(handler=training, params={'p1': 5}, artifact_path=out))
# After the function runs it generates the result widget, you can click the `model` artifact to see its content.
# In[ ]:
train_run.outputs
# The output from the first training function is passed to the validation function, let's run it:
# In[ ]:
model_path = train_run.outputs['model']
validation_run = run_local(
NewTask(handler=validation,
from mlrun import run_local, RunTemplate, NewTask, mlconf
from os import path
mlconf.dbpath = mlconf.dbpath or './'
out = mlconf.artifact_path or path.abspath('./data')
# {{run.uid}} will be substituted with the run id, so output will be written to different directoried per run
artifact_path = path.join(out, '{{run.uid}}')
task = NewTask(name='demo', params={
'p1': 5
}, artifact_path=artifact_path).with_secrets('file', 'secrets.txt').set_label(
'type', 'demo')
# run our task using our new function
run_object = run_local(task, command='training.py')
run_object.uid()
run_object.to_dict()
run_object.state()
run_object.show()
run_object.outputs
run_object.logs()
run_object.artifact('dataset')
def test_run_local():
spec = tag_test(base_spec, "test_run_local")
result = run_local(spec,
command=f"{examples_path}/training.py",
workdir=examples_path)
verify_state(result)
def test_run_local():
spec = tag_test(base_spec, 'test_run_local')
result = run_local(spec,
command='{}/training.py'.format(examples_path),
workdir=examples_path)
verify_state(result)
