def test_validate_json_valid_inputs():
"""
Unit test to check the validate_json function with valid inputs
"""
json_object = {
"name": "workspace-name",
"resource_group": "resource-group-name",
"create_workspace": False,
"friendly_name": "friendly-name",
"create_resource_group": True,
"location": "location",
"sku": "basic",
"storage_account":
"Microsoft.Storage/storageAccounts/<your-storage-account-name>",
"key_vault": "Microsoft.KeyVault/vaults/<your-key-vault-name>",
"app_insights":
"Microsoft.Insights/components/<your-app-insights-name>",
"container_registry":
"Microsoft.ContainerRegistry/registries/<your-container-registry-name>",
"cmk_key_vault": "Microsoft.KeyVault/vaults/<your-key-vault-name>",
"resource_cmk_uri": "https://<your-cmk-uri>",
"hbi_workspace": False
}
validate_json(data=json_object,
schema=parameters_schema,
input_name="PARAMETERS_FILE")
def test_validate_json_valid_inputs():
"""
Unit test to check the validate_json function with valid inputs
"""
json_object = {
"model_name": "model-name",
"model_file_name": "model-file-name",
"model_framework": "onnx",
"metrics_min": []
}
validate_json(data=json_object,
schema=parameters_schema,
input_name="PARAMETERS_FILE")
def check_if_agents_exist(context, orb_tags, status):
context.agent_name = generate_random_string_with_predefined_prefix(
agent_name_prefix)
context.orb_tags = create_tags_set(orb_tags)
context.agent = create_agent(context.token, context.agent_name,
context.orb_tags)
context.agent_key = context.agent["key"]
token = context.token
run_local_agent_container(context, "available")
agent_id = context.agent['id']
existing_agents = get_agent(token, agent_id)
assert_that(len(existing_agents), greater_than(0), "Agent not created")
timeout = 30
agent_status = wait_until_expected_agent_status(token,
agent_id,
status,
timeout=timeout)
context.agent = get_agent(token, agent_id)
logs = get_orb_agent_logs(context.container_id)
assert_that(
agent_status, is_(equal_to(status)),
f"Agent did not get '{status}' after {str(timeout)} seconds, but was '{agent_status}'. \n"
f"Agent: {json.dumps(context.agent, indent=4)}. \n Logs: {logs}")
local_orb_path = configs.get("local_orb_path")
agent_schema_path = local_orb_path + "/python-test/features/steps/schemas/agent_schema.json"
is_schema_valid = validate_json(context.agent, agent_schema_path)
assert_that(
is_schema_valid, equal_to(True),
f"Invalid agent json. \n Agent = {context.agent}."
f"Agent logs: {get_orb_agent_logs(context.container_id)}."
f"\nLogs: {logs}")
def create_invalid_sink(context, credential):
assert_that(
credential,
any_of(equal_to('endpoint'), equal_to('username'),
equal_to('password')), "Invalid prometheus field")
check_prometheus_grafana_credentials(context)
sink_label_name = sink_label_name_prefix + random_string(10)
token = context.token
prometheus_credentials = {
'endpoint': context.remote_prometheus_endpoint,
'username': context.prometheus_username,
'password': context.prometheus_key
}
prometheus_credentials[credential] = prometheus_credentials[
credential][:-2]
context.sink = create_new_sink(token, sink_label_name,
prometheus_credentials['endpoint'],
prometheus_credentials['username'],
prometheus_credentials['password'])
local_orb_path = configs.get("local_orb_path")
sink_schema_path = local_orb_path + "/python-test/features/steps/schemas/sink_schema.json"
is_schema_valid = validate_json(context.sink, sink_schema_path)
assert_that(is_schema_valid, equal_to(True),
f"Invalid sink json. \n Sink = {context.sink}")
context.existent_sinks_id.append(context.sink['id'])
def check_agent_backend_pktvisor_routes(context, route):
assert_that(
route,
any_of(equal_to("taps"), equal_to("handlers"), equal_to("inputs"),
equal_to("backends")), "Invalid agent route")
agent_backend_routes = {
"backends": "backends",
"taps": "backends/pktvisor/taps",
"inputs": "backends/pktvisor/inputs",
"handlers": "backends/pktvisor/handlers"
}
response = requests.get(
orb_url + '/api/v1/agents/' + agent_backend_routes[route],
headers={'Authorization': f'Bearer {context.token}'})
assert_that(
response.status_code, equal_to(200),
f"Request to get {route} route failed with status =" +
str(response.status_code))
local_orb_path = configs.get("local_orb_path")
route_schema_path = local_orb_path + f"/python-test/features/steps/schemas/{route}_schema.json"
is_schema_valid = validate_json(response.json(), route_schema_path)
assert_that(is_schema_valid, equal_to(True),
f"Invalid route json. \n Route = {route}")
def divide_data(dfile, ofolder):
jdata = load_json(dfile)
if not validate_json(jdata):
print("Invalid JSON data: ignoring %s" % dfile)
return False
n = len(jdata[0])
assert len(jdata) == 2 and len(jdata[1]) == n
#identify all dims
int_ixs, int_vals = [], []
for i in range(n):
var = jdata[0][i]
val = jdata[1][i]
if is_int(val) and val >= 2:
to_divide_ixs = get_arrays_to_divide(n, jdata, val)
if to_divide_ixs is not None:
jd1 = copy.deepcopy(jdata)
jd2 = copy.deepcopy(jdata)
jd1[1][i] = int(val / 2)
jd2[1][i] = val - int(val / 2)
for j in to_divide_ixs:
jd1[1][j] = jd1[1][j][:int(val / 2)]
jd2[1][j] = jd2[1][j][int(val / 2):]
write_to_folder(ofolder, jd1, jd2, dfile)
return True
print("Cannot divide this dataset! :(")
print_shape(jdata)
return False
def ordoro_madness(api_url):
'''
Main function to initiate fetching parsing login data.
'''
res = requests.get(api_url,
params={},
headers={},
verify=False)
if res.ok and utils.validate_json(res.text):
master_data = utils.marshal_data(res.json().get("data"))
print "# Uniques Total {0}".format(len(master_data.get("uniques")))
for unique in master_data.get("uniques"):
print unique
print "# domains with > 1 user"
for domain in master_data.get("domains"):
print domain
print "# April Logins {0}".format(len(master_data.get("april_logins")))
for login in master_data.get("april_logins"):
print login
else:
logging.error("Bad Request or Invalid json.")
raise
return master_data
def test_validate_json_invalid_json():
"""
Unit test to check the validate_json function with invalid json_object inputs
"""
json_object = {"sku": ""}
with pytest.raises(AMLConfigurationException):
assert validate_json(data=json_object,
schema=parameters_schema,
input_name="PARAMETERS_FILE")
async def main():
sub = await get_redis_client()
pub = await get_redis_client()
(pattern, ) = await sub.subscribe(
config["CHANNELS"]["CAM-RES"]
) # read all channels prefixed with `SOME_`
while await pattern.wait_message():
data = await pattern.get()
validate_json(json.loads(data))
message = json.loads(data.decode())
img = base64.b64decode(message["data"].encode())
img = np.frombuffer(img, dtype=np.float64)
# run model inference here
print(img.tolist()[0:30])
# change out message once inference is implemented
await pub.publish(config["CHANNELS"]["FC-OUT"], data)
await asyncio.sleep(1)
def test_validate_json_incorrect_field():
"""
Unit test to check if field incorrect
"""
json_object = {
"name": "workspace-name",
"resour_group": "resource-group-name",
}
with pytest.raises(AMLConfigurationException):
assert validate_json(data=json_object,
schema=parameters_schema,
input_name="PARAMETERS_FILE")
async def main():
pub = await get_redis_client()
loop = asyncio.get_event_loop()
while True:
if TEST:
await asyncio.sleep(5)
data = config["TEST-MSG"]["IMG-TEST"]
else:
data = await loop.run_in_executor(None, device.read_until)
msg = json.loads(data)
if validate_json(msg):
await pub.publish(config["CHANNELS"]["FC-IN"], data)
else:
print(f"Invalid serial in {msg}")
def create_sink(context):
sink_label_name = sink_label_name_prefix + random_string(10)
token = context.token
endpoint = context.remote_prometheus_endpoint
username = context.prometheus_username
password = context.prometheus_key
context.sink = create_new_sink(token, sink_label_name, endpoint, username,
password)
local_orb_path = configs.get("local_orb_path")
sink_schema_path = local_orb_path + "/python-test/features/steps/schemas/sink_schema.json"
is_schema_valid = validate_json(context.sink, sink_schema_path)
assert_that(is_schema_valid, equal_to(True),
f"Invalid sink json. \n Sink = {context.sink}")
context.existent_sinks_id.append(context.sink['id'])
def function_create():
with utils.AtomicRequest() as atomic:
function_id = uuid.uuid4().hex
atomic.driver_endpoint = driver_endpoint
user, tenant = utils.get_headers(request)
zip_file = utils.get_zip(request)
zip_url = utils.upload_zip(function_id, zip_file)
if not zip_url:
atomic.errors = True
return critical_error('Not able to store zip.')
atomic.zip_url = zip_url
metadata = utils.get_metadata(request)
if not utils.validate_json(utils.build_schema, metadata):
atomic.errors = True
return bad_request("Error validating json.")
tag = "{0}_{1}_{2}".format(tenant, user, metadata.get('name'))
payload = {
"memory": metadata.get('memory'),
"tags": [tag],
"runtime": metadata.get('runtime'),
"zip_location": zip_url,
"name": metadata.get('name')
}
image_id = utils.create_image(driver_endpoint, payload)
atomic.image_id = image_id
function = utils.create_function(tenant, user, function_id, image_id,
zip_url, tag, metadata)
if not function:
atomic.errors = True
return critical_error('Error building the function.')
return Response(function_id, status=201)
def generate_group_with_valid_json(token, agent_group_name, group_description,
tags_to_group, agent_groups):
"""
Create a group and validate the json schema
:param (str) token: used for API authentication
:param (str) agent_group_name: of the agent group to be created
:param (str) group_description: description of group
:param (dict) tags_to_group: dict with all pairs key:value that will be used as tags
:returns: (dict) a dictionary containing the created agent group data
:return: agent group data
"""
agent_group_data = create_agent_group(token, agent_group_name,
group_description, tags_to_group)
group_id = agent_group_data['id']
agent_groups[group_id] = agent_group_name
local_orb_path = configs.get("local_orb_path")
agent_group_schema_path = local_orb_path + "/python-test/features/steps/schemas/groups_schema.json"
is_schema_valid = validate_json(agent_group_data, agent_group_schema_path)
assert_that(is_schema_valid, equal_to(True),
f"Invalid group json. \n Group = {agent_group_data}")
return agent_group_data
def main():
# Loading azure credentials
print("::debug::Loading azure credentials")
azure_credentials = os.environ.get("INPUT_AZURE_CREDENTIALS", default="{}")
try:
azure_credentials = json.loads(azure_credentials)
except JSONDecodeError:
print(
"::error::Please paste output of `az ad sp create-for-rbac --name <your-sp-name> --role contributor --scopes /subscriptions/<your-subscriptionId>/resourceGroups/<your-rg> --sdk-auth` as value of secret variable: AZURE_CREDENTIALS"
)
raise AMLConfigurationException(
"Incorrect or poorly formed output from azure credentials saved in AZURE_CREDENTIALS secret. See setup in https://github.com/Azure/aml-workspace/blob/master/README.md"
)
# Checking provided parameters
print("::debug::Checking provided parameters")
validate_json(data=azure_credentials,
schema=azure_credentials_schema,
input_name="AZURE_CREDENTIALS")
# Mask values
print("::debug::Masking parameters")
mask_parameter(parameter=azure_credentials.get("tenantId", ""))
mask_parameter(parameter=azure_credentials.get("clientId", ""))
mask_parameter(parameter=azure_credentials.get("clientSecret", ""))
mask_parameter(parameter=azure_credentials.get("subscriptionId", ""))
# Loading parameters file
print("::debug::Loading parameters file")
parameters_file = os.environ.get("INPUT_PARAMETERS_FILE",
default="run.json")
parameters_file_path = os.path.join(".cloud", ".azure", parameters_file)
try:
with open(parameters_file_path) as f:
parameters = json.load(f)
except FileNotFoundError:
print(
f"::debug::Could not find parameter file in {parameters_file_path}. Please provide a parameter file in your repository if you do not want to use default settings (e.g. .cloud/.azure/run.json)."
)
parameters = {}
# Checking provided parameters
print("::debug::Checking provided parameters")
validate_json(data=parameters,
schema=parameters_schema,
input_name="PARAMETERS_FILE")
# Define target cloud
if azure_credentials.get(
"resourceManagerEndpointUrl",
"").startswith("https://management.usgovcloudapi.net"):
cloud = "AzureUSGovernment"
elif azure_credentials.get(
"resourceManagerEndpointUrl",
"").startswith("https://management.chinacloudapi.cn"):
cloud = "AzureChinaCloud"
else:
cloud = "AzureCloud"
# Loading Workspace
print("::debug::Loading AML Workspace")
sp_auth = ServicePrincipalAuthentication(
tenant_id=azure_credentials.get("tenantId", ""),
service_principal_id=azure_credentials.get("clientId", ""),
service_principal_password=azure_credentials.get("clientSecret", ""),
cloud=cloud)
config_file_path = os.environ.get("GITHUB_WORKSPACE",
default=".cloud/.azure")
config_file_name = "aml_arm_config.json"
try:
ws = Workspace.from_config(path=config_file_path,
_file_name=config_file_name,
auth=sp_auth)
except AuthenticationException as exception:
print(
f"::error::Could not retrieve user token. Please paste output of `az ad sp create-for-rbac --name <your-sp-name> --role contributor --scopes /subscriptions/<your-subscriptionId>/resourceGroups/<your-rg> --sdk-auth` as value of secret variable: AZURE_CREDENTIALS: {exception}"
)
raise AuthenticationException
except AuthenticationError as exception:
print(f"::error::Microsoft REST Authentication Error: {exception}")
raise AuthenticationError
except AdalError as exception:
print(
f"::error::Active Directory Authentication Library Error: {exception}"
)
raise AdalError
except ProjectSystemException as exception:
print(f"::error::Workspace authorizationfailed: {exception}")
raise ProjectSystemException
# Create experiment
print("::debug::Creating experiment")
try:
# Default experiment name
repository_name = os.environ.get("GITHUB_REPOSITORY").split("/")[-1]
branch_name = os.environ.get("GITHUB_REF").split("/")[-1]
default_experiment_name = f"{repository_name}-{branch_name}"
experiment = Experiment(
workspace=ws,
name=parameters.get("experiment_name",
default_experiment_name)[:36])
except TypeError as exception:
experiment_name = parameters.get("experiment", None)
print(
f"::error::Could not create an experiment with the specified name {experiment_name}: {exception}"
)
raise AMLExperimentConfigurationException(
f"Could not create an experiment with the specified name {experiment_name}: {exception}"
)
except UserErrorException as exception:
experiment_name = parameters.get("experiment", None)
print(
f"::error::Could not create an experiment with the specified name {experiment_name}: {exception}"
)
raise AMLExperimentConfigurationException(
f"Could not create an experiment with the specified name {experiment_name}: {exception}"
)
# Loading run config
print("::debug::Loading run config")
run_config = None
if run_config is None:
# Loading run config from runconfig yaml file
print("::debug::Loading run config from runconfig yaml file")
run_config = load_runconfig_yaml(runconfig_yaml_file=parameters.get(
"runconfig_yaml_file", "code/train/run_config.yml"))
if run_config is None:
# Loading run config from pipeline yaml file
print("::debug::Loading run config from pipeline yaml file")
run_config = load_pipeline_yaml(workspace=ws,
pipeline_yaml_file=parameters.get(
"pipeline_yaml_file",
"code/train/pipeline.yml"))
if run_config is None:
# Loading run config from python runconfig file
print("::debug::Loading run config from python runconfig file")
run_config = load_runconfig_python(
workspace=ws,
runconfig_python_file=parameters.get("runconfig_python_file",
"code/train/run_config.py"),
runconfig_python_function_name=parameters.get(
"runconfig_python_function_name", "main"))
if run_config is None:
# Loading values for errors
pipeline_yaml_file = parameters.get("pipeline_yaml_file",
"code/train/pipeline.yml")
runconfig_yaml_file = parameters.get("runconfig_yaml_file",
"code/train/run_config.yml")
runconfig_python_file = parameters.get("runconfig_python_file",
"code/train/run_config.py")
runconfig_python_function_name = parameters.get(
"runconfig_python_function_name", "main")
print(
f"::error::Error when loading runconfig yaml definition your repository (Path: /{runconfig_yaml_file})."
)
print(
f"::error::Error when loading pipeline yaml definition your repository (Path: /{pipeline_yaml_file})."
)
print(
f"::error::Error when loading python script or function in your repository which defines the experiment config (Script path: '/{runconfig_python_file}', Function: '{runconfig_python_function_name}()')."
)
print(
"::error::You have to provide either a yaml definition for your run, a yaml definition of your pipeline or a python script, which returns a runconfig (Pipeline, ScriptRunConfig, AutoMlConfig, Estimator, etc.). Please read the documentation for more details."
)
raise AMLExperimentConfigurationException(
"You have to provide a yaml definition for your run, a yaml definition of your pipeline or a python script, which returns a runconfig. Please read the documentation for more details."
)
# Submit run config
print("::debug::Submitting experiment config")
try:
# Defining default tags
print("::debug::Defining default tags")
default_tags = {
"GITHUB_ACTOR": os.environ.get("GITHUB_ACTOR"),
"GITHUB_REPOSITORY": os.environ.get("GITHUB_REPOSITORY"),
"GITHUB_SHA": os.environ.get("GITHUB_SHA"),
"GITHUB_REF": os.environ.get("GITHUB_REF")
}
run = experiment.submit(config=run_config,
tags=dict(parameters.get("tags", {}),
**default_tags))
except AzureMLException as exception:
print(
f"::error::Could not submit experiment config. Your script passed object of type {type(run_config)}. Object must be correctly configured and of type e.g. estimator, pipeline, etc.: {exception}"
)
raise AMLExperimentConfigurationException(
f"Could not submit experiment config. Your script passed object of type {type(run_config)}. Object must be correctly configured and of type e.g. estimator, pipeline, etc.: {exception}"
)
except TypeError as exception:
print(
f"::error::Could not submit experiment config. Your script passed object of type {type(run_config)}. Object must be correctly configured and of type e.g. estimator, pipeline, etc.: {exception}"
)
raise AMLExperimentConfigurationException(
f"Could not submit experiment config. Your script passed object of type {type(run_config)}. Object must be correctly configured and of type e.g. estimator, pipeline, etc.: {exception}"
)
# Create outputs
print("::debug::Creating outputs")
print(f"::set-output name=experiment_name::{run.experiment.name}")
print(f"::set-output name=run_id::{run.id}")
print(f"::set-output name=run_url::{run.get_portal_url()}")
# Waiting for run to complete
print("::debug::Waiting for run to complete")
if parameters.get("wait_for_completion", True):
run.wait_for_completion(show_output=True)
# Creating additional outputs of finished run
run_metrics = run.get_metrics(recursive=True)
print(f"::set-output name=run_metrics::{run_metrics}")
run_metrics_markdown = convert_to_markdown(run_metrics)
print(
f"::set-output name=run_metrics_markdown::{run_metrics_markdown}")
# Download artifacts if enabled
if parameters.get("download_artifacts", False):
# Defining artifacts folder
print("::debug::Defining artifacts folder")
root_path = os.environ.get("GITHUB_WORKSPACE", default=None)
folder_name = f"aml_artifacts_{run.id}"
artifact_path = os.path.join(root_path, folder_name)
# Downloading artifacts
print("::debug::Downloading artifacts")
run.download_files(
output_directory=os.path.join(artifact_path, "parent"))
children = run.get_children(recursive=True)
for i, child in enumerate(children):
child.download_files(
output_directory=os.path.join(artifact_path, f"child_{i}"))
# Creating additional outputs
print(f"::set-output name=artifact_path::{artifact_path}")
# Publishing pipeline
print("::debug::Publishing pipeline")
if type(run) is PipelineRun and parameters.get("publish_pipeline", False):
# Default pipeline name
repository_name = os.environ.get("GITHUB_REPOSITORY").split("/")[-1]
branch_name = os.environ.get("GITHUB_REF").split("/")[-1]
default_pipeline_name = f"{repository_name}-{branch_name}"
published_pipeline = run.publish_pipeline(
name=parameters.get("pipeline_name", default_pipeline_name),
description="Pipeline registered by GitHub Run Action",
version=parameters.get("pipeline_version", None),
continue_on_step_failure=parameters.get(
"pipeline_continue_on_step_failure", False))
# Creating additional outputs
print(
f"::set-output name=published_pipeline_id::{published_pipeline.id}"
)
print(
f"::set-output name=published_pipeline_status::{published_pipeline.status}"
)
print(
f"::set-output name=published_pipeline_endpoint::{published_pipeline.endpoint}"
)
elif parameters.get("publish_pipeline", False):
print(
"::error::Could not register pipeline because you did not pass a pipeline to the action"
)
print("::debug::Successfully finished Azure Machine Learning Train Action")
def main():
# Loading azure credentials
print("::debug::Loading azure credentials")
azure_credentials = os.environ.get("INPUT_AZURE_CREDENTIALS", default="{}")
try:
azure_credentials = json.loads(azure_credentials)
except JSONDecodeError:
print(
"::error::Please paste output of `az ad sp create-for-rbac --name <your-sp-name> --role contributor --scopes /subscriptions/<your-subscriptionId>/resourceGroups/<your-rg> --sdk-auth` as value of secret variable: AZURE_CREDENTIALS. The JSON should include the following keys: 'tenantId', 'clientId', 'clientSecret' and 'subscriptionId'."
)
raise AMLConfigurationException(
"Incorrect or poorly formed output from azure credentials saved in AZURE_CREDENTIALS secret. See setup in https://github.com/Azure/aml-workspace/blob/master/README.md"
)
# Checking provided parameters
print("::debug::Checking provided parameters")
validate_json(data=azure_credentials,
schema=azure_credentials_schema,
input_name="AZURE_CREDENTIALS")
# Mask values
print("::debug::Masking parameters")
mask_parameter(parameter=azure_credentials.get("tenantId", ""))
mask_parameter(parameter=azure_credentials.get("clientId", ""))
mask_parameter(parameter=azure_credentials.get("clientSecret", ""))
mask_parameter(parameter=azure_credentials.get("subscriptionId", ""))
# Loading parameters file
print("::debug::Loading parameters file")
parameters_file = os.environ.get("INPUT_PARAMETERS_FILE",
default="compute.json")
parameters_file_path = os.path.join(".cloud", ".azure", parameters_file)
try:
with open(parameters_file_path) as f:
parameters = json.load(f)
except FileNotFoundError:
print(
f"::debug::Could not find parameter file in {parameters_file_path}. Please provide a parameter file in your repository if you do not want to use default settings (e.g. .cloud/.azure/compute.json)."
)
parameters = {}
# Checking provided parameters
print("::debug::Checking provided parameters")
validate_json(data=parameters,
schema=parameters_schema,
input_name="PARAMETERS_FILE")
# Define target cloud
if azure_credentials.get(
"resourceManagerEndpointUrl",
"").startswith("https://management.usgovcloudapi.net"):
cloud = "AzureUSGovernment"
elif azure_credentials.get(
"resourceManagerEndpointUrl",
"").startswith("https://management.chinacloudapi.cn"):
cloud = "AzureChinaCloud"
else:
cloud = "AzureCloud"
# Loading Workspace
print("::debug::Loading AML Workspace")
sp_auth = ServicePrincipalAuthentication(
tenant_id=azure_credentials.get("tenantId", ""),
service_principal_id=azure_credentials.get("clientId", ""),
service_principal_password=azure_credentials.get("clientSecret", ""),
cloud=cloud)
config_file_path = os.environ.get("GITHUB_WORKSPACE",
default=".cloud/.azure")
config_file_name = "aml_arm_config.json"
try:
ws = Workspace.from_config(path=config_file_path,
_file_name=config_file_name,
auth=sp_auth)
except AuthenticationException as exception:
print(
f"::error::Could not retrieve user token. Please paste output of `az ad sp create-for-rbac --name <your-sp-name> --role contributor --scopes /subscriptions/<your-subscriptionId>/resourceGroups/<your-rg> --sdk-auth` as value of secret variable: AZURE_CREDENTIALS: {exception}"
)
raise AuthenticationException
except AuthenticationError as exception:
print(f"::error::Microsoft REST Authentication Error: {exception}")
raise AuthenticationError
except AdalError as exception:
print(
f"::error::Active Directory Authentication Library Error: {exception}"
)
raise AdalError
except ProjectSystemException as exception:
print(f"::error::Workspace authorizationfailed: {exception}")
raise ProjectSystemException
# Loading compute target
try:
# Default compute target name
repository_name = os.environ.get("GITHUB_REPOSITORY").split(
"/")[-1][:16] # names can be max 16 characters
print("::debug::Loading existing compute target")
compute_target = ComputeTarget(workspace=ws,
name=parameters.get(
"name", repository_name))
print(
f"::debug::Found compute target with same name. Not updating the compute target: {compute_target.serialize()}"
)
except ComputeTargetException:
print(
"::debug::Could not find existing compute target with provided name"
)
# Checking provided parameters
print("::debug::Checking provided parameters")
required_parameters_provided(
parameters=parameters,
keys=["compute_type"],
message=
"Required parameter(s) not found in your parameters file for creating a compute target. Please provide a value for the following key(s): "
)
print("::debug::Creating new compute target")
compute_type = parameters.get("compute_type", "")
print(f"::debug::Compute type listed is{compute_type}")
if compute_type == "amlcluster":
compute_target = create_aml_cluster(workspace=ws,
parameters=parameters)
print(
f"::debug::Successfully created AML cluster: {compute_target.serialize()}"
)
elif compute_type == "akscluster":
compute_target = create_aks_cluster(workspace=ws,
parameters=parameters)
print(
f"::debug::Successfully created AKS cluster: {compute_target.serialize()}"
)
else:
print(f"::error::Compute type '{compute_type}' is not supported")
raise AMLConfigurationException(
f"Compute type '{compute_type}' is not supported.")
print(
"::debug::Successfully finished Azure Machine Learning Compute Action")
def main():
# Loading azure credentials
print("::debug::Loading azure credentials")
azure_credentials = os.environ.get("INPUT_AZURE_CREDENTIALS", default="{}")
try:
azure_credentials = json.loads(azure_credentials)
except JSONDecodeError:
print("::error::Please paste output of `az ad sp create-for-rbac --name <your-sp-name> --role contributor --scopes /subscriptions/<your-subscriptionId>/resourceGroups/<your-rg> --sdk-auth` as value of secret variable: AZURE_CREDENTIALS")
raise AMLConfigurationException(
"Incorrect or poorly formed output from azure credentials saved in AZURE_CREDENTIALS secret. See setup in https://github.com/Azure/aml-workspace/blob/master/README.md")
# Checking provided parameters
print("::debug::Checking provided parameters")
validate_json(
data=azure_credentials,
schema=azure_credentials_schema,
input_name="AZURE_CREDENTIALS"
)
# Mask values
print("::debug::Masking parameters")
mask_parameter(parameter=azure_credentials.get("tenantId", ""))
mask_parameter(parameter=azure_credentials.get("clientId", ""))
mask_parameter(parameter=azure_credentials.get("clientSecret", ""))
mask_parameter(parameter=azure_credentials.get("subscriptionId", ""))
# Loading parameters file
print("::debug::Loading parameters file")
parameters_file = os.environ.get(
"INPUT_PARAMETERS_FILE", default="run.json")
parameters_file_path = os.path.join(".cloud", ".azure", parameters_file)
try:
with open(parameters_file_path) as f:
parameters = json.load(f)
except FileNotFoundError:
print(
f"::debug::Could not find parameter file in {parameters_file_path}. Please provide a parameter file in your repository if you do not want to use default settings (e.g. .cloud/.azure/run.json).")
parameters = {}
# Checking provided parameters
print("::debug::Checking provided parameters")
validate_json(
data=parameters,
schema=parameters_schema,
input_name="PARAMETERS_FILE"
)
# Define target cloud
if azure_credentials.get("resourceManagerEndpointUrl", "").startswith("https://management.usgovcloudapi.net"):
cloud = "AzureUSGovernment"
elif azure_credentials.get("resourceManagerEndpointUrl", "").startswith("https://management.chinacloudapi.cn"):
cloud = "AzureChinaCloud"
else:
cloud = "AzureCloud"
# Loading Workspace
print("::debug::Loading AML Workspace")
sp_auth = ServicePrincipalAuthentication(
tenant_id=azure_credentials.get("tenantId", ""),
service_principal_id=azure_credentials.get("clientId", ""),
service_principal_password=azure_credentials.get("clientSecret", ""),
cloud=cloud
)
config_file_path = os.environ.get(
"GITHUB_WORKSPACE", default=".cloud/.azure")
config_file_name = "aml_arm_config.json"
try:
ws = Workspace.from_config(
path=config_file_path,
_file_name=config_file_name,
auth=sp_auth
)
except AuthenticationException as exception:
print(
f"::error::Could not retrieve user token. Please paste output of `az ad sp create-for-rbac --name <your-sp-name> --role contributor --scopes /subscriptions/<your-subscriptionId>/resourceGroups/<your-rg> --sdk-auth` as value of secret variable: AZURE_CREDENTIALS: {exception}")
raise AuthenticationException
except AuthenticationError as exception:
print(f"::error::Microsoft REST Authentication Error: {exception}")
raise AuthenticationError
except AdalError as exception:
print(
f"::error::Active Directory Authentication Library Error: {exception}")
raise AdalError
except ProjectSystemException as exception:
print(f"::error::Workspace authorizationfailed: {exception}")
raise ProjectSystemException
# Create experiment
print("::debug::Creating experiment")
try:
# Default experiment name
repository_name = os.environ.get("GITHUB_REPOSITORY").split("/")[-1]
branch_name = os.environ.get("GITHUB_REF").split("/")[-1]
default_experiment_name = f"{repository_name}-{branch_name}"
experiment = Experiment(
workspace=ws,
name=parameters.get("experiment_name",
default_experiment_name)[:36]
)
except TypeError as exception:
experiment_name = parameters.get("experiment", None)
print(
f"::error::Could not create an experiment with the specified name {experiment_name}: {exception}")
raise AMLExperimentConfigurationException(
f"Could not create an experiment with the specified name {experiment_name}: {exception}")
except UserErrorException as exception:
experiment_name = parameters.get("experiment", None)
print(
f"::error::Could not create an experiment with the specified name {experiment_name}: {exception}")
raise AMLExperimentConfigurationException(
f"Could not create an experiment with the specified name {experiment_name}: {exception}")
# Reading the dataset
print("::debug::Reading the dataset")
ds_workspace = Workspace(
'aeefecca-6f22-4523-93ba-bd49686ea0ce', 'mshack-azureml', 'ms-hack')
train = Dataset.get_by_name(ds_workspace, name='HistogramTrain')
test = Dataset.get_by_name(ds_workspace, name='HistogramTest')
label_column_name = 'class'
# Setting AutoML config
print("::debug::Setting AutoML config")
automl_settings = {
"primary_metric": 'accuracy',
"verbosity": logging.INFO,
"enable_stack_ensemble": True
}
compute_target = ComputeTarget(ws, 'githubcluster')
automl_config = AutoMLConfig(task='classification',
debug_log='automl_errors.log',
compute_target=compute_target,
training_data=train,
validation_data=test,
experiment_timeout_hours=.25,
label_column_name=label_column_name,
**automl_settings
)
# Submit run config
print("::debug::Submitting experiment config")
try:
# Defining default tags
print("::debug::Defining default tags")
default_tags = {
"GITHUB_ACTOR": os.environ.get("GITHUB_ACTOR"),
"GITHUB_REPOSITORY": os.environ.get("GITHUB_REPOSITORY"),
"GITHUB_SHA": os.environ.get("GITHUB_SHA"),
"GITHUB_REF": os.environ.get("GITHUB_REF")
}
run = experiment.submit(
automl_config,
tags=dict(parameters.get("tags", {}), **default_tags)
)
best_run, fitted_model = run.get_output(metric='accuracy')
except AzureMLException as exception:
print(
f"::error::Could not submit experiment config. Your script passed object of type {type(automl_config)}. Object must be correctly configured and of type e.g. estimator, pipeline, etc.: {exception}")
raise AMLExperimentConfigurationException(
f"Could not submit experiment config. Your script passed object of type {type(automl_config)}. Object must be correctly configured and of type e.g. estimator, pipeline, etc.: {exception}")
except TypeError as exception:
print(
f"::error::Could not submit experiment config. Your script passed object of type {type(automl_config)}. Object must be correctly configured and of type e.g. estimator, pipeline, etc.: {exception}")
raise AMLExperimentConfigurationException(
f"Could not submit experiment config. Your script passed object of type {type(automl_config)}. Object must be correctly configured and of type e.g. estimator, pipeline, etc.: {exception}")
# Create outputs
print("::debug::Creating outputs")
print(f"::set-output name=experiment_name::{best_run.experiment.name}")
print(f"::set-output name=run_id::{best_run.id}")
print(f"::set-output name=run_url::{best_run.get_portal_url()}")
# Waiting for run to complete
print("::debug::Waiting for run to complete")
if parameters.get("wait_for_completion", True):
run.wait_for_completion(show_output=True)
# Creating additional outputs of finished run
run_metrics = run.get_metrics() if type(
run) is HyperDriveRun else run.get_metrics(recursive=True)
# run_metrics = run.get_metrics(recursive=True) # Not working atm because HyperDriveRun thrown error
print(f"::set-output name=run_metrics::{run_metrics}")
run_metrics_markdown = convert_to_markdown(run_metrics)
print(
f"::set-output name=run_metrics_markdown::{run_metrics_markdown}")
# Download artifacts if enabled
if parameters.get("download_artifacts", False):
# Defining artifacts folder
print("::debug::Defining artifacts folder")
root_path = os.environ.get("GITHUB_WORKSPACE", default=None)
folder_name = f"aml_artifacts_{run.id}"
artifact_path = os.path.join(root_path, folder_name)
# Downloading artifacts
print("::debug::Downloading artifacts")
run.download_files(
output_directory=os.path.join(artifact_path, "parent"))
children = run.get_children(recursive=True)
for i, child in enumerate(children):
child.download_files(output_directory=os.path.join(
artifact_path, f"child_{i}"))
# Creating additional outputs
print(f"::set-output name=artifact_path::{artifact_path}")
# Publishing pipeline
print("::debug::Publishing pipeline")
if type(run) is PipelineRun and parameters.get("pipeline_publish", False):
# Default pipeline name
repository_name = os.environ.get("GITHUB_REPOSITORY").split("/")[-1]
branch_name = os.environ.get("GITHUB_REF").split("/")[-1]
default_pipeline_name = f"{repository_name}-{branch_name}"
published_pipeline = run.publish_pipeline(
name=parameters.get("pipeline_name", default_pipeline_name),
description="Pipeline registered by GitHub Run Action",
version=parameters.get("pipeline_version", None),
continue_on_step_failure=parameters.get(
"pipeline_continue_on_step_failure", False)
)
# Creating additional outputs
print(
f"::set-output name=published_pipeline_id::{published_pipeline.id}")
print(
f"::set-output name=published_pipeline_status::{published_pipeline.status}")
print(
f"::set-output name=published_pipeline_endpoint::{published_pipeline.endpoint}")
elif parameters.get("pipeline_publish", False):
print("::error::Could not register pipeline because you did not pass a pipeline to the action")
print("::debug::Successfully finished Azure Machine Learning Train Action")
