You can find the Docs for Python and API by going to User Settings -> API Keys From the Python CML APIv2 Docs, these are the two methods you need: Step 1: Create Job from __future__ import print_function
import time
import cmlapi
from cmlapi.rest import ApiException
from pprint import pprint
# create an instance of the API class
api_instance = cmlapi.CMLServiceApi()
body = cmlapi.CreateJobRequest() # CreateJobRequest |
project_id = 'project_id_example' # str | ID of the project containing the job.
try:
# Create a new job.
api_response = api_instance.create_job(body, project_id)
pprint(api_response)
except ApiException as e:
print("Exception when calling CMLServiceApi->create_job: %s\n" % e) Step 2: Run the Job from __future__ import print_function
import time
import cmlapi
from cmlapi.rest import ApiException
from pprint import pprint
# create an instance of the API class
api_instance = cmlapi.CMLServiceApi()
body = cmlapi.CreateJobRunRequest() # CreateJobRunRequest |
project_id = 'project_id_example' # str | ID of the project containing the job.
job_id = 'job_id_example' # str | The job ID to create a new job run for.
try:
# Create and start a new job run for a job.
api_response = api_instance.create_job_run(body, project_id, job_id)
pprint(api_response)
except ApiException as e:
print("Exception when calling CMLServiceApi->create_job_run: %s\n" % e) Using the "cmlapi.CreateJobRequest()" or "cmlapi.CreateJobRunRequest()" methods can be tricky. Here's an advanced example: https://github.com/pdefusco/SparkGen/blob/main/autogen/cml_orchestrator.py In particular: sparkgen_1_job_body = cmlapi.CreateJobRequest(
project_id = project_id,
name = "SPARKGEN_1_"+session_id,
script = "autogen/cml_sparkjob_1.py",
cpu = 4.0,
memory = 8.0,
runtime_identifier = "docker.repository.cloudera.com/cloudera/cdsw/ml-runtime-workbench-python3.7-standard:2023.05.1-b4",
runtime_addon_identifiers = ["spark320-18-hf4"],
environment = {
"x":str(x),
"y":str(y),
"z":str(z),
"ROW_COUNT_car_installs":str(ROW_COUNT_car_installs),
"UNIQUE_VALS_car_installs":str(UNIQUE_VALS_car_installs),
"PARTITIONS_NUM_car_installs":str(PARTITIONS_NUM_car_installs),
"ROW_COUNT_car_sales":str(ROW_COUNT_car_sales),
"UNIQUE_VALS_car_sales":str(UNIQUE_VALS_car_sales),
"PARTITIONS_NUM_car_sales":str(PARTITIONS_NUM_car_sales),
"ROW_COUNT_customer_data":str(ROW_COUNT_customer_data),
"UNIQUE_VALS_customer_data":str(UNIQUE_VALS_customer_data),
"PARTITIONS_NUM_customer_data":str(PARTITIONS_NUM_customer_data),
"ROW_COUNT_factory_data":str(ROW_COUNT_factory_data),
"UNIQUE_VALS_factory_data":str(UNIQUE_VALS_factory_data),
"PARTITIONS_NUM_factory_data":str(PARTITIONS_NUM_factory_data),
"ROW_COUNT_geo_data":str(ROW_COUNT_geo_data),
"UNIQUE_VALS_geo_data":str(UNIQUE_VALS_geo_data),
"PARTITIONS_NUM_geo_data":str(PARTITIONS_NUM_geo_data)
}
)
sparkgen_1_job = client.create_job(sparkgen_1_job_body, project_id) And jobrun_body = cmlapi.CreateJobRunRequest(project_id, sparkgen_1_job.id)
job_run = client.create_job_run(jobrun_body, project_id, sparkgen_1_job.id) Hope this helps,
... View more
