Python CMLBootstrap.start_job Examples

Example #1

File: cml_train.py Project: tspannhw/deepad

    "report_attachments": [],
    "success_recipients": [],
    "failure_recipients": [],
    "timeout_recipients": [],
    "stopped_recipients": []
}

new_job = cml.create_job(create_jobs_params)
new_job_id = new_job["id"]
print("Created new job with jobid", new_job_id)

##
# Start a job
job_env_params = {}
start_job_params = {"environment": job_env_params}
job_status = cml.start_job(new_job_id, start_job_params)
print("Job started")

# Create model build script
cdsw_script = """#!/bin/bash
pip3 install -r requirements.txt"""

with open("cdsw-build.sh", 'w+') as f:
    f.write(cdsw_script)
    f.close()
os.chmod("cdsw-build.sh", 0o777)

# Get Default Engine Details
# Engine id is required for next step (create model)

default_engine_details = cml.get_default_engine({})

Example #2

File: 9_check_model.py Project: fastforwardlabs/cml_churn_demo_mlops

PROJECT_NAME = os.getenv("CDSW_PROJECT")

cml = CMLBootstrap(HOST, USERNAME, API_KEY, PROJECT_NAME)

latest_model = cml.get_model({
    "id": model_id,
    "latestModelDeployment": True,
    "latestModelBuild": True
})

Model_CRN = latest_model["crn"]
Deployment_CRN = latest_model["latestModelDeployment"]["crn"]

# Read in the model metrics dict.
model_metrics = cdsw.read_metrics(model_crn=Model_CRN,
                                  model_deployment_crn=Deployment_CRN)

# This is a handy way to unravel the dict into a big pandas dataframe.
metrics_df = pd.io.json.json_normalize(model_metrics["metrics"])

latest_aggregate_metric = metrics_df.dropna(
    subset=["metrics.accuracy"]).sort_values(
        'startTimeStampMs')[-1:]["metrics.accuracy"]

if latest_aggregate_metric.to_list()[0] < 0.6:
    print("model is below threshold, retraining")
    cml.start_job(job_id, {})
    #TODO reploy new model
else:
    print("model does not need to be retrained")

Example #3

File: 0_build_project.py Project: namessanti/cml_churn_demo

                      "success_recipients": [],
                      "failure_recipients": [],
                      "timeout_recipients": [],
                      "stopped_recipients": []
                      }

new_job = cml.create_job(create_jobs_params)
new_job_id = new_job["id"]
print("Created new job with jobid", new_job_id)

##
# Start the Training Job
job_env_params = {}
start_job_params = {"environment": job_env_params}
job_id = new_job_id
job_status = cml.start_job(job_id, start_job_params)
print("Training Job started")

# Stop a job
#job_dict = cml.start_job(job_id, start_job_params)
#cml.stop_job(job_id, start_job_params)

# Run experiment

run_experiment_params = {
    "size": {
        "id": 1,
        "description": "1 vCPU / 2 GiB Memory",
        "cpu": 1,
        "memory": 2,
        "route": "engine-profiles",

Example #4

File: 9_model_check_job.py Project: victordibia/cml_flight_demo

HOST = os.getenv("CDSW_API_URL").split(
    ":")[0] + "://" + os.getenv("CDSW_DOMAIN")
USERNAME = os.getenv("CDSW_PROJECT_URL").split(
    "/")[6]  # args.username  # "vdibia"
API_KEY = os.getenv("CDSW_API_KEY") 
PROJECT_NAME = os.getenv("CDSW_PROJECT")  

cml = CMLBootstrap(HOST, USERNAME, API_KEY, PROJECT_NAME)

latest_model = cml.get_model({"id": model_id, "latestModelDeployment": True, "latestModelBuild": True})

Model_CRN = latest_model ["crn"]
Deployment_CRN = latest_model["latestModelDeployment"]["crn"]

# Read in the model metrics dict.
model_metrics = cdsw.read_metrics(model_crn=Model_CRN,model_deployment_crn=Deployment_CRN)

# This is a handy way to unravel the dict into a big pandas dataframe.
metrics_df = pd.io.json.json_normalize(model_metrics["metrics"])

latest_aggregate_metric = metrics_df.dropna(subset=["metrics.accuracy"]).sort_values('startTimeStampMs')[-1:]["metrics.accuracy"]


if latest_aggregate_metric.to_list()[0] < 0.6:
  print("model is below threshold, retraining")
  cml.start_job(244,{})
  #TODO reploy new model
else:
  print("model does not need to be retrained")
  

Example #5

HOST = os.getenv("CDSW_API_URL").split(
    ":")[0] + "://" + os.getenv("CDSW_DOMAIN")
USERNAME = os.getenv("CDSW_PROJECT_URL").split(
    "/")[6]  # args.username  # "vdibia"
API_KEY = os.getenv("CDSW_API_KEY") 
PROJECT_NAME = os.getenv("CDSW_PROJECT")  

cml = CMLBootstrap(HOST, USERNAME, API_KEY, PROJECT_NAME)

latest_model = cml.get_model({"id": model_id, "latestModelDeployment": True, "latestModelBuild": True})

Model_CRN = latest_model ["crn"]
Deployment_CRN = latest_model["latestModelDeployment"]["crn"]

# Read in the model metrics dict.
model_metrics = cdsw.read_metrics(model_crn=Model_CRN,model_deployment_crn=Deployment_CRN)

# This is a handy way to unravel the dict into a big pandas dataframe.
metrics_df = pd.io.json.json_normalize(model_metrics["metrics"])

latest_aggregate_metric = metrics_df.dropna(subset=["metrics.accuracy"]).sort_values('startTimeStampMs')[-1:]["metrics.accuracy"]


if latest_aggregate_metric.to_list()[0] < 0.6:
  print("model is below threshold, retraining")
  cml.start_job(68,{})
  #TODO reploy new model
else:
  print("model does not need to be retrained")