cv_results['n_features'] = X.shape[1]
cv_results['y_0'] = y.tolist().count(0)
cv_results['y_1'] = y.tolist().count(1)
print(cv_results["mean_test_pr_auc"].to_string(index=False))
run.log(name="mean_test_pr_auc",
value=cv_results["mean_test_pr_auc"].to_string(index=False))
if not os.path.isdir(args.train_model):
os.makedirs(args.train_model, exist_ok=True)
timestamp_id = datetime.datetime.now()
time = timestamp_id.strftime("%m-%d-%Y_%H%M")
model_name = "{}__{}.json".format(args.repo_owner, args.repo_name)
output_path = os.path.join(args.train_model, model_name)
with open(output_path, 'w') as outfile:
cv_results.to_json(outfile, orient='table', index=False)
# Get the blob storage associated with the workspace
pipeline_datastore = Datastore(ws, "datastore_pipeline")
#Upload production model to main blob folder
pipeline_datastore.upload_files([args.train_model + '/' + model_name],
target_path="train_model" + '/' +
args.repo_owner + '/' + args.repo_name +
'/' + time,
overwrite=True)
print("Model is trained!")
}
word_vectors = {
"en_vectors_web_lg":
"https://github.com/explosion/spacy-models/releases/download/en_vectors_web_lg-2.1.0/en_vectors_web_lg-2.1.0.tar.gz"
}
toDownload = [dataset, word_vectors]
download_files(toDownload, data_temp_folder)
zip_file = zipfile.ZipFile(os.path.join(data_temp_folder, "train.csv.zip"),
'r')
zip_file.extractall(data_temp_folder)
zip_file.close()
def_blob_store.upload_files(
[os.path.join(data_temp_folder, "train.csv")],
target_path=f"{project_config['project_name']}/data/original/",
overwrite=True)
def_blob_store.upload_files(
[os.path.join(data_temp_folder, "en_vectors_web_lg-2.1.0.tar.gz")],
target_path=f"{project_config['project_name']}/data/install/",
overwrite=False)
#step1
cluster_name = "cpucluster"
try:
compute_target_cpu = ComputeTarget(workspace=ws, name=cluster_name)
except ComputeTargetException:
compute_config = AmlCompute.provisioning_configuration(
vm_size='STANDARD_D3_V2', max_nodes=1, min_nodes=1)
compute_target_cpu = ComputeTarget.create(ws, cluster_name,
compute_config)
lambda x: x.created_time == max(model.created_time for model in model_list),
model_list,
)
)
model = Model(ws, name=production_model.name)
model
service = Model.deploy_from_model(workspace=ws,
name=service_name,
models=[model],
inference_config=inference_config,
deployment_config=aci_config)
service.wait_for_deployment(show_output=True)
aci_webservice = {}
aci_webservice["aci_name"] = service.name
aci_webservice["aci_url"] = service.scoring_uri
with open(args.aci_store+"/aci_webservice.json", "w") as outfile:
json.dump(aci_webservice, outfile)
# Get the blob storage associated with the workspace
pipeline_datastore = Datastore(ws, "datastore_pipeline")
#Upload production model to main blob folder
pipeline_datastore.upload_files([args.aci_store+"/aci_webservice.json"], target_path="webservice"+'/'+args.repo_owner+'/'+args.repo_name, overwrite=True)
print("Deployed ACI Webservice: {} \nWebservice Uri: {}".format(service.name, service.scoring_uri)