# Make experiment reproducible
tf.random.set_seed(CONFIG.SPLIT_SEED)
random.seed(CONFIG.SPLIT_SEED)
DATA_DIR = REPO_DIR / 'data' if run.id.startswith("OfflineRun") else Path(".")
logger.info('DATA_DIR: %s', DATA_DIR)
# Offline run. Download the sample dataset and run locally. Still push results to Azure.
if run.id.startswith("OfflineRun"):
logger.info('Running in offline mode...')
# Access workspace.
logger.info('Accessing workspace...')
workspace = Workspace.from_config()
experiment = Experiment(workspace, "training-junkyard")
run = experiment.start_logging(outputs=None, snapshot_directory=None)
dataset_name = CONFIG.DATASET_NAME_LOCAL
dataset_path = get_dataset_path(DATA_DIR / "datasets", dataset_name)
download_dataset(workspace, dataset_name, dataset_path)
# Online run. Use dataset provided by training notebook.
else:
logger.info('Running in online mode...')
experiment = run.experiment
workspace = experiment.workspace
dataset_name = CONFIG.DATASET_NAME
# Mount or download
from azureml.core.runconfig import RunConfiguration
from azureml.core import Workspace
from azureml.core import Experiment
from azureml.core import ScriptRunConfig
import json
from azureml.core.authentication import AzureCliAuthentication
cli_auth = AzureCliAuthentication()
# Get workspace
ws = Workspace.from_config(auth=cli_auth)
# Attach Experiment
experiment_name = "devops-ai-demo"
exp = Experiment(workspace=ws, name=experiment_name)
print(exp.name, exp.workspace.name, sep="\n")
# Editing a run configuration property on-fly.
run_config_user_managed = RunConfiguration()
run_config_user_managed.environment.python.user_managed_dependencies = True
print("Submitting an experiment.")
src = ScriptRunConfig(
source_directory="./code",
script="training/train.py",
run_config=run_config_user_managed,
)
run = exp.submit(src)
# Shows output of the run on stdout.
"environments/data_preperation_full/RunConfig/runconfig_data_preperation.yml",
)),
name="dataprep_full")
dataprep_subset = PythonScriptStep(
name="subset",
script_name="data_engineering.py",
arguments=script_params_sub,
runconfig=run_config_sub,
source_directory=os.path.join(os.path.dirname(os.path.realpath(__file__)),
'..', 'data'))
dataprep_fulldata = PythonScriptStep(
name="full",
script_name="data_engineering.py",
arguments=script_params,
runconfig=run_config,
source_directory=os.path.join(os.path.dirname(os.path.realpath(__file__)),
'..', 'data'))
# Attach step to the pipelines
pipeline = Pipeline(workspace=workspace,
steps=[dataprep_subset, dataprep_fulldata])
# Submit the pipeline
# Define the experiment
experiment = Experiment(workspace, 'pipeline-dataprep')
# Run the experiment
pipeline_run = experiment.submit(pipeline)
def main():
run = Run.get_context()
if (run.id.startswith('OfflineRun')):
from dotenv import load_dotenv
# For local development, set values in this section
load_dotenv()
workspace_name = os.environ.get("WORKSPACE_NAME")
experiment_name = os.environ.get("EXPERIMENT_NAME")
resource_group = os.environ.get("RESOURCE_GROUP")
subscription_id = os.environ.get("SUBSCRIPTION_ID")
# run_id useful to query previous runs
run_id = "bd184a18-2ac8-4951-8e78-e290bef3b012"
aml_workspace = Workspace.get(
name=workspace_name,
subscription_id=subscription_id,
resource_group=resource_group
)
ws = aml_workspace
exp = Experiment(ws, experiment_name)
else:
ws = run.experiment.workspace
exp = run.experiment
run_id = 'amlcompute'
parser = argparse.ArgumentParser("register")
parser.add_argument(
"--run_id",
type=str,
help="Training run ID",
)
parser.add_argument(
"--model_name",
type=str,
help="Name of the Model",
default="londonboiler_model.pkl",
)
parser.add_argument(
"--step_input",
type=str,
help=("input from previous steps")
)
args = parser.parse_args()
if (args.run_id is not None):
run_id = args.run_id
if (run_id == 'amlcompute'):
run_id = run.parent.id
model_name = args.model_name
model_path = args.step_input
print("Getting registration parameters")
# Load the registration parameters from the parameters file
with open("parameters.json") as f:
pars = json.load(f)
try:
register_args = pars["registration"]
except KeyError:
print("Could not load registration values from file")
register_args = {"tags": []}
model_tags = {}
for tag in register_args["tags"]:
try:
mtag = run.parent.get_metrics()[tag]
model_tags[tag] = mtag
except KeyError:
print(f"Could not find {tag} metric on parent run.")
# load the model
print("Loading model from " + model_path)
model_file = os.path.join(model_path, model_name)
model = joblib.load(model_file)
parent_tags = run.parent.get_tags()
try:
build_id = parent_tags["BuildId"]
except KeyError:
build_id = None
print("BuildId tag not found on parent run.")
print(f"Tags present: {parent_tags}")
try:
build_uri = parent_tags["BuildUri"]
except KeyError:
build_uri = None
print("BuildUri tag not found on parent run.")
print(f"Tags present: {parent_tags}")
if (model is not None):
dataset_id = parent_tags["dataset_id"]
if (build_id is None):
register_aml_model(
model_file,
model_name,
model_tags,
exp,
run_id,
dataset_id)
elif (build_uri is None):
register_aml_model(
model_file,
model_name,
model_tags,
exp,
run_id,
dataset_id,
build_id)
else:
register_aml_model(
model_file,
model_name,
model_tags,
exp,
run_id,
dataset_id,
build_id,
build_uri)
else:
print("Model not found. Skipping model registration.")
sys.exit(0)
workspace_name=workspace_name,
auth=msi_auth)
#Retrieve dataset and compute for the AutoML run
dataset = Dataset.get_by_name(workspace=ws, name=dataset_name)
compute_target = ws.compute_targets[compute_name]
automl_config = AutoMLConfig(task='regression',
experiment_timeout_minutes=30,
primary_metric='normalized_root_mean_squared_error',
training_data=dataset,
compute_target=compute_target,
label_column_name=dataset_label_column)
#Execute the AutoML run
experiment = Experiment(ws, experiment_name)
run = experiment.submit(automl_config, show_output=True)
run.wait_for_completion()
#Get the best model from the AutoML run and register it
best_run = run.get_best_child()
best_run.download_files(prefix='outputs', append_prefix=False)
model = Model.register(model_path='outputs/model.pkl',
model_name=model_name,
workspace=ws)
#Prepare an environment for the model
myenv = Environment.from_conda_specification(name='project_environment', file_path='outputs/conda_env_v_1_0_0.yml')
myenv.docker.enabled = True
inference_config = InferenceConfig(entry_script='outputs/scoring_file_v_1_0_0.py', environment=myenv)
label_config = label_ds.as_named_input("labels_input")
batch_score_step = ParallelRunStep(
name=parallel_step_name,
inputs=[input_images.as_named_input("input_images")],
output=output_dir,
arguments=["--model_name", "inception", "--labels_dir", label_config],
side_inputs=[label_config],
parallel_run_config=parallel_run_config,
allow_reuse=False)
from azureml.core import Experiment
from azureml.pipeline.core import Pipeline
pipeline = Pipeline(workspace=ws, steps=[batch_score_step])
pipeline_run = Experiment(ws, 'batch_scoring').submit(pipeline)
pipeline_run.wait_for_completion(show_output=True)
import pandas as pd
batch_run = next(pipeline_run.get_children())
batch_output = batch_run.get_output_data("scores")
batch_output.download(local_path="inception_results")
for root, dirs, files in os.walk("inception_results"):
for file in files:
if file.endswith("parallel_run_step.txt"):
result_file = os.path.join(root, file)
df = pd.read_csv(result_file, delimiter=":", header=None)
df.columns = ["Filename", "Prediction"]
type=str,
required=True,
help="The id of the run that contains the trained model.")
args = parser.parse_args()
# Get the current run.
run = Run.get_context()
# Offline run. Download the sample dataset and run locally. Still push results to Azure.
if (run.id.startswith("OfflineRun")):
print("Running in offline mode...")
# Access workspace.
print("Accessing workspace...")
workspace = Workspace.from_config()
experiment = Experiment(workspace, "gapnet-offline")
run = experiment.start_logging(outputs=None, snapshot_directory=".")
# Get dataset.
print("Accessing dataset...")
if os.path.exists("premiumfileshare") == False:
dataset_name = "cgmmldevpremium-SampleDataset-Example"
dataset = workspace.datasets[dataset_name]
dataset.download(target_path='.', overwrite=False)
dataset_path = glob.glob(os.path.join("premiumfileshare", "*"))[0]
# Online run. Use dataset provided by training notebook.
else:
print("Running in online mode...")
experiment = run.experiment
workspace = experiment.workspace
# These run metrics will become particularly important when we begin hyperparameter tuning our model in the "Tune model hyperparameters" section.
# Once your script is ready, copy the training script pytorch_train.py into your project directory for staging.
import shutil
shutil.copy('pytorch_train.py', project_folder)
# Create an experiment
# Create an Experiment to track all the runs in your workspace for this transfer learning PyTorch tutorial.
from azureml.core import Experiment
experiment_name = 'pytorch-hymenoptera'
experiment = Experiment(ws, name=experiment_name)
# Create a PyTorch estimator
# The Azure ML SDK's PyTorch estimator enables you to easily submit PyTorch training jobs for both single-node and distributed runs. For more information on the PyTorch estimator, refer here. The following code will define a single-node PyTorch job.
from azureml.train.dnn import PyTorch
script_params = {'--num_epochs': 30, '--output_dir': './outputs'}
estimator = PyTorch(source_directory=project_folder,
script_params=script_params,
compute_target=compute_target,
entry_script='pytorch_train.py',
use_gpu=True)
allow_reuse=False)
print("evaluateStep created")
evaluateStep.run_after(trainStep)
steps = [evaluateStep]
pipeline = Pipeline(workspace=ws, steps=steps)
print("Pipeline is built")
pipeline.validate()
print("Simple validation complete")
run = Run.get_context()
experiment_name = run.experiment.name
pipeline_run = Experiment(ws, experiment_name).submit(pipeline)
print("Pipeline is submitted for execution")
pipeline_run.wait_for_completion(show_output=True)
print("Downloading evaluation results...")
# access the evaluate_output
data = pipeline_run.find_step_run('evaluate')[0].get_output_data(
'evaluate_output')
# download the predictions to local path
data.download('.', show_progress=True)
import json
# load the eval info json
with open(os.path.join('./', data.path_on_datastore, 'eval_info.json')) as f:
eval_info = json.load(f)
import pandas as pd
import json
print("SDK Version:", azureml.core.VERSION)
ws = Workspace.from_config()
print('Workspace name: ' + ws.name,
'Subscription id: ' + ws.subscription_id,
'Resource group: ' + ws.resource_group,
sep='\n')
experiment_name = 'aml-pipeline_cicd' # choose a name for experiment
project_folder = '.' # project folder
experiment = Experiment(ws, experiment_name)
print("Location:", ws.location)
output = {}
output['SDK version'] = azureml.core.VERSION
output['Subscription ID'] = ws.subscription_id
output['Workspace'] = ws.name
output['Resource Group'] = ws.resource_group
output['Location'] = ws.location
output['Project Directory'] = project_folder
output['Experiment Name'] = experiment.name
pd.set_option('display.max_colwidth', -1)
pd.DataFrame(data=output, index=['']).T
set_diagnostics_collection(send_diagnostics=True)
print("SDK Version:", azureml.core.VERSION)
# 05-train-remote-with-remote-data.py
from azureml.core import Workspace
from azureml.core import Experiment
from azureml.core import Environment
from azureml.core import ScriptRunConfig
from azureml.core import Dataset
if __name__ == "__main__":
ws = Workspace.from_config(path='./.azureml',_file_name='config.json')
datastore = ws.get_default_datastore()
dataset = Dataset.File.from_files(path=(datastore, 'datasets/Monografia_limpio.csv'))
experiment = Experiment(workspace=ws, name='dia2-experimento-train-data-remote')
config = ScriptRunConfig(
source_directory='./src',
script='rcv_model.py',
compute_target='cpu-cluster-mon',
arguments=[
'--data_path', dataset.as_named_input('input').as_mount()
],
)
# setup environment
env = Environment.from_conda_specification(
name='amlrcv-env',
file_path='./.azureml/rcv-aml-env.yml'
)
config.run_config.environment = env
run = experiment.submit(config)
aml_url = run.get_portal_url()
# set aml workspace parameters here.
subscription_id = ""
resource_group = ""
workspace_name = ""
workspace_region = ""
ws = Workspace(subscription_id=subscription_id,
resource_group=resource_group,
workspace_name=workspace_name)
# COMMAND ----------
# create experiment
experiment_name = 'bikeSharingDemand'
exp = Experiment(workspace=ws, name=experiment_name)
# COMMAND ----------
run = exp.start_logging(snapshot_directory=None)
# COMMAND ----------
df = (spark.read.format("csv").option("inferSchema", "True").option(
"header",
"True").load("/databricks-datasets/bikeSharing/data-001/day.csv"))
# split data
train_df, test_df = df.randomSplit([0.7, 0.3])
# One Hot Encoding
data_preprocess_outputs['valid_dir'],
gpu_compute_target)
# Step 4: Evaluate Model
evaluate_step, evaluate_outputs = evaluate_step(
train_outputs['model_dir'], data_preprocess_outputs['test_dir'],
gpu_compute_target)
# Step 5: Deploy Model
deploy_step, deploy_outputs = deploy_step(train_outputs['model_dir'],
evaluate_outputs['accuracy_file'],
data_preprocess_outputs['test_dir'],
cpu_compute_target)
# Submit pipeline
print('Submitting pipeline ...')
pipeline_parameters = {
'num_images': 100,
'image_dim': 200,
'num_epochs': 10,
'batch_size': 16,
'learning_rate': 0.001,
'momentum': 0.9
}
pipeline = Pipeline(workspace=workspace,
steps=[
data_ingestion_step, data_preprocess_step, train_step,
evaluate_step, deploy_step
])
pipeline_run = Experiment(workspace, 'Object-Classification-Demo').submit(
pipeline, pipeline_parameters=pipeline_parameters)
def main():
run = Run.get_context()
if (run.id.startswith('OfflineRun')):
from dotenv import load_dotenv
load_dotenv()
sources_dir = os.environ.get("SOURCES_DIR_TRAIN")
if (sources_dir is None):
sources_dir = 'aml_recommender'
workspace_name = os.environ.get("WORKSPACE_NAME")
experiment_name = os.environ.get("EXPERIMENT_NAME")
resource_group = os.environ.get("RESOURCE_GROUP")
subscription_id = os.environ.get("SUBSCRIPTION_ID")
build_id = os.environ.get('BUILD_BUILDID')
aml_workspace = Workspace.get(
name=workspace_name,
subscription_id=subscription_id,
resource_group=resource_group
)
ws = aml_workspace
exp = Experiment(ws, experiment_name)
else:
exp = run.experiment
e = Env()
parser = argparse.ArgumentParser("register")
parser.add_argument(
"--build_id",
type=str,
help="The Build ID of the build triggering this pipeline run",
)
parser.add_argument(
"--output_model_version_file",
type=str,
default="model_version.txt",
help="Name of a file to write model version to"
)
args = parser.parse_args()
if (args.build_id is not None):
build_id = args.build_id
model_name = e.model_name
try:
tag_name = 'BuildId'
model = get_latest_model(
model_name, tag_name, build_id, exp.workspace)
if (model is not None):
print("Model was registered for this build.")
if (model is None):
print("Model was not registered for this run.")
sys.exit(1)
except Exception as e:
print(e)
print("Model was not registered for this run.")
sys.exit(1)
# Save the Model Version for other AzDO jobs after script is complete
if args.output_model_version_file is not None:
with open(args.output_model_version_file, "w") as out_file:
out_file.write(str(model.version))
# Parametrize dataset input to the pipeline
batch_dataset_parameter = PipelineParameter(name="batch_dataset", default_value=batch_dataset)
batch_dataset_consumption = DatasetConsumptionConfig("batch_dataset", batch_dataset_parameter).as_mount()
datastore = ws.get_default_datastore()
output_dir = PipelineData(name='batch_output', datastore=datastore)
batch_step = ParallelRunStep(
name="batch-inference-step",
parallel_run_config=parallel_run_config,
arguments=['--model_name', args.model_name],
inputs=[batch_dataset_consumption],
side_inputs=[],
output=output_dir,
allow_reuse=False
)
steps = [batch_step]
print('Creating and validating pipeline')
pipeline = Pipeline(workspace=ws, steps=steps)
pipeline.validate()
print('Publishing pipeline')
published_pipeline = pipeline.publish(args.pipeline_name)
# Output pipeline_id in specified format which will convert it to a variable in Azure DevOps
print(f'##vso[task.setvariable variable=pipeline_id]{published_pipeline.id}')
pipeline_run = Experiment(ws, 'batch-inferencing-pipeline').submit(pipeline)
pipeline_run.wait_for_completion()
workspace = Workspace.from_config()
instance = ComputeTarget(workspace=workspace, name=args.aml_compute_target)
dataset = Dataset.get_by_name(workspace, name="recursionbio")
tf_env = Environment.from_conda_specification(
name="regbio-tf-env", file_path=args.conda_env_file)
train_scr = ScriptRunConfig(
source_directory=args.source_directory,
script=args.script,
arguments=[
"--data-path",
dataset.as_mount(),
"--epochs",
1000,
"--batch",
24,
"--learning-rate",
0.001,
],
compute_target=instance,
environment=tf_env,
)
run = Experiment(workspace=workspace,
name=args.experiment_name).submit(train_scr)
run.wait_for_completion(show_output=True)
# Check core SDK version number
import azureml.core
print("SDK version:", azureml.core.VERSION)
# Initialize Workspace
from azureml.core import Workspace
ws = Workspace.from_config()
print("Resource group: ", ws.resource_group)
print("Location: ", ws.location)
print("Workspace name: ", ws.name)
from azureml.core import Experiment
experiment_name = 'fashion-mnist'
experiment = Experiment(workspace=ws, name=experiment_name)
from azureml.core.runconfig import RunConfiguration
from azureml.core.conda_dependencies import CondaDependencies
# create a new runconfig object
run_config = RunConfiguration()
# signal that you want to use ACI to execute script.
run_config.target = "containerinstance"
# ACI container group is only supported in certain regions, which can be different than the region the Workspace is in.
run_config.container_instance.region = ws.location
# set the ACI CPU and Memory
run_config.container_instance.cpu_cores = 1
run_config.container_instance.memory_gb = 2
)
parser.add_argument("--box_iou_thresh",
type=float,
required=False,
help="IoU threshold")
# parse arguments
args = parser.parse_args()
ws = Workspace.create(
name=args.workspace_name,
subscription_id=args.subscription_id,
resource_group=args.resource_group,
exist_ok=True,
)
experiment = Experiment(ws, name=args.experiment_name)
# load the best child
automl_image_run = AutoMLRun(experiment=experiment, run_id=args.run_id)
best_child_run = automl_image_run.get_best_child()
model_type = None
if args.task_type == "image-object-detection":
if args.model_name.startswith("yolo"):
# yolo settings
model_settings = {
"img_size": args.img_size,
"model_size": args.model_size,
"box_score_thresh": args.box_score_thresh,
"box_iou_thresh": args.box_iou_thresh,
}
cluster_name=args.clustername,
vm_size=args.vmsize,
max_nodes=args.maxnodes,
)
run_config = create_run_config(
cpu_cluster=cpu_cluster,
docker_proc_type=docker_proc_type,
conda_env_file=args.condafile,
)
logger.info("exp: In Azure, look for experiment named {}".format(
args.expname))
# create new or use existing experiment
experiment = Experiment(workspace=workspace, name=args.expname)
run = submit_experiment_to_azureml(
test=args.test,
test_folder=args.testfolder,
test_markers=args.testmarkers,
junitxml=args.junitxml,
run_config=run_config,
experiment=experiment,
)
# add helpful information to experiment on Azure
run.tag("RepoName", args.reponame)
run.tag("Branch", args.branch)
run.tag("PR", args.pr)
# download files from AzureML
run.download_files(prefix="reports", output_paths="./reports")
# 06-run-pytorch-data.py
from azureml.core import Workspace
from azureml.core import Experiment
from azureml.core import Environment
from azureml.core import ScriptRunConfig
from azureml.core import Dataset
if __name__ == "__main__":
ws = Workspace.from_config()
datastore = ws.get_default_datastore()
dataset = Dataset.File.from_files(path=(datastore, 'datasets/cifar10'))
experiment = Experiment(workspace=ws, name='day1-experiment-data')
config = ScriptRunConfig(
source_directory='./src',
script='train.py',
compute_target='cpu-cluster',
arguments=[
'--data_path',
dataset.as_named_input('input').as_mount(), '--learning_rate',
0.003, '--momentum', 0.92
],
)
# set up pytorch environment
env = Environment.from_conda_specification(
name='pytorch-env', file_path='./environments/pytorch-env.yml')
config.run_config.environment = env
run = experiment.submit(config)
aml_url = run.get_portal_url()
sj = modelIncubation(sj)
iq = modelIncubation(iq)
return sj, iq
sj_train, iq_train = preprocess_data('./data/dengue_features_train.csv',
labels_path="./data/dengue_labels_train.csv")
sj_train.head(10)
#%% create experiment
experiment_name = 'myDengueExp'
from azureml.core import Experiment
exp = Experiment(workspace=ws, name=experiment_name)
print('Experiment created.')
#%% attach existing compute target or attach a new one
from azureml.core.compute import AmlCompute
from azureml.core.compute import ComputeTarget
import os
# choose a name for your cluster
compute_name = os.environ.get("AML_COMPUTE_CLUSTER_NAME", "cpucluster")
compute_min_nodes = os.environ.get("AML_COMPUTE_CLUSTER_MIN_NODES", 0)
compute_max_nodes = os.environ.get("AML_COMPUTE_CLUSTER_MAX_NODES", 4)
# This example uses CPU VM. For using GPU VM, set SKU to STANDARD_NC6
vm_size = os.environ.get("AML_COMPUTE_CLUSTER_SKU", "STANDARD_D2_V2")
import os
from azureml.core import Experiment, Workspace, Model
from azureml.core.compute import ComputeTarget, AmlCompute
from azureml.core.compute_target import ComputeTargetException
from azureml.train.hyperdrive import GridParameterSampling, BanditPolicy, HyperDriveConfig, PrimaryMetricGoal
from azureml.train.hyperdrive import choice
from azureml.widgets import RunDetails
from azureml.train.sklearn import SKLearn
ws = Workspace.from_config()
print("Ready to use Azure ML", azureml.core.VERSION)
print('Ready to work with', ws.name)
# Create an experiment
experiment_name = 'diabetes_training'
experiment = Experiment(workspace=ws, name=experiment_name)
# Create a folder for the experiment files
experiment_folder = './' + experiment_name
os.makedirs(experiment_folder, exist_ok=True)
print("Experiment:", experiment.name)
#Fetch GPU cluster for computations
gpu_cluster = ComputeTarget(workspace=ws, name='demo-GPU-cluster')
# Sample a range of parameter values
params = GridParameterSampling({
# There's only one parameter, so grid sampling will try each value - with multiple parameters it would try every combination
'--regularization':
choice(0.001, 0.005, 0.01, 0.05, 0.1, 1.0)
shutil.copy(f'./project/{args.project_name}.config.json',
f'./src/{fn_config_infer}')
script_folder = "./"
tasks = params.get("tasks")
############################################
##### PREPARE
############################################
if args.do_prepare:
logging.warning(f'[INFO] Running prepare for {args.project_name}')
for task in tasks:
config = tasks.get(task)
if config.get('prepare'):
exp = Experiment(workspace=ws,
name=f'{args.project_name}_prepare_{task}')
print(f'[INFO] Running prepare for {task}')
script_params = {
'--task': int(task),
'--do_format': '',
'--register_data': ''
}
est = Estimator(source_directory=script_folder,
compute_target=compute_target,
script_params=script_params,
entry_script='src/prepare.py',
pip_packages=pip_packages,
use_gpu=False)
run = exp.submit(est)
if args.do_train:
run.wait_for_completion(show_output=True)
type=str,
required=True,
help="The id of the run that contains the trained model.")
args = parser.parse_args()
# Get the current run.
run = Run.get_context()
# Offline run. Download the sample dataset and run locally. Still push results to Azure.
if (run.id.startswith("OfflineRun")):
print("Running in offline mode...")
# Access workspace.
print("Accessing workspace...")
workspace = Workspace.from_config()
experiment = Experiment(workspace, "gapnet-offline")
run = experiment.start_logging(outputs=None, snapshot_directory=".")
# Get dataset.
print("Accessing dataset...")
if os.path.exists("premiumfileshare") == False:
dataset_name = "cgmmldevpremium-SampleDataset-Example"
dataset = workspace.datasets[dataset_name]
dataset.download(target_path='.', overwrite=False)
dataset_path = glob.glob(os.path.join("premiumfileshare", "*"))[0]
# Online run. Use dataset provided by training notebook.
else:
print("Running in online mode...")
experiment = run.experiment
workspace = experiment.workspace
def start(self):
ws = AzureProject(self.ctx)._get_ws()
dataset_name = self.ctx.config.get('dataset', None)
if dataset_name is None:
raise AzureException('Please specify Dataset name...')
experiment_name = self._fix_name(
self.ctx.config.get('experiment/name', dataset_name))
cluster_name = self._fix_name(
self.ctx.config.get('cluster/name', 'cpucluster'))
self.ctx.log("Starting search on %s Dataset..." % dataset_name)
dataset = Dataset.get_by_name(ws, dataset_name)
#TODO dataset = dataset.drop_columns(columns)
compute_target = self._get_compute_target(ws, cluster_name)
model_type = self.ctx.config.get('model_type')
if not model_type:
raise AzureException('Please specify model type...')
primary_metric = self.ctx.config.get(
'experiment/metric','spearman_correlation')
if not primary_metric:
raise AzureException('Please specify primary metric...')
#TODO: check if primary_metric is constent with model_type
target = self.ctx.config.get('target')
if not target:
raise AzureException('Please specify target column...')
automl_settings = {
"iteration_timeout_minutes" : self.ctx.config.get(
'experiment/max_eval_time',10),
"iterations" : self.ctx.config.get(
'experiment/max_n_trials',10),
"primary_metric" : primary_metric,
"verbosity" : logging.INFO,
"enable_stack_ensemble": self.ctx.config.get(
'experiment/use_ensemble', False)
}
validation_data = None
if self.ctx.config.get('experiment/validation_data'):
if self.ctx.config.get('validation_dataset'):
validation_data = Dataset.get_by_name(ws, self.ctx.config.get('validation_dataset'))
if not validation_data:
res = AzureDataset(self.ctx).create(
source = self.ctx.config.get('experiment/validation_data'),
validation = True
)
validation_data = Dataset.get_by_name(ws, res['dataset'])
else:
automl_settings["n_cross_validations"] = self.ctx.config.get(
'experiment/cross_validation_folds', 5)
if self.ctx.config.get('experiment/validation_size'):
automl_settings["validation_size"] = self.ctx.config.get('experiment/validation_size')
if self.ctx.config.get('experiment/max_total_time'):
automl_settings["experiment_timeout_hours"] = float(self.ctx.config.get('experiment/max_total_time'))/60.0
if self.ctx.config.get('exclude'):
fc = FeaturizationConfig()
fc.drop_columns = self.ctx.config.get('exclude').split(",")
automl_settings["featurization"] = fc
automl_config = AutoMLConfig(
task = model_type,
debug_log = 'automl_errors.log',
path = os.getcwd(),
compute_target = compute_target,
training_data = dataset,
validation_data = validation_data,
label_column_name = target,
**automl_settings)
experiment = Experiment(ws, experiment_name)
run = experiment.submit(automl_config, show_output = False)
self.ctx.log("Started Experiment %s search..." % experiment_name)
self.ctx.config.set('azure', 'experiment/name', experiment_name)
self.ctx.config.set('azure', 'experiment/run_id', run.run_id)
self.ctx.config.write('azure')
return {'eperiment_name': experiment_name, 'run_id': run.run_id}
from utils import load_data
import matplotlib.pyplot as plt
import azureml.core
print(azureml.core.VERSION)
from azureml.core import Workspace
ws = Workspace.create(name='mnist1',
subscription_id='bcbc4e01-e5d6-42b0-95af-06286341e6ca',
resource_group='mnist3',
create_resource_group=True,
location='eastus2')
ws.get_details()
from azureml.core import Experiment
# Create a new experiment in your workspace.
exp = Experiment(workspace=ws, name='myexp1')
# note we also shrink the intensity values (X) from 0-255 to 0-1. This helps the model converge faster.
X_train = load_data(os.path.join(data_folder, 'train-images.gz'),
False) / 255.0
X_test = load_data(os.path.join(data_folder, 'test-images.gz'), False) / 255.0
y_train = load_data(os.path.join(data_folder, 'train-labels.gz'),
True).reshape(-1)
y_test = load_data(os.path.join(data_folder, 'test-labels.gz'),
True).reshape(-1)
# now let's show some randomly chosen images from the traininng set.
# for simply mapping x_train to y_train
count = 0
sample_size = 30
plt.figure(figsize=(16, 6))
for i in np.random.permutation(X_train.shape[0])[:sample_size]:
# Get the latest evaluation result
try:
with open("aml_config/run_id.json") as f:
config = json.load(f)
if not config["run_id"]:
raise Exception(
"No new model to register as production model perform better")
except:
print("No new model to register as production model perform better")
# raise Exception('No new model to register as production model perform better')
sys.exit(0)
run_id = config["run_id"]
experiment_name = config["experiment_name"]
exp = Experiment(workspace=ws, name=experiment_name)
run = Run(experiment=exp, run_id=run_id)
names = run.get_file_names
names()
print("Run ID for last run: {}".format(run_id))
model_local_dir = "model"
os.makedirs(model_local_dir, exist_ok=True)
# Download Model to Project root directory
model_name = "sklearn_regression_model.pkl"
run.download_file(name="./outputs/" + model_name,
output_file_path="./model/" + model_name)
print("Downloaded model {} to Project root directory".format(model_name))
os.chdir("./model")
model = Model.register(
import tensorflow as tf
logs_dir = os.path.join(os.curdir, "logs")
data_dir = os.path.abspath(os.path.join(os.curdir, "mnist_data"))
if not path.exists(data_dir):
makedirs(data_dir)
os.environ["TEST_TMPDIR"] = data_dir
# Writing logs to ./logs results in their being uploaded to Artifact Service,
# and thus, made accessible to our TensorBoard instance.
arguments_list = ["--log_dir", logs_dir, "--data_dir", data_dir]
# Create an experiment
exp = Experiment(ws, experiment_name)
# If you would like the run to go for longer, add --max_steps 5000 to the arguments list:
# arguments_list += ["--max_steps", "5000"]
script = ScriptRunConfig('./scripts',
script="mnist_with_summaries.py",
run_config=run_config,
arguments=arguments_list)
run = exp.submit(script)
runs.append(run)
run.wait_for_completion(show_output=True)
# Once more, with a Batch AI cluster
load_dotenv()
workspace_name = os.environ.get("WORKSPACE_NAME")
experiment_name = os.environ.get("EXPERIMENT_NAME")
resource_group = os.environ.get("RESOURCE_GROUP")
subscription_id = os.environ.get("SUBSCRIPTION_ID")
tenant_id = os.environ.get("TENANT_ID")
model_name = os.environ.get("MODEL_NAME")
app_id = os.environ.get('SP_APP_ID')
app_secret = os.environ.get('SP_APP_SECRET')
build_id = os.environ.get('BUILD_BUILDID')
aml_workspace = Workspace.get(name=workspace_name,
subscription_id=subscription_id,
resource_group=resource_group)
ws = aml_workspace
exp = Experiment(ws, experiment_name)
else:
sys.path.append(os.path.abspath("./util")) # NOQA: E402
from model_helper import get_model_by_tag
exp = run.experiment
ws = run.experiment.workspace
run_id = 'amlcompute'
parser = argparse.ArgumentParser("evaluate")
parser.add_argument(
"--build_id",
type=str,
help="The Build ID of the build triggering this pipeline run",
)
parser.add_argument(
"--run_id",
import azureml
from azureml.core import Workspace, Experiment
from azureml.train.estimator import Estimator
azureml._restclient.snapshots_client.SNAPSHOT_MAX_SIZE_BYTES = 10 * 10**9 # 10GB
# Loading the workspace
ws = Workspace.from_config()
# Creating an Estimator which is the environment for your experiment
estimator = Estimator(
source_directory="./model",
entry_script="train_char_rnn.py",
script_params={
"--dataset":
"shakespeare", # TODO: Specify the same dataset_name you provided earlier
"--modelname": "shakespeare_model", # TODO: Specify your modelname
"--n_epochs": 2000
},
compute_target="az-workshop-ci", # TODO: Specify your compute target
pip_packages=[
"azureml-core", "azureml-dataprep", "azureml-train", "pandas", "torch",
"torchvision", "tqdm", "Unidecode"
])
# TODO: Create a "Experiment" and use the submit method to submit the "estimator" object
# Recieve the return object of the submittet experiment and use the "wait_for_completion(show_output=True)" method.
# This will show you the logs for the submitted experiment
experiment = Experiment(workspace=ws, name="demo-skatteetaten-dataset")
run = experiment.submit(config=estimator)
run.wait_for_completion(show_output=True)