def register_dataset(dataset_name, dataframe):
dataset_config = next(
iter(
filter(lambda x: x["name"] == dataset_name,
self.output_reg_datasets)))
datastore = dataset_config.get("datastore") or "default"
description = dataset_config.get("description")
tags = dataset_config.get("tags")
if datastore == "default":
ds = ws.get_default_datastore()
else:
ds = Datastore.get(workspace=ws, datastore_name=datastore)
target_path = f'experiment/{run.experiment.name}/run/{run.number}/out/{dataset_name}'
default_output_dataset_tags = {
"format": self.
OUTPUT_FORMAT, # Dataset.Tabular.register_pandas_dataframe always writes a parquet
"experiment": run.experiment.name,
"run": run.number
}
output_dataset_tags = {**default_output_dataset_tags, **tags}
Dataset.Tabular.register_pandas_dataframe(
dataframe,
target=(ds, target_path),
name=dataset_name,
description=description,
tags=output_dataset_tags)
def get_blob_datastore(workspace: Workspace, data_store_name: str,
storage_name: str, storage_key: str,
container_name: str):
"""
Returns a reference to a datastore
Parameters:
workspace (Workspace): existing AzureML Workspace object
data_store_name (string): data store name
storage_name (string): blob storage account name
storage_key (string): blob storage account key
container_name (string): container name
Returns:
Datastore: a reference to datastore
"""
try:
blob_datastore = Datastore.get(workspace, data_store_name)
print("Found Blob Datastore with name: %s", data_store_name)
except HttpOperationError:
blob_datastore = Datastore.register_azure_blob_container(
workspace=workspace,
datastore_name=data_store_name,
account_name=storage_name, # Storage account name
container_name=container_name, # Name of Azure blob container
account_key=storage_key) # Storage account key
print("Registered blob datastore with name: %s", data_store_name)
return blob_datastore
def get_ds_object(ws, name):
"""
get_ds_object - Get workspace datastore object
:param str ws: workspace
:param str name: data store name
:returns: ws, name
:rtype: blob object, str
"""
return Datastore.get(ws, name)
def register_dataset(path, aml_interface, storage_acct_name, storage_acct_key):
workspace = aml_interface.workspace
datastore = Datastore.register_azure_blob_container(
workspace=workspace,
datastore_name='prediction',
container_name='prediction',
account_name=storage_acct_name,
account_key=storage_acct_key)
prediction_datastore = Datastore.get(workspace, 'prediction')
datastore_path = [(prediction_datastore, path)]
dataset = Dataset.Tabular.from_delimited_files(path=datastore_path)
dataset = dataset.register(workspace=aml_interface.workspace,
name='Prediction')
def get_or_create_dataset(azure_config: AzureConfig,
azure_dataset_id: str) -> Dataset:
"""
Looks in the AzureML datastore for a dataset of the given name. If there is no such dataset, a dataset is created
and registered, assuming that the files are in a folder that has the same name as the dataset. For example, if
azure_dataset_id is 'foo', then the 'foo' dataset is pointing to <container_root>/datasets/foo folder.
WARNING: the behaviour of Dataset.File.from_files, used below, is idiosyncratic. For example,
if "mydataset" storage has two "foo..." subdirectories each containing
a file dataset.csv and a directory ABC,
datastore = Datastore.get(workspace, "mydataset")
# This dataset has the file(s) in foo-bar01 at top level, e.g. dataset.csv
ds1 = Dataset.File.from_files([(datastore, "foo-bar01/*")])
# This dataset has two directories at top level, each with a name matching foo-bar*, and each
# containing dataset.csv.
ds2 = Dataset.File.from_files([(datastore, "foo-bar*/*")])
# This dataset contains a single directory "mydataset" at top level, containing a subdirectory
# foo-bar01, containing dataset.csv and (part of) ABC.
ds3 = Dataset.File.from_files([(datastore, "foo-bar01/*"),
(datastore, "foo-bar01/ABC/abc_files/*/*.nii.gz")])
These behaviours can be verified by calling "ds.download()" on each dataset ds.
"""
if not azure_config.azureml_datastore:
raise ValueError(
"No value set for 'azureml_datastore' (name of the datastore in the AzureML workspace)"
)
logging.info(
f"Retrieving datastore '{azure_config.azureml_datastore}' from AzureML workspace"
)
workspace = azure_config.get_workspace()
datastore = Datastore.get(workspace, azure_config.azureml_datastore)
try:
logging.info(
f"Trying to retrieve AzureML Dataset '{azure_dataset_id}'")
azureml_dataset = Dataset.get_by_name(workspace, name=azure_dataset_id)
logging.info("Dataset found.")
except:
logging.info(
f"Dataset does not yet exist, creating a new one from data in folder '{azure_dataset_id}'"
)
# See WARNING above before changing the from_files call!
azureml_dataset = Dataset.File.from_files([(datastore,
azure_dataset_id)])
logging.info("Registering the dataset for future use.")
azureml_dataset.register(workspace, name=azure_dataset_id)
return azureml_dataset
def config(ws, blob_datastore_name, account_name, container_name,
account_key):
try:
blob_datastore = Datastore.get(ws, blob_datastore_name)
print("Found Blob Datastore with name: %s" % blob_datastore_name)
except HttpOperationError:
blob_datastore = Datastore.register_azure_blob_container(
workspace=ws,
datastore_name=blob_datastore_name,
account_name=account_name, # Storage account name
container_name=container_name, # Name of Azure blob container
account_key=account_key) # Storage account key
print("Registered blob datastore with name: %s" %
blob_datastore_name)
return blob_datastore
def createDataReference(workspace, storage_name, storage_key,
storage_container_name, data_store_name,
data_reference_name):
'''
If no present, registers a new azureml.core.datastore.Datastore
Once the data store is in hand it creates an instance of azureml.data.data_reference.DataReference that
can be used in an Azure ML pipeline step.
PARAMS:
workspace : azureml.core.Workspace : Existing AMLS Workspace
storage_name : string : Name of the Azure Storage Account
storage_key : string : Access Key to the Azure Storage Account
storage_container_name : string : Container name to recieve blobs. Must exist
data_store_name : string : Name of the registere data store.
data_reference_name : string : Name of the data reference
RETURNS:
tuple(azureml.core.datastore.Datastore, azureml.data.data_reference.DataReference)
'''
data_store = None
try:
data_store = Datastore.get(workspace, data_store_name)
print("Found existing data store - ", data_store_name)
except Exception as ex:
print("Creating data store - ", data_store_name)
data_store = Datastore.register_azure_blob_container(
workspace,
datastore_name=data_store_name,
container_name=storage_container_name,
account_name=storage_name,
account_key=storage_key,
)
if data_store == None:
raise Exception("Could not create/find data store.")
return data_store, DataReference(datastore=data_store,
data_reference_name=data_reference_name)
if 'creditcard' not in ws.datasets:
#Set blobdatastore
blob_datastore_name = 'MyBlobDatastore'
account_name = os.getenv(
"BLOB_ACCOUNTNAME_62",
"PUT YOUR STORAGE ACCOUNT NAME HERE") # Storage account name
container_name = os.getenv(
"BLOB_CONTAINER_62",
"PUT YOUR STORAGE CONTAINER NAME HERE") # Name of Azure blob container
account_key = os.getenv(
"BLOB_ACCOUNT_KEY_62",
"PUT YOUR STORAGE ACCOUNT KEY HERE") # Storage account key
try:
blob_datastore = Datastore.get(ws, blob_datastore_name)
print("Found Blob Datastore with name: %s" % blob_datastore_name)
except:
blob_datastore = Datastore.register_azure_blob_container(
workspace=ws,
datastore_name=blob_datastore_name,
account_name=account_name, # Storage account name
container_name=container_name, # Name of Azure blob container
account_key=account_key) # Storage account key
print("Registered blob datastore with name: %s" % blob_datastore_name)
blob_data_ref = DataReference(datastore=blob_datastore,
data_reference_name="blob_test_data",
path_on_datastore="testdata")
csv_path = (blob_datastore, '/creditcard.csv')
import argparse
from pathlib import Path
from azureml.core.datastore import Datastore
from azureml.core.workspace import Workspace
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--subscription-id", type=str)
parser.add_argument("--resource-group", type=str)
parser.add_argument("--workspace-name", type=str)
parser.add_argument("--datastore-name", type=str)
parser.add_argument("--data-directory", type=str)
parser.add_argument("--dataset-name", type=str)
args = parser.parse_args()
print(args.workspace_name)
workspace = Workspace(
subscription_id=args.subscription_id,
resource_group=args.resource_group,
workspace_name=args.workspace_name,
)
datastore = Datastore.get(workspace, args.datastore_name)
local_path = Path(args.data_directory)
for phase in ["train", "val"]:
local_directory = str(local_path / phase)
target_path = str(Path(args.dataset_name) / phase)
datastore.upload(local_directory,
target_path=target_path,
show_progress=True)
try:
compute_target = ComputeTarget(workspace=ws, name=cluster_name)
print('Found existing compute target')
except ComputeTargetException:
print('No compute cluster named {}'.format(cluster_name))
exit()
curated_env_name = 'Resnet50v15-CPU-cluster'
# pytorch_env = Environment.get(workspace=ws, name=curated_env_name)
pytorch_env = Environment.from_conda_specification(
name=curated_env_name, file_path='./conda_dependencies.yml')
project_folder = './'
data_path = 'datasets'
datastore = Datastore.get(ws, 'workspaceblobstore')
dataset = Dataset.File.from_files(path=(datastore, data_path))
data_loc = dataset.as_named_input('input').as_mount()
src = ScriptRunConfig(
source_directory=project_folder,
# command=['ls'],
script='train_resnet.py',
arguments=[
'--num_epochs',
16,
'--batch',
'32',
'--shuffle',
'True',
'--dataloc',
import os
from pathlib import Path
from utils import get_workspace
raw_data_dir = "C:\\Dataspace\\IMS\\2nd_test"
prep_data_dir = "C:\\Dataspace\\IMS\\processed\\2nd_test"
datastore_name = "bearing_datastore"
dataset_name = "bearing_dataset"
container_name = "bearingdata"
sensor_data = pd.DataFrame()
ws = get_workspace()
try:
datastore = Datastore.get(ws, datastore_name)
print("Datastore found: ", datastore_name)
except Exception:
datastore = Datastore.register_azure_blob_container(
workspace=ws,
datastore_name=datastore_name,
account_name=os.environ.get('AML_BLOB_ACCOUNT_NAME'),
container_name=container_name,
account_key=os.environ.get('AML_BLOB_ACCOUNT_KEY'),
endpoint="core.chinacloudapi.cn")
print("Datastore registered: ", datastore_name)
for filename in os.listdir(raw_data_dir):
data = pd.read_csv(os.path.join(raw_data_dir, filename),
names=["c1", "c2", "c3", "c4"],
sep='\t')
datastore_name=blob_datastore_name,
account_name=account_name, # ADLS Gen2 account name
container_name ='nyctaxi', # ADLS Gen2 filesystem
account_key = account_key)
# COMMAND ----------
print(dsNYCTaxi.datastore_type)
# COMMAND ----------
from azureml.pipeline.core import PipelineParameter,Pipeline, PipelineData
from azureml.data.data_reference import DataReference
# Use the default blob storage
dsNYCTaxi = Datastore.get(ws, "dsblob")
print('Datastore {} will be used'.format(dsNYCTaxi.name))
#pipeline_param = PipelineParameter(name="my_pipeline_param", default_value="pipeline_param1")
datasetFilePath = DataReference(datastore=dsNYCTaxi, path_on_datastore="/merged_aml_dbr",
data_reference_name="datasetFilePath")
output = PipelineData("output", datastore=dsNYCTaxi)
# COMMAND ----------
from azureml.pipeline.steps import DatabricksStep
from azureml.core.databricks import PyPiLibrary
