def downloadPickles(ws, modelName, outputPath="./pickles", modelVer=None):
if modelVer == 'best':
bestModel = None
maxAcc = -1
for model in Model.list(ws, modelName, ["accuracy"]):
modelAcc = float(model.tags["accuracy"])
if modelAcc > maxAcc:
bestModel = model
maxAcc = modelAcc
print(f"### Best model with highest accuracy of {maxAcc} found")
if not bestModel:
model = Model(ws, modelName)
print("### WARNING! No best model found, using latest instead")
elif modelVer is not None:
model = Model(ws, modelName, version=modelVer)
else:
model = Model(ws, modelName)
print(f"### Using model version {model.version}")
# Echo'ing out this magic string sets an output variable in Azure DevOps pipeline
# Set AZML_MODEL_VER for use by subsequent steps
print(f"##vso[task.setvariable variable=AZML_MODEL_VER]{model.version}")
# These are special tags, lets us get back to the run that created the model
try:
runId = model.tags['aml-runid']
experimentName = model.tags['aml-experiment']
except:
print(
"### ERROR! Model missing `aml-runid` and `aml-experiment` tags, Can't continue!"
)
exit()
exp = Experiment(workspace=ws, name=experimentName)
run = Run(exp, runId)
if run.status != "Completed":
print(f'### ERROR! Run {runId} did not complete!')
return
print(f'### Will download from run {runId} in {experimentName}')
# Now we can get all the files created with the run, grab all the .pkls
for f in run.get_file_names():
if f.endswith('.pkl'):
output_file_path = os.path.join(outputPath, f.split('/')[-1])
print('### Downloading from {} to {} ...'.format(
f, output_file_path))
run.download_file(name=f, output_file_path=output_file_path)
# Add some extra metadata, handy to have
metadata = {
'name': model.name,
'version': model.version,
'tags': model.tags
}
with open(f"{outputPath}/metadata.json", 'w') as metadata_file:
print(f"### Storing metadata in {outputPath}/metadata.json")
json.dump(metadata, metadata_file)
def download_run_outputs_by_prefix(
blobs_prefix: Path, destination: Path, run: Run
) -> None:
"""
Download all the blobs from the run's default output directory: DEFAULT_AML_UPLOAD_DIR ("outputs") that
have a given prefix (folder structure). When saving, the prefix string will be stripped off. For example,
if blobs_prefix = "foo", and the run has a file "outputs/foo/bar.csv", it will be downloaded to destination/bar.csv.
If there is in addition a file "foo.txt", that file will be skipped.
:param blobs_prefix: The prefix for all files in "outputs" that should be downloaded.
:param run: The AzureML run to download the files from.
:param destination: Local path to save the downloaded blobs to.
"""
prefix_str = str((fixed_paths.DEFAULT_AML_UPLOAD_DIR / blobs_prefix).as_posix())
logging.info(
f"Downloading multiple files from run {run.id}: {prefix_str} -> {str(destination)}"
)
# There is a download_files function, but that can time out when downloading several large checkpoints file
# (120sec timeout for all files).
for file in run.get_file_names():
if file.startswith(prefix_str):
target_path = file[len(prefix_str):]
if target_path.startswith("/"):
target_path = target_path[1:]
logging.info(f"Downloading {file}")
run.download_file(
file, str(destination / target_path), _validate_checksum=True
)
else:
logging.warning(
f"Skipping file {file}, because the desired prefix {prefix_str} is not aligned with "
f"the folder structure"
)
def register_model(run_id, experiment):
best_run = Run(experiment=experiment, run_id=run_id)
files = best_run.get_file_names()
r = re.compile('outputs.*')
model_path = [l for l in files if r.match(l)]
path, model = os.path.split(model_path[0])
model = best_run.register_model(model_name=model,
model_path='outputs/model.pkl')
return path
def get_job_log_file(run: Run, index: Optional[int] = None) -> str:
"""
Reads the job log file (70_driver_log.txt or std_log.txt) of the given job. If an index is provided, get
the matching file from a multi-node job.
:return: The contents of the job log file.
"""
assert run.status == RunStatus.COMPLETED
files = run.get_file_names()
suffix = (f"_{index}" if index is not None else "") + ".txt"
file1 = "azureml-logs/70_driver_log" + suffix
file2 = "user_logs/std_log" + suffix
if file1 in files:
file = file1
elif file2 in files:
file = file2
else:
raise ValueError(f"No log file ({file1} or {file2}) present in the run. Existing files: {files}")
downloaded = tempfile.NamedTemporaryFile().name
run.download_file(name=file, output_file_path=downloaded)
return Path(downloaded).read_text()
model_name = "model_alpha_" + str(alpha) + ".pkl"
filename = "outputs/" + model_name
joblib.dump(value=model, filename=filename)
run.upload_file(name=model_name, path_or_stream=filename)
run.complete()
minimum_rmse_runid = None
minimum_rmse = None
for run in experiment.get_runs():
run_metrics = run.get_metrics()
run_details = run.get_details()
# each logged metric becomes a key in this returned dict
run_rmse = run_metrics["rmse"]
run_id = run_details["runId"]
if minimum_rmse is None:
minimum_rmse = run_rmse
minimum_rmse_runid = run_id
else:
if run_rmse < minimum_rmse:
minimum_rmse = run_rmse
minimum_rmse_runid = run_id
print("Best run_id: " + minimum_rmse_runid)
print("Best run_id rmse: " + str(minimum_rmse))
best_run = Run(experiment=experiment, run_id=minimum_rmse_runid)
print(best_run.get_file_names())
run_details = run.get_details()
# each logged metric becomes a key in this returned dict
run_rmse = run_metrics["rmse"]
run_id = run_details["runId"]
if minimum_rmse is None:
minimum_rmse = run_rmse
minimum_rmse_runid = run_id
else:
if run_rmse < minimum_rmse:
minimum_rmse = run_rmse
minimum_rmse_runid = run_id
#Sobre el mejor modelo, obtener una referencia del mismo
from azureml.core import Run
best_run = Run(experiment=experiment, run_id=minimum_rmse_runid)
print(best_run.get_file_names())
#Descargar el modelo
model_file_name = best_run.get_file_names()[0]
best_run.download_file(name=model_file_name)
#Cargamos el modelo en python
import joblib
clf = joblib.load(model_file_name)
print("El proceso ha finalizado correctamente!!")
#Uso del clasificador para nuevos datos (referencia)
#y_predecido = clf.predict(X)
#Comparar x con y y calcular rmse
#rmse = math.sqrt(mean_squared_error(y_true=y_realdelosdatos, y_pred=y_predecido))
from azureml.core.authentication import AzureCliAuthentication
cli_auth = AzureCliAuthentication()
# Get workspace
ws = Workspace.from_config(auth=cli_auth)
# Get the latest evaluation result
try:
with open("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)
os.makedirs('../mnist-tf/ckpt', exist_ok=True)
for f in run.get_file_names():
if f.startswith('outputs/model'):
output_file_path = os.path.join('../mnist-tf/ckpt/', f.split('/')[-1])
print('Downloading from {} to {} ...'.format(f, output_file_path))
run.download_file(name=f, output_file_path=output_file_path)
run_id = run._run_id
last = False
print()
print(f"Last Run ID: {run_id}")
# register last run_id as environment variable so it can be used in %sh commands
os.environ['RUN_ID_LAST'] = run_id
# print(os.getenv('RUN_ID_LAST'))
# COMMAND ----------
import mlflow.sklearn
# run_id = "434c0e56-307a-4e40-a170-343530c77386"
run = Run(experiment, run_id=run_id)
run.get_file_names()
# COMMAND ----------
run.download_files(output_directory=f"/tmp/{run_id}")
# COMMAND ----------
# MAGIC %sh
# MAGIC ls -l /tmp/$RUN_ID_LAST/random_forest_model
# COMMAND ----------
model_uri_aml = f"/tmp/{run_id}/random_forest_model"
model = mlflow.sklearn.load_model(model_uri_aml)
# MAGIC Each time we ran the models, we stored a zip file with the trained model in AML. We can now retrieve the trained model of the particular run that we want to deploy. We'll copy the relevant `id` from above and retrieve the Run object.
# COMMAND ----------
best_run_id = '6d670807-6477-4ea6-a98b-84069c888346'
best_run = Run(experiment, best_run_id)
# COMMAND ----------
# MAGIC %md
# MAGIC #### 4. Download the model locally and unzip
# COMMAND ----------
# First, let's list the filenames
best_run.get_file_names()
# COMMAND ----------
# In this case, we're looking for the 'outputs/{MODEL_NAME}Model.zip' file
import shutil
import os
saved_model_name = 'model.zip' # Saved model filename in AML Service - leave out the 'outputs/' folder at the beginning
aml_location = 'outputs/{0}'.format(saved_model_name)
user_folder = '/dbfs/tmp/{0}/'.format(user_name)
# Create objects with folder names
temporary_zip_path = os.path.join(
user_folder, 'trained_model_zip') # Folder to zipped model file
