def run_databricks(uri, entry_point, version, parameters, experiment_id,
cluster_spec, git_username, git_password):
"""
Runs the project at the specified URI on Databricks, returning a `SubmittedRun` that can be
used to query the run's status or wait for the resulting Databricks Job run to terminate.
"""
_check_databricks_auth_available()
if cluster_spec is None:
raise ExecutionException(
"Cluster spec must be provided when launching MLflow project runs "
"on Databricks.")
# Fetch the project into work_dir & validate parameters
work_dir = _fetch_project(uri=uri,
use_temp_cwd=True,
version=version,
git_username=git_username,
git_password=git_password)
project = _load_project(work_dir)
project.get_entry_point(entry_point)._validate_parameters(parameters)
# Upload the project to DBFS, get the URI of the project
dbfs_project_uri = _upload_project_to_dbfs(work_dir, experiment_id)
# Create run object with remote tracking server. Get the git commit from the working directory,
# etc.
tracking_uri = tracking.get_tracking_uri()
remote_run = _create_databricks_run(
tracking_uri=tracking_uri,
experiment_id=experiment_id,
source_name=_expand_uri(uri),
source_version=tracking._get_git_commit(work_dir),
entry_point_name=entry_point)
# Set up environment variables for remote execution
env_vars = {}
if experiment_id is not None:
eprint("=== Using experiment ID %s ===" % experiment_id)
env_vars[tracking._EXPERIMENT_ID_ENV_VAR] = experiment_id
if remote_run is not None:
env_vars[tracking._TRACKING_URI_ENV_VAR] = tracking.get_tracking_uri()
env_vars[tracking._RUN_ID_ENV_VAR] = remote_run.run_info.run_uuid
eprint("=== Running entry point %s of project %s on Databricks. ===" %
(entry_point, uri))
# Launch run on Databricks
with open(cluster_spec, 'r') as handle:
try:
cluster_spec = json.load(handle)
except ValueError:
eprint(
"Error when attempting to load and parse JSON cluster spec from file "
"%s. " % cluster_spec)
raise
fuse_dst_dir = os.path.join(
"/dbfs/",
_parse_dbfs_uri_path(dbfs_project_uri).lstrip("/"))
final_run_id = remote_run.run_info.run_uuid if remote_run else None
command = _get_databricks_run_cmd(fuse_dst_dir, final_run_id, entry_point,
parameters)
db_run_id = _run_shell_command_job(uri, command, env_vars, cluster_spec)
run_id = remote_run.run_info.run_uuid if remote_run else None
return DatabricksSubmittedRun(db_run_id, run_id)
def run_databricks(uri, entry_point, version, parameters, experiment_id, cluster_spec,
git_username, git_password):
"""
Runs the project at the specified URI on Databricks, returning a `SubmittedRun` that can be
used to query the run's status or wait for the resulting Databricks Job run to terminate.
"""
tracking_uri = tracking.get_tracking_uri()
_before_run_validations(tracking_uri, cluster_spec)
work_dir = _fetch_and_clean_project(
uri=uri, version=version, git_username=git_username, git_password=git_password)
project = _load_project(work_dir)
project.get_entry_point(entry_point)._validate_parameters(parameters)
dbfs_project_uri = _upload_project_to_dbfs(work_dir, experiment_id)
remote_run = tracking._create_run(
experiment_id=experiment_id, source_name=_expand_uri(uri),
source_version=tracking._get_git_commit(work_dir), entry_point_name=entry_point,
source_type=SourceType.PROJECT)
env_vars = {
tracking._TRACKING_URI_ENV_VAR: tracking_uri,
tracking._EXPERIMENT_ID_ENV_VAR: experiment_id,
}
run_id = remote_run.run_info.run_uuid
eprint("=== Running entry point %s of project %s on Databricks. ===" % (entry_point, uri))
# Launch run on Databricks
with open(cluster_spec, 'r') as handle:
try:
cluster_spec = json.load(handle)
except ValueError:
eprint("Error when attempting to load and parse JSON cluster spec from file "
"%s. " % cluster_spec)
raise
fuse_dst_dir = os.path.join("/dbfs/", _parse_dbfs_uri_path(dbfs_project_uri).lstrip("/"))
command = _get_databricks_run_cmd(fuse_dst_dir, run_id, entry_point, parameters)
db_run_id = _run_shell_command_job(uri, command, env_vars, cluster_spec)
return DatabricksSubmittedRun(db_run_id, run_id)
def _run_project(project, entry_point, work_dir, parameters, use_conda,
storage_dir, experiment_id):
"""Locally run a project that has been checked out in `work_dir`."""
storage_dir_for_run = _get_storage_dir(storage_dir)
eprint(
"=== Created directory %s for downloading remote URIs passed to arguments of "
"type 'path' ===" % storage_dir_for_run)
# Try to build the command first in case the user mis-specified parameters
run_project_command = project.get_entry_point(entry_point)\
.compute_command(parameters, storage_dir_for_run)
commands = []
if use_conda:
conda_env_path = os.path.abspath(
os.path.join(work_dir, project.conda_env))
_maybe_create_conda_env(conda_env_path)
commands.append("source activate %s" %
_get_conda_env_name(conda_env_path))
# Create a new run and log every provided parameter into it.
active_run = tracking.start_run(
experiment_id=experiment_id,
source_name=project.uri,
source_version=tracking._get_git_commit(work_dir),
entry_point_name=entry_point,
source_type=SourceType.PROJECT)
if parameters is not None:
for key, value in parameters.items():
active_run.log_param(Param(key, value))
# Add the run id into a magic environment variable that the subprocess will read,
# causing it to reuse the run.
exp_id = experiment_id or tracking._get_experiment_id()
env_map = {
tracking._RUN_NAME_ENV_VAR: active_run.run_info.run_uuid,
tracking._TRACKING_URI_ENV_VAR: tracking.get_tracking_uri(),
tracking._EXPERIMENT_ID_ENV_VAR: str(exp_id),
}
commands.append(run_project_command)
command = " && ".join(commands)
eprint("=== Running command: %s ===" % command)
try:
process.exec_cmd([os.environ.get("SHELL", "bash"), "-c", command],
cwd=work_dir,
stream_output=True,
env=env_map)
tracking.end_run()
eprint("=== Run succeeded ===")
except process.ShellCommandException:
tracking.end_run("FAILED")
eprint("=== Run failed ===")
def _run_project(project, entry_point, work_dir, parameters, use_conda,
storage_dir, experiment_id):
"""Locally run a project that has been checked out in `work_dir`."""
mlflow.set_tracking_uri('..\\') #added by cliicy
if storage_dir is not None and not os.path.exists(storage_dir):
os.makedirs(storage_dir)
storage_dir_for_run = tempfile.mkdtemp(dir=storage_dir)
print(
"=== Created directory %s for downloading remote URIs passed to arguments of "
"type 'path' ===" % storage_dir_for_run)
# Try to build the command first in case the user mis-specified parameters
run_project_command = project.get_entry_point(entry_point).compute_command(
parameters, storage_dir_for_run)
commands = []
# Create a new run and log every provided parameter into it.
active_run = tracking.start_run(
experiment_id=experiment_id,
source_name=project.uri,
source_version=tracking._get_git_commit(work_dir),
entry_point_name=entry_point,
source_type=SourceType.PROJECT)
for key, value in parameters.items():
active_run.log_param(Param(key, value))
# Add the run id into a magic environment variable that the subprocess will read,
# causing it to reuse the run.
exp_id = experiment_id or tracking._get_experiment_id()
env_map = {
tracking._RUN_NAME_ENV_VAR: active_run.run_info.run_uuid,
tracking._TRACKING_URI_ENV_VAR: tracking.get_tracking_uri(),
tracking._EXPERIMENT_ID_ENV_VAR: str(exp_id),
}
commands.append(run_project_command)
command = " && ".join(commands)
print("=== Running command: %s ===" % command)
try:
command = "python my_train.py 0.4 0.1"
print("will run command aaaaa " + command + " " + work_dir + " aaaaa ")
process.exec_cmd(command,
cwd=work_dir,
stream_output=True,
env=env_map)
#process.exec_cmd([os.environ.get("SHELL", "bash"), "-c", command], cwd=work_dir,
# stream_output=True, env=env_map)
tracking.end_run()
print("=== Run succeeded ===")
except process.ShellCommandException:
tracking.end_run("FAILED")
print("=== Run failed ===")
def _create_run(uri, experiment_id, work_dir, entry_point, parameters):
"""
Create a ``Run`` against the current MLflow tracking server, logging metadata (e.g. the URI,
entry point, and parameters of the project) about the run. Return an ``ActiveRun`` that can be
used to report additional data about the run (metrics/params) to the tracking server.
"""
active_run = tracking._create_run(
experiment_id=experiment_id, source_name=_expand_uri(uri),
source_version=tracking._get_git_commit(work_dir), entry_point_name=entry_point,
source_type=SourceType.PROJECT)
if parameters is not None:
for key, value in parameters.items():
active_run.log_param(Param(key, value))
return active_run
def _run_project(project, entry_point, work_dir, parameters, use_conda,
storage_dir, experiment_id, block):
"""Locally run a project that has been checked out in `work_dir`."""
storage_dir_for_run = _get_storage_dir(storage_dir)
eprint(
"=== Created directory %s for downloading remote URIs passed to arguments of "
"type 'path' ===" % storage_dir_for_run)
# Try to build the command first in case the user mis-specified parameters
run_project_command = project.get_entry_point(entry_point)\
.compute_command(parameters, storage_dir_for_run)
commands = []
if use_conda:
conda_env_path = os.path.abspath(
os.path.join(work_dir, project.conda_env))
_maybe_create_conda_env(conda_env_path)
commands.append("source activate %s" %
_get_conda_env_name(conda_env_path))
# Create a new run and log every provided parameter into it.
active_run = tracking._create_run(
experiment_id=experiment_id,
source_name=project.uri,
source_version=tracking._get_git_commit(work_dir),
entry_point_name=entry_point,
source_type=SourceType.PROJECT)
if parameters is not None:
for key, value in parameters.items():
active_run.log_param(Param(key, value))
# Add the run id into a magic environment variable that the subprocess will read,
# causing it to reuse the run.
env_map = {
tracking._RUN_ID_ENV_VAR: active_run.run_info.run_uuid,
tracking._TRACKING_URI_ENV_VAR: tracking.get_tracking_uri(),
tracking._EXPERIMENT_ID_ENV_VAR: str(experiment_id),
}
commands.append(run_project_command)
command = " && ".join(commands)
eprint("=== Running command '%s' in run with ID '%s' === " %
(command, active_run.run_info.run_uuid))
return _launch_local_run(active_run,
command,
work_dir,
env_map,
stream_output=block)
def _run_project(project, entry_point, work_dir, parameters, use_conda,
storage_dir, experiment_id):
"""Locally run a project that has been checked out in `work_dir`."""
if storage_dir is not None and not os.path.exists(storage_dir):
os.makedirs(storage_dir)
storage_dir_for_run = tempfile.mkdtemp(dir=storage_dir)
eprint(
"=== Created directory %s for downloading remote URIs passed to arguments of "
"type 'path' ===" % storage_dir_for_run)
# Try to build the command first in case the user mis-specified parameters
run_project_command = project.get_entry_point(entry_point)\
.compute_command(parameters, storage_dir_for_run)
commands = []
if use_conda:
with open(os.path.join(work_dir, project.conda_env)) as conda_env_file:
conda_env_sha = hashlib.sha1(
conda_env_file.read().encode("utf-8")).hexdigest()
conda_env = "mlflow-%s" % conda_env_sha
(exit_code, _, stderr) = process.exec_cmd(["conda", "--help"],
throw_on_error=False)
if exit_code != 0:
eprint(
'conda is not installed properly. Please follow the instructions on '
'https://conda.io/docs/user-guide/install/index.html')
eprint(stderr)
sys.exit(1)
(_, stdout,
stderr) = process.exec_cmd(["conda", "env", "list", "--json"])
env_names = [
os.path.basename(env) for env in json.loads(stdout)['envs']
]
conda_action = 'create'
if conda_env not in env_names:
eprint('=== Creating conda environment %s ===' % conda_env)
process.exec_cmd([
"conda", "env", conda_action, "-n", conda_env, "--file",
project.conda_env
],
cwd=work_dir,
stream_output=True)
commands.append("source activate %s" % conda_env)
# Create a new run and log every provided parameter into it.
active_run = tracking.start_run(
experiment_id=experiment_id,
source_name=project.uri,
source_version=tracking._get_git_commit(work_dir),
entry_point_name=entry_point,
source_type=SourceType.PROJECT)
for key, value in parameters.items():
active_run.log_param(Param(key, value))
# Add the run id into a magic environment variable that the subprocess will read,
# causing it to reuse the run.
exp_id = experiment_id or tracking._get_experiment_id()
env_map = {
tracking._RUN_NAME_ENV_VAR: active_run.run_info.run_uuid,
tracking._TRACKING_URI_ENV_VAR: tracking.get_tracking_uri(),
tracking._EXPERIMENT_ID_ENV_VAR: str(exp_id),
}
commands.append(run_project_command)
command = " && ".join(commands)
eprint("=== Running command: %s ===" % command)
try:
process.exec_cmd([os.environ.get("SHELL", "bash"), "-c", command],
cwd=work_dir,
stream_output=True,
env=env_map)
tracking.end_run()
eprint("=== Run succeeded ===")
except process.ShellCommandException:
tracking.end_run("FAILED")
eprint("=== Run failed ===")
