def test_uri_types():
assert is_local_uri("mlruns")
assert is_local_uri("./mlruns")
assert is_local_uri("file:///foo/mlruns")
assert is_local_uri("file:foo/mlruns")
assert not is_local_uri("https://whatever")
assert not is_local_uri("http://whatever")
assert not is_local_uri("databricks")
assert not is_local_uri("databricks:whatever")
assert not is_local_uri("databricks://whatever")
assert is_databricks_uri("databricks")
assert is_databricks_uri("databricks:whatever")
assert is_databricks_uri("databricks://whatever")
assert not is_databricks_uri("mlruns")
assert not is_databricks_uri("http://whatever")
assert is_http_uri("http://whatever")
assert is_http_uri("https://whatever")
assert not is_http_uri("file://whatever")
assert not is_http_uri("databricks://whatever")
assert not is_http_uri("mlruns")
def __init__(self, db_uri, default_artifact_root):
"""
Create a database backed store.
:param db_uri: The SQLAlchemy database URI string to connect to the database. See
the `SQLAlchemy docs
<https://docs.sqlalchemy.org/en/latest/core/engines.html#database-urls>`_
for format specifications. Mlflow supports the dialects ``mysql``,
``mssql``, ``sqlite``, and ``postgresql``.
:param default_artifact_root: Path/URI to location suitable for large data (such as a blob
store object, DBFS path, or shared NFS file system).
"""
super(SqlAlchemyStore, self).__init__()
self.db_uri = db_uri
self.db_type = extract_db_type_from_uri(db_uri)
self.artifact_root_uri = default_artifact_root
self.engine = kiwi.store.db.utils.create_sqlalchemy_engine(db_uri)
# On a completely fresh MLflow installation against an empty database (verify database
# emptiness by checking that 'experiments' etc aren't in the list of table names), run all
# DB migrations
expected_tables = [
SqlExperiment.__tablename__,
SqlRun.__tablename__,
SqlMetric.__tablename__,
SqlParam.__tablename__,
SqlTag.__tablename__,
SqlExperimentTag.__tablename__,
SqlLatestMetric.__tablename__,
]
inspected_tables = set(
sqlalchemy.inspect(self.engine).get_table_names())
if any([table not in inspected_tables for table in expected_tables]):
kiwi.store.db.utils._initialize_tables(self.engine)
Base.metadata.bind = self.engine
SessionMaker = sqlalchemy.orm.sessionmaker(bind=self.engine)
self.ManagedSessionMaker = kiwi.store.db.utils._get_managed_session_maker(
SessionMaker, self.db_type)
kiwi.store.db.utils._verify_schema(self.engine)
if is_local_uri(default_artifact_root):
mkdir(local_file_uri_to_path(default_artifact_root))
if len(self.list_experiments()) == 0:
with self.ManagedSessionMaker() as session:
self._create_default_experiment(session)
def server(backend_store_uri, default_artifact_root, host, port, workers,
static_prefix, gunicorn_opts, waitress_opts, expose_prometheus):
"""
Run the MLflow tracking server.
The server which listen on http://localhost:5000 by default, and only accept connections
from the local machine. To let the server accept connections from other machines, you will need
to pass ``--host 0.0.0.0`` to listen on all network interfaces
(or a specific interface address).
"""
_validate_server_args(gunicorn_opts=gunicorn_opts,
workers=workers,
waitress_opts=waitress_opts)
# Ensure that both backend_store_uri and default_artifact_uri are set correctly.
if not backend_store_uri:
backend_store_uri = DEFAULT_LOCAL_FILE_AND_ARTIFACT_PATH
if not default_artifact_root:
if is_local_uri(backend_store_uri):
default_artifact_root = backend_store_uri
else:
eprint(
"Option 'default-artifact-root' is required, when backend store is not "
"local file based.")
sys.exit(1)
try:
initialize_backend_stores(backend_store_uri, default_artifact_root)
except Exception as e: # pylint: disable=broad-except
_logger.error("Error initializing backend store")
_logger.exception(e)
sys.exit(1)
try:
_run_server(backend_store_uri, default_artifact_root, host, port,
static_prefix, workers, gunicorn_opts, waitress_opts,
expose_prometheus)
except ShellCommandException:
eprint(
"Running the mlflow server failed. Please see the logs above for details."
)
sys.exit(1)
def ui(backend_store_uri, default_artifact_root, port, host):
"""
Launch the MLflow tracking UI for local viewing of run results. To launch a production
server, use the "mlflow server" command instead.
The UI will be visible at http://localhost:5000 by default, and only accept connections
from the local machine. To let the UI server accept connections from other machines, you will
need to pass ``--host 0.0.0.0`` to listen on all network interfaces (or a specific interface
address).
"""
# Ensure that both backend_store_uri and default_artifact_uri are set correctly.
if not backend_store_uri:
backend_store_uri = DEFAULT_LOCAL_FILE_AND_ARTIFACT_PATH
if not default_artifact_root:
if is_local_uri(backend_store_uri):
default_artifact_root = backend_store_uri
else:
default_artifact_root = DEFAULT_LOCAL_FILE_AND_ARTIFACT_PATH
try:
initialize_backend_stores(backend_store_uri, default_artifact_root)
except Exception as e: # pylint: disable=broad-except
_logger.error("Error initializing backend store")
_logger.exception(e)
sys.exit(1)
# TODO: We eventually want to disable the write path in this version of the server.
try:
_run_server(backend_store_uri, default_artifact_root, host, port, None,
1)
except ShellCommandException:
eprint(
"Running the mlflow server failed. Please see the logs above for details."
)
sys.exit(1)
def log_model(spark_model,
artifact_path,
conda_env=None,
dfs_tmpdir=None,
sample_input=None,
registered_model_name=None,
signature: ModelSignature = None,
input_example: ModelInputExample = None):
"""
Log a Spark MLlib model as an MLflow artifact for the current run. This uses the
MLlib persistence format and produces an MLflow Model with the Spark flavor.
Note: If no run is active, it will instantiate a run to obtain a run_id.
:param spark_model: Spark model to be saved - MLflow can only save descendants of
pyspark.ml.Model which implement MLReadable and MLWritable.
:param artifact_path: Run relative artifact path.
:param conda_env: Either a dictionary representation of a Conda environment or the path to a
Conda environment yaml file. If provided, this decsribes the environment
this model should be run in. At minimum, it should specify the dependencies
contained in :func:`get_default_conda_env()`. If `None`, the default
:func:`get_default_conda_env()` environment is added to the model.
The following is an *example* dictionary representation of a Conda
environment::
{
'name': 'mlflow-env',
'channels': ['defaults'],
'dependencies': [
'python=3.7.0',
'pyspark=2.3.0'
]
}
:param dfs_tmpdir: Temporary directory path on Distributed (Hadoop) File System (DFS) or local
filesystem if running in local mode. The model is written in this
destination and then copied into the model's artifact directory. This is
necessary as Spark ML models read from and write to DFS if running on a
cluster. If this operation completes successfully, all temporary files
created on the DFS are removed. Defaults to ``/tmp/mlflow``.
:param sample_input: A sample input used to add the MLeap flavor to the model.
This must be a PySpark DataFrame that the model can evaluate. If
``sample_input`` is ``None``, the MLeap flavor is not added.
:param registered_model_name: (Experimental) If given, create a model version under
``registered_model_name``, also creating a registered model if one
with the given name does not exist.
:param signature: (Experimental) :py:class:`ModelSignature <mlflow.models.ModelSignature>`
describes model input and output :py:class:`Schema <mlflow.types.Schema>`.
The model signature can be :py:func:`inferred <mlflow.models.infer_signature>`
from datasets with valid model input (e.g. the training dataset with target
column omitted) and valid model output (e.g. model predictions generated on
the training dataset), for example:
.. code-block:: python
from mlflow.models.signature import infer_signature
train = df.drop_column("target_label")
predictions = ... # compute model predictions
signature = infer_signature(train, predictions)
:param input_example: (Experimental) Input example provides one or several instances of valid
model input. The example can be used as a hint of what data to feed the
model. The given example will be converted to a Pandas DataFrame and then
serialized to json using the Pandas split-oriented format. Bytes are
base64-encoded.
.. code-block:: python
:caption: Example
from pyspark.ml import Pipeline
from pyspark.ml.classification import LogisticRegression
from pyspark.ml.feature import HashingTF, Tokenizer
training = spark.createDataFrame([
(0, "a b c d e spark", 1.0),
(1, "b d", 0.0),
(2, "spark f g h", 1.0),
(3, "hadoop mapreduce", 0.0) ], ["id", "text", "label"])
tokenizer = Tokenizer(inputCol="text", outputCol="words")
hashingTF = HashingTF(inputCol=tokenizer.getOutputCol(), outputCol="features")
lr = LogisticRegression(maxIter=10, regParam=0.001)
pipeline = Pipeline(stages=[tokenizer, hashingTF, lr])
model = pipeline.fit(training)
mlflow.spark.log_model(model, "spark-model")
"""
from py4j.protocol import Py4JJavaError
_validate_model(spark_model)
from pyspark.ml import PipelineModel
if not isinstance(spark_model, PipelineModel):
spark_model = PipelineModel([spark_model])
run_id = kiwi.tracking.fluent._get_or_start_run().info.run_id
run_root_artifact_uri = kiwi.get_artifact_uri()
# If the artifact URI is a local filesystem path, defer to Model.log() to persist the model,
# since Spark may not be able to write directly to the driver's filesystem. For example,
# writing to `file:/uri` will write to the local filesystem from each executor, which will
# be incorrect on multi-node clusters - to avoid such issues we just use the Model.log() path
# here.
if is_local_uri(run_root_artifact_uri):
return Model.log(artifact_path=artifact_path,
flavor=kiwi.spark,
spark_model=spark_model,
conda_env=conda_env,
dfs_tmpdir=dfs_tmpdir,
sample_input=sample_input,
registered_model_name=registered_model_name)
# If Spark cannot write directly to the artifact repo, defer to Model.log() to persist the
# model
model_dir = os.path.join(run_root_artifact_uri, artifact_path)
try:
spark_model.save(os.path.join(model_dir, _SPARK_MODEL_PATH_SUB))
except Py4JJavaError:
return Model.log(artifact_path=artifact_path,
flavor=kiwi.spark,
spark_model=spark_model,
conda_env=conda_env,
dfs_tmpdir=dfs_tmpdir,
sample_input=sample_input,
registered_model_name=registered_model_name,
signature=signature,
input_example=input_example)
# Otherwise, override the default model log behavior and save model directly to artifact repo
mlflow_model = Model(artifact_path=artifact_path, run_id=run_id)
with TempDir() as tmp:
tmp_model_metadata_dir = tmp.path()
_save_model_metadata(tmp_model_metadata_dir,
spark_model,
mlflow_model,
sample_input,
conda_env,
signature=signature,
input_example=input_example)
kiwi.tracking.fluent.log_artifacts(tmp_model_metadata_dir,
artifact_path)
if registered_model_name is not None:
kiwi.register_model("runs:/%s/%s" % (run_id, artifact_path),
registered_model_name)