Spark

zenml.integrations.spark

The Spark integration module to enable distributed processing for steps.

Attributes

SPARK = 'spark' module-attribute

SPARK_KUBERNETES_STEP_OPERATOR = 'spark-kubernetes' module-attribute

Classes

Flavor

Class for ZenML Flavors.

Attributes

config_class: Type[StackComponentConfig] abstractmethod property

Returns StackComponentConfig config class.

Returns:

Type	Description
Type[StackComponentConfig]	The config class.

config_schema: Dict[str, Any] property

The config schema for a flavor.

Returns:

Type	Description
Dict[str, Any]	The config schema.

docs_url: Optional[str] property

A url to point at docs explaining this flavor.

Returns:

Type	Description
Optional[str]	A flavor docs url.

implementation_class: Type[StackComponent] abstractmethod property

Implementation class for this flavor.

Returns:

Type	Description
Type[StackComponent]	The implementation class for this flavor.

logo_url: Optional[str] property

A url to represent the flavor in the dashboard.

Returns:

Type	Description
Optional[str]	The flavor logo.

name: str abstractmethod property

The flavor name.

Returns:

Type	Description
str	The flavor name.

sdk_docs_url: Optional[str] property

A url to point at SDK docs explaining this flavor.

Returns:

Type	Description
Optional[str]	A flavor SDK docs url.

service_connector_requirements: Optional[ServiceConnectorRequirements] property

Service connector resource requirements for service connectors.

Specifies resource requirements that are used to filter the available service connector types that are compatible with this flavor.

Returns:

Type	Description
Optional[ServiceConnectorRequirements]	Requirements for compatible service connectors, if a service
Optional[ServiceConnectorRequirements]	connector is required for this flavor.

type: StackComponentType abstractmethod property

The stack component type.

Returns:

Type	Description
StackComponentType	The stack component type.

Functions

from_model(flavor_model: FlavorResponse) -> Flavor classmethod

Loads a flavor from a model.

Parameters:

Name	Type	Description	Default
flavor_model	FlavorResponse	The model to load from.	required

Raises:

Type	Description
CustomFlavorImportError	If the custom flavor can't be imported.
ImportError	If the flavor can't be imported.

Returns:

Type	Description
Flavor	The loaded flavor.

Source code in src/zenml/stack/flavor.py

@classmethod
def from_model(cls, flavor_model: FlavorResponse) -> "Flavor":
    """Loads a flavor from a model.

    Args:
        flavor_model: The model to load from.

    Raises:
        CustomFlavorImportError: If the custom flavor can't be imported.
        ImportError: If the flavor can't be imported.

    Returns:
        The loaded flavor.
    """
    try:
        flavor = source_utils.load(flavor_model.source)()
    except (ModuleNotFoundError, ImportError, NotImplementedError) as err:
        if flavor_model.is_custom:
            flavor_module, _ = flavor_model.source.rsplit(".", maxsplit=1)
            expected_file_path = os.path.join(
                source_utils.get_source_root(),
                flavor_module.replace(".", os.path.sep),
            )
            raise CustomFlavorImportError(
                f"Couldn't import custom flavor {flavor_model.name}: "
                f"{err}. Make sure the custom flavor class "
                f"`{flavor_model.source}` is importable. If it is part of "
                "a library, make sure it is installed. If "
                "it is a local code file, make sure it exists at "
                f"`{expected_file_path}.py`."
            )
        else:
            raise ImportError(
                f"Couldn't import flavor {flavor_model.name}: {err}"
            )
    return cast(Flavor, flavor)

generate_default_docs_url() -> str

Generate the doc urls for all inbuilt and integration flavors.

Note that this method is not going to be useful for custom flavors, which do not have any docs in the main zenml docs.

Returns:

Type	Description
str	The complete url to the zenml documentation

Source code in src/zenml/stack/flavor.py

def generate_default_docs_url(self) -> str:
    """Generate the doc urls for all inbuilt and integration flavors.

    Note that this method is not going to be useful for custom flavors,
    which do not have any docs in the main zenml docs.

    Returns:
        The complete url to the zenml documentation
    """
    from zenml import __version__

    component_type = self.type.plural.replace("_", "-")
    name = self.name.replace("_", "-")

    try:
        is_latest = is_latest_zenml_version()
    except RuntimeError:
        # We assume in error cases that we are on the latest version
        is_latest = True

    if is_latest:
        base = "https://docs.zenml.io"
    else:
        base = f"https://zenml-io.gitbook.io/zenml-legacy-documentation/v/{__version__}"
    return f"{base}/stack-components/{component_type}/{name}"

generate_default_sdk_docs_url() -> str

Generate SDK docs url for a flavor.

Returns:

Type	Description
str	The complete url to the zenml SDK docs

Source code in src/zenml/stack/flavor.py

def generate_default_sdk_docs_url(self) -> str:
    """Generate SDK docs url for a flavor.

    Returns:
        The complete url to the zenml SDK docs
    """
    from zenml import __version__

    base = f"https://sdkdocs.zenml.io/{__version__}"

    component_type = self.type.plural

    if "zenml.integrations" in self.__module__:
        # Get integration name out of module path which will look something
        #  like this "zenml.integrations.<integration>....
        integration = self.__module__.split(
            "zenml.integrations.", maxsplit=1
        )[1].split(".")[0]

        return (
            f"{base}/integration_code_docs"
            f"/integrations-{integration}/#{self.__module__}"
        )

    else:
        return (
            f"{base}/core_code_docs/core-{component_type}/"
            f"#{self.__module__}"
        )

to_model(integration: Optional[str] = None, is_custom: bool = True) -> FlavorRequest

Converts a flavor to a model.

Parameters:

Name	Type	Description	Default
integration	Optional[str]	The integration to use for the model.	None
is_custom	bool	Whether the flavor is a custom flavor.	True

Returns:

Type	Description
FlavorRequest	The model.

Source code in src/zenml/stack/flavor.py

def to_model(
    self,
    integration: Optional[str] = None,
    is_custom: bool = True,
) -> FlavorRequest:
    """Converts a flavor to a model.

    Args:
        integration: The integration to use for the model.
        is_custom: Whether the flavor is a custom flavor.

    Returns:
        The model.
    """
    connector_requirements = self.service_connector_requirements
    connector_type = (
        connector_requirements.connector_type
        if connector_requirements
        else None
    )
    resource_type = (
        connector_requirements.resource_type
        if connector_requirements
        else None
    )
    resource_id_attr = (
        connector_requirements.resource_id_attr
        if connector_requirements
        else None
    )

    model = FlavorRequest(
        name=self.name,
        type=self.type,
        source=source_utils.resolve(self.__class__).import_path,
        config_schema=self.config_schema,
        connector_type=connector_type,
        connector_resource_type=resource_type,
        connector_resource_id_attr=resource_id_attr,
        integration=integration,
        logo_url=self.logo_url,
        docs_url=self.docs_url,
        sdk_docs_url=self.sdk_docs_url,
        is_custom=is_custom,
    )
    return model

Integration

Base class for integration in ZenML.

Functions

activate() -> None classmethod

Abstract method to activate the integration.

Source code in src/zenml/integrations/integration.py

@classmethod
def activate(cls) -> None:
    """Abstract method to activate the integration."""

check_installation() -> bool classmethod

Method to check whether the required packages are installed.

Returns:

Type	Description
bool	True if all required packages are installed, False otherwise.

Source code in src/zenml/integrations/integration.py

@classmethod
def check_installation(cls) -> bool:
    """Method to check whether the required packages are installed.

    Returns:
        True if all required packages are installed, False otherwise.
    """
    for r in cls.get_requirements():
        try:
            # First check if the base package is installed
            dist = pkg_resources.get_distribution(r)

            # Next, check if the dependencies (including extras) are
            # installed
            deps: List[Requirement] = []

            _, extras = parse_requirement(r)
            if extras:
                extra_list = extras[1:-1].split(",")
                for extra in extra_list:
                    try:
                        requirements = dist.requires(extras=[extra])  # type: ignore[arg-type]
                    except pkg_resources.UnknownExtra as e:
                        logger.debug(f"Unknown extra: {str(e)}")
                        return False
                    deps.extend(requirements)
            else:
                deps = dist.requires()

            for ri in deps:
                try:
                    # Remove the "extra == ..." part from the requirement string
                    cleaned_req = re.sub(
                        r"; extra == \"\w+\"", "", str(ri)
                    )
                    pkg_resources.get_distribution(cleaned_req)
                except pkg_resources.DistributionNotFound as e:
                    logger.debug(
                        f"Unable to find required dependency "
                        f"'{e.req}' for requirement '{r}' "
                        f"necessary for integration '{cls.NAME}'."
                    )
                    return False
                except pkg_resources.VersionConflict as e:
                    logger.debug(
                        f"Package version '{e.dist}' does not match "
                        f"version '{e.req}' required by '{r}' "
                        f"necessary for integration '{cls.NAME}'."
                    )
                    return False

        except pkg_resources.DistributionNotFound as e:
            logger.debug(
                f"Unable to find required package '{e.req}' for "
                f"integration {cls.NAME}."
            )
            return False
        except pkg_resources.VersionConflict as e:
            logger.debug(
                f"Package version '{e.dist}' does not match version "
                f"'{e.req}' necessary for integration {cls.NAME}."
            )
            return False

    logger.debug(
        f"Integration {cls.NAME} is installed correctly with "
        f"requirements {cls.get_requirements()}."
    )
    return True

flavors() -> List[Type[Flavor]] classmethod

Abstract method to declare new stack component flavors.

Returns:

Type	Description
List[Type[Flavor]]	A list of new stack component flavors.

Source code in src/zenml/integrations/integration.py

@classmethod
def flavors(cls) -> List[Type[Flavor]]:
    """Abstract method to declare new stack component flavors.

    Returns:
        A list of new stack component flavors.
    """
    return []

get_requirements(target_os: Optional[str] = None, python_version: Optional[str] = None) -> List[str] classmethod

Method to get the requirements for the integration.

Parameters:

Name	Type	Description	Default
target_os	Optional[str]	The target operating system to get the requirements for.	None
python_version	Optional[str]	The Python version to use for the requirements.	None

Returns:

Type	Description
List[str]	A list of requirements.

Source code in src/zenml/integrations/integration.py

@classmethod
def get_requirements(
    cls,
    target_os: Optional[str] = None,
    python_version: Optional[str] = None,
) -> List[str]:
    """Method to get the requirements for the integration.

    Args:
        target_os: The target operating system to get the requirements for.
        python_version: The Python version to use for the requirements.

    Returns:
        A list of requirements.
    """
    return cls.REQUIREMENTS

get_uninstall_requirements(target_os: Optional[str] = None) -> List[str] classmethod

Method to get the uninstall requirements for the integration.

Parameters:

Name	Type	Description	Default
target_os	Optional[str]	The target operating system to get the requirements for.	None

Returns:

Type	Description
List[str]	A list of requirements.

Source code in src/zenml/integrations/integration.py

@classmethod
def get_uninstall_requirements(
    cls, target_os: Optional[str] = None
) -> List[str]:
    """Method to get the uninstall requirements for the integration.

    Args:
        target_os: The target operating system to get the requirements for.

    Returns:
        A list of requirements.
    """
    ret = []
    for each in cls.get_requirements(target_os=target_os):
        is_ignored = False
        for ignored in cls.REQUIREMENTS_IGNORED_ON_UNINSTALL:
            if each.startswith(ignored):
                is_ignored = True
                break
        if not is_ignored:
            ret.append(each)
    return ret

plugin_flavors() -> List[Type[BasePluginFlavor]] classmethod

Abstract method to declare new plugin flavors.

Returns:

Type	Description
List[Type[BasePluginFlavor]]	A list of new plugin flavors.

Source code in src/zenml/integrations/integration.py

@classmethod
def plugin_flavors(cls) -> List[Type["BasePluginFlavor"]]:
    """Abstract method to declare new plugin flavors.

    Returns:
        A list of new plugin flavors.
    """
    return []

SparkIntegration

Bases: Integration

Definition of Spark integration for ZenML.

Functions

activate() -> None classmethod

Activating the corresponding Spark materializers.

Source code in src/zenml/integrations/spark/__init__.py

@classmethod
def activate(cls) -> None:
    """Activating the corresponding Spark materializers."""
    from zenml.integrations.spark import materializers  # noqa

flavors() -> List[Type[Flavor]] classmethod

Declare the stack component flavors for the Spark integration.

Returns:

Type	Description
List[Type[Flavor]]	The flavor wrapper for the step operator flavor

Source code in src/zenml/integrations/spark/__init__.py

@classmethod
def flavors(cls) -> List[Type[Flavor]]:
    """Declare the stack component flavors for the Spark integration.

    Returns:
        The flavor wrapper for the step operator flavor
    """
    from zenml.integrations.spark.flavors import (
        KubernetesSparkStepOperatorFlavor,
    )

    return [KubernetesSparkStepOperatorFlavor]

StackComponentType

Bases: StrEnum

All possible types a StackComponent can have.

Attributes

plural: str property

Returns the plural of the enum value.

Returns:

Type	Description
str	The plural of the enum value.

Modules

flavors

Spark integration flavors.

Classes

KubernetesSparkStepOperatorConfig(warn_about_plain_text_secrets: bool = False, **kwargs: Any)

Bases: SparkStepOperatorConfig

Config for the Kubernetes Spark step operator.

Attributes:

Name	Type	Description
namespace	Optional[str]	the namespace under which the driver and executor pods will run.
service_account	Optional[str]	the service account that will be used by various Spark components (to create and watch the pods).

Source code in src/zenml/stack/stack_component.py

def __init__(
    self, warn_about_plain_text_secrets: bool = False, **kwargs: Any
) -> None:
    """Ensures that secret references don't clash with pydantic validation.

    StackComponents allow the specification of all their string attributes
    using secret references of the form `{{secret_name.key}}`. This however
    is only possible when the stack component does not perform any explicit
    validation of this attribute using pydantic validators. If this were
    the case, the validation would run on the secret reference and would
    fail or in the worst case, modify the secret reference and lead to
    unexpected behavior. This method ensures that no attributes that require
    custom pydantic validation are set as secret references.

    Args:
        warn_about_plain_text_secrets: If true, then warns about using
            plain-text secrets.
        **kwargs: Arguments to initialize this stack component.

    Raises:
        ValueError: If an attribute that requires custom pydantic validation
            is passed as a secret reference, or if the `name` attribute
            was passed as a secret reference.
    """
    for key, value in kwargs.items():
        try:
            field = self.__class__.model_fields[key]
        except KeyError:
            # Value for a private attribute or non-existing field, this
            # will fail during the upcoming pydantic validation
            continue

        if value is None:
            continue

        if not secret_utils.is_secret_reference(value):
            if (
                secret_utils.is_secret_field(field)
                and warn_about_plain_text_secrets
            ):
                logger.warning(
                    "You specified a plain-text value for the sensitive "
                    f"attribute `{key}` for a `{self.__class__.__name__}` "
                    "stack component. This is currently only a warning, "
                    "but future versions of ZenML will require you to pass "
                    "in sensitive information as secrets. Check out the "
                    "documentation on how to configure your stack "
                    "components with secrets here: "
                    "https://docs.zenml.io/getting-started/deploying-zenml/secret-management"
                )
            continue

        if pydantic_utils.has_validators(
            pydantic_class=self.__class__, field_name=key
        ):
            raise ValueError(
                f"Passing the stack component attribute `{key}` as a "
                "secret reference is not allowed as additional validation "
                "is required for this attribute."
            )

    super().__init__(**kwargs)

KubernetesSparkStepOperatorFlavor

Bases: SparkStepOperatorFlavor

Flavor for the Kubernetes Spark step operator.

Attributes

config_class: Type[KubernetesSparkStepOperatorConfig] property

Returns KubernetesSparkStepOperatorConfig config class.

Returns:

Type	Description
Type[KubernetesSparkStepOperatorConfig]	The config class.

docs_url: Optional[str] property

A url to point at docs explaining this flavor.

Returns:

Type	Description
Optional[str]	A flavor docs url.

implementation_class: Type[KubernetesSparkStepOperator] property

Implementation class for this flavor.

Returns:

Type	Description
Type[KubernetesSparkStepOperator]	The implementation class.

logo_url: str property

A url to represent the flavor in the dashboard.

Returns:

Type	Description
str	The flavor logo.

name: str property

Name of the flavor.

Returns:

Type	Description
str	The name of the flavor.

sdk_docs_url: Optional[str] property

A url to point at SDK docs explaining this flavor.

Returns:

Type	Description
Optional[str]	A flavor SDK docs url.

SparkStepOperatorConfig(warn_about_plain_text_secrets: bool = False, **kwargs: Any)

Bases: BaseStepOperatorConfig, SparkStepOperatorSettings

Spark step operator config.

Attributes:

Name	Type	Description
master	str	is the master URL for the cluster. You might see different schemes for different cluster managers which are supported by Spark like Mesos, YARN, or Kubernetes. Within the context of this PR, the implementation supports Kubernetes as a cluster manager.

Source code in src/zenml/stack/stack_component.py

def __init__(
    self, warn_about_plain_text_secrets: bool = False, **kwargs: Any
) -> None:
    """Ensures that secret references don't clash with pydantic validation.

    StackComponents allow the specification of all their string attributes
    using secret references of the form `{{secret_name.key}}`. This however
    is only possible when the stack component does not perform any explicit
    validation of this attribute using pydantic validators. If this were
    the case, the validation would run on the secret reference and would
    fail or in the worst case, modify the secret reference and lead to
    unexpected behavior. This method ensures that no attributes that require
    custom pydantic validation are set as secret references.

    Args:
        warn_about_plain_text_secrets: If true, then warns about using
            plain-text secrets.
        **kwargs: Arguments to initialize this stack component.

    Raises:
        ValueError: If an attribute that requires custom pydantic validation
            is passed as a secret reference, or if the `name` attribute
            was passed as a secret reference.
    """
    for key, value in kwargs.items():
        try:
            field = self.__class__.model_fields[key]
        except KeyError:
            # Value for a private attribute or non-existing field, this
            # will fail during the upcoming pydantic validation
            continue

        if value is None:
            continue

        if not secret_utils.is_secret_reference(value):
            if (
                secret_utils.is_secret_field(field)
                and warn_about_plain_text_secrets
            ):
                logger.warning(
                    "You specified a plain-text value for the sensitive "
                    f"attribute `{key}` for a `{self.__class__.__name__}` "
                    "stack component. This is currently only a warning, "
                    "but future versions of ZenML will require you to pass "
                    "in sensitive information as secrets. Check out the "
                    "documentation on how to configure your stack "
                    "components with secrets here: "
                    "https://docs.zenml.io/getting-started/deploying-zenml/secret-management"
                )
            continue

        if pydantic_utils.has_validators(
            pydantic_class=self.__class__, field_name=key
        ):
            raise ValueError(
                f"Passing the stack component attribute `{key}` as a "
                "secret reference is not allowed as additional validation "
                "is required for this attribute."
            )

    super().__init__(**kwargs)

SparkStepOperatorFlavor

Bases: BaseStepOperatorFlavor

Spark step operator flavor.

Attributes

config_class: Type[SparkStepOperatorConfig] property

Returns SparkStepOperatorConfig config class.

Returns:

Type	Description
Type[SparkStepOperatorConfig]	The config class.

docs_url: Optional[str] property

A url to point at docs explaining this flavor.

Returns:

Type	Description
Optional[str]	A flavor docs url.

implementation_class: Type[SparkStepOperator] property

Implementation class for this flavor.

Returns:

Type	Description
Type[SparkStepOperator]	The implementation class.

name: str property

Name of the flavor.

Returns:

Type	Description
str	The name of the flavor.

sdk_docs_url: Optional[str] property

A url to point at SDK docs explaining this flavor.

Returns:

Type	Description
Optional[str]	A flavor SDK docs url.

Modules

spark_on_kubernetes_step_operator_flavor

Spark on Kubernetes step operator flavor.

Classes

KubernetesSparkStepOperatorConfig(warn_about_plain_text_secrets: bool = False, **kwargs: Any)

Bases: SparkStepOperatorConfig

Config for the Kubernetes Spark step operator.

Attributes:

Name	Type	Description
namespace	Optional[str]	the namespace under which the driver and executor pods will run.
service_account	Optional[str]	the service account that will be used by various Spark components (to create and watch the pods).

Source code in src/zenml/stack/stack_component.py

def __init__(
    self, warn_about_plain_text_secrets: bool = False, **kwargs: Any
) -> None:
    """Ensures that secret references don't clash with pydantic validation.

    StackComponents allow the specification of all their string attributes
    using secret references of the form `{{secret_name.key}}`. This however
    is only possible when the stack component does not perform any explicit
    validation of this attribute using pydantic validators. If this were
    the case, the validation would run on the secret reference and would
    fail or in the worst case, modify the secret reference and lead to
    unexpected behavior. This method ensures that no attributes that require
    custom pydantic validation are set as secret references.

    Args:
        warn_about_plain_text_secrets: If true, then warns about using
            plain-text secrets.
        **kwargs: Arguments to initialize this stack component.

    Raises:
        ValueError: If an attribute that requires custom pydantic validation
            is passed as a secret reference, or if the `name` attribute
            was passed as a secret reference.
    """
    for key, value in kwargs.items():
        try:
            field = self.__class__.model_fields[key]
        except KeyError:
            # Value for a private attribute or non-existing field, this
            # will fail during the upcoming pydantic validation
            continue

        if value is None:
            continue

        if not secret_utils.is_secret_reference(value):
            if (
                secret_utils.is_secret_field(field)
                and warn_about_plain_text_secrets
            ):
                logger.warning(
                    "You specified a plain-text value for the sensitive "
                    f"attribute `{key}` for a `{self.__class__.__name__}` "
                    "stack component. This is currently only a warning, "
                    "but future versions of ZenML will require you to pass "
                    "in sensitive information as secrets. Check out the "
                    "documentation on how to configure your stack "
                    "components with secrets here: "
                    "https://docs.zenml.io/getting-started/deploying-zenml/secret-management"
                )
            continue

        if pydantic_utils.has_validators(
            pydantic_class=self.__class__, field_name=key
        ):
            raise ValueError(
                f"Passing the stack component attribute `{key}` as a "
                "secret reference is not allowed as additional validation "
                "is required for this attribute."
            )

    super().__init__(**kwargs)

KubernetesSparkStepOperatorFlavor

Bases: SparkStepOperatorFlavor

Flavor for the Kubernetes Spark step operator.

Attributes

config_class: Type[KubernetesSparkStepOperatorConfig] property

Returns KubernetesSparkStepOperatorConfig config class.

Returns:

Type	Description
Type[KubernetesSparkStepOperatorConfig]	The config class.

docs_url: Optional[str] property

A url to point at docs explaining this flavor.

Returns:

Type	Description
Optional[str]	A flavor docs url.

implementation_class: Type[KubernetesSparkStepOperator] property

Implementation class for this flavor.

Returns:

Type	Description
Type[KubernetesSparkStepOperator]	The implementation class.

logo_url: str property

A url to represent the flavor in the dashboard.

Returns:

Type	Description
str	The flavor logo.

name: str property

Name of the flavor.

Returns:

Type	Description
str	The name of the flavor.

sdk_docs_url: Optional[str] property

A url to point at SDK docs explaining this flavor.

Returns:

Type	Description
Optional[str]	A flavor SDK docs url.

spark_step_operator_flavor

Spark step operator flavor.

Classes

SparkStepOperatorConfig(warn_about_plain_text_secrets: bool = False, **kwargs: Any)

Bases: BaseStepOperatorConfig, SparkStepOperatorSettings

Spark step operator config.

Attributes:

Name	Type	Description
master	str	is the master URL for the cluster. You might see different schemes for different cluster managers which are supported by Spark like Mesos, YARN, or Kubernetes. Within the context of this PR, the implementation supports Kubernetes as a cluster manager.

Source code in src/zenml/stack/stack_component.py

def __init__(
    self, warn_about_plain_text_secrets: bool = False, **kwargs: Any
) -> None:
    """Ensures that secret references don't clash with pydantic validation.

    StackComponents allow the specification of all their string attributes
    using secret references of the form `{{secret_name.key}}`. This however
    is only possible when the stack component does not perform any explicit
    validation of this attribute using pydantic validators. If this were
    the case, the validation would run on the secret reference and would
    fail or in the worst case, modify the secret reference and lead to
    unexpected behavior. This method ensures that no attributes that require
    custom pydantic validation are set as secret references.

    Args:
        warn_about_plain_text_secrets: If true, then warns about using
            plain-text secrets.
        **kwargs: Arguments to initialize this stack component.

    Raises:
        ValueError: If an attribute that requires custom pydantic validation
            is passed as a secret reference, or if the `name` attribute
            was passed as a secret reference.
    """
    for key, value in kwargs.items():
        try:
            field = self.__class__.model_fields[key]
        except KeyError:
            # Value for a private attribute or non-existing field, this
            # will fail during the upcoming pydantic validation
            continue

        if value is None:
            continue

        if not secret_utils.is_secret_reference(value):
            if (
                secret_utils.is_secret_field(field)
                and warn_about_plain_text_secrets
            ):
                logger.warning(
                    "You specified a plain-text value for the sensitive "
                    f"attribute `{key}` for a `{self.__class__.__name__}` "
                    "stack component. This is currently only a warning, "
                    "but future versions of ZenML will require you to pass "
                    "in sensitive information as secrets. Check out the "
                    "documentation on how to configure your stack "
                    "components with secrets here: "
                    "https://docs.zenml.io/getting-started/deploying-zenml/secret-management"
                )
            continue

        if pydantic_utils.has_validators(
            pydantic_class=self.__class__, field_name=key
        ):
            raise ValueError(
                f"Passing the stack component attribute `{key}` as a "
                "secret reference is not allowed as additional validation "
                "is required for this attribute."
            )

    super().__init__(**kwargs)

SparkStepOperatorFlavor

Bases: BaseStepOperatorFlavor

Spark step operator flavor.

Attributes

config_class: Type[SparkStepOperatorConfig] property

Returns SparkStepOperatorConfig config class.

Returns:

Type	Description
Type[SparkStepOperatorConfig]	The config class.

docs_url: Optional[str] property

A url to point at docs explaining this flavor.

Returns:

Type	Description
Optional[str]	A flavor docs url.

implementation_class: Type[SparkStepOperator] property

Implementation class for this flavor.

Returns:

Type	Description
Type[SparkStepOperator]	The implementation class.

name: str property

Name of the flavor.

Returns:

Type	Description
str	The name of the flavor.

sdk_docs_url: Optional[str] property

A url to point at SDK docs explaining this flavor.

Returns:

Type	Description
Optional[str]	A flavor SDK docs url.

SparkStepOperatorSettings(warn_about_plain_text_secrets: bool = False, **kwargs: Any)

Bases: BaseSettings

Spark step operator settings.

Attributes:

Name	Type	Description
deploy_mode	str	can either be 'cluster' (default) or 'client' and it decides where the driver node of the application will run.
submit_kwargs	Optional[Dict[str, Any]]	is the JSON string of a dict, which will be used to define additional params if required (Spark has quite a lot of different parameters, so including them, all in the step operator was not implemented).

Source code in src/zenml/config/secret_reference_mixin.py

def __init__(
    self, warn_about_plain_text_secrets: bool = False, **kwargs: Any
) -> None:
    """Ensures that secret references are only passed for valid fields.

    This method ensures that secret references are not passed for fields
    that explicitly prevent them or require pydantic validation.

    Args:
        warn_about_plain_text_secrets: If true, then warns about using plain-text secrets.
        **kwargs: Arguments to initialize this object.

    Raises:
        ValueError: If an attribute that requires custom pydantic validation
            or an attribute which explicitly disallows secret references
            is passed as a secret reference.
    """
    for key, value in kwargs.items():
        try:
            field = self.__class__.model_fields[key]
        except KeyError:
            # Value for a private attribute or non-existing field, this
            # will fail during the upcoming pydantic validation
            continue

        if value is None:
            continue

        if not secret_utils.is_secret_reference(value):
            if (
                secret_utils.is_secret_field(field)
                and warn_about_plain_text_secrets
            ):
                logger.warning(
                    "You specified a plain-text value for the sensitive "
                    f"attribute `{key}`. This is currently only a warning, "
                    "but future versions of ZenML will require you to pass "
                    "in sensitive information as secrets. Check out the "
                    "documentation on how to configure values with secrets "
                    "here: https://docs.zenml.io/getting-started/deploying-zenml/secret-management"
                )
            continue

        if secret_utils.is_clear_text_field(field):
            raise ValueError(
                f"Passing the `{key}` attribute as a secret reference is "
                "not allowed."
            )

        requires_validation = has_validators(
            pydantic_class=self.__class__, field_name=key
        )
        if requires_validation:
            raise ValueError(
                f"Passing the attribute `{key}` as a secret reference is "
                "not allowed as additional validation is required for "
                "this attribute."
            )

    super().__init__(**kwargs)

materializers

Spark Materializers.

Classes

Modules

spark_dataframe_materializer

Implementation of the Spark Dataframe Materializer.

Classes

SparkDataFrameMaterializer(uri: str, artifact_store: Optional[BaseArtifactStore] = None)

Bases: BaseMaterializer

Materializer to read/write Spark dataframes.

Source code in src/zenml/materializers/base_materializer.py

def __init__(
    self, uri: str, artifact_store: Optional[BaseArtifactStore] = None
):
    """Initializes a materializer with the given URI.

    Args:
        uri: The URI where the artifact data will be stored.
        artifact_store: The artifact store used to store this artifact.
    """
    self.uri = uri
    self._artifact_store = artifact_store

Functions

extract_metadata(df: DataFrame) -> Dict[str, MetadataType]

Extract metadata from the given DataFrame object.

Parameters:

Name	Type	Description	Default
df	DataFrame	The DataFrame object to extract metadata from.	required

Returns:

Type	Description
Dict[str, MetadataType]	The extracted metadata as a dictionary.

Source code in src/zenml/integrations/spark/materializers/spark_dataframe_materializer.py

def extract_metadata(self, df: DataFrame) -> Dict[str, "MetadataType"]:
    """Extract metadata from the given `DataFrame` object.

    Args:
        df: The `DataFrame` object to extract metadata from.

    Returns:
        The extracted metadata as a dictionary.
    """
    return {
        "shape": (df.count(), len(df.columns)),
    }

load(data_type: Type[Any]) -> DataFrame

Reads and returns a spark dataframe.

Parameters:

Name	Type	Description	Default
data_type	Type[Any]	The type of the data to read.	required

Returns:

Type	Description
DataFrame	A loaded spark dataframe.

Source code in src/zenml/integrations/spark/materializers/spark_dataframe_materializer.py

def load(self, data_type: Type[Any]) -> DataFrame:
    """Reads and returns a spark dataframe.

    Args:
        data_type: The type of the data to read.

    Returns:
        A loaded spark dataframe.
    """
    # Create the Spark session
    spark = SparkSession.builder.getOrCreate()

    # Read the data
    path = os.path.join(self.uri, DEFAULT_FILEPATH)
    return spark.read.parquet(path)

save(df: DataFrame) -> None

Writes a spark dataframe.

Parameters:

Name	Type	Description	Default
df	DataFrame	A spark dataframe object.	required

Source code in src/zenml/integrations/spark/materializers/spark_dataframe_materializer.py

def save(self, df: DataFrame) -> None:
    """Writes a spark dataframe.

    Args:
        df: A spark dataframe object.
    """
    # Write the dataframe to the artifact store
    path = os.path.join(self.uri, DEFAULT_FILEPATH)
    df.write.parquet(path)

spark_model_materializer

Implementation of the Spark Model Materializer.

Classes

SparkModelMaterializer(uri: str, artifact_store: Optional[BaseArtifactStore] = None)

Bases: BaseMaterializer

Materializer to read/write Spark models.

Source code in src/zenml/materializers/base_materializer.py

def __init__(
    self, uri: str, artifact_store: Optional[BaseArtifactStore] = None
):
    """Initializes a materializer with the given URI.

    Args:
        uri: The URI where the artifact data will be stored.
        artifact_store: The artifact store used to store this artifact.
    """
    self.uri = uri
    self._artifact_store = artifact_store

Functions

load(model_type: Type[Any]) -> Union[Transformer, Estimator, Model]

Reads and returns a Spark ML model.

Parameters:

Name	Type	Description	Default
model_type	Type[Any]	The type of the model to read.	required

Returns:

Type	Description
Union[Transformer, Estimator, Model]	A loaded spark model.

Source code in src/zenml/integrations/spark/materializers/spark_model_materializer.py

def load(
    self, model_type: Type[Any]
) -> Union[Transformer, Estimator, Model]:  # type: ignore[type-arg]
    """Reads and returns a Spark ML model.

    Args:
        model_type: The type of the model to read.

    Returns:
        A loaded spark model.
    """
    path = os.path.join(self.uri, DEFAULT_FILEPATH)
    return model_type.load(path)  # type: ignore[no-any-return]

save(model: Union[Transformer, Estimator, Model]) -> None

Writes a spark model.

Parameters:

Name	Type	Description	Default
model	Union[Transformer, Estimator, Model]	A spark model.	required

Source code in src/zenml/integrations/spark/materializers/spark_model_materializer.py

def save(
    self,
    model: Union[Transformer, Estimator, Model],  # type: ignore[type-arg]
) -> None:
    """Writes a spark model.

    Args:
        model: A spark model.
    """
    # Write the dataframe to the artifact store
    path = os.path.join(self.uri, DEFAULT_FILEPATH)
    model.save(path)  # type: ignore[union-attr]

step_operators

Spark Step Operators.

Classes

KubernetesSparkStepOperator(name: str, id: UUID, config: StackComponentConfig, flavor: str, type: StackComponentType, user: Optional[UUID], created: datetime, updated: datetime, labels: Optional[Dict[str, Any]] = None, connector_requirements: Optional[ServiceConnectorRequirements] = None, connector: Optional[UUID] = None, connector_resource_id: Optional[str] = None, *args: Any, **kwargs: Any)

Bases: SparkStepOperator

Step operator which runs Steps with Spark on Kubernetes.

Source code in src/zenml/stack/stack_component.py

def __init__(
    self,
    name: str,
    id: UUID,
    config: StackComponentConfig,
    flavor: str,
    type: StackComponentType,
    user: Optional[UUID],
    created: datetime,
    updated: datetime,
    labels: Optional[Dict[str, Any]] = None,
    connector_requirements: Optional[ServiceConnectorRequirements] = None,
    connector: Optional[UUID] = None,
    connector_resource_id: Optional[str] = None,
    *args: Any,
    **kwargs: Any,
):
    """Initializes a StackComponent.

    Args:
        name: The name of the component.
        id: The unique ID of the component.
        config: The config of the component.
        flavor: The flavor of the component.
        type: The type of the component.
        user: The ID of the user who created the component.
        created: The creation time of the component.
        updated: The last update time of the component.
        labels: The labels of the component.
        connector_requirements: The requirements for the connector.
        connector: The ID of a connector linked to the component.
        connector_resource_id: The custom resource ID to access through
            the connector.
        *args: Additional positional arguments.
        **kwargs: Additional keyword arguments.

    Raises:
        ValueError: If a secret reference is passed as name.
    """
    if secret_utils.is_secret_reference(name):
        raise ValueError(
            "Passing the `name` attribute of a stack component as a "
            "secret reference is not allowed."
        )

    self.id = id
    self.name = name
    self._config = config
    self.flavor = flavor
    self.type = type
    self.user = user
    self.created = created
    self.updated = updated
    self.labels = labels
    self.connector_requirements = connector_requirements
    self.connector = connector
    self.connector_resource_id = connector_resource_id
    self._connector_instance: Optional[ServiceConnector] = None

Attributes

application_path: Any property

Provides the application path in the corresponding docker image.

Returns:

Type	Description
Any	The path to the application entrypoint within the docker image

config: KubernetesSparkStepOperatorConfig property

Returns the KubernetesSparkStepOperatorConfig config.

Returns:

Type	Description
KubernetesSparkStepOperatorConfig	The configuration.

validator: Optional[StackValidator] property

Validates the stack.

Returns:

Type	Description
Optional[StackValidator]	A validator that checks that the stack contains a remote container
Optional[StackValidator]	registry and a remote artifact store.

Functions

get_docker_builds(deployment: PipelineDeploymentBase) -> List[BuildConfiguration]

Gets the Docker builds required for the component.

Parameters:

Name	Type	Description	Default
deployment	PipelineDeploymentBase	The pipeline deployment for which to get the builds.	required

Returns:

Type	Description
List[BuildConfiguration]	The required Docker builds.

Source code in src/zenml/integrations/spark/step_operators/kubernetes_step_operator.py

def get_docker_builds(
    self, deployment: "PipelineDeploymentBase"
) -> List["BuildConfiguration"]:
    """Gets the Docker builds required for the component.

    Args:
        deployment: The pipeline deployment for which to get the builds.

    Returns:
        The required Docker builds.
    """
    from zenml.config.build_configuration import BuildConfiguration

    builds = []
    extra_files = {ENTRYPOINT_NAME: LOCAL_ENTRYPOINT}
    for step_name, step in deployment.step_configurations.items():
        if step.config.step_operator == self.name:
            build = BuildConfiguration(
                key=SPARK_DOCKER_IMAGE_KEY,
                settings=step.config.docker_settings,
                step_name=step_name,
                extra_files=extra_files,
            )
            builds.append(build)

    return builds

Modules

kubernetes_step_operator

Implementation of the Kubernetes Spark Step Operator.

Classes

KubernetesSparkStepOperator(name: str, id: UUID, config: StackComponentConfig, flavor: str, type: StackComponentType, user: Optional[UUID], created: datetime, updated: datetime, labels: Optional[Dict[str, Any]] = None, connector_requirements: Optional[ServiceConnectorRequirements] = None, connector: Optional[UUID] = None, connector_resource_id: Optional[str] = None, *args: Any, **kwargs: Any)

Bases: SparkStepOperator

Step operator which runs Steps with Spark on Kubernetes.

Source code in src/zenml/stack/stack_component.py

def __init__(
    self,
    name: str,
    id: UUID,
    config: StackComponentConfig,
    flavor: str,
    type: StackComponentType,
    user: Optional[UUID],
    created: datetime,
    updated: datetime,
    labels: Optional[Dict[str, Any]] = None,
    connector_requirements: Optional[ServiceConnectorRequirements] = None,
    connector: Optional[UUID] = None,
    connector_resource_id: Optional[str] = None,
    *args: Any,
    **kwargs: Any,
):
    """Initializes a StackComponent.

    Args:
        name: The name of the component.
        id: The unique ID of the component.
        config: The config of the component.
        flavor: The flavor of the component.
        type: The type of the component.
        user: The ID of the user who created the component.
        created: The creation time of the component.
        updated: The last update time of the component.
        labels: The labels of the component.
        connector_requirements: The requirements for the connector.
        connector: The ID of a connector linked to the component.
        connector_resource_id: The custom resource ID to access through
            the connector.
        *args: Additional positional arguments.
        **kwargs: Additional keyword arguments.

    Raises:
        ValueError: If a secret reference is passed as name.
    """
    if secret_utils.is_secret_reference(name):
        raise ValueError(
            "Passing the `name` attribute of a stack component as a "
            "secret reference is not allowed."
        )

    self.id = id
    self.name = name
    self._config = config
    self.flavor = flavor
    self.type = type
    self.user = user
    self.created = created
    self.updated = updated
    self.labels = labels
    self.connector_requirements = connector_requirements
    self.connector = connector
    self.connector_resource_id = connector_resource_id
    self._connector_instance: Optional[ServiceConnector] = None

Attributes

application_path: Any property

Provides the application path in the corresponding docker image.

Returns:

Type	Description
Any	The path to the application entrypoint within the docker image

config: KubernetesSparkStepOperatorConfig property

Returns the KubernetesSparkStepOperatorConfig config.

Returns:

Type	Description
KubernetesSparkStepOperatorConfig	The configuration.

validator: Optional[StackValidator] property

Validates the stack.

Returns:

Type	Description
Optional[StackValidator]	A validator that checks that the stack contains a remote container
Optional[StackValidator]	registry and a remote artifact store.

Functions

get_docker_builds(deployment: PipelineDeploymentBase) -> List[BuildConfiguration]

Gets the Docker builds required for the component.

Parameters:

Name	Type	Description	Default
deployment	PipelineDeploymentBase	The pipeline deployment for which to get the builds.	required

Returns:

Type	Description
List[BuildConfiguration]	The required Docker builds.

Source code in src/zenml/integrations/spark/step_operators/kubernetes_step_operator.py

def get_docker_builds(
    self, deployment: "PipelineDeploymentBase"
) -> List["BuildConfiguration"]:
    """Gets the Docker builds required for the component.

    Args:
        deployment: The pipeline deployment for which to get the builds.

    Returns:
        The required Docker builds.
    """
    from zenml.config.build_configuration import BuildConfiguration

    builds = []
    extra_files = {ENTRYPOINT_NAME: LOCAL_ENTRYPOINT}
    for step_name, step in deployment.step_configurations.items():
        if step.config.step_operator == self.name:
            build = BuildConfiguration(
                key=SPARK_DOCKER_IMAGE_KEY,
                settings=step.config.docker_settings,
                step_name=step_name,
                extra_files=extra_files,
            )
            builds.append(build)

    return builds

Functions Modules

spark_entrypoint_configuration

Spark step operator entrypoint configuration.

Classes

SparkEntrypointConfiguration(arguments: List[str])

Bases: StepOperatorEntrypointConfiguration

Entrypoint configuration for the Spark step operator.

Source code in src/zenml/entrypoints/base_entrypoint_configuration.py

def __init__(self, arguments: List[str]):
    """Initializes the entrypoint configuration.

    Args:
        arguments: Command line arguments to configure this object.
    """
    self.entrypoint_args = self._parse_arguments(arguments)

Functions

run() -> None

Runs the entrypoint configuration.

This prepends the directory containing the source files to the python path so that spark can find them.

Source code in src/zenml/integrations/spark/step_operators/spark_entrypoint_configuration.py

def run(self) -> None:
    """Runs the entrypoint configuration.

    This prepends the directory containing the source files to the python
    path so that spark can find them.
    """
    with source_utils.prepend_python_path(DOCKER_IMAGE_WORKDIR):
        super().run()

Modules

spark_step_operator

Implementation of the Spark Step Operator.

Classes

SparkStepOperator(name: str, id: UUID, config: StackComponentConfig, flavor: str, type: StackComponentType, user: Optional[UUID], created: datetime, updated: datetime, labels: Optional[Dict[str, Any]] = None, connector_requirements: Optional[ServiceConnectorRequirements] = None, connector: Optional[UUID] = None, connector_resource_id: Optional[str] = None, *args: Any, **kwargs: Any)

Bases: BaseStepOperator

Base class for all Spark-related step operators.

Source code in src/zenml/stack/stack_component.py

def __init__(
    self,
    name: str,
    id: UUID,
    config: StackComponentConfig,
    flavor: str,
    type: StackComponentType,
    user: Optional[UUID],
    created: datetime,
    updated: datetime,
    labels: Optional[Dict[str, Any]] = None,
    connector_requirements: Optional[ServiceConnectorRequirements] = None,
    connector: Optional[UUID] = None,
    connector_resource_id: Optional[str] = None,
    *args: Any,
    **kwargs: Any,
):
    """Initializes a StackComponent.

    Args:
        name: The name of the component.
        id: The unique ID of the component.
        config: The config of the component.
        flavor: The flavor of the component.
        type: The type of the component.
        user: The ID of the user who created the component.
        created: The creation time of the component.
        updated: The last update time of the component.
        labels: The labels of the component.
        connector_requirements: The requirements for the connector.
        connector: The ID of a connector linked to the component.
        connector_resource_id: The custom resource ID to access through
            the connector.
        *args: Additional positional arguments.
        **kwargs: Additional keyword arguments.

    Raises:
        ValueError: If a secret reference is passed as name.
    """
    if secret_utils.is_secret_reference(name):
        raise ValueError(
            "Passing the `name` attribute of a stack component as a "
            "secret reference is not allowed."
        )

    self.id = id
    self.name = name
    self._config = config
    self.flavor = flavor
    self.type = type
    self.user = user
    self.created = created
    self.updated = updated
    self.labels = labels
    self.connector_requirements = connector_requirements
    self.connector = connector
    self.connector_resource_id = connector_resource_id
    self._connector_instance: Optional[ServiceConnector] = None

Attributes

application_path: Optional[str] property

Optional method for providing the application path.

This is especially critical when using 'spark-submit' as it defines the path (to the application in the environment where Spark is running) which is used within the command.

For more information on how to set this property please check:

https://spark.apache.org/docs/latest/submitting-applications.html#advanced-dependency-management

Returns:

Type	Description
Optional[str]	The path to the application entrypoint

config: SparkStepOperatorConfig property

Returns the SparkStepOperatorConfig config.

Returns:

Type	Description
SparkStepOperatorConfig	The configuration.

settings_class: Optional[Type[BaseSettings]] property

Settings class for the Spark step operator.

Returns:

Type	Description
Optional[Type[BaseSettings]]	The settings class.

Functions

launch(info: StepRunInfo, entrypoint_command: List[str], environment: Dict[str, str]) -> None

Launches a step on Spark.

Parameters:

Name	Type	Description	Default
info	StepRunInfo	Information about the step run.	required
entrypoint_command	List[str]	Command that executes the step.	required
environment	Dict[str, str]	Environment variables to set in the step operator environment.	required

Source code in src/zenml/integrations/spark/step_operators/spark_step_operator.py

def launch(
    self,
    info: "StepRunInfo",
    entrypoint_command: List[str],
    environment: Dict[str, str],
) -> None:
    """Launches a step on Spark.

    Args:
        info: Information about the step run.
        entrypoint_command: Command that executes the step.
        environment: Environment variables to set in the step operator
            environment.
    """
    settings = cast(SparkStepOperatorSettings, self.get_settings(info))
    # Start off with an empty configuration
    conf = SparkConf()

    # Add the resource configuration such as cores, memory.
    self._resource_configuration(
        spark_config=conf,
        resource_settings=info.config.resource_settings,
    )

    # Add the backend configuration such as namespace, docker images names.
    self._backend_configuration(
        spark_config=conf, info=info, environment=environment
    )

    # Add the IO configuration for the inputs and the outputs
    self._io_configuration(
        spark_config=conf,
    )

    # Add any additional configuration given by the user.
    self._additional_configuration(spark_config=conf, settings=settings)

    info.force_write_logs()

    # Generate a spark-submit command given the configuration
    self._launch_spark_job(
        spark_config=conf,
        deploy_mode=settings.deploy_mode,
        entrypoint_command=entrypoint_command,
    )

Functions