python/pyspark/sql/connect/proto/ml_pb2.pyi - master - githubmirror/spark

python/pyspark/sql/connect/proto/ml_pb2.pyi
679 строк24 KB
Tian Gao
[SPARK-56018][PYTHON] Use ruff as formatter
20 мар 2026, 01:20
20 мар 2026, 01:20eac3fe3
#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements.  See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License.  You may obtain a copy of the License at
#
#    http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
"""
@generated by mypy-protobuf.  Do not edit manually!
isort:skip_file

Licensed to the Apache Software Foundation (ASF) under one or more
contributor license agreements.  See the NOTICE file distributed with
this work for additional information regarding copyright ownership.
The ASF licenses this file to You under the Apache License, Version 2.0
(the "License"); you may not use this file except in compliance with
the License.  You may obtain a copy of the License at

   http://www.apache.org/licenses/LICENSE-2.0

Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
"""

import builtins
import collections.abc
import google.protobuf.descriptor
import google.protobuf.internal.containers
import google.protobuf.message
import pyspark.sql.connect.proto.expressions_pb2
import pyspark.sql.connect.proto.ml_common_pb2
import pyspark.sql.connect.proto.relations_pb2
import sys
import typing

if sys.version_info >= (3, 8):
    import typing as typing_extensions
else:
    import typing_extensions

DESCRIPTOR: google.protobuf.descriptor.FileDescriptor

class MlCommand(google.protobuf.message.Message):
    """Command for ML"""

    DESCRIPTOR: google.protobuf.descriptor.Descriptor

    class Fit(google.protobuf.message.Message):
        """Command for estimator.fit(dataset)"""

        DESCRIPTOR: google.protobuf.descriptor.Descriptor

        ESTIMATOR_FIELD_NUMBER: builtins.int
        PARAMS_FIELD_NUMBER: builtins.int
        DATASET_FIELD_NUMBER: builtins.int
        @property
        def estimator(self) -> pyspark.sql.connect.proto.ml_common_pb2.MlOperator:
            """(Required) Estimator information (its type should be OPERATOR_TYPE_ESTIMATOR)"""
        @property
        def params(self) -> pyspark.sql.connect.proto.ml_common_pb2.MlParams:
            """(Optional) parameters of the Estimator"""
        @property
        def dataset(self) -> pyspark.sql.connect.proto.relations_pb2.Relation:
            """(Required) the training dataset"""
        def __init__(
            self,
            *,
            estimator: pyspark.sql.connect.proto.ml_common_pb2.MlOperator | None = ...,
            params: pyspark.sql.connect.proto.ml_common_pb2.MlParams | None = ...,
            dataset: pyspark.sql.connect.proto.relations_pb2.Relation | None = ...,
        ) -> None: ...
        def HasField(
            self,
            field_name: typing_extensions.Literal[
                "_params",
                b"_params",
                "dataset",
                b"dataset",
                "estimator",
                b"estimator",
                "params",
                b"params",
            ],
        ) -> builtins.bool: ...
        def ClearField(
            self,
            field_name: typing_extensions.Literal[
                "_params",
                b"_params",
                "dataset",
                b"dataset",
                "estimator",
                b"estimator",
                "params",
                b"params",
            ],
        ) -> None: ...
        def WhichOneof(
            self, oneof_group: typing_extensions.Literal["_params", b"_params"]
        ) -> typing_extensions.Literal["params"] | None: ...

    class Delete(google.protobuf.message.Message):
        """Command to delete the cached objects which could be a model
        or summary evaluated by a model
        """

        DESCRIPTOR: google.protobuf.descriptor.Descriptor

        OBJ_REFS_FIELD_NUMBER: builtins.int
        EVICT_ONLY_FIELD_NUMBER: builtins.int
        @property
        def obj_refs(
            self,
        ) -> google.protobuf.internal.containers.RepeatedCompositeFieldContainer[
            pyspark.sql.connect.proto.ml_common_pb2.ObjectRef
        ]: ...
        evict_only: builtins.bool
        """if set `evict_only` to true, only evict the cached model from memory,
        but keep the offloaded model in Spark driver local disk.
        """
        def __init__(
            self,
            *,
            obj_refs: collections.abc.Iterable[pyspark.sql.connect.proto.ml_common_pb2.ObjectRef]
            | None = ...,
            evict_only: builtins.bool | None = ...,
        ) -> None: ...
        def HasField(
            self,
            field_name: typing_extensions.Literal[
                "_evict_only", b"_evict_only", "evict_only", b"evict_only"
            ],
        ) -> builtins.bool: ...
        def ClearField(
            self,
            field_name: typing_extensions.Literal[
                "_evict_only", b"_evict_only", "evict_only", b"evict_only", "obj_refs", b"obj_refs"
            ],
        ) -> None: ...
        def WhichOneof(
            self, oneof_group: typing_extensions.Literal["_evict_only", b"_evict_only"]
        ) -> typing_extensions.Literal["evict_only"] | None: ...

    class CleanCache(google.protobuf.message.Message):
        """Force to clean up all the ML cached objects"""

        DESCRIPTOR: google.protobuf.descriptor.Descriptor

        def __init__(
            self,
        ) -> None: ...

    class GetCacheInfo(google.protobuf.message.Message):
        """Get the information of all the ML cached objects"""

        DESCRIPTOR: google.protobuf.descriptor.Descriptor

        def __init__(
            self,
        ) -> None: ...

    class Write(google.protobuf.message.Message):
        """Command to write ML operator"""

        DESCRIPTOR: google.protobuf.descriptor.Descriptor

        class OptionsEntry(google.protobuf.message.Message):
            DESCRIPTOR: google.protobuf.descriptor.Descriptor

            KEY_FIELD_NUMBER: builtins.int
            VALUE_FIELD_NUMBER: builtins.int
            key: builtins.str
            value: builtins.str
            def __init__(
                self,
                *,
                key: builtins.str = ...,
                value: builtins.str = ...,
            ) -> None: ...
            def ClearField(
                self, field_name: typing_extensions.Literal["key", b"key", "value", b"value"]
            ) -> None: ...

        OPERATOR_FIELD_NUMBER: builtins.int
        OBJ_REF_FIELD_NUMBER: builtins.int
        PARAMS_FIELD_NUMBER: builtins.int
        PATH_FIELD_NUMBER: builtins.int
        SHOULD_OVERWRITE_FIELD_NUMBER: builtins.int
        OPTIONS_FIELD_NUMBER: builtins.int
        @property
        def operator(self) -> pyspark.sql.connect.proto.ml_common_pb2.MlOperator:
            """Estimator or evaluator"""
        @property
        def obj_ref(self) -> pyspark.sql.connect.proto.ml_common_pb2.ObjectRef:
            """The cached model"""
        @property
        def params(self) -> pyspark.sql.connect.proto.ml_common_pb2.MlParams:
            """(Optional) The parameters of operator which could be estimator/evaluator or a cached model"""
        path: builtins.str
        """(Required) Save the ML instance to the path"""
        should_overwrite: builtins.bool
        """(Optional) Overwrites if the output path already exists."""
        @property
        def options(
            self,
        ) -> google.protobuf.internal.containers.ScalarMap[builtins.str, builtins.str]:
            """(Optional) The options of the writer"""
        def __init__(
            self,
            *,
            operator: pyspark.sql.connect.proto.ml_common_pb2.MlOperator | None = ...,
            obj_ref: pyspark.sql.connect.proto.ml_common_pb2.ObjectRef | None = ...,
            params: pyspark.sql.connect.proto.ml_common_pb2.MlParams | None = ...,
            path: builtins.str = ...,
            should_overwrite: builtins.bool | None = ...,
            options: collections.abc.Mapping[builtins.str, builtins.str] | None = ...,
        ) -> None: ...
        def HasField(
            self,
            field_name: typing_extensions.Literal[
                "_params",
                b"_params",
                "_should_overwrite",
                b"_should_overwrite",
                "obj_ref",
                b"obj_ref",
                "operator",
                b"operator",
                "params",
                b"params",
                "should_overwrite",
                b"should_overwrite",
                "type",
                b"type",
            ],
        ) -> builtins.bool: ...
        def ClearField(
            self,
            field_name: typing_extensions.Literal[
                "_params",
                b"_params",
                "_should_overwrite",
                b"_should_overwrite",
                "obj_ref",
                b"obj_ref",
                "operator",
                b"operator",
                "options",
                b"options",
                "params",
                b"params",
                "path",
                b"path",
                "should_overwrite",
                b"should_overwrite",
                "type",
                b"type",
            ],
        ) -> None: ...
        @typing.overload
        def WhichOneof(
            self, oneof_group: typing_extensions.Literal["_params", b"_params"]
        ) -> typing_extensions.Literal["params"] | None: ...
        @typing.overload
        def WhichOneof(
            self, oneof_group: typing_extensions.Literal["_should_overwrite", b"_should_overwrite"]
        ) -> typing_extensions.Literal["should_overwrite"] | None: ...
        @typing.overload
        def WhichOneof(
            self, oneof_group: typing_extensions.Literal["type", b"type"]
        ) -> typing_extensions.Literal["operator", "obj_ref"] | None: ...

    class Read(google.protobuf.message.Message):
        """Command to load ML operator."""

        DESCRIPTOR: google.protobuf.descriptor.Descriptor

        OPERATOR_FIELD_NUMBER: builtins.int
        PATH_FIELD_NUMBER: builtins.int
        @property
        def operator(self) -> pyspark.sql.connect.proto.ml_common_pb2.MlOperator:
            """(Required) ML operator information"""
        path: builtins.str
        """(Required) Load the ML instance from the input path"""
        def __init__(
            self,
            *,
            operator: pyspark.sql.connect.proto.ml_common_pb2.MlOperator | None = ...,
            path: builtins.str = ...,
        ) -> None: ...
        def HasField(
            self, field_name: typing_extensions.Literal["operator", b"operator"]
        ) -> builtins.bool: ...
        def ClearField(
            self, field_name: typing_extensions.Literal["operator", b"operator", "path", b"path"]
        ) -> None: ...

    class Evaluate(google.protobuf.message.Message):
        """Command for evaluator.evaluate(dataset)"""

        DESCRIPTOR: google.protobuf.descriptor.Descriptor

        EVALUATOR_FIELD_NUMBER: builtins.int
        PARAMS_FIELD_NUMBER: builtins.int
        DATASET_FIELD_NUMBER: builtins.int
        @property
        def evaluator(self) -> pyspark.sql.connect.proto.ml_common_pb2.MlOperator:
            """(Required) Evaluator information (its type should be OPERATOR_TYPE_EVALUATOR)"""
        @property
        def params(self) -> pyspark.sql.connect.proto.ml_common_pb2.MlParams:
            """(Optional) parameters of the Evaluator"""
        @property
        def dataset(self) -> pyspark.sql.connect.proto.relations_pb2.Relation:
            """(Required) the evaluating dataset"""
        def __init__(
            self,
            *,
            evaluator: pyspark.sql.connect.proto.ml_common_pb2.MlOperator | None = ...,
            params: pyspark.sql.connect.proto.ml_common_pb2.MlParams | None = ...,
            dataset: pyspark.sql.connect.proto.relations_pb2.Relation | None = ...,
        ) -> None: ...
        def HasField(
            self,
            field_name: typing_extensions.Literal[
                "_params",
                b"_params",
                "dataset",
                b"dataset",
                "evaluator",
                b"evaluator",
                "params",
                b"params",
            ],
        ) -> builtins.bool: ...
        def ClearField(
            self,
            field_name: typing_extensions.Literal[
                "_params",
                b"_params",
                "dataset",
                b"dataset",
                "evaluator",
                b"evaluator",
                "params",
                b"params",
            ],
        ) -> None: ...
        def WhichOneof(
            self, oneof_group: typing_extensions.Literal["_params", b"_params"]
        ) -> typing_extensions.Literal["params"] | None: ...

    class CreateSummary(google.protobuf.message.Message):
        """This is for re-creating the model summary when the model summary is lost
        (model summary is lost when the model is offloaded and then loaded back)
        """

        DESCRIPTOR: google.protobuf.descriptor.Descriptor

        MODEL_REF_FIELD_NUMBER: builtins.int
        DATASET_FIELD_NUMBER: builtins.int
        @property
        def model_ref(self) -> pyspark.sql.connect.proto.ml_common_pb2.ObjectRef: ...
        @property
        def dataset(self) -> pyspark.sql.connect.proto.relations_pb2.Relation: ...
        def __init__(
            self,
            *,
            model_ref: pyspark.sql.connect.proto.ml_common_pb2.ObjectRef | None = ...,
            dataset: pyspark.sql.connect.proto.relations_pb2.Relation | None = ...,
        ) -> None: ...
        def HasField(
            self,
            field_name: typing_extensions.Literal["dataset", b"dataset", "model_ref", b"model_ref"],
        ) -> builtins.bool: ...
        def ClearField(
            self,
            field_name: typing_extensions.Literal["dataset", b"dataset", "model_ref", b"model_ref"],
        ) -> None: ...

    class GetModelSize(google.protobuf.message.Message):
        """This is for query the model estimated in-memory size"""

        DESCRIPTOR: google.protobuf.descriptor.Descriptor

        MODEL_REF_FIELD_NUMBER: builtins.int
        @property
        def model_ref(self) -> pyspark.sql.connect.proto.ml_common_pb2.ObjectRef: ...
        def __init__(
            self,
            *,
            model_ref: pyspark.sql.connect.proto.ml_common_pb2.ObjectRef | None = ...,
        ) -> None: ...
        def HasField(
            self, field_name: typing_extensions.Literal["model_ref", b"model_ref"]
        ) -> builtins.bool: ...
        def ClearField(
            self, field_name: typing_extensions.Literal["model_ref", b"model_ref"]
        ) -> None: ...

    FIT_FIELD_NUMBER: builtins.int
    FETCH_FIELD_NUMBER: builtins.int
    DELETE_FIELD_NUMBER: builtins.int
    WRITE_FIELD_NUMBER: builtins.int
    READ_FIELD_NUMBER: builtins.int
    EVALUATE_FIELD_NUMBER: builtins.int
    CLEAN_CACHE_FIELD_NUMBER: builtins.int
    GET_CACHE_INFO_FIELD_NUMBER: builtins.int
    CREATE_SUMMARY_FIELD_NUMBER: builtins.int
    GET_MODEL_SIZE_FIELD_NUMBER: builtins.int
    @property
    def fit(self) -> global___MlCommand.Fit: ...
    @property
    def fetch(self) -> pyspark.sql.connect.proto.relations_pb2.Fetch: ...
    @property
    def delete(self) -> global___MlCommand.Delete: ...
    @property
    def write(self) -> global___MlCommand.Write: ...
    @property
    def read(self) -> global___MlCommand.Read: ...
    @property
    def evaluate(self) -> global___MlCommand.Evaluate: ...
    @property
    def clean_cache(self) -> global___MlCommand.CleanCache: ...
    @property
    def get_cache_info(self) -> global___MlCommand.GetCacheInfo: ...
    @property
    def create_summary(self) -> global___MlCommand.CreateSummary: ...
    @property
    def get_model_size(self) -> global___MlCommand.GetModelSize: ...
    def __init__(
        self,
        *,
        fit: global___MlCommand.Fit | None = ...,
        fetch: pyspark.sql.connect.proto.relations_pb2.Fetch | None = ...,
        delete: global___MlCommand.Delete | None = ...,
        write: global___MlCommand.Write | None = ...,
        read: global___MlCommand.Read | None = ...,
        evaluate: global___MlCommand.Evaluate | None = ...,
        clean_cache: global___MlCommand.CleanCache | None = ...,
        get_cache_info: global___MlCommand.GetCacheInfo | None = ...,
        create_summary: global___MlCommand.CreateSummary | None = ...,
        get_model_size: global___MlCommand.GetModelSize | None = ...,
    ) -> None: ...
    def HasField(
        self,
        field_name: typing_extensions.Literal[
            "clean_cache",
            b"clean_cache",
            "command",
            b"command",
            "create_summary",
            b"create_summary",
            "delete",
            b"delete",
            "evaluate",
            b"evaluate",
            "fetch",
            b"fetch",
            "fit",
            b"fit",
            "get_cache_info",
            b"get_cache_info",
            "get_model_size",
            b"get_model_size",
            "read",
            b"read",
            "write",
            b"write",
        ],
    ) -> builtins.bool: ...
    def ClearField(
        self,
        field_name: typing_extensions.Literal[
            "clean_cache",
            b"clean_cache",
            "command",
            b"command",
            "create_summary",
            b"create_summary",
            "delete",
            b"delete",
            "evaluate",
            b"evaluate",
            "fetch",
            b"fetch",
            "fit",
            b"fit",
            "get_cache_info",
            b"get_cache_info",
            "get_model_size",
            b"get_model_size",
            "read",
            b"read",
            "write",
            b"write",
        ],
    ) -> None: ...
    def WhichOneof(
        self, oneof_group: typing_extensions.Literal["command", b"command"]
    ) -> (
        typing_extensions.Literal[
            "fit",
            "fetch",
            "delete",
            "write",
            "read",
            "evaluate",
            "clean_cache",
            "get_cache_info",
            "create_summary",
            "get_model_size",
        ]
        | None
    ): ...

global___MlCommand = MlCommand

class MlCommandResult(google.protobuf.message.Message):
    """The result of MlCommand"""

    DESCRIPTOR: google.protobuf.descriptor.Descriptor

    class MlOperatorInfo(google.protobuf.message.Message):
        """Represents an operator info"""

        DESCRIPTOR: google.protobuf.descriptor.Descriptor

        OBJ_REF_FIELD_NUMBER: builtins.int
        NAME_FIELD_NUMBER: builtins.int
        UID_FIELD_NUMBER: builtins.int
        PARAMS_FIELD_NUMBER: builtins.int
        WARNING_MESSAGE_FIELD_NUMBER: builtins.int
        @property
        def obj_ref(self) -> pyspark.sql.connect.proto.ml_common_pb2.ObjectRef:
            """The cached object which could be a model or summary evaluated by a model"""
        name: builtins.str
        """Operator name"""
        uid: builtins.str
        """(Optional) the 'uid' of a ML object
        Note it is different from the 'id' of a cached object.
        """
        @property
        def params(self) -> pyspark.sql.connect.proto.ml_common_pb2.MlParams:
            """(Optional) parameters"""
        warning_message: builtins.str
        """(Optional) warning message generated during the ML command execution"""
        def __init__(
            self,
            *,
            obj_ref: pyspark.sql.connect.proto.ml_common_pb2.ObjectRef | None = ...,
            name: builtins.str = ...,
            uid: builtins.str | None = ...,
            params: pyspark.sql.connect.proto.ml_common_pb2.MlParams | None = ...,
            warning_message: builtins.str | None = ...,
        ) -> None: ...
        def HasField(
            self,
            field_name: typing_extensions.Literal[
                "_params",
                b"_params",
                "_uid",
                b"_uid",
                "_warning_message",
                b"_warning_message",
                "name",
                b"name",
                "obj_ref",
                b"obj_ref",
                "params",
                b"params",
                "type",
                b"type",
                "uid",
                b"uid",
                "warning_message",
                b"warning_message",
            ],
        ) -> builtins.bool: ...
        def ClearField(
            self,
            field_name: typing_extensions.Literal[
                "_params",
                b"_params",
                "_uid",
                b"_uid",
                "_warning_message",
                b"_warning_message",
                "name",
                b"name",
                "obj_ref",
                b"obj_ref",
                "params",
                b"params",
                "type",
                b"type",
                "uid",
                b"uid",
                "warning_message",
                b"warning_message",
            ],
        ) -> None: ...
        @typing.overload
        def WhichOneof(
            self, oneof_group: typing_extensions.Literal["_params", b"_params"]
        ) -> typing_extensions.Literal["params"] | None: ...
        @typing.overload
        def WhichOneof(
            self, oneof_group: typing_extensions.Literal["_uid", b"_uid"]
        ) -> typing_extensions.Literal["uid"] | None: ...
        @typing.overload
        def WhichOneof(
            self, oneof_group: typing_extensions.Literal["_warning_message", b"_warning_message"]
        ) -> typing_extensions.Literal["warning_message"] | None: ...
        @typing.overload
        def WhichOneof(
            self, oneof_group: typing_extensions.Literal["type", b"type"]
        ) -> typing_extensions.Literal["obj_ref", "name"] | None: ...

    PARAM_FIELD_NUMBER: builtins.int
    SUMMARY_FIELD_NUMBER: builtins.int
    OPERATOR_INFO_FIELD_NUMBER: builtins.int
    @property
    def param(self) -> pyspark.sql.connect.proto.expressions_pb2.Expression.Literal:
        """The result of the attribute"""
    summary: builtins.str
    """Evaluate a Dataset in a model and return the cached ID of summary"""
    @property
    def operator_info(self) -> global___MlCommandResult.MlOperatorInfo:
        """Operator information"""
    def __init__(
        self,
        *,
        param: pyspark.sql.connect.proto.expressions_pb2.Expression.Literal | None = ...,
        summary: builtins.str = ...,
        operator_info: global___MlCommandResult.MlOperatorInfo | None = ...,
    ) -> None: ...
    def HasField(
        self,
        field_name: typing_extensions.Literal[
            "operator_info",
            b"operator_info",
            "param",
            b"param",
            "result_type",
            b"result_type",
            "summary",
            b"summary",
        ],
    ) -> builtins.bool: ...
    def ClearField(
        self,
        field_name: typing_extensions.Literal[
            "operator_info",
            b"operator_info",
            "param",
            b"param",
            "result_type",
            b"result_type",
            "summary",
            b"summary",
        ],
    ) -> None: ...
    def WhichOneof(
        self, oneof_group: typing_extensions.Literal["result_type", b"result_type"]
    ) -> typing_extensions.Literal["param", "summary", "operator_info"] | None: ...

global___MlCommandResult = MlCommandResult