CrossValidator#

class spark_rapids_ml.tuning.CrossValidator(*, estimator: Optional[Estimator] = None, estimatorParamMaps: Optional[List[ParamMap]] = None, evaluator: Optional[Evaluator] = None, numFolds: int = 3, seed: Optional[int] = None, parallelism: int = 1, collectSubModels: bool = False, foldCol: str = '')#

K-fold cross validation performs model selection by splitting the dataset into a set of non-overlapping randomly partitioned folds which are used as separate training and test datasets e.g., with k=3 folds, K-fold cross validation will generate 3 (training, test) dataset pairs, each of which uses 2/3 of the data for training and 1/3 for testing. Each fold is used as the test set exactly once.

It is the gpu version CrossValidator which fits multiple models in a single pass for a single training dataset and transforms/evaluates in a single pass for multiple models.

Examples

>>> from pyspark.ml.linalg import Vectors
>>> from pyspark.ml.tuning import ParamGridBuilder, CrossValidatorModel
>>> from pyspark.ml.evaluation import MulticlassClassificationEvaluator
>>> from spark_rapids_ml.tuning import CrossValidator
>>> from spark_rapids_ml.classification import RandomForestClassifier
>>> import tempfile
>>> dataset = spark.createDataFrame(
...     [(Vectors.dense([0.0]), 0.0),
...      (Vectors.dense([0.4]), 1.0),
...      (Vectors.dense([0.5]), 0.0),
...      (Vectors.dense([0.6]), 2.0),
...      (Vectors.dense([1.0]), 1.0)] * 10,
...     ["features", "label"])
>>> rfc = RandomForestClassifier()
>>> grid = ParamGridBuilder().addGrid(rfc.maxBins, [8, 16]).build()
>>> evaluator = MulticlassClassificationEvaluator()
>>> cv = CrossValidator(estimator=rfc, estimatorParamMaps=grid, evaluator=evaluator,
...                     parallelism=2)
>>> cvModel = cv.fit(dataset)
...
>>> cvModel.getNumFolds()
3
>>> cvModel.avgMetrics[0]
1.0
>>> evaluator.evaluate(cvModel.transform(dataset))
1.0
>>> path = tempfile.mkdtemp()
>>> model_path = path + "/model"
>>> cvModel.write().save(model_path)
>>> cvModelRead = CrossValidatorModel.read().load(model_path)
>>> cvModelRead.avgMetrics
[1.0, 1.0]
>>> evaluator.evaluate(cvModel.transform(dataset))
1.0
>>> evaluator.evaluate(cvModelRead.transform(dataset))
1.0

Methods

clear(param)

Clears a param from the param map if it has been explicitly set.

copy([extra])

Creates a copy of this instance with a randomly generated uid and some extra params.

explainParam(param)

Explains a single param and returns its name, doc, and optional default value and user-supplied value in a string.

explainParams()

Returns the documentation of all params with their optionally default values and user-supplied values.

extractParamMap([extra])

Extracts the embedded default param values and user-supplied values, and then merges them with extra values from input into a flat param map, where the latter value is used if there exist conflicts, i.e., with ordering: default param values < user-supplied values < extra.

fit(dataset[, params])

Fits a model to the input dataset with optional parameters.

fitMultiple(dataset, paramMaps)

Fits a model to the input dataset for each param map in paramMaps.

getCollectSubModels()

Gets the value of collectSubModels or its default value.

getEstimator()

Gets the value of estimator or its default value.

getEstimatorParamMaps()

Gets the value of estimatorParamMaps or its default value.

getEvaluator()

Gets the value of evaluator or its default value.

getFoldCol()

Gets the value of foldCol or its default value.

getNumFolds()

Gets the value of numFolds or its default value.

getOrDefault(param)

Gets the value of a param in the user-supplied param map or its default value.

getParallelism()

Gets the value of parallelism or its default value.

getParam(paramName)

Gets a param by its name.

getSeed()

Gets the value of seed or its default value.

hasDefault(param)

Checks whether a param has a default value.

hasParam(paramName)

Tests whether this instance contains a param with a given (string) name.

isDefined(param)

Checks whether a param is explicitly set by user or has a default value.

isSet(param)

Checks whether a param is explicitly set by user.

load(path)

read()

Returns an MLReader instance for this class.

save(path)

Save this ML instance to the given path, a shortcut of 'write().save(path)'.

set(param, value)

Sets a parameter in the embedded param map.

setCollectSubModels(value)

Sets the value of collectSubModels.

setEstimator(value)

Sets the value of estimator.

setEstimatorParamMaps(value)

Sets the value of estimatorParamMaps.

setEvaluator(value)

Sets the value of evaluator.

setFoldCol(value)

Sets the value of foldCol.

setNumFolds(value)

Sets the value of numFolds.

setParallelism(value)

Sets the value of parallelism.

setParams(*[, estimator, ...])

setParams(self, *, estimator=None, estimatorParamMaps=None, evaluator=None, numFolds=3, seed=None, parallelism=1, collectSubModels=False, foldCol=""): Sets params for cross validator.

setSeed(value)

Sets the value of seed.

write()

Returns an MLWriter instance for this ML instance.

Attributes

Methods Documentation

clear(param: Param) None#

Clears a param from the param map if it has been explicitly set.

copy(extra: Optional[ParamMap] = None) CrossValidator#

Creates a copy of this instance with a randomly generated uid and some extra params. This copies creates a deep copy of the embedded paramMap, and copies the embedded and extra parameters over.

New in version 1.4.0.

Parameters:
extradict, optional

Extra parameters to copy to the new instance

Returns:
CrossValidator

Copy of this instance

explainParam(param: Union[str, Param]) str#

Explains a single param and returns its name, doc, and optional default value and user-supplied value in a string.

explainParams() str#

Returns the documentation of all params with their optionally default values and user-supplied values.

extractParamMap(extra: Optional[ParamMap] = None) ParamMap#

Extracts the embedded default param values and user-supplied values, and then merges them with extra values from input into a flat param map, where the latter value is used if there exist conflicts, i.e., with ordering: default param values < user-supplied values < extra.

Parameters:
extradict, optional

extra param values

Returns:
dict

merged param map

fit(dataset: DataFrame, params: Optional[Union[ParamMap, List[ParamMap], Tuple[ParamMap]]] = None) Union[M, List[M]]#

Fits a model to the input dataset with optional parameters.

New in version 1.3.0.

Parameters:
datasetpyspark.sql.DataFrame

input dataset.

paramsdict or list or tuple, optional

an optional param map that overrides embedded params. If a list/tuple of param maps is given, this calls fit on each param map and returns a list of models.

Returns:
Transformer or a list of Transformer

fitted model(s)

fitMultiple(dataset: DataFrame, paramMaps: Sequence[ParamMap]) Iterator[Tuple[int, M]]#

Fits a model to the input dataset for each param map in paramMaps.

New in version 2.3.0.

Parameters:
datasetpyspark.sql.DataFrame

input dataset.

paramMapscollections.abc.Sequence

A Sequence of param maps.

Returns:
_FitMultipleIterator

A thread safe iterable which contains one model for each param map. Each call to next(modelIterator) will return (index, model) where model was fit using paramMaps[index]. index values may not be sequential.

getCollectSubModels() bool#

Gets the value of collectSubModels or its default value.

getEstimator() Estimator#

Gets the value of estimator or its default value.

New in version 2.0.0.

getEstimatorParamMaps() List[ParamMap]#

Gets the value of estimatorParamMaps or its default value.

New in version 2.0.0.

getEvaluator() Evaluator#

Gets the value of evaluator or its default value.

New in version 2.0.0.

getFoldCol() str#

Gets the value of foldCol or its default value.

New in version 3.1.0.

getNumFolds() int#

Gets the value of numFolds or its default value.

New in version 1.4.0.

getOrDefault(param: Union[str, Param[T]]) Union[Any, T]#

Gets the value of a param in the user-supplied param map or its default value. Raises an error if neither is set.

getParallelism() int#

Gets the value of parallelism or its default value.

getParam(paramName: str) Param#

Gets a param by its name.

getSeed() int#

Gets the value of seed or its default value.

hasDefault(param: Union[str, Param[Any]]) bool#

Checks whether a param has a default value.

hasParam(paramName: str) bool#

Tests whether this instance contains a param with a given (string) name.

isDefined(param: Union[str, Param[Any]]) bool#

Checks whether a param is explicitly set by user or has a default value.

isSet(param: Union[str, Param[Any]]) bool#

Checks whether a param is explicitly set by user.

classmethod load(path: str) CrossValidator#
classmethod read() CrossValidatorReader#

Returns an MLReader instance for this class.

New in version 2.3.0.

save(path: str) None#

Save this ML instance to the given path, a shortcut of ‘write().save(path)’.

set(param: Param, value: Any) None#

Sets a parameter in the embedded param map.

setCollectSubModels(value: bool) CrossValidator#

Sets the value of collectSubModels.

setEstimator(value: Estimator) CrossValidator#

Sets the value of estimator.

New in version 2.0.0.

setEstimatorParamMaps(value: List[ParamMap]) CrossValidator#

Sets the value of estimatorParamMaps.

New in version 2.0.0.

setEvaluator(value: Evaluator) CrossValidator#

Sets the value of evaluator.

New in version 2.0.0.

setFoldCol(value: str) CrossValidator#

Sets the value of foldCol.

New in version 3.1.0.

setNumFolds(value: int) CrossValidator#

Sets the value of numFolds.

New in version 1.4.0.

setParallelism(value: int) CrossValidator#

Sets the value of parallelism.

setParams(*, estimator: Optional[Estimator] = None, estimatorParamMaps: Optional[List[ParamMap]] = None, evaluator: Optional[Evaluator] = None, numFolds: int = 3, seed: Optional[int] = None, parallelism: int = 1, collectSubModels: bool = False, foldCol: str = '') CrossValidator#

setParams(self, *, estimator=None, estimatorParamMaps=None, evaluator=None, numFolds=3, seed=None, parallelism=1, collectSubModels=False, foldCol=””): Sets params for cross validator.

New in version 1.4.0.

setSeed(value: int) CrossValidator#

Sets the value of seed.

write() MLWriter#

Returns an MLWriter instance for this ML instance.

New in version 2.3.0.

Attributes Documentation

collectSubModels: Param[bool] = Param(parent='undefined', name='collectSubModels', doc='Param for whether to collect a list of sub-models trained during tuning. If set to false, then only the single best sub-model will be available after fitting. If set to true, then all sub-models will be available. Warning: For large models, collecting all sub-models can cause OOMs on the Spark driver.')#
estimator: Param[Estimator] = Param(parent='undefined', name='estimator', doc='estimator to be cross-validated')#
estimatorParamMaps: Param[List['ParamMap']] = Param(parent='undefined', name='estimatorParamMaps', doc='estimator param maps')#
evaluator: Param[Evaluator] = Param(parent='undefined', name='evaluator', doc='evaluator used to select hyper-parameters that maximize the validator metric')#
foldCol: Param[str] = Param(parent='undefined', name='foldCol', doc="Param for the column name of user specified fold number. Once this is specified, :py:class:`CrossValidator` won't do random k-fold split. Note that this column should be integer type with range [0, numFolds) and Spark will throw exception on out-of-range fold numbers.")#
numFolds: Param[int] = Param(parent='undefined', name='numFolds', doc='number of folds for cross validation')#
parallelism: Param[int] = Param(parent='undefined', name='parallelism', doc='the number of threads to use when running parallel algorithms (>= 1).')#
params#

Returns all params ordered by name. The default implementation uses dir() to get all attributes of type Param.

seed: Param[int] = Param(parent='undefined', name='seed', doc='random seed.')#