merlin.systems.dag.ops.softmax_sampling.SoftmaxSampling

class merlin.systems.dag.ops.softmax_sampling.SoftmaxSampling(relevance_col, temperature=20.0, topk=10, _input_col=None)

Bases: merlin.systems.dag.ops.operator.PipelineableInferenceOperator

Given inputs of ID and prediction, this operator will sort all inputs in descending order.

__init__(relevance_col, temperature=20.0, topk=10, _input_col=None)

Create a SoftmaxSampling Pipelineable Inference Operator.

Parameters

• relevance_col (string) – The column to judge sorting order with.

• temperature (float, optional) – Value which will be used to effect the weights used in sorting, by default 20.0

• topk (int, optional) – The max number of results you wish to receive as output, by default 10

• _input_col (_type_, optional) – The column whose values will be sorted, by default None.

Methods

__init__(relevance_col[, temperature, topk, …])	Create a SoftmaxSampling Pipelineable Inference Operator.
column_mapping(col_selector)	Compute which output columns depend on which input columns
compute_column_schema(col_name, input_schema)
compute_input_schema(root_schema, …)
compute_output_schema(input_schema, col_selector)	Describe the operator’s outputs
compute_selector(input_schema, selector[, …])	Provides a hook method for sub-classes to override to implement custom column selection logic.
create_node(selector)	_summary_
export(path, input_schema, output_schema[, …])	Write out a Triton model config directory
from_config(config, **kwargs)	Load operator and properties from Triton config
from_model_registry(registry, **kwargs)	Loads the InferenceOperator from the provided ModelRegistry.
from_path(path, **kwargs)	Loads the InferenceOperator from the path where it was exported after training.
load_artifacts(artifact_path)	Hook method that provides a way to load saved artifacts for the operator
output_column_names(col_selector)	Given a set of columns names returns the names of the transformed columns this operator will produce
transform(col_selector, transformable)	Transform the dataframe by applying this operator to the set of input columns
validate_schemas(parents_schema, …[, …])	Provides a hook method that sub-classes can override to implement schema validation logic.

Attributes

dependencies
dynamic_dtypes
export_name	Provides a clear common english identifier for this operator.
exportable_backends
is_subgraph
label
output_dtype
output_properties
output_tags
scalar_shape
supported_formats
supports	Returns what kind of data representation this operator supports

classmethod from_config(config, **kwargs) → merlin.systems.dag.ops.softmax_sampling.SoftmaxSampling

Load operator and properties from Triton config

property dependencies

export(path: str, input_schema: merlin.schema.schema.Schema, output_schema: merlin.schema.schema.Schema, params: Optional[dict] = None, node_id: Optional[int] = None, version: int = 1, backend: str = 'ensemble')

Write out a Triton model config directory

compute_input_schema(root_schema: merlin.schema.schema.Schema, parents_schema: merlin.schema.schema.Schema, deps_schema: merlin.schema.schema.Schema, selector: merlin.dag.selector.ColumnSelector) → merlin.schema.schema.Schema

compute_output_schema(input_schema: merlin.schema.schema.Schema, col_selector: merlin.dag.selector.ColumnSelector, prev_output_schema: Optional[merlin.schema.schema.Schema] = None) → merlin.schema.schema.Schema

Describe the operator’s outputs

transform(col_selector: merlin.dag.selector.ColumnSelector, transformable: merlin.core.protocols.Transformable) → merlin.core.protocols.Transformable

Transform the dataframe by applying this operator to the set of input columns