nvtabular.ops.DropLowCardinality#

class nvtabular.ops.DropLowCardinality(min_cardinality=2)[source]#

Bases: Operator

DropLowCardinality drops low cardinality categorical columns. This requires the cardinality of these columns to be known in the schema - for instance by first encoding these columns using Categorify.

__init__(min_cardinality=2)[source]#

Methods

__init__([min_cardinality])

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, ...)

Given the schemas coming from upstream sources and a column selector for the input columns, returns a set of schemas for the input columns this operator will use

compute_output_schema(input_schema, col_selector)

Given a set of schemas and a column selector for the input columns, returns a set of schemas for the transformed columns this operator will produce

compute_selector(input_schema, selector, ...)

Checks the cardinality of the input columns and drops any categorical columns with cardinality less than the specified minimum.

create_node(selector)

export(path, input_schema, output_schema, ...)

Export the class object as a config and all related files to the user defined path.

inference_initialize(col_selector, model_config)

Configures this operator for use in inference.

load_artifacts([artifact_path])

Load artifacts from disk required for operator function.

output_column_names(col_selector)

Given a set of columns names returns the names of the transformed columns this operator will produce

save_artifacts([artifact_path])

Save artifacts required to be reload operator state from disk

transform(col_selector, df)

Selects all non-categorical columns and any categorical columns of at least the minimum cardinality from the dataframe.

validate_schemas(parents_schema, ...[, ...])

Provides a hook method that sub-classes can override to implement schema validation logic.

Attributes

dependencies

Defines an optional list of column dependencies for this operator.

dynamic_dtypes

export_name

Provides a clear common english identifier for this operator.

is_subgraph

label

output_dtype

output_properties

output_tags

supported_formats

supports

Returns what kind of data representation this operator supports

transform(col_selector: ColumnSelector, df: DataFrame) DataFrame[source]#

Selects all non-categorical columns and any categorical columns of at least the minimum cardinality from the dataframe.

Parameters:
  • col_selector (ColumnSelector) – The columns to select.

  • df (DataFrameType) – The dataframe to transform

Returns:

Dataframe with only the selected columns.

Return type:

DataFrameType

compute_selector(input_schema: Schema, selector: ColumnSelector, parents_selector: ColumnSelector, dependencies_selector: ColumnSelector) ColumnSelector[source]#

Checks the cardinality of the input columns and drops any categorical columns with cardinality less than the specified minimum.

Parameters:
  • input_schema (Schema) – The current node’s input schema

  • selector (ColumnSelector) – The current node’s selector

  • parents_selector (ColumnSelector) – A selector for the output columns of the current node’s parents

  • dependencies_selector (ColumnSelector) – A selector for the output columns of the current node’s dependencies

Returns:

Selector that contains all non-categorical columns and any categorical columns of at least the minimum cardinality.

Return type:

ColumnSelector