neuralogic.core.constructs.function package

Submodules

neuralogic.core.constructs.function.concat module

class ConcatAggregation(name: str, *, axis: int = -1)[source]

Bases: AggregationFunction

Represents a concatenation aggregation function that joins multiple groundings along a specified axis.

axis

get() → Any[source]

Returns the Java representation of the function.

Returns:: The Java function object.
Return type:: Any

is_parametrized() → bool[source]

class ConcatCombination(name: str, *, axis: int = -1)[source]

Bases: CombinationFunction

Represents a concatenation combination function that joins multiple tensors along a specified axis.

axis

get() → Any[source]

Returns the Java representation of the function.

Returns:: The Java function object.
Return type:: Any

is_parametrized() → bool[source]

neuralogic.core.constructs.function.enum module

class Aggregation[source]

Bases: object

Collection of aggregation functions. Aggregation functions are used to aggregate multiple inputs, typically from different groundings of the same rule.

AVG: AggregationFunction = <neuralogic.core.constructs.function.function.AggregationFunction object>

CONCAT: ConcatAggregation = <neuralogic.core.constructs.function.concat.ConcatAggregation object>

COUNT: AggregationFunction = <neuralogic.core.constructs.function.function.AggregationFunction object>

MAX: AggregationFunction = <neuralogic.core.constructs.function.function.AggregationFunction object>

MIN: AggregationFunction = <neuralogic.core.constructs.function.function.AggregationFunction object>

SOFTMAX: SoftmaxAggregation = <neuralogic.core.constructs.function.softmax.SoftmaxAggregation object>

SUM: AggregationFunction = <neuralogic.core.constructs.function.function.AggregationFunction object>

class Combination[source]

Bases: object

Collection of combination functions. Combination functions are used to combine multiple inputs into a single output, often as part of a rule body or for combining multiple rules.

AVG: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

CONCAT: ConcatCombination = <neuralogic.core.constructs.function.concat.ConcatCombination object>

COSSIM: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

COUNT: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

CROSSSUM: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

ELPRODUCT: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

MAX: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

MIN: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

PRODUCT: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

SOFTMAX: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

SPARSEMAX: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

SUM: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

class F[source]

Bases: object

Utility class providing a flat namespace for common functions. It includes transformation, combination, and aggregation functions.

avg: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

avg_agg: AggregationFunction = <neuralogic.core.constructs.function.function.AggregationFunction object>

concat: ConcatCombination = <neuralogic.core.constructs.function.concat.ConcatCombination object>

concat_agg: ConcatAggregation = <neuralogic.core.constructs.function.concat.ConcatAggregation object>

cossim: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

count: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

count_agg: AggregationFunction = <neuralogic.core.constructs.function.function.AggregationFunction object>

crossum: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

elproduct: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

exp: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

identity: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

inverse: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

leaky_relu: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

log: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

lukasiewicz: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

max: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

max_agg: AggregationFunction = <neuralogic.core.constructs.function.function.AggregationFunction object>

min: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

min_agg: AggregationFunction = <neuralogic.core.constructs.function.function.AggregationFunction object>

norm: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

product: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

relu: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

reshape: Reshape = <neuralogic.core.constructs.function.reshape.Reshape object>

reverse: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

sigmoid: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

signum: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

slice: Slice = <neuralogic.core.constructs.function.slice.Slice object>

softmax: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

softmax_agg: SoftmaxAggregation = <neuralogic.core.constructs.function.softmax.SoftmaxAggregation object>

softmax_comb: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

sparsemax: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

sparsemax_comb: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

sqrt: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

sum: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

sum_agg: AggregationFunction = <neuralogic.core.constructs.function.function.AggregationFunction object>

tanh: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

transp: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

class Transformation[source]

Bases: object

Collection of transformation functions. Transformation functions are applied element-wise or as join operations (e.g., Softmax, Transpose).

EXP: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

IDENTITY: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

INVERSE: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

LEAKY_RELU: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

LOG: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

LUKASIEWICZ: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

NORM: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

RELU: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

RESHAPE: Reshape = <neuralogic.core.constructs.function.reshape.Reshape object>

REVERSE: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

SIGMOID: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

SIGNUM: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

SLICE: Slice = <neuralogic.core.constructs.function.slice.Slice object>

SOFTMAX: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

SPARSEMAX: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

SQRT: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

TANH: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

TRANSP: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

neuralogic.core.constructs.function.function module

class AggregationFunction(name: str, *, namespace: str = '', operator: str | None = None, can_flatten: bool = False)[source]

Bases: Function

Represents an aggregation function used to aggregate multiple groundings of the same rule.

can_flatten

get() → Any[source]

Returns the Java representation of the function.

Returns:: The Java function object.
Return type:: Any

name: str

namespace

operator: str | None

class CombinationFunction(name: str, *, namespace: str = 'combination.{name}', operator: str | None = None, can_flatten: bool = False)[source]

Bases: Function

Represents a combination function used to combine multiple relations into a single output.

can_flatten

name: str

namespace

operator: str | None

class Function(name: str, *, namespace: str = '', operator: str | None = None, can_flatten: bool = False)[source]

Bases: object

Base class for all logic functions (transformation, combination, aggregation). Functions are used to transform, combine, or aggregate values in the logic program.

can_flatten

get() → Any[source]

Returns the Java representation of the function.

Returns:: The Java function object.
Return type:: Any

is_parametrized() → bool[source]

name: str

namespace

operator: str | None

pretty_str() → str[source]

process_head(head: Any) → Function[source]

rule_head_dependant() → bool[source]

wrap(content: str) → str[source]

class TransformationFunction(name: str, *, namespace: str = 'transformation.elementwise.{name}', operator: str | None = None, can_flatten: bool = False)[source]

Bases: Function

Represents a transformation function applied to a relation or a container of relations. Transformation functions can be applied element-wise or as join operations.

can_flatten

name: str

namespace

operator: str | None

neuralogic.core.constructs.function.function_container module

class FContainer(nodes: Iterable[Any], function: Function)[source]

Bases: object

A container for multiple logic nodes (relations or other containers) and a function to apply to them.

It allows for nesting and building complex function graphs.

function

static get_flattened_nodes(nodes: Iterable[Any], function: Function) → tuple[source]

Flattens the nodes if they are FContainers with the same function.

Parameters:

nodes (Iterable[Any]) – The nodes to flatten.
function (Function) – The function used for flattening criteria.

Returns:

The flattened nodes.

Return type:

tuple

property name: str

nodes

to_function() → Function[source]

Converts the container and its nested structure into a FunctionGraph.

Returns:: The generated FunctionGraph.
Return type:: Function

to_str(parentheses_wrap: bool = False) → str[source]

Returns a string representation of the container.

Parameters:: parentheses_wrap (bool) – Whether to wrap the output in parentheses. Default: False.
Returns:: The string representation.
Return type:: str

neuralogic.core.constructs.function.function_graph module

class FunctionGraph(name: str, *, function_graph)[source]

Bases: Function

function_graph

get()[source]

Returns the Java representation of the function.

Returns:: The Java function object.
Return type:: Any

is_parametrized() → bool[source]

neuralogic.core.constructs.function.reshape module

class Reshape(name: str, *, shape: tuple[int, int] | int | None = None)[source]

Bases: TransformationFunction

Represents a reshape transformation function that changes the shape of a tensor.

get() → Any[source]

Returns the Java representation of the function.

Returns:: The Java function object.
Return type:: Any

is_parametrized() → bool[source]

shape

wrap(content: str) → str[source]

neuralogic.core.constructs.function.slice module

class Slice(name: str, *, rows: EllipsisType | tuple[int, int] = Ellipsis, cols: EllipsisType | tuple[int, int] = Ellipsis)[source]

Bases: TransformationFunction

Represents a slice transformation function that extracts a sub-tensor from a tensor.

cols

get() → Any[source]

Returns the Java representation of the function.

Returns:: The Java function object.
Return type:: Any

is_parametrized() → bool[source]

rows

wrap(content: str) → str[source]

neuralogic.core.constructs.function.softmax module

class SoftmaxAggregation(name: str, *, agg_terms: Sequence[str] | None = None)[source]

Bases: AggregationFunction

Represents a Softmax aggregation function. It can be parametrized by specific terms (variables) to aggregate over.

agg_terms

get() → Any[source]

Returns the Java representation of the function.

Returns:: The Java function object.
Return type:: Any

is_parametrized() → bool[source]

process_head(head) → SoftmaxAggregation[source]

Processes the rule head to determine the indices of the aggregation terms.

Parameters:: head (Any) – The rule head.
Returns:: A new instance with the determined term indices.
Return type:: SoftmaxAggregation

rule_head_dependant() → bool[source]

var_terms

Module contents

class Aggregation[source]

Bases: object

Collection of aggregation functions. Aggregation functions are used to aggregate multiple inputs, typically from different groundings of the same rule.

AVG: AggregationFunction = <neuralogic.core.constructs.function.function.AggregationFunction object>

CONCAT: ConcatAggregation = <neuralogic.core.constructs.function.concat.ConcatAggregation object>

COUNT: AggregationFunction = <neuralogic.core.constructs.function.function.AggregationFunction object>

MAX: AggregationFunction = <neuralogic.core.constructs.function.function.AggregationFunction object>

MIN: AggregationFunction = <neuralogic.core.constructs.function.function.AggregationFunction object>

SOFTMAX: SoftmaxAggregation = <neuralogic.core.constructs.function.softmax.SoftmaxAggregation object>

SUM: AggregationFunction = <neuralogic.core.constructs.function.function.AggregationFunction object>

class Combination[source]

Bases: object

Collection of combination functions. Combination functions are used to combine multiple inputs into a single output, often as part of a rule body or for combining multiple rules.

AVG: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

CONCAT: ConcatCombination = <neuralogic.core.constructs.function.concat.ConcatCombination object>

COSSIM: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

COUNT: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

CROSSSUM: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

ELPRODUCT: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

MAX: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

MIN: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

PRODUCT: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

SOFTMAX: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

SPARSEMAX: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

SUM: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

class F[source]

Bases: object

Utility class providing a flat namespace for common functions. It includes transformation, combination, and aggregation functions.

avg: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

avg_agg: AggregationFunction = <neuralogic.core.constructs.function.function.AggregationFunction object>

concat: ConcatCombination = <neuralogic.core.constructs.function.concat.ConcatCombination object>

concat_agg: ConcatAggregation = <neuralogic.core.constructs.function.concat.ConcatAggregation object>

cossim: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

count: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

count_agg: AggregationFunction = <neuralogic.core.constructs.function.function.AggregationFunction object>

crossum: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

elproduct: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

exp: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

identity: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

inverse: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

leaky_relu: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

log: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

lukasiewicz: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

max: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

max_agg: AggregationFunction = <neuralogic.core.constructs.function.function.AggregationFunction object>

min: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

min_agg: AggregationFunction = <neuralogic.core.constructs.function.function.AggregationFunction object>

norm: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

product: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

relu: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

reshape: Reshape = <neuralogic.core.constructs.function.reshape.Reshape object>

reverse: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

sigmoid: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

signum: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

slice: Slice = <neuralogic.core.constructs.function.slice.Slice object>

softmax: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

softmax_agg: SoftmaxAggregation = <neuralogic.core.constructs.function.softmax.SoftmaxAggregation object>

softmax_comb: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

sparsemax: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

sparsemax_comb: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

sqrt: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

sum: CombinationFunction = <neuralogic.core.constructs.function.function.CombinationFunction object>

sum_agg: AggregationFunction = <neuralogic.core.constructs.function.function.AggregationFunction object>

tanh: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

transp: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

class FContainer(nodes: Iterable[Any], function: Function)[source]

Bases: object

A container for multiple logic nodes (relations or other containers) and a function to apply to them.

It allows for nesting and building complex function graphs.

function

static get_flattened_nodes(nodes: Iterable[Any], function: Function) → tuple[source]

Flattens the nodes if they are FContainers with the same function.

Parameters:

nodes (Iterable[Any]) – The nodes to flatten.
function (Function) – The function used for flattening criteria.

Returns:

The flattened nodes.

Return type:

tuple

property name: str

nodes

to_function() → Function[source]

Converts the container and its nested structure into a FunctionGraph.

Returns:: The generated FunctionGraph.
Return type:: Function

to_str(parentheses_wrap: bool = False) → str[source]

Returns a string representation of the container.

Parameters:: parentheses_wrap (bool) – Whether to wrap the output in parentheses. Default: False.
Returns:: The string representation.
Return type:: str

class Function(name: str, *, namespace: str = '', operator: str | None = None, can_flatten: bool = False)[source]

Bases: object

Base class for all logic functions (transformation, combination, aggregation). Functions are used to transform, combine, or aggregate values in the logic program.

can_flatten

get() → Any[source]

Returns the Java representation of the function.

Returns:: The Java function object.
Return type:: Any

is_parametrized() → bool[source]

name: str

namespace

operator: str | None

pretty_str() → str[source]

process_head(head: Any) → Function[source]

rule_head_dependant() → bool[source]

wrap(content: str) → str[source]

class Transformation[source]

Bases: object

Collection of transformation functions. Transformation functions are applied element-wise or as join operations (e.g., Softmax, Transpose).

EXP: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

IDENTITY: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

INVERSE: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

LEAKY_RELU: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

LOG: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

LUKASIEWICZ: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

NORM: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

RELU: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

RESHAPE: Reshape = <neuralogic.core.constructs.function.reshape.Reshape object>

REVERSE: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

SIGMOID: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

SIGNUM: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

SLICE: Slice = <neuralogic.core.constructs.function.slice.Slice object>

SOFTMAX: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

SPARSEMAX: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

SQRT: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

TANH: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>

TRANSP: TransformationFunction = <neuralogic.core.constructs.function.function.TransformationFunction object>