category

classifier_common

Shared predicates for classifier diagnostics, dataset validation, mixed-feature distance calculations, and export.

Availability:
logtalk_load(classification_protocols(loader))
Author: Paulo Moura
Version: 2:0:0
Date: 2026-05-11
Compilation flags:
static
Implements:
public classifier_protocol
Extends:
public options
Uses:
format
list
population
type
Remarks:
(none)
Inherited public predicates:
 check_classifier/1  check_option/1  check_options/1  classifier_options/2  default_option/1  default_options/1  diagnostic/2  diagnostics/2  export_to_clauses/4  export_to_file/4  learn/2  learn/3  option/2  option/3  predict/3  print_classifier/1  valid_classifier/1  valid_option/1  valid_options/1

Public predicates

(no local declarations; see entity ancestors if any)

Protected predicates

classifier_diagnostics_data/2

Hook predicate that importing classifier implementations must define in order to expose diagnostics metadata.

Compilation flags:
static
Template:
classifier_diagnostics_data(Classifier,Diagnostics)
Mode and number of proofs:
classifier_diagnostics_data(+compound,-list(compound)) - one

classifier_export_template/4

Hook predicate that importing classifier implementations must define in order to expose the exported classifier template for a given functor.

Compilation flags:
static
Template:
classifier_export_template(Dataset,Classifier,Functor,Template)
Mode and number of proofs:
classifier_export_template(+object_identifier,+compound,+atom,-callable) - one

classifier_term_template/2

Hook predicate that importing classifier implementations must define in order to expose the learned classifier term template used by pretty-printing helpers.

Compilation flags:
static
Template:
classifier_term_template(Classifier,Template)
Mode and number of proofs:
classifier_term_template(+compound,-callable) - one

valid_attribute_names/1

True when a list of attribute names is a proper list of distinct atoms.

Compilation flags:
static
Template:
valid_attribute_names(AttributeNames)
Mode and number of proofs:
valid_attribute_names(+list(atom)) - zero_or_one

valid_class_values/1

True when a list of class values is a non-empty proper list of distinct atoms.

Compilation flags:
static
Template:
valid_class_values(ClassValues)
Mode and number of proofs:
valid_class_values(+list(atom)) - zero_or_one

valid_feature_types/2

True when a list of feature type tags is non-empty and each tag belongs to the given allowed set.

Compilation flags:
static
Template:
valid_feature_types(FeatureTypes,AllowedTypes)
Mode and number of proofs:
valid_feature_types(+list,+list) - zero_or_one

valid_discrete_values/1

True when a list of categorical values is non-empty, contains only nonvar terms, and has no duplicates.

Compilation flags:
static
Template:
valid_discrete_values(Values)
Mode and number of proofs:
valid_discrete_values(+list) - zero_or_one

valid_linear_encoders/1

True when a list of encoders only contains valid continuous/3 or categorical/2 encoder terms with distinct attributes.

Compilation flags:
static
Template:
valid_linear_encoders(Encoders)
Mode and number of proofs:
valid_linear_encoders(+list(compound)) - zero_or_one

dataset_attributes/2

Collects the declared dataset attributes and their value domains.

Compilation flags:
static
Template:
dataset_attributes(Dataset,Attributes)
Mode and number of proofs:
dataset_attributes(+object_identifier,-list(pair)) - one

dataset_examples/2

Collects the dataset training examples as Id-Class-AttributeValues terms.

Compilation flags:
static
Template:
dataset_examples(Dataset,Examples)
Mode and number of proofs:
dataset_examples(+object_identifier,-list(compound)) - one

check_examples_non_empty/2

Checks that a training example collection is not empty.

Compilation flags:
static
Template:
check_examples_non_empty(Dataset,Examples)
Mode and number of proofs:
check_examples_non_empty(+object_identifier,+list) - one

check_examples/2

Checks that a training dataset is non-empty, that all example classes belong to the declared class values, and that provided attribute bindings use declared attributes with values matching the declared domains. Missing attribute bindings are allowed.

Compilation flags:
static
Template:
check_examples(Dataset,Examples)
Mode and number of proofs:
check_examples(+object_identifier,+list) - one_or_error

check_complete_examples/2

Checks that a training dataset is non-empty, that all example classes belong to the declared class values, and that each example contains every declared attribute exactly once with values matching the declared domains. Missing values represented using variables are allowed.

Compilation flags:
static
Template:
check_complete_examples(Dataset,Examples)
Mode and number of proofs:
check_complete_examples(+object_identifier,+list) - one_or_error

check_complete_examples_nonvar/2

Checks that a training dataset is non-empty, that all example classes belong to the declared class values, and that each example contains every declared attribute exactly once with non-variable values matching the declared domains.

Compilation flags:
static
Template:
check_complete_examples_nonvar(Dataset,Examples)
Mode and number of proofs:
check_complete_examples_nonvar(+object_identifier,+list) - one_or_error

build_linear_encoders/4

Builds linear-model encoders for continuous and categorical attributes. Continuous encoders optionally standardize features when FeatureScaling is true.

Compilation flags:
static
Template:
build_linear_encoders(Attributes,Examples,FeatureScaling,Encoders)
Mode and number of proofs:
build_linear_encoders(+list(pair),+list(compound),+boolean,-list(compound)) - one

examples_to_linear_rows/3

Encodes examples into Features-Class rows using the given linear encoders.

Compilation flags:
static
Template:
examples_to_linear_rows(Examples,Encoders,Rows)
Mode and number of proofs:
examples_to_linear_rows(+list(compound),+list(compound),-list(pair)) - one

encode_linear_instance/3

Encodes an instance into a numeric feature vector using the given linear encoders.

Compilation flags:
static
Template:
encode_linear_instance(Encoders,Instance,Features)
Mode and number of proofs:
encode_linear_instance(+list(compound),+list(pair),-list(float)) - one

linear_encoders_feature_count/2

Computes the number of numeric features produced by a set of linear encoders.

Compilation flags:
static
Template:
linear_encoders_feature_count(Encoders,Count)
Mode and number of proofs:
linear_encoders_feature_count(+list(compound),-integer) - one

valid_classifier_metadata/2

True when diagnostics metadata contains the expected model term.

Compilation flags:
static
Template:
valid_classifier_metadata(Model,Diagnostics)
Mode and number of proofs:
valid_classifier_metadata(+atom,+list(compound)) - zero_or_one

valid_classifier_metadata/3

True when diagnostics metadata contains the expected model term and records the given effective options.

Compilation flags:
static
Template:
valid_classifier_metadata(Model,Options,Diagnostics)
Mode and number of proofs:
valid_classifier_metadata(+atom,+list(compound),+list(compound)) - zero_or_one

mixed_feature_distance/5

Computes a distance between two mixed-feature vectors using the given feature types and one of the supported metrics euclidean, manhattan, chebyshev, cosine, or minkowski(Order).

Compilation flags:
static
Template:
mixed_feature_distance(Metric,FeatureTypes,Values1,Values2,Distance)
Mode and number of proofs:
mixed_feature_distance(+term,+list,+list,+list,-float) - one_or_error

Private predicates

(no local declarations; see entity ancestors if any)

Operators

(none)