3.3.3.145. NXsimilarity_grouping

Status:

base class, extends NXobject

Description:

Metadata to the results of a similarity grouping analysis. ...

Metadata to the results of a similarity grouping analysis.

Similarity grouping analyses can be supervised segmentation or machine learning clustering algorithms. These are routine methods which partition the member of a set of objects/geometric primitives into (sub-)groups, features of different type. A plethora of algorithms have been proposed which can be applied also on geometric primitives like points, triangles, or (abstract) features aka objects (including categorical sub-groups).

This base class considers metadata and results of one similarity grouping analysis applied to a set in which objects are either categorized as noise or belonging to a cluster. As the results of the analysis each similarity group, here called feature aka object can get a number of numerical and/or categorical labels.

Symbols:

The symbols used in the schema to specify e.g. dimensions of arrays.

c: Cardinality of the set.

n_lbl_num: Number of numerical labels per object.

n_lbl_cat: Number of categorical labels per object.

n_features: Total number of similarity groups aka features, objects, clusters.

Groups cited:

NXprocess

Structure:

cardinality: (optional) NX_UINT {units=NX_UNITLESS}

Number of members in the set which is partitioned into features.

number_of_numeric_labels: (optional) NX_UINT {units=NX_UNITLESS}

How many numerical labels does each feature have.

number_of_categorical_labels: (optional) NX_UINT {units=NX_UNITLESS}

How many categorical labels does each feature have.

identifier_offset: (optional) NX_UINT (Rank: 1, Dimensions: [n_lbl_num]) {units=NX_UNITLESS}

Which identifier is the first to be used to label a cluster. ...

Which identifier is the first to be used to label a cluster.

The value should be chosen in such a way that special values can be resolved: * identifier_offset-1 indicates an object belongs to no cluster. * identifier_offset-2 indicates an object belongs to the noise category. Setting for instance identifier_offset to 1 recovers the commonly used case that objects of the noise category get values to -1 and unassigned points to 0. Numerical identifier have to be strictly increasing.

numerical_label: (optional) NX_UINT (Rank: 2, Dimensions: [c, n_lbl_num]) {units=NX_UNITLESS}

Matrix of numerical label for each member in the set. ...

Matrix of numerical label for each member in the set. For classical clustering algorithms this can for instance encode the cluster_identifier.

categorical_label: (optional) NX_CHAR (Rank: 2, Dimensions: [c, n_lbl_cat])

Matrix of categorical attribute data for each member in the set.

statistics: (optional) NXprocess

In addition to the detailed storage which members was grouped to which ...

In addition to the detailed storage which members was grouped to which feature/group summary statistics are stored under this group.

number_of_unassigned_members: (optional) NX_UINT (Rank: 1, Dimensions: [n_lbl_num]) {units=NX_UNITLESS}

Total number of members in the set which are categorized as unassigned.

noise: (optional) NX_UINT (Rank: 1, Dimensions: [n_lbl_num]) {units=NX_UNITLESS}

Total number of members in the set which are categorized as noise.

number_of_features: (optional) NX_UINT {units=NX_UNITLESS}

Total number of clusters (excluding noise and unassigned).

feature_identifier: (optional) NX_UINT (Rank: 2, Dimensions: [n_features, n_lbl_num]) {units=NX_UNITLESS}

Array of numerical identifier of each feature (cluster).

feature_member_count: (optional) NX_UINT (Rank: 2, Dimensions: [n_features, n_lbl_num]) {units=NX_UNITLESS}

Array of number of members for each feature.

Hypertext Anchors

List of hypertext anchors for all groups, fields, attributes, and links defined in this class.

NXDL Source:

https://github.com/nexusformat/definitions/blob/main/contributed_definitions/NXsimilarity_grouping.nxdl.xml