Merge pull request #181 from linkml/first-class-arrays

First pass at native NDArray support.

linkml_model/model/schema/array.yaml

@@ -63,6 +63,8 @@ classes:
     slots:
       - axis
       - array
+    see_also:
+      - https://docs.xarray.dev/en/stable/generated/xarray.DataArray.html
 
   GroupingByArrayOrder:
     mixin: true

linkml_model/model/schema/meta.yaml

@@ -29,7 +29,6 @@ description: |-
   [https://w3id.org/linkml/is_a](https://w3id.org/linkml/is_a)
 
 license: https://creativecommons.org/publicdomain/zero/1.0/
-version: 2.0.0
 
 prefixes:
   linkml: https://w3id.org/linkml/
@@ -1419,6 +1418,62 @@ slots:
       - BasicSubset
       - ObjectOrientedProfile
 
+  array:
+    domain: slot_definition
+    range: array_expression
+    inherited: true
+    description: coerces the value of the slot into an array and defines the dimensions of that array
+    status: testing
+
+  dimensions:
+    aliases:
+      - axes
+    description: definitions of each axis in the array
+    domain: array_expression
+    range: dimension_expression
+    multivalued: true
+    list_elements_ordered: true
+    status: testing
+
+  minimum_number_dimensions:
+    description: minimum number of dimensions in the array
+    domain: array_expression
+    range: integer
+    status: testing
+    # minimum_value: 1
+    comments:
+      - minimum_cardinality cannot be greater than maximum_cardinality
+
+  maximum_number_dimensions:
+    description: maximum number of dimensions in the array, or False if explicitly no maximum.
+      If this is unset, and an explicit list of dimensions are passed using dimensions, then this is interpreted
+      as a closed list and the maximum_number_dimensions is the length of the dimensions list, unless this
+      value is set to False
+    domain: array_expression
+    range: Anything
+    any_of:
+      - range: integer
+        # minimum_value: 1
+      - range: boolean
+    status: testing
+    comments:
+      - maximum_number_dimensions cannot be less than minimum_number_dimensions
+
+  exact_number_dimensions:
+    description: exact number of dimensions in the array
+    domain: array_expression
+    range: integer
+    status: testing
+    # minimum_value: 1
+    comments:
+      - if exact_number_dimensions is set, then minimum_number_dimensions and maximum_number_dimensions must be unset or have the same value
+
+  has_extra_dimensions:
+    description: If this is set to true
+    domain: array_expression
+    range: boolean
+    status: testing
+
   inherited:
     domain: slot_definition
     range: boolean
@@ -1520,13 +1575,26 @@ slots:
     in_subset:
       - SpecificationSubset
 
+  exact_cardinality:
+    is_a: list_value_specification_constant
+    range: integer
+    inherited: true
+    description: the exact number of entries for a multivalued slot
+    in_subset:
+      - SpecificationSubset
+    comments:
+      - if exact_cardinality is set, then minimum_cardinalty and maximum_cardinality must be unset or have the same value
+
   minimum_cardinality:
     is_a: list_value_specification_constant
     range: integer
     inherited: true
     description: the minimum number of entries for a multivalued slot
     in_subset:
       - SpecificationSubset
+    # minimum_value: 0
+    comments:
+      - minimum_cardinality cannot be greater than maximum_cardinality
 
   maximum_cardinality:
     is_a: list_value_specification_constant
@@ -1535,6 +1603,9 @@ slots:
     description: the maximum number of entries for a multivalued slot
     in_subset:
       - SpecificationSubset
+    comments:
+      - maximum_cardinality cannot be less than minimum_cardinality
+    # minimum_value: 0
 
   equals_string_in:
     is_a: list_value_specification_constant
@@ -2714,6 +2785,7 @@ classes:
       - equals_string_in
       - equals_number
       - equals_expression
+      - exact_cardinality
       - minimum_cardinality
       - maximum_cardinality
       - has_member
@@ -2758,6 +2830,7 @@ classes:
       - domain
       - slot_uri
       - multivalued
+      - array
       - inherited
       - readonly
       - ifabsent
@@ -2916,6 +2989,33 @@ classes:
     in_subset:
       - SpecificationSubset
 
+  array_expression:
+    description: defines the dimensions of an array
+    mixins:
+      - extensible
+      - annotatable
+      - common_metadata
+    slots:
+      - exact_number_dimensions
+      - minimum_number_dimensions
+      - maximum_number_dimensions
+      - has_extra_dimensions
+      - dimensions
+    status: testing
+
+  dimension_expression:
+    description: defines one of the dimensions of an array
+    mixins:
+      - extensible
+      - annotatable
+      - common_metadata
+    slots:
+      - alias
+      - maximum_cardinality
+      - minimum_cardinality
+      - exact_cardinality
+    status: testing
+
   pattern_expression:
     description: a regular expression pattern used to evaluate conformance of a string
     mixins:

linkml_model/model/schema/types.yaml

@@ -4,7 +4,6 @@ id: https://w3id.org/linkml/types
 
 description: Shared type definitions for the core LinkML mode and metamodel
 license: https://creativecommons.org/publicdomain/zero/1.0/
-version: 2.0.0
 
 prefixes:
   linkml: https://w3id.org/linkml/

tests/input/examples/schema_definition-array-2.yaml

@@ -26,7 +26,7 @@ classes:
     implements:
       - linkml:NDArray
     annotations:
-      dimensions: 1
+      dimensions: "1"
     # TODO abstract from children
 
   IrregularlySampledTimestampSeries:
@@ -47,7 +47,7 @@ classes:
         unit:
           ucum_code: s
     annotations:
-      dimensions: 1
+      dimensions: "1"
 
   RegularlySampledTimestampSeries:
     is_a: TimestampSeries
@@ -82,7 +82,7 @@ classes:
         unit:
           ucum_code: s
     annotations:
-      dimensions: 1
+      dimensions: "1"
 
   Electrode:
     attributes:
@@ -106,7 +106,7 @@ classes:
         implements:
           - linkml:elements
     annotations:
-      dimensions: 1
+      dimensions: "1"
 
   ElectricalDataMatrix:
     description: >-

tests/input/examples/schema_definition-dynamic-enums.yaml

@@ -163,7 +163,6 @@ enums:
       source_ontology: http://loinc.org
       source_nodes:
         - LP43571-6
-      relationship_types: null
       is_direct: true
       include_self: true
       traverse_up: false

tests/input/examples/schema_definition-instantiates.yaml

@@ -42,8 +42,10 @@ classes:
   Reviewable:
     class_uri: mymetamodel:Reviewable
     attributes:
-      description: an expert review of a schema element
-      review: Review
+      description:
+        description: an expert review of a schema element
+      review:
+        description: Review
 
   Review:
     class_uri: mymetamodel:Review

tests/input/examples/schema_definition-native-array-1.yaml

@@ -0,0 +1,68 @@
+id: https://example.org/arrays
+name: arrays-temperature-example
+title: Array Temperature Example
+description: |-
+  Example LinkML schema to demonstrate a 3D DataArray of temperature values with labeled axes
+license: MIT
+
+prefixes:
+  linkml: https://w3id.org/linkml/
+  wgs84: http://www.w3.org/2003/01/geo/wgs84_pos#
+  example: https://example.org/
+
+default_prefix: example
+
+imports:
+  - linkml:types
+
+classes:
+
+  TemperatureDataset:
+    tree_root: true
+    annotations:
+      array_data_mapping:
+        data: temperatures_in_K
+        dims: [x, y, t]
+        coords:
+          latitude_in_deg: x
+          longitude_in_deg: y
+          time_in_d: t
+    attributes:
+      name:
+        identifier: true
+        range: string
+      latitude_in_deg:
+        required: true
+        range: float
+        multivalued: true
+        unit:
+          ucum_code: deg
+        array:
+          exact_number_dimensions: 1
+      longitude_in_deg:
+        required: true
+        range: float
+        multivalued: true
+        unit:
+          ucum_code: deg
+        array:
+          exact_number_dimensions: 1
+      time_in_d:
+        range: float
+        multivalued: true
+        implements:
+          - linkml:elements
+        required: true
+        unit:
+          ucum_code: d
+        array:
+          exact_number_dimensions: 1
+      temperatures_in_K:
+        range: float
+        multivalued: true
+        required: true
+        unit:
+          ucum_code: K
+        array:
+          exact_number_dimensions: 3
+

tests/input/examples/schema_definition-native-array-rgb.yaml

@@ -0,0 +1,52 @@
+id: https://example.org/arrays
+name: arrays-temperature-example
+title: Array Temperature Example
+description: |-
+  Example LinkML schema to demonstrate a 3D DataArray of temperature values with labeled axes
+license: MIT
+
+prefixes:
+  linkml: https://w3id.org/linkml/
+  wgs84: http://www.w3.org/2003/01/geo/wgs84_pos#
+  example: https://example.org/
+
+default_prefix: example
+
+imports:
+  - linkml:types
+
+classes:
+
+  RGBImage:
+    attributes:
+      rgb:
+        range: float
+        array:
+          # NPtyping: NDArray[Shape["* x, * y, 3 rgb"]
+          exact_number_dimensions: 3
+          dimensions:
+            - alias: x
+            - alias: y
+            - alias: rgb
+              exact_cardinality: 3
+              description: r, g, b values
+              annotations:
+                names: "[red, green, blue]"
+  SquareDataset:
+    attributes:
+      square_matrix:
+        array:
+          exact_number_dimensions: 2
+          dimensions:
+            - alias: x
+            - alias: y
+
+  UnboundedTimeSeries:
+    attributes:
+      my_matrix:
+        range: float
+        array:
+          dimensions:
+            - alias: time
+          maximum_number_dimensions: False
+