cognite-neat 0.101.0__tar.gz → 0.102.0__tar.gz

{cognite_neat-0.101.0 → cognite_neat-0.102.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cognite-neat
-Version: 0.101.0
+Version: 0.102.0
 Summary: Knowledge graph transformation
 Home-page: https://cognite-neat.readthedocs-hosted.com/
 License: Apache-2.0

{cognite_neat-0.101.0 → cognite_neat-0.102.0}/cognite/neat/_constants.py

@@ -71,7 +71,7 @@ UNKNOWN_TYPE = DEFAULT_NAMESPACE.UnknownType
 XML_SCHEMA_NAMESPACE = Namespace("http://www.w3.org/2001/XMLSchema#")
 
 
-def get_default_prefixes() -> dict[str, Namespace]:
+def get_default_prefixes_and_namespaces() -> dict[str, Namespace]:
     return {
         "owl": OWL._NS,
         "rdf": RDF._NS,
@@ -84,6 +84,10 @@ def get_default_prefixes() -> dict[str, Namespace]:
         "imf": Namespace("http://ns.imfid.org/imf#"),
         "pav": Namespace("http://purl.org/pav/"),
         "foaf": FOAF._NS,
+        "dexpi": Namespace("http://sandbox.dexpi.org/rdl/"),
+        "qudt": Namespace("https://qudt.org/vocab/unit/"),
+        "iodd": Namespace("http://www.io-link.com/IODD/2010/10/"),
+        "aml": Namespace("https://www.automationml.org/"),
     }
 
 

{cognite_neat-0.101.0 → cognite_neat-0.102.0}/cognite/neat/_graph/loaders/_rdf2dms.py

@@ -197,7 +197,7 @@ class DMSLoader(CDFLoader[dm.InstanceApply]):
         json_fields: list[str] = []
         for prop_name, prop in view.properties.items():
             if isinstance(prop, dm.EdgeConnection):
-                edge_by_property[prop.type.external_id] = prop_name, prop
+                edge_by_property[prop_name] = prop_name, prop
             if isinstance(prop, dm.MappedProperty):
                 if isinstance(prop.type, dm.DirectRelation):
                     direct_relation_by_property[prop_name] = prop.type

{cognite_neat-0.101.0 → cognite_neat-0.102.0}/cognite/neat/_graph/queries/_base.py

@@ -209,7 +209,10 @@ class Queries:
             elif (
                 isinstance(object_, URIRef)
                 and property_types
-                and property_types.get(property_, None) == EntityTypes.object_property
+                and (
+                    property_types.get(property_, None) == EntityTypes.object_property
+                    or property_types.get(property_, None) == EntityTypes.undefined
+                )
             ):
                 value = remove_namespace_from_uri(object_, validation="prefix")
 
@@ -233,7 +236,6 @@ class Queries:
                 else:
                     # we should not have multiple rdf:type values
                     continue
-
         if property_values:
             return (
                 identifier,
@@ -358,3 +360,21 @@ class Queries:
             dropped_types[t] = len(instance_ids)
             remove_instance_ids_in_batch(self.graph, instance_ids)
         return dropped_types
+
+    def multi_type_instances(self) -> dict[str, list[str]]:
+        """Find instances with multiple types"""
+
+        query = """
+        SELECT ?instance (GROUP_CONCAT(str(?type); SEPARATOR=",") AS ?types)
+        WHERE {
+            ?instance a ?type .
+        }
+        GROUP BY ?instance
+        HAVING (COUNT(?type) > 1)
+        """
+
+        result = {}
+        for instance, types in self.graph.query(query):  # type: ignore
+            result[remove_namespace_from_uri(instance)] = remove_namespace_from_uri(types.split(","))
+
+        return result

{cognite_neat-0.101.0 → cognite_neat-0.102.0}/cognite/neat/_graph/queries/_shared.py

@@ -6,7 +6,7 @@ from pydantic import BaseModel, ConfigDict, Field
 from rdflib import Graph, Literal, Namespace
 from rdflib.term import URIRef
 
-from cognite.neat._constants import get_default_prefixes
+from cognite.neat._constants import get_default_prefixes_and_namespaces
 from cognite.neat._rules.models._rdfpath import (
     Hop,
     Step,
@@ -51,7 +51,7 @@ def generate_prefix_header(prefixes: dict[str, Namespace] | None = None) -> str:
         Prefix header
     """
 
-    prefixes = prefixes or get_default_prefixes()
+    prefixes = prefixes or get_default_prefixes_and_namespaces()
 
     return "".join(f"PREFIX {key}:<{value}>\n" for key, value in prefixes.items())
 
@@ -81,7 +81,7 @@ def get_predicate_id(
         ID of predicate (aka property) connecting subject and object
     """
 
-    prefixes = prefixes or get_default_prefixes()
+    prefixes = prefixes or get_default_prefixes_and_namespaces()
 
     query = """
 
@@ -123,7 +123,7 @@ def hop2property_path(
     str
         Property path string for hop traversal (e.g. ^rdf:type/rdfs:subClassOf)
     """
-    prefixes = prefixes if prefixes else get_default_prefixes()
+    prefixes = prefixes if prefixes else get_default_prefixes_and_namespaces()
 
     # setting previous step to origin, as we are starting from there
     previous_step = Step(class_=hop.class_, direction="origin")

{cognite_neat-0.101.0 → cognite_neat-0.102.0}/cognite/neat/_graph/transformers/__init__.py

@@ -7,7 +7,13 @@ from ._classic_cdf import (
     AssetTimeSeriesConnector,
     RelationshipAsEdgeTransformer,
 )
-from ._prune_graph import AttachPropertyFromTargetToSource, PruneDanglingNodes
+from ._prune_graph import (
+    AttachPropertyFromTargetToSource,
+    PruneDanglingNodes,
+    PruneDeadEndEdges,
+    PruneInstancesOfUnknownType,
+    PruneTypes,
+)
 from ._rdfpath import AddSelfReferenceProperty, MakeConnectionOnExactMatch
 from ._value_type import SplitMultiValueProperty
 
@@ -24,6 +30,9 @@ __all__ = [
     "MakeConnectionOnExactMatch",
     "AttachPropertyFromTargetToSource",
     "PruneDanglingNodes",
+    "PruneTypes",
+    "PruneDeadEndEdges",
+    "PruneInstancesOfUnknownType",
 ]
 
 Transformers = (
@@ -39,4 +48,7 @@ Transformers = (
     | MakeConnectionOnExactMatch
     | AttachPropertyFromTargetToSource
     | PruneDanglingNodes
+    | PruneTypes
+    | PruneDeadEndEdges
+    | PruneInstancesOfUnknownType
 )

{cognite_neat-0.101.0 → cognite_neat-0.102.0}/cognite/neat/_graph/transformers/_base.py

@@ -6,7 +6,7 @@ from rdflib import Graph
 
 class BaseTransformer(ABC):
     description: str
-    _use_only_once: bool
+    _use_only_once: bool = False
     _need_changes: ClassVar[frozenset[str]] = frozenset()
 
     @abstractmethod

{cognite_neat-0.101.0 → cognite_neat-0.102.0}/cognite/neat/_graph/transformers/_iodd.py

@@ -17,9 +17,9 @@ class IODDAttachPropertyFromTargetToSource(AttachPropertyFromTargetToSource):
     def __init__(self):
         super().__init__(
             target_node_type=IODD.TextObject,
-            namespace=IODD,
-            target_property="value",
+            target_property=IODD.value,
             delete_target_node=True,
+            namespace=IODD,
         )
 
 

{cognite_neat-0.101.0 → cognite_neat-0.102.0}/cognite/neat/_graph/transformers/_prune_graph.py

@@ -1,6 +1,9 @@
+from typing import cast
+
 from rdflib import Graph, Namespace, URIRef
-from rdflib.query import ResultRow
 
+from cognite.neat._constants import DEFAULT_NAMESPACE
+from cognite.neat._shared import Triple
 from cognite.neat._utils.rdf_ import as_neat_compliant_uri
 from cognite.neat._utils.text import sentence_or_string_to_camel
 
@@ -55,12 +58,13 @@ class AttachPropertyFromTargetToSource(BaseTransformer):
 
     Args:
         target_node_type: RDF.type of edge Node
-        namespace: RDF Namespace to use when querying the graph
-        target_property: str with name of the property that holds the value attached to the intermediate node
-        target_property_holding_new_property_name: Optional str of the property name that holds
-        the new predicate to use when attaching the new property to the source node.
+        target_property: URIRef of the property that holds the value attached to the intermediate node
+        target_property_holding_new_property: URIRef of the property which value will be new
+        property that will be added to the source node
         delete_target_node: bool if the intermediate Node and Edge between source Node
                                 and target property should be deleted. Defaults to False.
+        convert_literal_to_uri: bool if the value of the new property should be converted to URIRef. Defaults to False.
+        namespace: Namespace to use when converting value to URIRef. Defaults to DEFAULT_NAMESPACE.
     """
 
     description: str = "Attaches a target property from a target node that is connected to a source node."
@@ -82,25 +86,26 @@ class AttachPropertyFromTargetToSource(BaseTransformer):
     def __init__(
         self,
         target_node_type: URIRef,
-        namespace: Namespace,
-        target_property: str,
-        target_property_holding_new_property_name: str | None = None,
+        target_property: URIRef,
+        target_property_holding_new_property: URIRef | None = None,
         delete_target_node: bool = False,
+        convert_literal_to_uri: bool = False,
+        namespace: Namespace | None = None,
     ):
         self.target_node_type = target_node_type
-        self.namespace = namespace
-        self.target_property = self.namespace[target_property]
+        self.target_property = target_property
         self.delete_target_node = delete_target_node
-        self.target_property_holding_new_property_name = target_property_holding_new_property_name
+        self.target_property_holding_new_property = target_property_holding_new_property
+        self.convert_literal_to_uri = convert_literal_to_uri
+        self.namespace = namespace or DEFAULT_NAMESPACE
 
     def transform(self, graph) -> None:
         nodes_to_delete: list[tuple] = []
 
-        if self.target_property_holding_new_property_name is not None:
-            target_property_holding_new_property_name = self.namespace[self.target_property_holding_new_property_name]
+        if self.target_property_holding_new_property is not None:
             query = self._query_template_use_case_b.format(
                 target_node_type=self.target_node_type,
-                target_property_holding_new_property_name=target_property_holding_new_property_name,
+                target_property_holding_new_property_name=self.target_property_holding_new_property,
                 target_property=self.target_property,
             )
         else:
@@ -116,15 +121,20 @@ class AttachPropertyFromTargetToSource(BaseTransformer):
             new_predicate_value,
             new_property_value,
         ) in graph.query(query):
-            if self.target_property_holding_new_property_name is not None:
+            if self.target_property_holding_new_property is not None:
                 # Ensure new predicate is URI compliant as we are creating a new predicate
                 new_predicate_value_string = sentence_or_string_to_camel(str(new_predicate_value))
                 predicate = as_neat_compliant_uri(self.namespace[new_predicate_value_string])
             else:
                 predicate = old_predicate
-
             # Create new connection from source node to value
-            graph.add((source_node, predicate, new_property_value))
+            graph.add(
+                (
+                    source_node,
+                    predicate,
+                    (self.namespace[new_property_value] if self.convert_literal_to_uri else new_property_value),
+                )
+            )
             # Remove old relationship between source node and destination node
             graph.remove((source_node, old_predicate, target_node))
 
@@ -158,7 +168,7 @@ class PruneDanglingNodes(BaseTransformer):
         node_prune_types: list of RDF types to prune from the Graph if they are stand-alone Nodes
     """
 
-    description: str = "Prunes the graph of specified rdf types that do not have connections to other nodes."
+    description: str = "Prunes nodes of specific rdf types that do not have any connection to them."
     _query_template = """
                     SELECT ?subject
                     WHERE {{
@@ -174,10 +184,74 @@ class PruneDanglingNodes(BaseTransformer):
         self.node_prune_types = node_prune_types
 
     def transform(self, graph: Graph) -> None:
-        for object_type in self.node_prune_types:
-            nodes_without_neighbours = list(graph.query(self._query_template.format(rdf_type=object_type)))
+        for type_ in self.node_prune_types:
+            for (subject,) in list(graph.query(self._query_template.format(rdf_type=type_))):  # type: ignore
+                graph.remove((subject, None, None))
+
+
+class PruneTypes(BaseTransformer):
+    """
+    Removes all the instances of specific type
+    """
+
+    description: str = "Prunes nodes of specific rdf types"
+    _query_template = """
+                        SELECT ?subject
+                        WHERE {{
+                            ?subject a <{rdf_type}> .
+                            }}
+                      """
+
+    def __init__(
+        self,
+        node_prune_types: list[URIRef],
+    ):
+        self.node_prune_types = node_prune_types
+
+    def transform(self, graph: Graph) -> None:
+        for type_ in self.node_prune_types:
+            for (subject,) in list(graph.query(self._query_template.format(rdf_type=type_))):  # type: ignore
+                graph.remove((subject, None, None))
 
-            for node in nodes_without_neighbours:
-                # Remove node and its property triples in the graph
-                if isinstance(node, ResultRow):
-                    graph.remove((node["subject"], None, None))
+
+class PruneDeadEndEdges(BaseTransformer):
+    """
+    Removes all the triples where object is a node that is not found in graph
+    """
+
+    description: str = "Prunes the graph of specified rdf types that do not have connections to other nodes."
+    _query_template = """
+                        SELECT ?subject ?predicate ?object
+                        WHERE {
+                            ?subject ?predicate ?object .
+                            FILTER (isIRI(?object) && ?predicate != rdf:type)
+                            FILTER NOT EXISTS {?object ?p ?o .}
+
+                            }
+
+                      """
+
+    def transform(self, graph: Graph) -> None:
+        for triple in graph.query(self._query_template):
+            graph.remove(cast(Triple, triple))
+
+
+class PruneInstancesOfUnknownType(BaseTransformer):
+    """
+    Removes all the triples where object is a node that is not found in graph
+    """
+
+    description: str = "Prunes the graph of specified rdf types that do not have connections to other nodes."
+    _query_template = """
+                    SELECT DISTINCT ?subject
+                    WHERE {
+                        ?subject ?p ?o .
+                        FILTER NOT EXISTS {?subject a ?object .}
+
+                        }
+
+                    """
+
+    def transform(self, graph: Graph) -> None:
+        for (subject,) in graph.query(self._query_template):  # type: ignore
+            graph.remove((subject, None, None))

{cognite_neat-0.101.0 → cognite_neat-0.102.0}/cognite/neat/_rules/exporters/_rules2excel.py

@@ -34,8 +34,6 @@ class ExcelExporter(BaseExporter[VerifiedRules, Workbook]):
     Args:
         styling: The styling to use for the Excel file. Defaults to "default". See below for details
             on the different styles.
-        output_role: The role to use for the exported spreadsheet. If provided, the rules will be converted to
-            this role formate before being written to excel. If not provided, the role from the rules will be used.
         new_model_id: The new model ID to use for the exported spreadsheet. This is only applicable if the input
             rules have 'is_reference' set. If provided, the model ID will be used to automatically create the
             new metadata sheet in the Excel file. The model id is expected to be a tuple of (prefix, title)
@@ -120,6 +118,10 @@ class ExcelExporter(BaseExporter[VerifiedRules, Workbook]):
             main_header = self._main_header_by_sheet_name[sheet_name]
             sheet.append([main_header] + [""] * (len(headers) - 1))
             sheet.merge_cells(start_row=1, start_column=1, end_row=1, end_column=len(headers))
+            if headers[0] == "Neat ID":
+                # Move the Neat ID to the end of the columns
+                headers = headers[1:] + ["Neat ID"]
+
             sheet.append(headers)
 
             fill_colors = itertools.cycle(["CADCFC", "FFFFFF"])
@@ -127,6 +129,9 @@ class ExcelExporter(BaseExporter[VerifiedRules, Workbook]):
             last_class: str | None = None
             item: dict[str, Any]
             for item in dumped_rules.get(sheet_name) or []:
+                if "Neat ID" in item:
+                    # Move the Neat ID to the end of the columns
+                    item["Neat ID"] = item.pop("Neat ID")
                 row = list(item.values())
                 class_ = row[0]
 

{cognite_neat-0.101.0 → cognite_neat-0.102.0}/cognite/neat/_rules/importers/_dms2rules.py

@@ -1,4 +1,4 @@
-from collections import Counter
+from collections import Counter, defaultdict
 from collections.abc import Collection, Iterable, Sequence
 from datetime import datetime, timezone
 from pathlib import Path
@@ -222,12 +222,18 @@ class DMSImporter(BaseImporter[DMSInputRules]):
         schema: DMSSchema,
         metadata: DMSInputMetadata | None = None,
     ) -> DMSInputRules:
+        enum_by_container_property = self._create_enum_collections(schema.containers.values())
+        enum_collection_by_container_property = {
+            key: enum_list[0].collection for key, enum_list in enum_by_container_property.items() if enum_list
+        }
+
         properties: list[DMSInputProperty] = []
         for view_id, view in schema.views.items():
             view_entity = ViewEntity.from_id(view_id)
-            class_entity = view_entity.as_class()
             for prop_id, prop in (view.properties or {}).items():
-                dms_property = self._create_dms_property(prop_id, prop, view_entity, class_entity)
+                dms_property = self._create_dms_property(
+                    prop_id, prop, view_entity, enum_collection_by_container_property
+                )
                 if dms_property is not None:
                     properties.append(dms_property)
 
@@ -237,8 +243,6 @@ class DMSImporter(BaseImporter[DMSInputRules]):
 
         metadata = metadata or DMSInputMetadata.from_data_model(data_model)
 
-        enum = self._create_enum_collections(schema.containers.values())
-
         return DMSInputRules(
             metadata=metadata,
             properties=properties,
@@ -248,7 +252,7 @@ class DMSImporter(BaseImporter[DMSInputRules]):
                 for view_id, view in schema.views.items()
             ],
             nodes=[DMSInputNode.from_node_type(node_type) for node_type in schema.node_types.values()],
-            enum=enum,
+            enum=[enum for enum_list in enum_by_container_property.values() for enum in enum_list] or None,
         )
 
     @classmethod
@@ -267,7 +271,11 @@ class DMSImporter(BaseImporter[DMSInputRules]):
         )
 
     def _create_dms_property(
-        self, prop_id: str, prop: ViewPropertyApply, view_entity: ViewEntity, class_entity: ClassEntity
+        self,
+        prop_id: str,
+        prop: ViewPropertyApply,
+        view_entity: ViewEntity,
+        enum_collection_by_container_property: dict[tuple[dm.ContainerId, str], str],
     ) -> DMSInputProperty | None:
         if isinstance(prop, dm.MappedPropertyApply) and prop.container not in self._all_containers_by_id:
             self.issue_list.append(
@@ -300,7 +308,7 @@ class DMSImporter(BaseImporter[DMSInputRules]):
             )
             return None
 
-        value_type = self._get_value_type(prop, view_entity, prop_id)
+        value_type = self._get_value_type(prop, view_entity, prop_id, enum_collection_by_container_property)
         if value_type is None:
             return None
 
@@ -347,7 +355,11 @@ class DMSImporter(BaseImporter[DMSInputRules]):
             return None
 
     def _get_value_type(
-        self, prop: ViewPropertyApply, view_entity: ViewEntity, prop_id
+        self,
+        prop: ViewPropertyApply,
+        view_entity: ViewEntity,
+        prop_id: str,
+        enum_collection_by_container_property: dict[tuple[dm.ContainerId, str], str],
     ) -> DataType | ViewEntity | DMSUnknownEntity | None:
         if isinstance(
             prop,
@@ -367,7 +379,16 @@ class DMSImporter(BaseImporter[DMSInputRules]):
             elif isinstance(container_prop.type, PropertyTypeWithUnit) and container_prop.type.unit:
                 return DataType.load(f"{container_prop.type._type}(unit={container_prop.type.unit.external_id})")
             elif isinstance(container_prop.type, DMSEnum):
-                return Enum(collection=ClassEntity(suffix=prop_id), unknownValue=container_prop.type.unknown_value)
+                collection = enum_collection_by_container_property.get(
+                    (prop.container, prop.container_property_identifier)
+                )
+                if collection is None:
+                    # This should never happen
+                    raise ValueError(
+                        f"BUG in Neat: Enum for {prop.container}.{prop.container_property_identifier} not found."
+                    )
+
+                return Enum(collection=ClassEntity(suffix=collection), unknownValue=container_prop.type.unknown_value)
             else:
                 return DataType.load(container_prop.type._type)
         else:
@@ -477,15 +498,26 @@ class DMSImporter(BaseImporter[DMSInputRules]):
         return candidates[0]
 
     @staticmethod
-    def _create_enum_collections(containers: Collection[dm.ContainerApply]) -> list[DMSInputEnum] | None:
-        enum_collections: list[DMSInputEnum] = []
+    def _create_enum_collections(
+        containers: Collection[dm.ContainerApply],
+    ) -> dict[tuple[dm.ContainerId, str], list[DMSInputEnum]]:
+        enum_by_container_property: dict[tuple[dm.ContainerId, str], list[DMSInputEnum]] = defaultdict(list)
+
+        is_external_id_unique = len({container.external_id for container in containers}) == len(containers)
+
         for container in containers:
+            container_id = container.as_id()
             for prop_id, prop in container.properties.items():
-                if isinstance(prop.type, DMSEnum):
-                    for identifier, value in prop.type.values.items():
-                        enum_collections.append(
-                            DMSInputEnum(
-                                collection=prop_id, value=identifier, name=value.name, description=value.description
-                            )
+                if not isinstance(prop.type, DMSEnum):
+                    continue
+                if is_external_id_unique:
+                    collection = f"{container.external_id}.{prop_id}"
+                else:
+                    collection = f"{container.space}:{container.external_id}.{prop_id}"
+                for identifier, value in prop.type.values.items():
+                    enum_by_container_property[(container_id, prop_id)].append(
+                        DMSInputEnum(
+                            collection=collection, value=identifier, name=value.name, description=value.description
                         )
-        return enum_collections
+                    )
+        return enum_by_container_property

{cognite_neat-0.101.0 → cognite_neat-0.102.0}/cognite/neat/_rules/importers/_rdf/_base.py

@@ -4,7 +4,7 @@ from pathlib import Path
 from cognite.client import data_modeling as dm
 from rdflib import Graph, Namespace, URIRef
 
-from cognite.neat._constants import get_default_prefixes
+from cognite.neat._constants import get_default_prefixes_and_namespaces
 from cognite.neat._issues import IssueList
 from cognite.neat._issues.errors import FileReadError
 from cognite.neat._issues.errors._general import NeatValueError
@@ -97,7 +97,7 @@ class BaseRDFImporter(BaseImporter[InformationInputRules]):
             issue_list.append(FileReadError(filepath, str(e)))
 
         # bind key namespaces
-        for prefix, namespace in get_default_prefixes().items():
+        for prefix, namespace in get_default_prefixes_and_namespaces().items():
             graph.bind(prefix, namespace)
 
         return cls(

{cognite_neat-0.101.0 → cognite_neat-0.102.0}/cognite/neat/_rules/models/information/_rules.py

@@ -7,7 +7,7 @@ from pydantic import Field, field_serializer, field_validator, model_validator
 from pydantic_core.core_schema import SerializationInfo
 from rdflib import Namespace, URIRef
 
-from cognite.neat._constants import get_default_prefixes
+from cognite.neat._constants import get_default_prefixes_and_namespaces
 from cognite.neat._issues.errors import NeatValueError, PropertyDefinitionError
 from cognite.neat._rules._constants import EntityTypes
 from cognite.neat._rules.models._base_rules import (
@@ -255,7 +255,7 @@ class InformationRules(BaseRules):
     classes: SheetList[InformationClass] = Field(alias="Classes", description="List of classes")
     prefixes: dict[str, Namespace] = Field(
         alias="Prefixes",
-        default_factory=get_default_prefixes,
+        default_factory=get_default_prefixes_and_namespaces,
         description="the definition of the prefixes that are used in the semantic data model",
     )
 
@@ -264,7 +264,7 @@ class InformationRules(BaseRules):
         if isinstance(values, dict):
             return {key: Namespace(value) if isinstance(value, str) else value for key, value in values.items()}
         elif values is None:
-            values = get_default_prefixes()
+            values = get_default_prefixes_and_namespaces()
         return values
 
     def as_dms_rules(self) -> "DMSRules":

{cognite_neat-0.101.0 → cognite_neat-0.102.0}/cognite/neat/_session/_prepare.py

@@ -7,8 +7,18 @@ from cognite.client.data_classes.data_modeling import DataModelIdentifier
 from rdflib import URIRef
 
 from cognite.neat._client import NeatClient
-from cognite.neat._constants import DEFAULT_NAMESPACE
-from cognite.neat._graph.transformers import RelationshipAsEdgeTransformer
+from cognite.neat._constants import (
+    DEFAULT_NAMESPACE,
+    get_default_prefixes_and_namespaces,
+)
+from cognite.neat._graph.transformers import (
+    AttachPropertyFromTargetToSource,
+    PruneDeadEndEdges,
+    PruneInstancesOfUnknownType,
+    PruneTypes,
+    RelationshipAsEdgeTransformer,
+    Transformers,
+)
 from cognite.neat._graph.transformers._rdfpath import MakeConnectionOnExactMatch
 from cognite.neat._rules._shared import InputRules, ReadRules
 from cognite.neat._rules.importers import DMSImporter
@@ -50,6 +60,79 @@ class InstancePrepareAPI:
         self._state = state
         self._verbose = verbose
 
+    def dexpi(self) -> None:
+        """Prepares extracted DEXPI graph for further usage in CDF
+
+        This method bundles several graph transformers which:
+        - attach values of generic attributes to nodes
+        - create associations between nodes
+        - remove unused generic attributes
+        - remove associations between nodes that do not exist in the extracted graph
+        - remove edges to nodes that do not exist in the extracted graph
+
+        and therefore safeguard CDF from a bad graph
+        """
+
+        DEXPI = get_default_prefixes_and_namespaces()["dexpi"]
+
+        transformers = [
+            # Remove any instance which type is unknown
+            PruneInstancesOfUnknownType(),
+            # Directly connect generic attributes
+            AttachPropertyFromTargetToSource(
+                target_property=DEXPI.Value,
+                target_property_holding_new_property=DEXPI.Name,
+                target_node_type=DEXPI.GenericAttribute,
+                delete_target_node=True,
+            ),
+            # Directly connect associations
+            AttachPropertyFromTargetToSource(
+                target_property=DEXPI.ItemID,
+                target_property_holding_new_property=DEXPI.Type,
+                target_node_type=DEXPI.Association,
+                delete_target_node=True,
+            ),
+            # Remove unused generic attributes and associations
+            PruneTypes([DEXPI.GenericAttribute, DEXPI.Association]),
+            # Remove edges to nodes that do not exist in the extracted graph
+            PruneDeadEndEdges(),
+        ]
+
+        for transformer in transformers:
+            self._state.instances.store.transform(cast(Transformers, transformer))
+
+    def aml(self) -> None:
+        """Prepares extracted AutomationML graph for further usage in CDF
+
+        This method bundles several graph transformers which:
+        - attach values of attributes to nodes
+        - remove unused attributes
+        - remove edges to nodes that do not exist in the extracted graph
+
+        and therefore safeguard CDF from a bad graph
+        """
+
+        AML = get_default_prefixes_and_namespaces()["aml"]
+
+        transformers = [
+            # Remove any instance which type is unknown
+            PruneInstancesOfUnknownType(),
+            # Directly connect generic attributes
+            AttachPropertyFromTargetToSource(
+                target_property=AML.Value,
+                target_property_holding_new_property=AML.Name,
+                target_node_type=AML.Attribute,
+                delete_target_node=True,
+            ),
+            # Prune unused attributes
+            PruneTypes([AML.Attribute]),
+            # # Remove edges to nodes that do not exist in the extracted graph
+            PruneDeadEndEdges(),
+        ]
+
+        for transformer in transformers:
+            self._state.instances.store.transform(cast(Transformers, transformer))
+
     def make_connection_on_exact_match(
         self,
         source: tuple[str, str],