h5rdmtoolbox 2.7.2__tar.gz → 2.7.4__tar.gz

{h5rdmtoolbox-2.7.2 → h5rdmtoolbox-2.7.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: h5rdmtoolbox
-Version: 2.7.2
+Version: 2.7.4
 Summary: Supporting a FAIR Research Data lifecycle using Python and HDF5.
 Author-email: Matthias Probst <matth.probst@gmail.com>
 License-Expression: MIT
@@ -61,7 +61,7 @@ Requires-Dist: pytest>=8.3.3; extra == "test-core"
 Requires-Dist: pytest-cov>=5.0.0; extra == "test-core"
 Requires-Dist: pylint; extra == "test-core"
 Requires-Dist: ssnolib<3.0.0,>=2.2.0.2; extra == "test-core"
-Requires-Dist: mongomock==4.1.2; extra == "test-core"
+Requires-Dist: mongomock==4.3.0; extra == "test-core"
 Requires-Dist: scipy>=1.10.1; extra == "test-core"
 Requires-Dist: scikit-image>=0.21.0; extra == "test-core"
 Requires-Dist: scikit-learn; extra == "test-core"
@@ -75,7 +75,7 @@ Requires-Dist: sphinx_design==0.6.1; extra == "docs"
 Requires-Dist: myst_nb==1.2.0; extra == "docs"
 Requires-Dist: sphinxcontrib_bibtex==2.6.3; extra == "docs"
 Provides-Extra: complete
-Requires-Dist: h5rdmtoolbox[catalog,csv,database,gui,layout_validation,snt,test]; extra == "complete"
+Requires-Dist: h5rdmtoolbox[gui,test]; extra == "complete"
 Provides-Extra: complete-with-docs
 Requires-Dist: h5rdmtoolbox[complete,docs]; extra == "complete-with-docs"
 Dynamic: license-file
@@ -120,46 +120,117 @@ M4I = rdflib.Namespace("http://w3id.org/nfdi4ing/metadata4ing#")
 
 # Create a new HDF5 file with FAIR metadata
 with h5tbx.File("example.h5", "w") as h5:
-    h5.create_dataset("temperature", data=np.array([20, 21, 19, 22]))
-    h5.attrs["units", M4I.hasUnit] = "degree_Celsius"
-    h5.rdf["units"].object = "http://qudt.org/vocab/unit/DEG_C"
-    h5.attrs["description", "https://schema.org/description"] = "Room temperature measurements"
+    ds = h5.create_dataset("temperature", data=np.array([20, 21, 19, 22]))
+    ds.attrs["units"] = h5tbx.Attribute(
+        value="degree_Celsius",
+        rdf_predicate=M4I.hasUnit,
+        rdf_object="http://qudt.org/vocab/unit/DEG_C",
+    )
+    ds.attrs["description", "https://schema.org/description"] = "Room temperature measurements"
+
+    ds_mean = h5.create_dataset("mean_temperature", data=np.mean(h5["temperature"][()]))
+    ds_mean.attrs["units", M4I.hasUnit] = "degree_Celsius"
+    ds_mean.rdf["units"].object = "http://qudt.org/vocab/unit/DEG_C"
+    ds_mean.attrs["description", "https://schema.org/description"] = "Mean room temperature measurements"
+
+    ds_mean.rdf.type = M4I.NumericalVariable
+    ds_mean.rdf.data_predicate = M4I.hasNumericalValue
+
+    ttl_ctx = h5.serialize("ttl", structural=False, contextual=True, file_uri="https://example.org#example.h5/")
+    ttl_struc = h5.serialize("ttl", structural=True, contextual=False, file_uri="https://example.org#example.h5/")
+    ttl_full = h5.serialize("ttl", file_uri="https://example.org#example.h5/")
+```
 
-    ttl = h5.serialize("ttl")
+The above saves three different serializations of the HDF5 content as RDF in Turtle (ttl) format.
+The first one (`ttl_ctx`) is the **contextual** RDF serialization, which only includes the RDF triples that the user
+has enriched the HDF5 file with. The second one (`ttl_struc`) is the **structural** RDF serialization, which includes 
+all RDF triples that can be derived from the HDF5 file content. the third one (`ttl_full`) is the combination of the 
+first two, which includes both the user enriched RDF triples and the RDF triples that can be derived from the HDF5 file 
+content.
 
-```
-The serialization in Turtle (ttl) is teh RDF serialization of the HDF5 data (without arrays):
+Below we show the first two serializations.
+
+`ttl_ctx`:
 ```ttl
-@prefix hdf: <http://purl.allotrope.org/ontologies/hdf5/1.8#> .
 @prefix m4i: <http://w3id.org/nfdi4ing/metadata4ing#> .
 @prefix schema: <https://schema.org/> .
 @prefix xsd: <http://www.w3.org/2001/XMLSchema#> .
 
+<https://example.org#example.h5/example.h5/mean_temperature> a m4i:NumericalVariable ;
+    m4i:hasNumericalValue "20.5"^^xsd:float ;
+    m4i:hasUnit <http://qudt.org/vocab/unit/DEG_C> ;
+    schema:description "Mean room temperature measurements" .
+
+<https://example.org#example.h5/example.h5/temperature> m4i:hasUnit <http://qudt.org/vocab/unit/DEG_C> ;
+    schema:description "Room temperature measurements" .
+```
+
+`ttl_ctx`:
+```ttl
+@prefix hdf: <http://purl.allotrope.org/ontologies/hdf5/1.8#> .
+@prefix xsd: <http://www.w3.org/2001/XMLSchema#> .
+
+<https://example.org#example.h5/example.h5> a hdf:File ;
+    hdf:rootGroup <https://example.org#example.h5/example.h5/> .
+
+hdf:H5T_IEEE_F64LE a hdf:Datatype .
+
 hdf:H5T_INTEL_I64 a hdf:Datatype .
 
-[] a hdf:File ;
-    hdf:rootGroup [ a hdf:Group ;
-            hdf:attribute [ a hdf:StringAttribute ;
-                    hdf:data "Room temperature measurements" ;
-                    hdf:name "description" ],
-                [ a hdf:StringAttribute ;
-                    hdf:data "degree_Celsius" ;
-                    hdf:name "units" ] ;
-            hdf:member [ a hdf:Dataset ;
-                    hdf:dataspace [ a hdf:SimpleDataspace ;
-                            hdf:dimension [ a hdf:DataspaceDimension ;
-                                    hdf:dimensionIndex 0 ;
-                                    hdf:size 4 ] ] ;
-                    hdf:datatype hdf:H5T_INTEGER,
-                        hdf:H5T_INTEL_I64 ;
-                    hdf:layout hdf:H5D_CONTIGUOUS ;
-                    hdf:maximumSize 4 ;
-                    hdf:name "/temperature" ;
-                    hdf:rank 1 ;
-                    hdf:size 4 ] ;
-            hdf:name "/" ;
-            m4i:hasUnit <http://qudt.org/vocab/unit/DEG_C> ;
-            schema:description "Room temperature measurements" ] .
+<https://example.org#example.h5/example.h5/> a hdf:Group ;
+    hdf:member <https://example.org#example.h5/example.h5/mean_temperature>,
+        <https://example.org#example.h5/example.h5/temperature> ;
+    hdf:name "/" .
+
+<https://example.org#example.h5/example.h5/mean_temperature> a hdf:Dataset ;
+    hdf:attribute <https://example.org#example.h5/example.h5/mean_temperature@description>,
+        <https://example.org#example.h5/example.h5/mean_temperature@units> ;
+    hdf:dataspace <https://example.org#example.h5/example.h5/mean_temperature__dataspace> ;
+    hdf:datatype hdf:H5T_FLOAT,
+        hdf:H5T_IEEE_F64LE ;
+    hdf:layout hdf:H5D_CONTIGUOUS ;
+    hdf:maximumSize -1 ;
+    hdf:name "/mean_temperature" ;
+    hdf:rank 0 ;
+    hdf:size 1 ;
+    hdf:value 2.05e+01 .
+
+<https://example.org#example.h5/example.h5/mean_temperature@description> a hdf:StringAttribute ;
+    hdf:data "Mean room temperature measurements" ;
+    hdf:name "description" .
+
+<https://example.org#example.h5/example.h5/mean_temperature@units> a hdf:StringAttribute ;
+    hdf:data "degree_Celsius" ;
+    hdf:name "units" .
+
+<https://example.org#example.h5/example.h5/mean_temperature__dataspace> a hdf:ScalarDataspace .
+
+<https://example.org#example.h5/example.h5/temperature> a hdf:Dataset ;
+    hdf:attribute <https://example.org#example.h5/example.h5/temperature@description>,
+        <https://example.org#example.h5/example.h5/temperature@units> ;
+    hdf:dataspace <https://example.org#example.h5/example.h5/temperature__dataspace> ;
+    hdf:datatype hdf:H5T_INTEGER,
+        hdf:H5T_INTEL_I64 ;
+    hdf:layout hdf:H5D_CONTIGUOUS ;
+    hdf:maximumSize 4 ;
+    hdf:name "/temperature" ;
+    hdf:rank 1 ;
+    hdf:size 4 .
+
+<https://example.org#example.h5/example.h5/temperature@description> a hdf:StringAttribute ;
+    hdf:data "Room temperature measurements" ;
+    hdf:name "description" .
+
+<https://example.org#example.h5/example.h5/temperature@units> a hdf:StringAttribute ;
+    hdf:data "degree_Celsius" ;
+    hdf:name "units" .
+
+<https://example.org#example.h5/example.h5/temperature__dataspace> a hdf:SimpleDataspace ;
+    hdf:dimension <https://example.org#example.h5/example.h5/temperature__dataspace_dimension_0> .
+
+<https://example.org#example.h5/example.h5/temperature__dataspace_dimension_0> a hdf:DataspaceDimension ;
+    hdf:dimensionIndex 0 ;
+    hdf:size 4 .
 ```
 
 [//]: # (The "HDF5 Research Data Management Toolbox" &#40;h5RDMtoolbox&#41; is a Python package supporting everybody who is working with)

{h5rdmtoolbox-2.7.2 → h5rdmtoolbox-2.7.4}/README.md

@@ -38,46 +38,117 @@ M4I = rdflib.Namespace("http://w3id.org/nfdi4ing/metadata4ing#")
 
 # Create a new HDF5 file with FAIR metadata
 with h5tbx.File("example.h5", "w") as h5:
-    h5.create_dataset("temperature", data=np.array([20, 21, 19, 22]))
-    h5.attrs["units", M4I.hasUnit] = "degree_Celsius"
-    h5.rdf["units"].object = "http://qudt.org/vocab/unit/DEG_C"
-    h5.attrs["description", "https://schema.org/description"] = "Room temperature measurements"
+    ds = h5.create_dataset("temperature", data=np.array([20, 21, 19, 22]))
+    ds.attrs["units"] = h5tbx.Attribute(
+        value="degree_Celsius",
+        rdf_predicate=M4I.hasUnit,
+        rdf_object="http://qudt.org/vocab/unit/DEG_C",
+    )
+    ds.attrs["description", "https://schema.org/description"] = "Room temperature measurements"
+
+    ds_mean = h5.create_dataset("mean_temperature", data=np.mean(h5["temperature"][()]))
+    ds_mean.attrs["units", M4I.hasUnit] = "degree_Celsius"
+    ds_mean.rdf["units"].object = "http://qudt.org/vocab/unit/DEG_C"
+    ds_mean.attrs["description", "https://schema.org/description"] = "Mean room temperature measurements"
+
+    ds_mean.rdf.type = M4I.NumericalVariable
+    ds_mean.rdf.data_predicate = M4I.hasNumericalValue
+
+    ttl_ctx = h5.serialize("ttl", structural=False, contextual=True, file_uri="https://example.org#example.h5/")
+    ttl_struc = h5.serialize("ttl", structural=True, contextual=False, file_uri="https://example.org#example.h5/")
+    ttl_full = h5.serialize("ttl", file_uri="https://example.org#example.h5/")
+```
 
-    ttl = h5.serialize("ttl")
+The above saves three different serializations of the HDF5 content as RDF in Turtle (ttl) format.
+The first one (`ttl_ctx`) is the **contextual** RDF serialization, which only includes the RDF triples that the user
+has enriched the HDF5 file with. The second one (`ttl_struc`) is the **structural** RDF serialization, which includes 
+all RDF triples that can be derived from the HDF5 file content. the third one (`ttl_full`) is the combination of the 
+first two, which includes both the user enriched RDF triples and the RDF triples that can be derived from the HDF5 file 
+content.
 
-```
-The serialization in Turtle (ttl) is teh RDF serialization of the HDF5 data (without arrays):
+Below we show the first two serializations.
+
+`ttl_ctx`:
 ```ttl
-@prefix hdf: <http://purl.allotrope.org/ontologies/hdf5/1.8#> .
 @prefix m4i: <http://w3id.org/nfdi4ing/metadata4ing#> .
 @prefix schema: <https://schema.org/> .
 @prefix xsd: <http://www.w3.org/2001/XMLSchema#> .
 
+<https://example.org#example.h5/example.h5/mean_temperature> a m4i:NumericalVariable ;
+    m4i:hasNumericalValue "20.5"^^xsd:float ;
+    m4i:hasUnit <http://qudt.org/vocab/unit/DEG_C> ;
+    schema:description "Mean room temperature measurements" .
+
+<https://example.org#example.h5/example.h5/temperature> m4i:hasUnit <http://qudt.org/vocab/unit/DEG_C> ;
+    schema:description "Room temperature measurements" .
+```
+
+`ttl_ctx`:
+```ttl
+@prefix hdf: <http://purl.allotrope.org/ontologies/hdf5/1.8#> .
+@prefix xsd: <http://www.w3.org/2001/XMLSchema#> .
+
+<https://example.org#example.h5/example.h5> a hdf:File ;
+    hdf:rootGroup <https://example.org#example.h5/example.h5/> .
+
+hdf:H5T_IEEE_F64LE a hdf:Datatype .
+
 hdf:H5T_INTEL_I64 a hdf:Datatype .
 
-[] a hdf:File ;
-    hdf:rootGroup [ a hdf:Group ;
-            hdf:attribute [ a hdf:StringAttribute ;
-                    hdf:data "Room temperature measurements" ;
-                    hdf:name "description" ],
-                [ a hdf:StringAttribute ;
-                    hdf:data "degree_Celsius" ;
-                    hdf:name "units" ] ;
-            hdf:member [ a hdf:Dataset ;
-                    hdf:dataspace [ a hdf:SimpleDataspace ;
-                            hdf:dimension [ a hdf:DataspaceDimension ;
-                                    hdf:dimensionIndex 0 ;
-                                    hdf:size 4 ] ] ;
-                    hdf:datatype hdf:H5T_INTEGER,
-                        hdf:H5T_INTEL_I64 ;
-                    hdf:layout hdf:H5D_CONTIGUOUS ;
-                    hdf:maximumSize 4 ;
-                    hdf:name "/temperature" ;
-                    hdf:rank 1 ;
-                    hdf:size 4 ] ;
-            hdf:name "/" ;
-            m4i:hasUnit <http://qudt.org/vocab/unit/DEG_C> ;
-            schema:description "Room temperature measurements" ] .
+<https://example.org#example.h5/example.h5/> a hdf:Group ;
+    hdf:member <https://example.org#example.h5/example.h5/mean_temperature>,
+        <https://example.org#example.h5/example.h5/temperature> ;
+    hdf:name "/" .
+
+<https://example.org#example.h5/example.h5/mean_temperature> a hdf:Dataset ;
+    hdf:attribute <https://example.org#example.h5/example.h5/mean_temperature@description>,
+        <https://example.org#example.h5/example.h5/mean_temperature@units> ;
+    hdf:dataspace <https://example.org#example.h5/example.h5/mean_temperature__dataspace> ;
+    hdf:datatype hdf:H5T_FLOAT,
+        hdf:H5T_IEEE_F64LE ;
+    hdf:layout hdf:H5D_CONTIGUOUS ;
+    hdf:maximumSize -1 ;
+    hdf:name "/mean_temperature" ;
+    hdf:rank 0 ;
+    hdf:size 1 ;
+    hdf:value 2.05e+01 .
+
+<https://example.org#example.h5/example.h5/mean_temperature@description> a hdf:StringAttribute ;
+    hdf:data "Mean room temperature measurements" ;
+    hdf:name "description" .
+
+<https://example.org#example.h5/example.h5/mean_temperature@units> a hdf:StringAttribute ;
+    hdf:data "degree_Celsius" ;
+    hdf:name "units" .
+
+<https://example.org#example.h5/example.h5/mean_temperature__dataspace> a hdf:ScalarDataspace .
+
+<https://example.org#example.h5/example.h5/temperature> a hdf:Dataset ;
+    hdf:attribute <https://example.org#example.h5/example.h5/temperature@description>,
+        <https://example.org#example.h5/example.h5/temperature@units> ;
+    hdf:dataspace <https://example.org#example.h5/example.h5/temperature__dataspace> ;
+    hdf:datatype hdf:H5T_INTEGER,
+        hdf:H5T_INTEL_I64 ;
+    hdf:layout hdf:H5D_CONTIGUOUS ;
+    hdf:maximumSize 4 ;
+    hdf:name "/temperature" ;
+    hdf:rank 1 ;
+    hdf:size 4 .
+
+<https://example.org#example.h5/example.h5/temperature@description> a hdf:StringAttribute ;
+    hdf:data "Room temperature measurements" ;
+    hdf:name "description" .
+
+<https://example.org#example.h5/example.h5/temperature@units> a hdf:StringAttribute ;
+    hdf:data "degree_Celsius" ;
+    hdf:name "units" .
+
+<https://example.org#example.h5/example.h5/temperature__dataspace> a hdf:SimpleDataspace ;
+    hdf:dimension <https://example.org#example.h5/example.h5/temperature__dataspace_dimension_0> .
+
+<https://example.org#example.h5/example.h5/temperature__dataspace_dimension_0> a hdf:DataspaceDimension ;
+    hdf:dimensionIndex 0 ;
+    hdf:size 4 .
 ```
 
 [//]: # (The "HDF5 Research Data Management Toolbox" &#40;h5RDMtoolbox&#41; is a Python package supporting everybody who is working with)

{h5rdmtoolbox-2.7.2 → h5rdmtoolbox-2.7.4}/h5rdmtoolbox/__init__.py

@@ -2,7 +2,6 @@
 
 import logging
 import pathlib
-import warnings
 from logging.handlers import RotatingFileHandler
 from typing import Optional, Dict
 
@@ -136,13 +135,24 @@ def get_ld(
         context: Optional[Dict] = None
 ) -> rdflib.Graph:
     """Return the HDF file content as a rdflib.Graph object."""
-    from h5rdmtoolbox.ld import get_ld
-    return get_ld(hdf_filename,
-                  structural=structural,
-                  contextual=contextual,
-                  skipND=skipND,
-                  file_uri=file_uri,
-                  context=context)
+    from . import ld
+    return ld.get_ld(
+        hdf_filename,
+        structural=structural,
+        contextual=contextual,
+        skipND=skipND,
+        file_uri=file_uri,
+        context=context,
+    )
+
+
+def _optimize_ld_context(graph: rdflib.Graph, context: Optional[Dict]) -> Dict:
+    from .ld import optimize_context
+    return optimize_context(graph, context or {})
+
+
+def _resolve_serialize_format(fmt: str, kwargs: Dict) -> str:
+    return kwargs.pop("format", fmt)
 
 
 def dump_jsonld(
@@ -155,19 +165,16 @@ def dump_jsonld(
         file_uri: Optional[str] = None
 ):
     """Return the file content as a JSON-LD string."""
-    from .ld import optimize_context
-    context = context or {}
     graph = get_ld(hdf_filename,
                    structural=structural,
                    contextual=contextual,
                    file_uri=file_uri,
                    skipND=skipND)
-    context = optimize_context(graph, context)
     return graph.serialize(
         format="json-ld",
         indent=indent,
         auto_compact=True,
-        context=context
+        context=_optimize_ld_context(graph, context)
     )
 
 
@@ -282,11 +289,11 @@ def serialize(hdf_filename,
               skipND: int = 1,
               structural: bool = True,
               contextual: bool = True,
-              file_uri: Optional[str] = None,
+              file_uri: Optional[Union[str, Dict[str, str]]] = None,
               rdf_mappings: Dict[str, RDFMappingEntry] = None,
               **kwargs):
     """Alternative to json-ld but allows multiple serialization options"""
-    fmt = kwargs.pop("format", fmt)
+    fmt = _resolve_serialize_format(fmt, kwargs)
     with File(hdf_filename) as h5:
         return h5.serialize(fmt=fmt,
                             skipND=skipND,
@@ -296,6 +303,32 @@ def serialize(hdf_filename,
                             rdf_mappings=rdf_mappings)
 
 
+def sparql(
+        hdf_filename: Union[str, pathlib.Path],
+        query: str,
+        structural: bool = True,
+        contextual: bool = True,
+        skipND: int = 1,
+        file_uri: Optional[Union[str, Dict[str, str]]] = None,
+        rdf_mappings: Dict[str, RDFMappingEntry] = None,
+        as_dataframe: bool = False,
+        **kwargs
+) -> rdflib.query.Result:
+    """Run a SPARQL query on the HDF5 file content. Returns a rdflib.query.Result object."""
+    from .ld import sparql
+    return sparql(
+        source=hdf_filename,
+        query=query,
+        structural=structural,
+        contextual=contextual,
+        skipND=skipND,
+        file_uri=file_uri,
+        rdf_mappings=rdf_mappings,
+        as_dataframe=as_dataframe,
+        **kwargs
+    )
+
+
 def build_pyvis_graph(hdf_filename, output_filename="kg-graph.html", notebook=False,
                       structural: bool = True,
                       contextual: bool = True,