bioregistry 0.13.8__py3-none-any.whl → 0.13.10__py3-none-any.whl

bioregistry/__init__.py

@@ -127,7 +127,7 @@ from .resolve_identifier import (
     standardize_identifier,
 )
 from .resource_manager import Manager, manager
-from .schema.struct import (
+from .schema import (
     Author,
     Collection,
     Context,

bioregistry/analysis/paper_ranking.py

@@ -400,7 +400,7 @@ def predict_and_save(
     :param path: Path to save the predictions.
     """
     x_meta = pd.DataFrame()
-    x_transformed = vectorizer.transform(df["title"] + " " + df["abstract"])
+    x_transformed = vectorizer.transform(_concat(df))
     for name, clf in classifiers:
         x_meta[name] = _predict(clf, x_transformed)
 
@@ -524,7 +524,7 @@ def train(
     df = pd.concat(curated_dfs)[["pubmed", "title", "abstract", "relevant"]]
 
     df["abstract"] = df["abstract"].fillna("")
-    df["title_abstract"] = df["title"] + " " + df["abstract"]
+    df["title_abstract"] = _concat(df)
     df = df[df.title_abstract.notna()]
     df = df.drop_duplicates()
     _echo_stats(df, "combine curated publications")
@@ -582,5 +582,9 @@ def train(
     return TrainingResult(curated_pubmed_ids, vectorizer, classifiers, meta_clf)
 
 
+def _concat(df: pd.DataFrame) -> pd.Series[str]:
+    return cast("pd.Series[str]", df["title"]) + " " + cast("pd.Series[str]", df["abstract"])
+
+
 if __name__ == "__main__":
     main()

bioregistry/app/api.py

@@ -19,8 +19,7 @@ from ..export.rdf_export import (
     resource_to_rdf_str,
 )
 from ..resource_manager import Manager
-from ..schema import Attributable, sanitize_mapping
-from ..schema.struct import Collection, Context, Registry, Resource
+from ..schema import Attributable, Collection, Context, Registry, Resource, sanitize_mapping
 from ..schema_utils import (
     read_collections_contributions,
     read_prefix_contacts,

bioregistry/app/ui.py

@@ -38,9 +38,8 @@ from ..export.rdf_export import (
     metaresource_to_rdf_str,
     resource_to_rdf_str,
 )
-from ..schema import Context
-from ..schema.constants import SCHEMA_TERMS
-from ..schema.struct import (
+from ..schema import (
+    Context,
     Registry,
     RegistryGovernance,
     RegistryQualities,
@@ -49,6 +48,7 @@ from ..schema.struct import (
     get_json_schema,
     schema_status_map,
 )
+from ..schema.constants import SCHEMA_TERMS
 from ..schema_utils import (
     read_collections_contributions,
     read_context_contributions,

bioregistry/bibliometrics.py

@@ -8,7 +8,7 @@ from collections.abc import Iterable
 from typing import TYPE_CHECKING
 
 from .resource_manager import manager
-from .schema.struct import Publication, deduplicate_publications
+from .schema import Publication, deduplicate_publications
 
 if TYPE_CHECKING:
     import pandas

bioregistry/cli.py

@@ -8,7 +8,7 @@ from .app.cli import web
 from .compare import compare
 from .export.cli import export
 from .lint import lint
-from .schema.struct import generate_schema
+from .schema import generate_schema
 from .utils import get_hexdigests, secho
 from .validate.cli import validate
 from .version import VERSION

bioregistry/curation/add_cessda.py

@@ -13,7 +13,7 @@ from tabulate import tabulate
 from tqdm import tqdm
 
 import bioregistry
-from bioregistry.schema.struct import Author, Organization
+from bioregistry.schema import Author, Organization
 
 BASE = "https://vocabularies.cessda.eu"
 MODULE = pystow.module("cessda")

bioregistry/curation/add_provider_status_curations.py

@@ -8,7 +8,7 @@ import pandas as pd
 from tqdm import tqdm
 
 from bioregistry import manager
-from bioregistry.schema.struct import StatusCheck
+from bioregistry.schema import StatusCheck
 
 URL = "https://docs.google.com/spreadsheets/d/e/2PACX-1vSC8RAMlNGauLHJb1RGwFuvC2LBJBjeeICRtq596npE6G4ZjZwX8W_Fz031hAfqsbu6f9Ruxl2PTsFx/pub?gid=1207894592&single=true&output=tsv"
 

bioregistry/curation/add_sweet.py

@@ -0,0 +1,146 @@
+"""Add SWEET ontologies."""
+
+from typing import cast
+
+import click
+import pystow
+
+import bioregistry
+
+MODULE = pystow.module("bioregistry", "sweet")
+
+ALL_PREFIXES_URL = "https://github.com/ESIPFed/sweet/raw/refs/heads/master/sweetPrefixes.ttl"
+
+MANUAL = {
+    "sosto": "Acute",
+    "sostri": "Catastrophic",
+    "sostsp": "Big",
+    "sorel": "hasPhenomena",
+    "sorelch": "atomicMass",
+    "sorelh": "hasAttribute",
+    "soreaer": "AbyssopelagicZone",
+    "sorelcl": "hasAverageAnnualPrecipitation",
+    "sorelm": "averageOver",
+    "sorelph": "colderThan",
+    "sorelsc": "causedBy",
+    "sorelt": "dayOfYear",
+    "sorelsp": "adjacentTo",
+    "sorepsd": "Counterclockwise",
+    "sorelpr": "fillValue",
+    "sostss": "Continental",
+    "sostrt": "Accurate",
+    "sostsl": "CaK",
+    "sosttf": "Annual",
+    "sosttg": "0MYA",
+    "sostv": "Clear",
+}
+
+
+@click.command()
+def main() -> None:
+    """Add SWEET ontologies."""
+    graph = MODULE.ensure_rdf(url=ALL_PREFIXES_URL)
+    sparql = """
+        SELECT ?prefix ?namespace
+        WHERE {
+            ?x sh:prefix ?prefix;
+               sh:namespace ?namespace .
+        }
+    """
+    for sweet_internal_prefix, uri_prefix in graph.query(sparql):  # type:ignore
+        sweet_internal_prefix = str(sweet_internal_prefix)
+        uri_prefix = str(uri_prefix)
+
+        if sweet_internal_prefix in {"soall", "sweet"}:
+            continue  # this is the combine one, not its own prefix
+
+        sweet_internal_key = uri_prefix.removeprefix("http://sweetontology.net/").rstrip("/")
+        if not sweet_internal_key:
+            raise ValueError(f"no internal key found for {sweet_internal_prefix}")
+
+        download_rdf = (
+            f"https://github.com/ESIPFed/sweet/raw/refs/heads/master/src/{sweet_internal_key}.ttl"
+        )
+        inner_graph = MODULE.ensure_rdf(url=download_rdf)
+
+        ontology_name_query = """
+            SELECT ?name
+            WHERE { owl:Ontology ^rdf:type/rdfs:label ?name }
+            LIMIT 1
+        """
+        name = str(next(iter(inner_graph.query(ontology_name_query)))[0])  # type:ignore
+        name_short = name.removeprefix("SWEET Ontology ")
+
+        example_query = f"""
+            SELECT ?term
+            WHERE {{
+                ?term rdf:type owl:Class;
+                      rdfs:label ?name ;
+                FILTER STRSTARTS(str(?term), "{uri_prefix}")
+            }}
+            LIMIT 1
+        """
+        example_records = list(inner_graph.query(example_query))
+        if example_records:
+            example_uri = cast(str, example_records[0][0])  # type:ignore[index]
+            example = example_uri.removeprefix(uri_prefix)
+        elif sweet_internal_prefix in MANUAL:
+            example = MANUAL[sweet_internal_prefix]
+        else:
+            raise ValueError(
+                f"[{sweet_internal_prefix}] missing example in {name_short} ({uri_prefix})"
+            )
+
+        if not sweet_internal_prefix.startswith("so"):
+            raise ValueError
+
+        nsl = name_short.lower()
+        if nsl.startswith("human "):
+            keywords = [nsl.removeprefix("human ")]
+        elif nsl.startswith("material "):
+            keywords = ["materials", nsl.removeprefix("material ")]
+        elif nsl.startswith("phenomena "):
+            keywords = ["phenomena", nsl.removeprefix("phenomena ")]
+        elif nsl.startswith("property relationships "):
+            keywords = [nsl.removeprefix("property relationships ")]
+        elif nsl.startswith("property "):
+            keywords = [nsl.removeprefix("property ")]
+        elif nsl.startswith("process "):
+            keywords = [nsl.removeprefix("process ")]
+        elif nsl.startswith("realm land "):
+            keywords = [nsl.removeprefix("realm land") + "land"]
+        elif nsl.startswith("realm "):
+            keywords = ["realm", nsl.removeprefix("realm ")]
+        elif nsl.startswith("representation "):
+            keywords = [nsl.removeprefix("realm ")]
+        elif nsl.startswith("state "):
+            keywords = [nsl.removeprefix("realm ")]
+        elif nsl.startswith("relationships "):
+            keywords = [nsl.removeprefix("relationships ")]
+        else:
+            keywords = [nsl.lower()]
+
+        prefix = f"sweet.{sweet_internal_prefix.removeprefix('so')}"
+        resource = bioregistry.Resource(
+            prefix=prefix,
+            synonyms=[sweet_internal_prefix],
+            name=name,
+            keywords=sorted(keywords),
+            homepage=str(uri_prefix),
+            uri_format=f"{uri_prefix}$1",
+            description=f"The Semantic Web for Earth and Environmental Terminology (SWEET) ontology for {name_short}",
+            example=example,
+            download_rdf=download_rdf,
+            part_of="sweet",
+            license="CC0-1.0",
+            repository="https://github.com/ESIPFed/sweet",
+            contributor=bioregistry.Author.get_charlie(),
+            github_request_issue=1772,
+        )
+        bioregistry.add_resource(resource)
+
+    bioregistry.manager.write_registry()
+
+
+if __name__ == "__main__":
+    main()

bioregistry/curation/clean_publications.py

@@ -7,7 +7,7 @@
 import click
 
 import bioregistry
-from bioregistry.schema.struct import deduplicate_publications
+from bioregistry.schema import deduplicate_publications
 
 
 @click.command()

bioregistry/curation/enrich_publications.py

@@ -13,7 +13,7 @@ from manubot.cite.pubmed import get_pmid_for_doi, get_pubmed_csl_item
 from tqdm import tqdm
 
 from bioregistry import manager
-from bioregistry.schema.struct import Publication, deduplicate_publications
+from bioregistry.schema import Publication, deduplicate_publications
 from bioregistry.utils import removeprefix