bioregistry 0.13.9__py3-none-any.whl → 0.13.11__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/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