Adding possibility to select cim10 and atc in eds.cim10 and eds.drugs

changelog.md

@@ -6,6 +6,10 @@
 
 - Numbers are now only detected without trying to remove the pollution in between digits, ie `55 @ 77777` could be detected as a full number before, but not anymore.
 
+### Changed
+
+- Rename `eds.measurements` to `eds.quantities`
+
 ## v0.13.0
 
 ### Added

demo/app.py

@@ -68,7 +68,7 @@
     "Drugs": "drugs",
     "CIM10": "cim10",
     "Dates": "dates",
-    "Measurements": "measurements",
+    "Quantities": "quantities",
     "Charlson": "charlson",
     "SOFA": "sofa",
     "Elston & Ellis": "elston_ellis",
@@ -220,7 +220,7 @@ def load_model(custom_regex: str, **enabled):
 
 doc = nlp(text)
 doc.ents = filter_spans(
-    (*doc.ents, *doc.spans.get("dates", []), *doc.spans.get("measurements", []))
+    (*doc.ents, *doc.spans.get("dates", []), *doc.spans.get("quantities", []))
 )
 
 st.header("Visualisation")

docs/pipes/misc/index.md

@@ -12,7 +12,7 @@ For instance, the date detection and normalisation pipeline falls in this catego
 |--------------------------|---------------------------------------------|
 | `eds.dates`              | Date extraction and normalisation           |
 | `eds.consultation_dates` | Identify consultation dates                 |
-| `eds.measurements`       | Measure extraction and normalisation        |
+| `eds.quantities`         | Quantity extraction and normalisation        |
 | `eds.sections`           | Section detection                           |
 | `eds.reason`             | Rule-based hospitalisation reason detection |
 | `eds.tables`             | Tables detection                            |

docs/pipes/misc/quantities.md

@@ -0,0 +1,8 @@
+# Quantities {: #edsnlp.pipes.misc.quantities.factory.create_component }
+
+::: edsnlp.pipes.misc.quantities.factory.create_component
+    options:
+        heading_level: 2
+        show_bases: false
+        show_source: false
+        only_class_level: true

docs/pipes/ner/index.md

@@ -2,7 +2,7 @@
 
 We provide several Named Entity Recognition (NER) components.
 Named Entity Recognition is the task of identifying short relevant spans of text, named entities, and classifying them into pre-defined categories.
-In the case of clinical documents, these entities can be scores, disorders, behaviors, codes, dates, measurements, etc.
+In the case of clinical documents, these entities can be scores, disorders, behaviors, codes, dates, quantities, etc.
 
 ## Span setters: where are stored extracted entities ? {: #edsnlp.pipes.base.SpanSetterArg }
 

edsnlp/pipes/__init__.py

@@ -20,7 +20,7 @@
     from .core.terminology.factory import create_component as terminology
     from .misc.consultation_dates.factory import create_component as consultation_dates
     from .misc.dates.factory import create_component as dates
-    from .misc.measurements.factory import create_component as measurements
+    from .misc.quantities.factory import create_component as quantities
     from .misc.reason.factory import create_component as reason
     from .misc.sections.factory import create_component as sections
     from .misc.tables.factory import create_component as tables

edsnlp/pipes/misc/quantities/__init__.py

@@ -0,0 +1,4 @@
+from edsnlp.pipes.misc.quantities.quantities import QuantitiesMatcher
+from edsnlp.pipes.misc.quantities.patterns import *
+
+from . import factory

edsnlp/pipes/misc/measurements/factory.py → edsnlp/pipes/misc/quantities/factory.py

@@ -1,10 +1,10 @@
 from edsnlp.core import registry
 
 from . import patterns
-from .measurements import MeasurementsMatcher
+from .quantities import QuantitiesMatcher
 
 DEFAULT_CONFIG = dict(
-    measurements=list(patterns.common_measurements.keys()),  # noqa: E501
+    quantities=list(patterns.common_quantities.keys()),  # noqa: E501
     units_config=patterns.units_config,
     number_terms=patterns.number_terms,
     number_regex=patterns.number_regex,
@@ -24,7 +24,7 @@
 )
 
 create_component = registry.factory.register(
-    "eds.measurements",
+    "eds.quantities",
     assigns=["doc.spans", "doc.ents"],
-    deprecated=["eds.measures"],
-)(MeasurementsMatcher)
+    deprecated=["eds.measures", "eds.measurements"],
+)(QuantitiesMatcher)

edsnlp/pipes/misc/measurements/patterns.py → edsnlp/pipes/misc/quantities/patterns.py

@@ -57,7 +57,7 @@
 )?"""
 
 
-common_measurements = {
+common_quantities = {
     "weight": {
         "unit": "kg",
         "unitless_patterns": [