Test 3.12

.github/workflows/release.yml

@@ -33,6 +33,7 @@ jobs:
         uses: pypa/cibuildwheel@v2.16.5
         env:
           CIBW_ARCHS_MACOS: "x86_64 arm64"
+          PIP_EXTRA_INDEX_URL: "https://download.pytorch.org/whl/cpu"
 
       - uses: actions/upload-artifact@v2
         with:

.github/workflows/tests.yml

@@ -154,7 +154,7 @@ jobs:
     strategy:
       fail-fast: true
       matrix:
-        python-version: ["3.7", "3.8", "3.9"]
+        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11", "3.12"]
     steps:
       - uses: actions/checkout@v2
 
@@ -172,6 +172,7 @@ jobs:
 
       - name: Install library
         run: |
-          pip install .
+          pip install ".[ml]" pytest
+          pytest tests/pipelines/test_pipelines.py
 #          uv venv
 #          uv pip install .

README.md

@@ -34,13 +34,13 @@ Check out our interactive [demo](https://aphp.github.io/edsnlp/demo/) !
 You can install EDS-NLP via `pip`. We recommend pinning the library version in your projects, or use a strict package manager like [Poetry](https://python-poetry.org/).
 
 ```shell
-pip install edsnlp==0.13.0
+pip install edsnlp==0.13.1
 ```
 
 or if you want to use the trainable components (using pytorch)
 
 ```shell
-pip install "edsnlp[ml]==0.13.0"
+pip install "edsnlp[ml]==0.13.1"
 ```
 
 ### A first pipeline

changelog.md

@@ -1,25 +1,26 @@
 # Changelog
 
-## Unreleased
+## v0.13.1
 
 ### Added
 
 - `eds.tables` accepts a minimum_table_size (default 2) argument to reduce pollution
-- `RuleBasedQualifier` now expose a `process` method that only returns qualified entities and token without actually tagging them, defering this task to the `__call__` method.
+- `RuleBasedQualifier` now expose a `process` method that only returns qualified entities and token without actually tagging them, deferring this task to the `__call__` method.
 - Added new patterns for metastasis detection. Developed on CT-Scan reports.
 - Added citation of articles
 
 ### Fixed
 
-- Disorder and Behavor pipes don't use a "PRESENT" or "ABSENT" `status` anymore. Instead, `status=None` by default,
+- Disorder and Behavior pipes don't use a "PRESENT" or "ABSENT" `status` anymore. Instead, `status=None` by default,
   and `ent._.negation` is set to True instead of setting `status` to "ABSENT". To this end, the *tobacco* and *alcohol*
-  now use the `NegationQualifier` internaly.
+  now use the `NegationQualifier` internally.
 - 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.
 - Fix fsspec open file encoding to "utf-8".
 
 ### Changed
 
 - Rename `eds.measurements` to `eds.quantities`
+- scikit-learn (used in `eds.endlines`) is no longer installed by default when installing `edsnlp[ml]`
 
 ## v0.13.0
 

docs/index.md

@@ -15,13 +15,13 @@ Check out our interactive [demo](https://aphp.github.io/edsnlp/demo/) !
 You can install EDS-NLP via `pip`. We recommend pinning the library version in your projects, or use a strict package manager like [Poetry](https://python-poetry.org/).
 
 ```{: data-md-color-scheme="slate" }
-pip install edsnlp==0.13.0
+pip install edsnlp==0.13.1
 ```
 
 or if you want to use the trainable components (using pytorch)
 
 ```{: data-md-color-scheme="slate" }
-pip install "edsnlp[ml]==0.13.0"
+pip install "edsnlp[ml]==0.13.1"
 ```
 
 ### A first pipeline

edsnlp/pipes/core/endlines/endlines.py

@@ -22,6 +22,10 @@ class EndLinesMatcher(GenericMatcher):
     Behind the scenes, it uses a `endlinesmodel` instance, which is an unsupervised
     algorithm based on the work of [@zweigenbaum2016].
 
+    !!! warning "Installation"
+
+        To use this component, you need to install the `scikit-learn` library.
+
     Training
     --------
     ```python
@@ -93,12 +97,12 @@ class EndLinesMatcher(GenericMatcher):
 
     Extensions
     ----------
-    The `eds.endlines` pipeline declares one extension, on both `Span` and `Token`
-    objects. The `end_line` attribute is a boolean, set to `True` if the pipeline
+    The `eds.endlines` pipe declares one extension, on both `Span` and `Token`
+    objects. The `end_line` attribute is a boolean, set to `True` if the pipe
     predicts that the new line is an end line character. Otherwise, it is set to
     `False` if the new line is classified as a space.
 
-    The pipeline also sets the `excluded` custom attribute on newlines that are
+    The pipe also sets the `excluded` custom attribute on newlines that are
     classified as spaces. It lets downstream matchers skip excluded tokens
     (see [normalisation](/pipes/core/normalisation/)) for more detail.
 
@@ -113,7 +117,7 @@ class EndLinesMatcher(GenericMatcher):
 
     Authors and citation
     --------------------
-    The `eds.endlines` pipeline was developed by AP-HP's Data Science team based on
+    The `eds.endlines` pipe was developed by AP-HP's Data Science team based on
     the work of [@zweigenbaum2016].
     '''
 

edsnlp/pipes/misc/quantities/quantities.py

@@ -612,7 +612,7 @@ def __init__(
             as_ents: bool = False,
             span_setter: Optional[SpanSetterArg] = None,
             use_tables: bool = True,
-            measurements: Union[str, List[Union[str, MsrConfig]], Dict[str, MsrConfig]] = None # deprecated # noqa: E501
+            measurements: Optional[Union[str, List[Union[str, MsrConfig]], Dict[str, MsrConfig]]] = None,  # deprecated # noqa: E501
     ):
 
         if measurements:
@@ -632,7 +632,7 @@ def __init__(
                 "Skipping that step."
             )
 
-        self.all_quantities = (quantities == "all")
+        self.all_quantities = quantities == "all"
         if self.all_quantities:
             quantities = []
 
@@ -659,9 +659,7 @@ def __init__(
         self.extract_ranges = extract_ranges
         self.range_patterns = range_patterns
         self.span_getter = (
-            validate_span_getter(span_getter)
-            if span_getter is not None
-            else None
+            validate_span_getter(span_getter) if span_getter is not None else None
         )
         self.merge_mode = merge_mode
         self.before_snippet_limit = before_snippet_limit
@@ -676,10 +674,7 @@ def __init__(
                 "ents": as_ents,
                 "measurements": True,
                 "quantities": True,
-                **{
-                    name: [name]
-                    for name in self.measure_names.values()
-                }
+                **{name: [name] for name in self.measure_names.values()},
             }
 
         super().__init__(nlp=nlp, name=name, span_setter=span_setter)
@@ -1033,10 +1028,17 @@ def get_matches_before(i):
                         table_pd = table._.to_pd_table(as_spans=True)
                         # Find out the number's row
                         for _, row in table_pd.iterrows():
-                            start_line = next((item.start for item in row
-                                               if item is not None), None)
-                            end_line = next((item.end for item in reversed(row)
-                                             if item is not None), None)
+                            start_line = next(
+                                (item.start for item in row if item is not None), None
+                            )
+                            end_line = next(
+                                (
+                                    item.end
+                                    for item in reversed(row)
+                                    if item is not None
+                                ),
+                                None,
+                            )
                             if start_line is None:
                                 continue
 
@@ -1136,10 +1138,7 @@ def is_within_row(x):
 
             else:
                 ent.label_ = self.measure_names[dims]
-            ent._.set(
-                ent.label_,
-                SimpleQuantity(value, unit_norm, self.unit_registry)
-            )
+            ent._.set(ent.label_, SimpleQuantity(value, unit_norm, self.unit_registry))
 
             quantities.append(ent)
 
@@ -1224,9 +1223,7 @@ def merge_quantities_in_ranges(self, quantities: List[Span]) -> List[Span]:
             ]
             if len(matching_patterns):
                 try:
-                    new_value = RangeQuantity.from_quantities(
-                        last._.value, ent._.value
-                    )
+                    new_value = RangeQuantity.from_quantities(last._.value, ent._.value)
                     merged[-1] = last = last.doc[
                                         last.start
                                         if matching_patterns[0][0] is None
@@ -1296,7 +1293,8 @@ def __call__(self, doc):
         existing = (
             list(get_spans(doc, self.span_getter))
             if self.span_getter is not None
-            else ())
+            else ()
+        )
         snippets = (
             dict.fromkeys(ent.sent for ent in existing)
             if self.span_getter is not None

pyproject.toml

@@ -13,7 +13,7 @@ dependencies = [
     "pytz",
     "pysimstring>=1.2.1",
     "regex",
-    "spacy>=3.1,<3.8",
+    "spacy>=3.2,<3.8",
     "confit>=0.5.5",
     "tqdm",
     "umls-downloader>=0.1.1",
@@ -105,7 +105,6 @@ ml = [
     "safetensors>=0.3.0",
     "transformers>=4.0.0,<5.0.0",
     "accelerate>=0.20.3,<1.0.0",
-    "scikit-learn>=1.0.0",
 ]
 
 [project.urls]

tests/pipelines/test_pipelines.py

@@ -12,5 +12,5 @@ def test_import_all():
     import edsnlp.pipes
 
     for name in dir(edsnlp.pipes):
-        if not name.startswith("_"):
+        if not name.startswith("_") and "endlines" not in name:
             getattr(edsnlp.pipes, name)