Fix use count based fp

mkdocs/docs/development/dev.md

@@ -254,7 +254,7 @@ The semantic release configuration is defined in `pyproject.toml`:
 [tool.semantic_release]
 version_toml = ["pyproject.toml:project.version"]
 build_command = "uv build"
-upload_to_release = true
+upload_to_vcs_release = true
 
 [tool.semantic_release.changelog]
 mode = "update"
@@ -280,14 +280,11 @@ Releases are automatically triggered when commits are pushed to the `main` branc
 While releases are automated, you can manually trigger a release:
 
 ```bash
-# Dry run to see what would happen
-uv run semantic-release version --no-push
+# Print the next version without changing files
+uv run semantic-release version --print
 
 # Generate changelog only
 uv run semantic-release changelog
-
-# Print current version
-uv run semantic-release version --print
 ```
 
 ### Best Practices

mkdocs/docs/feature_generation.md

@@ -31,12 +31,12 @@ for k, v in Descriptors.descList:
 
     #### Binary vs. Count Fingerprints
 
-    By default, fingerprints are generated as **binary** vectors — each bit is either `0` (substructure absent) or `1` (substructure present). You can switch to **count-based** fingerprints by setting `use_counts=True`, which records ***how many times*** each substructure occurs in the molecule. Count fingerprints can improve model performance when the frequency of substructures is informative.
+    By default, `FingerprintsGeneric` and `MorganFingerprints` generate **count-based** vectors, which record ***how many times*** each substructure occurs in a molecule. Count fingerprints can improve model performance when substructure frequency is informative. Set `use_counts=False` to generate a binary vector, where each bit is either `0` (substructure absent) or `1` (substructure present).
 
     | Mode | Parameter | Output values | Use case |
     |------|-----------|---------------|----------|
-    | Binary (default) | `use_counts=False` | 0 or 1 | General-purpose fingerprinting |
-    | Count | `use_counts=True` | 0, 1, 2, … | When substructure frequency matters |
+    | Count (default) | `use_counts=True` | 0, 1, 2, ... | When substructure frequency matters |
+    | Binary | `use_counts=False` | 0 or 1 | When only substructure presence matters |
 
     The `use_counts` parameter is available on both `FingerprintsGeneric` and the `MorganFingerprints` convenience class:
 
@@ -46,17 +46,19 @@ from mother.feature_generation import FingerprintsGeneric, MorganFingerprints
 
 molecule_objects = [Chem.MolFromSmiles(smi) for smi in ["CCO", "CCN", "c1ccccc1"]]
 
-# Count-based Morgan fingerprints via the convenience class
-morgan_counts = MorganFingerprints(radius=2, fpSize=1024, use_counts=True)
+# Count-based Morgan fingerprints are the default
+morgan_counts = MorganFingerprints(radius=2, fpSize=2048)
 features = morgan_counts.fit_transform(molecule_objects)
 
 # Count-based fingerprints via the generic class (works with any supported fp_type)
 fp_counts = FingerprintsGeneric(
     fp_type="AtomPairFP",
     parameters={"fpSize": 2048},
-    use_counts=True,
 )
 features = fp_counts.fit_transform(molecule_objects)
+
+# Opt in to binary Morgan fingerprints
+morgan_binary = MorganFingerprints(radius=2, fpSize=2048, use_counts=False)
 ```
 
     !!! note
@@ -86,10 +88,12 @@ from mother.feature_generation import ChemicalDescriptors, MorganFingerprints
 
 molecule_objects = [Chem.MolFromSmiles(smi) for smi in ["CCO", "CCN", "c1ccccc1"]]
 
-feature_generator = FeatureUnion([
-    ("descriptors", ChemicalDescriptors(descriptor_list=["MolWt", "MolLogP"])),
-    ("morgan_fp", MorganFingerprints(radius=2, fpSize=1024)),
-])
+feature_generator = FeatureUnion(
+    [
+        ("descriptors", ChemicalDescriptors(descriptor_list=["MolWt", "MolLogP"])),
+        ("morgan_fp", MorganFingerprints(radius=2, fpSize=2048)),
+    ]
+)
 features = feature_generator.fit_transform(molecule_objects)
 ```
 

src/mother/feature_generation/config.py

@@ -139,7 +139,7 @@ class FeatureGenerationConfig(BaseModel):
     fingerprints: List[Dict[str, Any]] = Field(default=[], description="List of fingerprint generator settings")
     maccs: bool = Field(default=False, description="Flag if maccs fingerprints should be generated")
     chemical_descriptors: Optional[ChemicalDescriptorsParams] = Field(default=None)
-    use_counts: bool = Field(default=False, description="Whether to use count fingerprints")
+    use_counts: bool = Field(default=True, description="Whether to use count fingerprints")
 
     @field_validator("fingerprints", mode="before")
     @classmethod

src/mother/feature_generation/core.py

@@ -64,7 +64,7 @@ class FingerprintsGeneric(BaseEstimator, TransformerMixin, _TransformOnlyValidMo
     the type and configuration of the fingerprint is determined by the parameters
     """
 
-    def __init__(self, fp_type: str, parameters: dict, use_counts: bool = False) -> None:
+    def __init__(self, fp_type: str, parameters: dict, use_counts: bool = True) -> None:
         self.fp_type: str = fp_type
         self.parameters: dict = parameters
         self.use_counts: bool = use_counts
@@ -119,7 +119,7 @@ def handle_bad_conformer(self, compound, error) -> Chem.rdchem.Mol:
 
 class MorganFingerprints(FingerprintsGeneric):
     def __init__(
-        self, radius: int = 2, fpSize=1024, include_chirality: bool = False, use_counts: bool = False, **kwargs
+        self, radius: int = 2, fpSize: int = 2048, include_chirality: bool = False, use_counts: bool = True, **kwargs
     ) -> None:
         super().__init__(
             "MorganFP",

test/unit/test_use_counts.py

@@ -87,13 +87,13 @@ def test_count_and_binary_differ(self, mols_with_repeated_substructures):
             "Count and binary fingerprints should produce different outputs"
         )
 
-    def test_use_counts_default_is_false(self):
-        """RED if default changed: use_counts should default to False."""
+    def test_use_counts_default_is_true(self):
+        """use_counts should default to True."""
         fg = FingerprintsGeneric(
             fp_type="MorganFP",
             parameters={"radius": 2, "fpSize": 2048},
         )
-        assert fg.use_counts is False
+        assert fg.use_counts is True
 
     def test_output_shape_consistent(self, mols_with_repeated_substructures):
         """Both modes should produce the same output shape."""
@@ -123,18 +123,17 @@ def test_output_shape_consistent(self, mols_with_repeated_substructures):
 class TestUseCountsMorganFingerprints:
     """Tests for use_counts on the MorganFingerprints convenience class."""
 
-    def test_morgan_binary_default(self, mols_with_repeated_substructures):
-        """MorganFingerprints with default use_counts=False should produce binary output."""
-        fg = MorganFingerprints(radius=2, fpSize=1024)
+    def test_morgan_count_default(self, mols_with_repeated_substructures):
+        """MorganFingerprints with default use_counts=True should produce count output."""
+        fg = MorganFingerprints(radius=2, fpSize=2048)
         fg.fit()
         result = fg.transform(mols_with_repeated_substructures)
 
-        unique_values = np.unique(result[~np.isnan(result)])
-        assert set(unique_values).issubset({0, 1})
+        assert np.nanmax(result) > 1
 
     def test_morgan_count_mode(self, mols_with_repeated_substructures):
         """RED if use_counts not wired through MorganFingerprints: should produce counts > 1."""
-        fg = MorganFingerprints(radius=2, fpSize=1024, use_counts=True)
+        fg = MorganFingerprints(radius=2, fpSize=2048, use_counts=True)
         fg.fit()
         result = fg.transform(mols_with_repeated_substructures)
 
@@ -143,7 +142,7 @@ def test_morgan_count_mode(self, mols_with_repeated_substructures):
 
     def test_morgan_use_counts_preserved_after_set_params(self, mols_with_repeated_substructures):
         """use_counts should persist after set_params on other parameters."""
-        fg = MorganFingerprints(radius=2, fpSize=1024, use_counts=True)
+        fg = MorganFingerprints(radius=2, fpSize=2048, use_counts=True)
         fg.set_params(radius=3)
         fg.fit()
         result = fg.transform(mols_with_repeated_substructures)
@@ -153,7 +152,7 @@ def test_morgan_use_counts_preserved_after_set_params(self, mols_with_repeated_s
 
     def test_morgan_use_counts_toggled_via_set_params(self, mols_with_repeated_substructures):
         """RED if use_counts isn't a proper sklearn param: set_params should toggle it."""
-        fg = MorganFingerprints(radius=2, fpSize=1024, use_counts=False)
+        fg = MorganFingerprints(radius=2, fpSize=2048, use_counts=False)
         fg.set_params(use_counts=True)
         fg.fit()
         result = fg.transform(mols_with_repeated_substructures)
@@ -165,15 +164,15 @@ def test_morgan_clone_preserves_use_counts(self):
         """sklearn.clone should preserve use_counts parameter."""
         from sklearn.base import clone
 
-        fg = MorganFingerprints(radius=2, fpSize=1024, use_counts=True)
+        fg = MorganFingerprints(radius=2, fpSize=2048, use_counts=True)
         fg_cloned = clone(fg)
 
         assert fg_cloned.use_counts is True
         assert fg_cloned.get_params()["use_counts"] is True
 
     def test_morgan_get_params_includes_use_counts(self):
         """use_counts should be visible in get_params()."""
-        fg = MorganFingerprints(radius=2, fpSize=1024, use_counts=True)
+        fg = MorganFingerprints(radius=2, fpSize=2048, use_counts=True)
         params = fg.get_params()
         assert "use_counts" in params
         assert params["use_counts"] is True