Update dependencies (#474)

Author: j-adamczyk

.github/workflows/tests.yml

@@ -49,32 +49,3 @@ jobs:
 
       - name: Run tests with pytest
         run: uv run make test
-
-  ci-docs:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.10"
-
-      - name: Install uv
-        uses: astral-sh/setup-uv@v5
-
-      - name: Install the project dependencies
-        run: uv sync --group docs
-
-      - name: Install Pandoc
-        uses: r-lib/actions/setup-pandoc@v2
-
-      - uses: actions/cache@v4
-        name: Cache datasets
-        with:
-          path: ~/scikit_learn_data
-          key: datasets
-
-      - name: Build documentation
-        run: uv run make doctest

pyproject.toml

@@ -32,7 +32,7 @@ dependencies = [
     "numba<1",
     "numpy>=1.20.0,<3",
     "pandas<3",
-    "rdkit<=2024.9.5",
+    "rdkit<=2025.3.3",
     "scikit-learn>=1.0.0,<2",
     "scipy>=1.0.0,<2",
     "tqdm>=4.0.0,<5"
@@ -70,11 +70,12 @@ test = [
 ]
 
 docs = [
-  "ipython",
-  "nbsphinx",
-  "pydata-sphinx-theme",
-  "sphinx",
-  "sphinx-copybutton"
+    "ipython",
+    "nbsphinx",
+    "pydata-sphinx-theme",
+    "scikit-learn!=1.7.1",  # due to scikit-learn docs issue: https://github.com/microsoft/lightgbm/issues/6978
+    "sphinx",
+    "sphinx-copybutton"
 ]
 
 eval = [

skfp/fingerprints/mhfp.py

@@ -189,8 +189,7 @@ def _calculate_fingerprint(self, X: Sequence[str | Mol]) -> np.ndarray | csr_arr
 
         # outputs raw hash values, not feature vectors!
         encoder = MHFPEncoder(self.fp_size, self.random_state)
-        X = MHFPEncoder.EncodeSmilesBulk(
-            encoder,
+        X = encoder.EncodeSmilesBulk(
             X,
             radius=self.radius,
             min_radius=self.min_radius,

tests/fingerprints/mhfp.py

@@ -107,16 +107,13 @@ def test_mhfp_sparse_count_fingerprint(smiles_list, mols_list):
     assert np.all(X_skfp.data > 0)
 
 
-def test_mhfp_sparse_raw_hashes_fingerprint(smiles_list, mols_list):
+def test_mhfp_sparse_raw_hashes_fingerprint(smiles_list):
     mhfp_fp = MHFPFingerprint(variant="raw_hashes", sparse=True, n_jobs=-1)
     X_skfp = mhfp_fp.transform(smiles_list)
 
     encoder = MHFPEncoder(2048, 0)
-    X_rdkit = MHFPEncoder.EncodeMolsBulk(
-        encoder,
-        mols_list,
-    )
-    X_rdkit = csr_array(X_rdkit)
+    X_rdkit = encoder.EncodeSmilesBulk(smiles_list)
+    X_rdkit = csr_array(np.array(X_rdkit))
 
     assert np.array_equal(X_skfp.data, X_rdkit.data)
     assert X_skfp.shape == (len(smiles_list), mhfp_fp.fp_size)

tests/preprocessing/input_output/smiles.py

@@ -20,31 +20,26 @@ def test_mol_to_smiles(mols_list):
     assert all(isinstance(x, str) for x in smiles_list)
 
 
-def test_mol_to_and_from_smiles(smiles_list):
+def test_mol_to_and_from_smiles(mols_list):
     mol_from_smiles = MolFromSmilesTransformer()
     mol_to_smiles = MolToSmilesTransformer()
 
-    mols_list = mol_from_smiles.transform(smiles_list)
-    smiles_list_2 = mol_to_smiles.transform(mols_list)
-
-    assert smiles_list_2 == smiles_list
+    smiles_list_1 = mol_to_smiles.transform(mols_list)
+    smiles_list_2 = mol_to_smiles.transform(
+        mol_from_smiles.transform(mol_to_smiles.transform(mols_list))
+    )
 
+    assert smiles_list_1 == smiles_list_2
 
-def test_parallel_to_and_from_smiles(smiles_list):
-    mol_from_smiles_seq = MolFromSmilesTransformer()
-    mol_from_smiles_parallel = MolFromSmilesTransformer(n_jobs=-1)
 
+def test_parallel_to_and_from_smiles(mols_list):
     mol_to_smiles_seq = MolToSmilesTransformer()
     mol_to_smiles_parallel = MolToSmilesTransformer(n_jobs=-1)
 
-    mols_list_seq = mol_from_smiles_seq.transform(smiles_list)
-    mols_list_parallel = mol_from_smiles_parallel.transform(smiles_list)
-
-    smiles_list_2_seq = mol_to_smiles_seq.transform(mols_list_seq)
-    smiles_list_2_parallel = mol_to_smiles_parallel.transform(mols_list_parallel)
+    smiles_list_seq = mol_to_smiles_seq.transform(mols_list)
+    smiles_list_parallel = mol_to_smiles_parallel.transform(mols_list)
 
-    assert smiles_list_2_seq == smiles_list
-    assert smiles_list_2_seq == smiles_list_2_parallel
+    assert smiles_list_seq == smiles_list_parallel
 
 
 def test_from_invalid_smiles(smiles_list):