fix: ruff check

Author: r-fedorov

examples/eval_via_opsin.py

@@ -61,4 +61,3 @@ def try_name_smiles(smi):
 accuracy = np.mean(matches)
 
 print(f"Accuracy: {accuracy:.2%}")
-

examples/opsin_eval_ZINC22.py

@@ -94,8 +94,7 @@ def load_parquet_shard(parquet_path):
 
     if SMILES_COLUMN not in ds.column_names:
         raise RuntimeError(
-            f"Column {SMILES_COLUMN!r} not found in {parquet_path}. "
-            f"Available columns: {ds.column_names}"
+            f"Column {SMILES_COLUMN!r} not found in {parquet_path}. Available columns: {ds.column_names}"
         )
 
     return ds
@@ -133,15 +132,10 @@ def sample_zinc22_from_random_parquet_batches(parquet_files, seed):
     )
 
     for batch_start in range(0, len(shuffled_parquets), PARQUET_BATCH_SIZE):
-        batch = shuffled_parquets[
-            batch_start : batch_start + PARQUET_BATCH_SIZE
-        ]
+        batch = shuffled_parquets[batch_start : batch_start + PARQUET_BATCH_SIZE]
         parquet_batches_read += 1
 
-        print(
-            f"Seed {seed}: reading parquet batch {parquet_batches_read} "
-            f"with {len(batch)} shard(s)"
-        )
+        print(f"Seed {seed}: reading parquet batch {parquet_batches_read} with {len(batch)} shard(s)")
 
         for parquet_path in batch:
             if len(pool) >= target_pool_size:
@@ -276,10 +270,7 @@ def opsin_batch_with_fallback(names):
                 converted = [converted]
 
             if len(converted) != len(name_chunk):
-                raise ValueError(
-                    f"OPSIN returned {len(converted)} results for "
-                    f"{len(name_chunk)} names"
-                )
+                raise ValueError(f"OPSIN returned {len(converted)} results for {len(name_chunk)} names")
 
         except Exception:
             converted = [opsin_one(name) for name in name_chunk]
@@ -511,6 +502,7 @@ def main():
     print(f"Total failures: {len(all_failures):,}")
     print(f"Wrote results to: {OUT_DIR.resolve()}")
 
+
 if __name__ == "__main__":
     mp.freeze_support()
     main()

examples/opsin_eval_pubchem.py

@@ -106,10 +106,7 @@ def opsin_batch_with_fallback(names):
                 converted = [converted]
 
             if len(converted) != len(name_chunk):
-                raise ValueError(
-                    f"OPSIN returned {len(converted)} results for "
-                    f"{len(name_chunk)} names"
-                )
+                raise ValueError(f"OPSIN returned {len(converted)} results for {len(name_chunk)} names")
 
         except Exception:
             converted = [opsin_one(name) for name in name_chunk]

examples/test_qm9_opsin_batch.py

@@ -160,7 +160,6 @@ def main():
     else:
         smiles_col = ds.column_names[0]
 
-
     dataset = list([smiles_col])
 
     print("Converting SMILES to IUPAC names...")

src/bluenamer/opsin_verify.py

@@ -115,7 +115,6 @@ def verify_with_opsin(name: str, smiles: str, standardize_smiles: bool = True) -
         return OpsinCheck(status="skipped_no_java", name=name)
 
     if standardize_smiles:
-
         canonical_original = standardize_mol(smiles)
     else:
         canonical_original = _canonicalize(smiles)
@@ -147,7 +146,9 @@ def verify_with_opsin(name: str, smiles: str, standardize_smiles: bool = True) -
             canonical_original=canonical_original,
             opsin_smiles=opsin_smiles,
             canonical_roundtrip=canonical_roundtrip,
-            error_message= "Failed to standardize SMILES for comparison." if standardize_smiles else "Failed to canonicalize SMILES for comparison.",
+            error_message="Failed to standardize SMILES for comparison."
+            if standardize_smiles
+            else "Failed to canonicalize SMILES for comparison.",
         )
 
     if equivalent_smiles(smiles, opsin_smiles):

test_opsin_qm9_batch.py

@@ -1,16 +1,15 @@
+import multiprocessing as mp
 import os
 import random
-import multiprocessing as mp
 from concurrent.futures import ProcessPoolExecutor
 
 import numpy as np
 import py2opsin
 from datasets import load_dataset
-from structure_to_iupac.namer import name_smiles
 from rdkit.Chem import CanonSmiles
+from structure_to_iupac.namer import name_smiles
 from tqdm import tqdm
 
-
 # --- Configuration ---
 N_TEST = 5_000
 SEED = 42
@@ -51,7 +50,7 @@ def main():
 
     indices = random.sample(range(len(all_smiles)), min(N_TEST, len(all_smiles)))
     dataset = [all_smiles[i] for i in indices]
-    #dataset = all_smiles
+    # dataset = all_smiles
 
     # 2. Parallelize SMILES -> IUPAC
     print("Converting SMILES to IUPAC names...")
@@ -85,10 +84,7 @@ def main():
 
     # 5. Calculate Accuracy
     matches = np.array(
-        [
-            predicted == original and predicted is not None
-            for predicted, original in zip(smiles_strings, original_canon)
-        ]
+        [predicted == original and predicted is not None for predicted, original in zip(smiles_strings, original_canon)]
     )
 
     accuracy = np.mean(matches)