⚡ Bolt: [performance improvement] Replace slow pandas iterrows() with itertuples()/to_dict()

ml_peg/calcs/bulk_crystal/elasticity/calc_elasticity.py

@@ -235,7 +235,7 @@ def run_elasticity_benchmark(
 
     # Save relaxed structures to extxyz for visualisation
     atoms_list = []
-    for _, row in results.iterrows():
+    for row in results.to_dict("records"):
         struct = row.get("final_structure")
         if struct is not None:
             atoms = AseAtomsAdaptor.get_atoms(struct).copy()

ml_peg/calcs/conformers/MPCONF196/calc_MPCONF196.py

@@ -85,9 +85,9 @@ def get_ref_energies(data_path: Path) -> dict[str, float]:
     )
     ref_energies = {}
 
-    for row in df.iterrows():
-        label = row[1][0]
-        ref_energies[label] = float(row[1][2]) * KCAL_TO_EV
+    for row in df.itertuples(index=False, name=None):
+        label = row[0]
+        ref_energies[label] = float(row[2]) * KCAL_TO_EV
 
     return ref_energies
 

ml_peg/calcs/conformers/solvMPCONF196/calc_solvMPCONF196.py

@@ -83,9 +83,9 @@ def get_ref_energies(data_path: Path) -> dict[str, float]:
     )
     ref_energies = {}
 
-    for row in df.iterrows():
-        label = row[1][0]
-        e_ref = float(row[1][1]) * units.Hartree
+    for row in df.itertuples(index=False, name=None):
+        label = row[0]
+        e_ref = float(row[1]) * units.Hartree
         ref_energies[label] = e_ref
 
     return ref_energies

ml_peg/calcs/utils/gscdb138.py

@@ -105,11 +105,13 @@ def run_gscdb138(
         df_refs["Reference"] *= units.Hartree
 
         # Calculate relative energy for each entry.
-        for _, row in tqdm(df_refs.iterrows(), dataset, total=df_refs.shape[0]):
+        for row in tqdm(
+            df_refs.itertuples(index=False), dataset, total=df_refs.shape[0]
+        ):
             atoms_list = []
-            identifier = row["Reaction"]
-            reactions = row["Stoichiometry"].split(",")  # Parse stoichiometry string.
-            e_rel_ref = row["Reference"]
+            identifier = row.Reaction
+            reactions = row.Stoichiometry.split(",")  # Parse stoichiometry string.
+            e_rel_ref = row.Reference
             num_species = len(reactions) // 2  # Each species has coefficient and name.
 
             e_rel_model = 0