Faster ConditionsTable.from_df

Author: dweindl

petab/v1/lint.py

@@ -53,6 +53,9 @@
     "observable_table_has_nontrivial_noise_formula",
 ]
 
+#: Regular expression pattern for valid PEtab IDs
+_petab_id_pattern = re.compile(r"^[a-zA-Z_]\w*$")
+
 
 def _check_df(df: pd.DataFrame, req_cols: Iterable, name: str) -> None:
     """Check if given columns are present in DataFrame
@@ -1189,7 +1192,7 @@ def is_valid_identifier(x: str) -> bool:
     if pd.isna(x):
         return False
 
-    return re.match(r"^[a-zA-Z_]\w*$", x) is not None
+    return _petab_id_pattern.match(x) is not None
 
 
 def check_ids(ids: Iterable[str], kind: str = "") -> None:

petab/v2/core.py

@@ -404,7 +404,7 @@ def from_df(cls, df: pd.DataFrame) -> ConditionsTable:
 
         conditions = []
         for condition_id, sub_df in df.reset_index().groupby(C.CONDITION_ID):
-            changes = [Change(**row.to_dict()) for _, row in sub_df.iterrows()]
+            changes = [Change(**row) for row in sub_df.to_dict("records")]
             conditions.append(Condition(id=condition_id, changes=changes))
 
         return cls(conditions=conditions)