Merge pull request #23 from fedebenelli/main

Migration to `pathlib` and cache groups for better end-user experience

tests/writers/test_to_clapeyron.py

@@ -24,8 +24,6 @@ def test_to_clapeyron():
     with open(f"{path_db}/PSRK_groups.csv", mode="r") as f:
         df_psrk = pd.read_csv(f, sep="|", index_col=None)
 
-    os.mkdir(f"{here}/database")
-
     limonene = Groups("CC1=CCC(CC1)C(=C)C", "smiles")
     ethanol = Groups("CCO", "smiles", normal_boiling_temperature=78 + 273.15)
 
@@ -93,8 +91,6 @@ def test_to_clapeyron_batch_name():
     with open(f"{path_db}/PSRK_groups.csv", mode="r") as f:
         df_psrk = pd.read_csv(f, sep="|", index_col=None)
 
-    os.mkdir(f"{here}/database")
-
     limonene = Groups("CC1=CCC(CC1)C(=C)C", "smiles")
     ethanol = Groups("CCO", "smiles", normal_boiling_temperature=78 + 273.15)
 
@@ -156,7 +152,6 @@ def test_to_clapeyron_batch_name():
 
 
 def test_molar_mass_csv():
-    os.mkdir(f"{here}/database")
 
     limonene = Groups("CC1=CCC(CC1)C(=C)C", "smiles")
     ethanol = Groups("CCO", "smiles", normal_boiling_temperature=78 + 273.15)

ugropy/core/get_rdkit_object.py

@@ -1,12 +1,14 @@
 """get_rdkit_object module."""
 
+from functools import cache
 from typing import Union
 
 import pubchempy as pcp
 
 from rdkit import Chem
 
 
+@cache
 def instantiate_mol_object(
     identifier: Union[str, Chem.rdchem.Mol], identifier_type: str = "name"
 ) -> Chem.rdchem.Mol:

ugropy/groups.py

@@ -53,6 +53,7 @@ def __init__(
         identifier_type: str = "name",
         normal_boiling_temperature: float = None,
     ) -> None:
+
         self.identifier_type = identifier_type.lower()
         self.identifier = identifier
         self.mol_object = instantiate_mol_object(identifier, identifier_type)

ugropy/writers/clapeyron.py

@@ -1,5 +1,6 @@
 """to_clapeyron module."""
 
+import pathlib
 from typing import List
 
 from ugropy.properties.joback_properties import JobackProperties
@@ -43,10 +44,16 @@ def to_clapeyron(
         "batch1_ogUNIFAC_groups.csv". With the default value will be
         "ogUNIFAC_groups.csv", by default "".
     """
+    # Use pathlib's Path internally
+    path_pathlib = pathlib.Path(path)
+
     # Check if all list have correct data:
     if len(molecules_names) == 0:
         raise ValueError("No names provided for the molecules.")
 
+    if not path_pathlib.is_dir():
+        path_pathlib.mkdir(parents=True)
+
     if unifac_groups and len(unifac_groups) != len(molecules_names):
         raise ValueError(
             "UNIFAC groups list must have the same amount of elements than"
@@ -67,7 +74,7 @@ def to_clapeyron(
 
     # Molar mass
     write_molar_mass(
-        path,
+        path_pathlib,
         batch_name,
         molecules_names,
         unifac_groups,
@@ -77,12 +84,14 @@ def to_clapeyron(
 
     # LV-UNIFAC
     if unifac_groups:
-        write_unifac(path, batch_name, molecules_names, unifac_groups)
+        write_unifac(path_pathlib, batch_name, molecules_names, unifac_groups)
 
     # PSRK
     if psrk_groups:
-        write_psrk(path, batch_name, molecules_names, psrk_groups)
+        write_psrk(path_pathlib, batch_name, molecules_names, psrk_groups)
 
     # Critical
     if joback_objects:
-        write_critical(path, batch_name, molecules_names, joback_objects)
+        write_critical(
+            path_pathlib, batch_name, molecules_names, joback_objects
+        )

ugropy/writers/clapeyron_writers/critical.py

@@ -1,5 +1,6 @@
 """Joback critical properties writer module."""
 
+import pathlib
 from io import StringIO
 from typing import List
 
@@ -9,7 +10,7 @@
 
 
 def write_critical(
-    path: str,
+    path: pathlib.Path,
     batch_name: str,
     molecules_names: List[str],
     joback_objects: List[JobackProperties] = [],
@@ -20,7 +21,7 @@ def write_critical(
 
     Parameters
     ----------
-    path : str, optional
+    path : pathlib.Path, optional
         Path to the directory to store de .csv files, by default "./database".
     batch_name : str, optional
         Name of the writing batch. For example, if you name the batch with
@@ -42,6 +43,7 @@ def write_critical(
         "Critical Single Parameters,,,,,\n"
         "species,CAS,Tc,Pc,Vc,acentricfactor\n"
     )
+    path_critical = pathlib.Path(path)
     # =========================================================================
     # Build dataframe
     # =========================================================================
@@ -62,13 +64,13 @@ def write_critical(
 
     if batch_name == "":
         with open(
-            f"{path}/critical.csv", "w", newline="", encoding="utf-8"
+            path_critical / "critical.csv", "w", newline="", encoding="utf-8"
         ) as file:
             df.to_csv(file, index=False)
 
     else:
         with open(
-            f"{path}/{batch_name}_critical.csv",
+            path_critical / f"{batch_name}_critical.csv",
             "w",
             newline="",
             encoding="utf-8",

ugropy/writers/clapeyron_writers/molar_mass.py

@@ -1,5 +1,6 @@
 """Molar mass writer module."""
 
+import pathlib
 from io import StringIO
 from typing import List
 
@@ -12,7 +13,7 @@
 
 
 def write_molar_mass(
-    path: str,
+    path: pathlib.Path,
     batch_name: str,
     molecules_names: List[str],
     unifac_groups: List[dict] = [],
@@ -23,7 +24,7 @@ def write_molar_mass(
 
     Parameters
     ----------
-    path : str, optional
+    path : pathlib.Path
         Path to the directory to store de .csv files, by default "./database".
     batch_name : str, optional
         Name of the writing batch. For example, if you name the batch with
@@ -49,6 +50,7 @@ def write_molar_mass(
         "Molar Mases Single Params,,\n"
         "species,CAS,Mw\n"
     )
+    path_molar_mass = pathlib.Path(path)
     # =========================================================================
     # Get molecular weights
     # =========================================================================
@@ -90,13 +92,16 @@ def write_molar_mass(
 
     if batch_name == "":
         with open(
-            f"{path}/molarmass.csv", "w", newline="", encoding="utf-8"
+            path_molar_mass / "molarmass.csv",
+            "w",
+            newline="",
+            encoding="utf-8",
         ) as file:
             df.to_csv(file, index=False)
 
     else:
         with open(
-            f"{path}/{batch_name}_molarmass.csv",
+            path_molar_mass / f"{batch_name}_molarmass.csv",
             "w",
             newline="",
             encoding="utf-8",

ugropy/writers/clapeyron_writers/psrk_groups.py

@@ -1,11 +1,11 @@
 """PSRK groups writer module."""
 
-import os
+import pathlib
 from typing import List
 
 
 def write_psrk(
-    path: str,
+    path: pathlib.Path,
     batch_name: str,
     molecules_names: List[str],
     psrk_groups: List[dict],
@@ -14,7 +14,7 @@ def write_psrk(
 
     Parameters
     ----------
-    path : str, optional
+    path : pathlib.Path
         Path to the directory to store de .csv files, by default "./database".
     batch_name : str, optional
         Name of the writing batch. For example, if you name the batch with
@@ -37,6 +37,8 @@ def write_psrk(
         "species,groups\n"
     ]
 
+    path_psrk = path / "PSRK"
+
     for name, groups in zip(molecules_names, psrk_groups):
         groups_str = '"['
 
@@ -51,14 +53,14 @@ def write_psrk(
         lines.extend(new_line)
 
     # Create folder for PSRK groups
-    if not os.path.exists(f"{path}/PSRK"):
-        os.makedirs(f"{path}/PSRK")
+    if not path_psrk.is_dir():
+        path_psrk.mkdir(parents=True)
 
     # Write .csv
     if batch_name == "":
-        write_path = f"{path}/PSRK/PSRK_groups.csv"
+        write_path = path_psrk / "PSRK_groups.csv"
     else:
-        write_path = f"{path}/PSRK/{batch_name}_PSRK_groups.csv"
+        write_path = path_psrk / f"{batch_name}_PSRK_groups.csv"
 
-    with open(f"{write_path}", "w", encoding="utf-8", newline="\n") as file:
+    with open(write_path, "w", encoding="utf-8", newline="\n") as file:
         file.writelines(lines)

ugropy/writers/clapeyron_writers/unifac_groups.py

@@ -1,11 +1,11 @@
 """UNIFAC groups writer module."""
 
-import os
+import pathlib
 from typing import List
 
 
 def write_unifac(
-    path: str,
+    path: pathlib.Path,
     batch_name: str,
     molecules_names: List[str],
     unifac_groups: List[dict],
@@ -14,7 +14,7 @@ def write_unifac(
 
     Parameters
     ----------
-    path : str, optional
+    path : pathlib.Path
         Path to the directory to store de .csv files, by default "./database".
     batch_name : str, optional
         Name of the writing batch. For example, if you name the batch with
@@ -32,6 +32,8 @@ def write_unifac(
         "species,groups\n"
     ]
 
+    path_ogunifac = path / "ogUNIFAC"
+
     for name, groups in zip(molecules_names, unifac_groups):
         groups_str = '"['
 
@@ -46,14 +48,14 @@ def write_unifac(
         lines.extend(new_line)
 
     # Create folder for ogUNIFAC groups
-    if not os.path.exists(f"{path}/ogUNIFAC"):
-        os.makedirs(f"{path}/ogUNIFAC")
+    if not path_ogunifac.is_dir():
+        path_ogunifac.mkdir(parents=True)
 
     # Write .csv
     if batch_name == "":
-        write_path = f"{path}/ogUNIFAC/ogUNIFAC_groups.csv"
+        write_path = path_ogunifac / "ogUNIFAC_groups.csv"
     else:
-        write_path = f"{path}/ogUNIFAC/{batch_name}_ogUNIFAC_groups.csv"
+        write_path = path_ogunifac / f"{batch_name}_ogUNIFAC_groups.csv"
 
-    with open(f"{write_path}", "w", encoding="utf-8", newline="\n") as file:
+    with open(write_path, "w", encoding="utf-8", newline="\n") as file:
         file.writelines(lines)