Utility module updates

CONTRIBUTING.md

@@ -0,0 +1,50 @@
+# Contributing
+
+This is a quick guide on how to follow best practice and contribute smoothly to `SMACT`.
+
+## Workflow
+
+We follow the [GitHub flow](<https://docs.github.com/en/get-started/using-github/github-flow>), using
+branches for new work and pull requests for verifying the work.
+
+The steps for a new piece of work can be summarised as follows:
+
+1. Push up or create [an issue](https://github.com/WMD-group/SMACT/issues).
+2. Create a branch from main, with a sensible name that relates to the issue.
+3. Do the work and commit changes to the branch. Push the branch
+   regularly to GitHub to make sure no work is accidentally lost.
+4. Write or update unit tests for the code you work on.
+5. When you are finished with the work, ensure that all of the unit
+   tests pass on your own machine.
+6. Open a pull request [on the pull request page](https://github.com/WMD-group/SMACT/pulls).
+7. If nobody acknowledges your pull request promptly, feel free to poke one of the main developers into action.
+
+## Pull requests
+
+For a general overview of using pull requests on GitHub look [in the GitHub docs](https://help.github.com/en/articles/about-pull-requests).
+
+When creating a pull request you should:
+
+- Ensure that the title succinctly describes the changes so it is easy to read on the overview page
+- Reference the issue which the pull request is closing
+
+Recommended reading: [How to Write the Perfect Pull Request](https://github.blog/2015-01-21-how-to-write-the-perfect-pull-request/)
+
+## Dev requirements
+
+When developing locally, it is recommended to install the python packages in `requirements-dev.txt`.
+
+```bash
+pip install -r requirements-dev.txt
+```
+
+This will allow you to run the tests locally with pytest as described in the main README,
+as well as run pre-commit hooks to automatically format python files with isort and black.
+To install the pre-commit hooks (only needs to be done once):
+
+```bash
+pre-commit install
+pre-commit run --all-files # optionally run hooks on all files
+```
+
+Pre-commit hooks will check all files when you commit changes, automatically fixing any files which are not formatted correctly. Those files will need to be staged again before re-attempting the commit.

smact/properties.py

@@ -6,6 +6,7 @@
 import numpy as np
 
 import smact
+from smact.utils.composition import parse_formula
 
 
 def eneg_mulliken(element: Union[smact.Element, str]) -> float:
@@ -179,16 +180,6 @@ def valence_electron_count(compound: str) -> float:
     Raises:
         ValueError: If an element in the compound is not found in the valence data.
     """
-    from typing import Dict
-
-    def parse_formula(formula: str) -> Dict[str, int]:
-        pattern = re.compile(r"([A-Z][a-z]*)(\d*)")
-        elements = pattern.findall(formula)
-        element_stoich: Dict[str, int] = defaultdict(int)
-        for element, count in elements:
-            count = int(count) if count else 1
-            element_stoich[element] += count
-        return element_stoich
 
     def get_element_valence(element: str) -> int:
         try:

smact/tests/test_utils.py

@@ -0,0 +1,76 @@
+import unittest
+
+from pymatgen.core import Composition
+
+from smact import Element
+from smact.screening import smact_filter
+from smact.utils.composition import comp_maker, formula_maker, parse_formula
+
+
+class TestComposition(unittest.TestCase):
+    """Test composition utilities"""
+
+    def setUp(self) -> None:
+        self.mock_filter_output = [
+            (("Fe", "O"), (2, -2), (1, 1)),
+            (("Fe", "O"), (1, 1)),
+            (("Fe", "Fe", "O"), (2, 3, -2), (1, 2, 4)),
+        ]
+        self.smact_filter_output = smact_filter(
+            els=[Element("Li"), Element("Ge"), Element("P"), Element("S")],
+            stoichs=[[10], [1], [2], [12]],
+        )
+
+    def test_parse_formula(self):
+        """Test the parse_formula function"""
+
+        formulas = ["Li10GeP2S12", "Mg0.5O0.5", "CaMg(CO3)2"]
+
+        LGPS = parse_formula(formulas[0])
+        self.assertIsInstance(LGPS, dict)
+        for el_sym, ammt in LGPS.items():
+            self.assertIsInstance(el_sym, str)
+            self.assertIsInstance(ammt, float)
+        self.assertEqual(LGPS["Li"], 10)
+        self.assertEqual(LGPS["Ge"], 1)
+        self.assertEqual(LGPS["P"], 2)
+        self.assertEqual(LGPS["S"], 12)
+
+        MgO = parse_formula(formulas[1])
+        self.assertIsInstance(MgO, dict)
+        self.assertEqual(MgO["Mg"], 0.5)
+        self.assertEqual(MgO["O"], 0.5)
+
+        dolomite = parse_formula(formulas[2])
+        self.assertIsInstance(dolomite, dict)
+        self.assertEqual(dolomite["Ca"], 1)
+        self.assertEqual(dolomite["Mg"], 1)
+        self.assertEqual(dolomite["C"], 2)
+        self.assertEqual(dolomite["O"], 6)
+
+    def test_comp_maker(self):
+        """Test the comp_maker function"""
+        comp1 = comp_maker(self.mock_filter_output[0])
+        comp2 = comp_maker(self.mock_filter_output[1])
+        comp3 = comp_maker(self.mock_filter_output[2])
+        comp4 = comp_maker(self.smact_filter_output[1])
+        for comp in [comp1, comp2, comp3, comp4]:
+            self.assertIsInstance(comp, Composition)
+        self.assertEqual(Composition("FeO"), comp2)
+        self.assertEqual(Composition({"Fe2+": 1, "O2-": 1}), comp1)
+        self.assertEqual(Composition({"Fe2+": 1, "Fe3+": 2, "O2-": 4}), comp3)
+        self.assertEqual(
+            Composition({"Li+": 10, "Ge4+": 1, "P5+": 2, "S2-": 12}), comp4
+        )
+
+    def test_formula_maker(self):
+        """Test the formula_maker function"""
+        form1 = formula_maker(self.mock_filter_output[0])
+        form2 = formula_maker(self.mock_filter_output[1])
+        form3 = formula_maker(self.mock_filter_output[2])
+        form4 = formula_maker(self.smact_filter_output[1])
+        self.assertEqual(form1, "FeO")
+        self.assertEqual(form2, "FeO")
+        self.assertEqual(form1, form2)
+        self.assertEqual(form3, "Fe3O4")
+        self.assertEqual(form4, "Li10Ge(PS6)2")

smact/utils/composition.py

@@ -0,0 +1,95 @@
+"""Utility functioms for handling elements, species, formulas and composition"""
+import re
+from collections import defaultdict
+
+from pymatgen.core import Composition
+
+from smact.structure_prediction.utilities import unparse_spec
+
+
+# Adapted from ElementEmbeddings and Pymatgen
+def parse_formula(formula: str) -> dict[str, int]:
+    """Parse a formula into a dict of el:amt
+
+    Args:
+        formula (str): Chemical formula
+
+    Returns:
+        dict: Dictionary of element symbol: amount
+    """
+    regex = r"\(([^\(\)]+)\)\s*([\.e\d]*)"
+    r = re.compile(regex)
+    m = re.search(r, formula)
+    if m:
+        factor = 1.0
+        if m.group(2) != "":
+            factor = float(m.group(2))
+        unit_sym_dict = _get_sym_dict(m.group(1), factor)
+        expanded_sym = "".join(
+            [f"{el}{amt}" for el, amt in unit_sym_dict.items()]
+        )
+        expanded_formula = formula.replace(m.group(), expanded_sym)
+        return parse_formula(expanded_formula)
+    return _get_sym_dict(formula, 1)
+
+
+def _get_sym_dict(formula: str, factor: float) -> dict[str, float]:
+    sym_dict: dict[str, float] = defaultdict(float)
+    regex = r"([A-Z][a-z]*)\s*([-*\.e\d]*)"
+    r = re.compile(regex)
+    for m in re.finditer(r, formula):
+        el = m.group(1)
+        amt = 1.0
+        if m.group(2).strip() != "":
+            amt = float(m.group(2))
+        sym_dict[el] += amt * factor
+        formula = formula.replace(m.group(), "", 1)
+    if formula.strip():
+        msg = f"{formula} is an invalid formula"
+        raise ValueError(msg)
+
+    return sym_dict
+
+
+def comp_maker(
+    smact_filter_output: tuple[str, int, int] | tuple[str, int]
+) -> Composition:
+    """Convert an output of smact.screening.smact_filer into a Pymatgen Compositions
+
+    Args:
+        smact_filter_output (tuple[str, int, int]|tuple[str, int]): An item in the list returned from smact_filter
+
+    Returns:
+        composition (pymatgen.core.Composition): An instance of the Composition class
+    """
+    if len(smact_filter_output) == 2:
+        form = []
+        for el, ammt in zip(smact_filter_output[0], smact_filter_output[-1]):
+            form.append(el)
+            form.append(ammt)
+        form = "".join(str(e) for e in form)
+    else:
+        form = {}
+        for el, ox, ammt in zip(
+            smact_filter_output[0],
+            smact_filter_output[1],
+            smact_filter_output[2],
+        ):
+            sp = unparse_spec((el, ox))
+            form[sp] = ammt
+    return Composition(form)
+
+
+def formula_maker(
+    smact_filter_output: tuple[str, int, int] | tuple[str, int]
+) -> str:
+    """Convert an output of smact.screening.smact_filter into a formula.
+
+    Args:
+        smact_filter_output (tuple[str, int, int]|tuple[str, int]): An item in the list returned from smact_filter
+
+        Returns:
+            formula (str): A formula
+
+    """
+    return comp_maker(smact_filter_output).reduced_formula