Update and test to_LaTeX_table

doped/chemical_potentials.py

@@ -37,7 +37,7 @@
 from pymatgen.ext.matproj import MPRester
 from pymatgen.io.vasp.inputs import Kpoints
 from pymatgen.io.vasp.outputs import UnconvergedVASPWarning, Vasprun
-from pymatgen.util.string import latexify
+from pymatgen.util.string import latexify, latexify_spacegroup
 from pymatgen.util.typing import PathLike
 from scipy.interpolate import griddata, interp1d
 from scipy.spatial import ConvexHull, Delaunay
@@ -2565,20 +2565,22 @@ def _calculate_extrinsic_chempot_lims(self, extrinsic_elements, chempots_df):
     def to_LaTeX_table(self, splits=1, prune_polymorphs=True):
         """
         A very simple function to print out the competing phase formation
-        energies in a LaTeX table format, showing the formula, kpoints (if
-        present in the parsed data) and formation energy.
+        energies in a LaTeX table format, showing the formula, space group,
+        energy above hull, kpoints (if present in the parsed data) and
+        formation energy.
 
-        Needs the mhchem package to work and does `not` use the booktabs package
-        - change hline to toprule, midrule and bottomrule if you want to use
-        booktabs style.
+        Needs the ``mhchem`` package to work and does `not` use the ``booktabs``
+        package; change ``hline`` to ``toprule``, ``midrule`` and ``bottomrule``
+        if you want to use ``booktabs`` style.
 
         Args:
             splits (int):
                 Number of splits for the table; either 1 (default) or 2 (with
                 two large columns, each with the formula, kpoints (if present)
                 and formation energy (sub-)columns).
             prune_polymorphs (bool):
-                Whether to only print out the lowest energy polymorphs for each composition.
+                Whether to only print out the lowest energy polymorphs for each
+                composition.
                 Default is True.
 
         Returns:
@@ -2587,8 +2589,9 @@ def to_LaTeX_table(self, splits=1, prune_polymorphs=True):
         if splits not in [1, 2]:
             raise ValueError("`splits` must be either 1 or 2")
         # done in the pyscfermi report style
-        # TODO: Update (now dataframe output)
-        formation_energy_data = self.get_formation_energy_df(prune_polymorphs).to_dict("records")
+        form_e_df = self.get_formation_energy_df(prune_polymorphs)
+        form_e_df["Formula"] = form_e_df.index
+        formation_energy_data = form_e_df.to_dict(orient="records")
 
         kpoints_col = any("k-points" in item for item in formation_energy_data)
 
@@ -2598,13 +2601,17 @@ def to_LaTeX_table(self, splits=1, prune_polymorphs=True):
             + self.composition.reduced_formula
             + "} and all competing phases"
             + (", with k-meshes used in calculations." if kpoints_col else ".")
-            + (" Only the lowest energy polymorphs are included}\n" if prune_polymorphs else "}\n")
+            + (" Only the lowest energy polymorphs are included.}\n" if prune_polymorphs else "}\n")
         )
         string += "\\label{tab:competing_phase_formation_energies}\n"
-        column_names_string = "Formula" + (" & k-mesh" if kpoints_col else "") + " & $\\Delta E_f$ (eV/fu)"
+        column_names_string = (
+            "Formula & Space Group & E$_{\\textrm{Hull}}$ (eV/atom)"
+            + (" & k-mesh" if kpoints_col else "")
+            + " & $\\Delta E_f$ (eV/fu)"
+        )
 
         if splits == 1:
-            string += "\\begin{tabular}" + ("{ccc}" if kpoints_col else "{cc}") + "\n"
+            string += "\\begin{tabular}" + ("{ccccc}" if kpoints_col else "{cccc}") + "\n"
             string += "\\hline\n"
             string += column_names_string + " \\\\ \\hline \n"
             for i in formation_energy_data:
@@ -2614,13 +2621,17 @@ def to_LaTeX_table(self, splits=1, prune_polymorphs=True):
                     "\\ce{"
                     + i["Formula"]
                     + "}"
+                    + " & "
+                    + latexify_spacegroup(i.get("Space Group", "N/A"))
+                    + " & "
+                    + f"{i['Energy above Hull (eV/atom)']:.3f}"
                     + (f" & {kpoints[0]}$\\times${kpoints[1]}$\\times${kpoints[2]}" if kpoints_col else "")
                     + " & "
                     + f"{fe:.3f} \\\\ \n"
                 )
 
         elif splits == 2:
-            string += "\\begin{tabular}" + ("{ccc|ccc}" if kpoints_col else "{cc|cc}") + "\n"
+            string += "\\begin{tabular}" + ("{ccccc|ccccc}" if kpoints_col else "{cccc|cccc}") + "\n"
             string += "\\hline\n"
             string += column_names_string + " & " + column_names_string + " \\\\ \\hline \n"
 
@@ -2637,6 +2648,10 @@ def to_LaTeX_table(self, splits=1, prune_polymorphs=True):
                     "\\ce{"
                     + i["Formula"]
                     + "}"
+                    + " & "
+                    + latexify_spacegroup(i.get("Space Group", "N/A"))
+                    + " & "
+                    + f"{i['Energy above Hull (eV/atom)']:.3f}"
                     + (
                         f" & {kpoints1[0]}$\\times${kpoints1[1]}$\\times${kpoints1[2]}"
                         if kpoints_col
@@ -2647,6 +2662,10 @@ def to_LaTeX_table(self, splits=1, prune_polymorphs=True):
                     + "\\ce{"
                     + j["Formula"]
                     + "}"
+                    + " & "
+                    + latexify_spacegroup(j.get("Space Group", "N/A"))
+                    + " & "
+                    + f"{j['Energy above Hull (eV/atom)']:.3f}"
                     + (
                         f" & {kpoints2[0]}$\\times${kpoints2[1]}$\\times${kpoints2[2]}"
                         if kpoints_col
@@ -2660,7 +2679,7 @@ def to_LaTeX_table(self, splits=1, prune_polymorphs=True):
         string += "\\end{tabular}\n"
         string += "\\end{table}"
 
-        return string
+        print(string)
 
     def plot_chempot_heatmap(
         self,

examples/chemical_potentials_tutorial.ipynb

@@ -940,8 +940,8 @@
    "metadata": {
     "collapsed": false,
     "ExecuteTime": {
-     "end_time": "2025-01-20T19:25:50.784828Z",
-     "start_time": "2025-01-20T19:25:47.029745Z"
+     "end_time": "2025-01-20T20:02:54.773008Z",
+     "start_time": "2025-01-20T20:02:50.914559Z"
     }
    },
    "id": "643890c87cd24d4f",
@@ -950,11 +950,11 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Parsing vaspruns...: 100%|██████████| 8/8 [00:00<00:00, 91.13it/s]\n"
+      "Parsing vaspruns...: 100%|██████████| 8/8 [00:00<00:00, 87.36it/s]\n"
      ]
     }
    ],
-   "execution_count": 1
+   "execution_count": 2
   },
   {
    "metadata": {},
@@ -1708,37 +1708,40 @@
    "metadata": {
     "collapsed": false,
     "ExecuteTime": {
-     "end_time": "2024-04-10T02:28:18.071044Z",
-     "start_time": "2024-04-10T02:28:18.057524Z"
+     "end_time": "2025-01-20T20:02:58.505508Z",
+     "start_time": "2025-01-20T20:02:58.498220Z"
     }
    },
    "cell_type": "code",
+   "source": [
+    "cpa.to_LaTeX_table()  # we can then copy and paste this into LaTeX\n",
+    "# this also comes with `prune_polymorphs` (True by default) and `splits` options, see docstring for info"
+   ],
+   "id": "cae6d4ecc44dc46c",
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
       "\\begin{table}[h]\n",
       "\\centering\n",
-      "\\caption{Formation energies per formula unit ($\\Delta E_f$) of \\ce{ZrO2} and all competing phases, with k-meshes used in calculations. Only the lowest energy polymorphs are included}\n",
+      "\\caption{Formation energies per formula unit ($\\Delta E_f$) of \\ce{ZrO2} and all competing phases, with k-meshes used in calculations. Only the lowest energy polymorphs are included.}\n",
       "\\label{tab:competing_phase_formation_energies}\n",
-      "\\begin{tabular}{ccc}\n",
+      "\\begin{tabular}{ccccc}\n",
       "\\hline\n",
-      "Formula & k-mesh & $\\Delta E_f$ (eV/fu) \\\\ \\hline \n",
-      "\\ce{ZrO2} & 3$\\times$3$\\times$3 & -10.975 \\\\ \n",
-      "\\ce{O2} & 2$\\times$2$\\times$2 & 0.000 \\\\ \n",
-      "\\ce{Zr} & 9$\\times$9$\\times$5 & 0.000 \\\\ \n",
-      "\\ce{Zr2O} & 5$\\times$5$\\times$2 & -5.729 \\\\ \n",
-      "\\ce{Zr3O} & 5$\\times$5$\\times$5 & -5.987 \\\\ \n",
+      "Formula & Space Group & E$_{\\textrm{Hull}}$ (eV/atom) & k-mesh & $\\Delta E_f$ (eV/fu) \\\\ \\hline \n",
+      "\\ce{ZrO2} & P2$_{1}$/c & 0.000 & 3$\\times$3$\\times$3 & -10.975 \\\\ \n",
+      "\\ce{Zr} & P6$_{3}$/mmc & 0.000 & 9$\\times$9$\\times$5 & 0.000 \\\\ \n",
+      "\\ce{O2} & P4/mmm & 0.000 & 2$\\times$2$\\times$2 & 0.000 \\\\ \n",
+      "\\ce{Zr3O} & R$\\overline{3}$c & 0.000 & 5$\\times$5$\\times$5 & -5.987 \\\\ \n",
+      "\\ce{Zr2O} & P312 & 0.019 & 5$\\times$5$\\times$2 & -5.729 \\\\ \n",
       "\\hline\n",
       "\\end{tabular}\n",
       "\\end{table}\n"
      ]
     }
    ],
-   "execution_count": 4,
-   "source": "cpa.to_LaTeX_table()  # we can then copy and paste this into LaTeX",
-   "id": "cae6d4ecc44dc46c"
+   "execution_count": 3
   },
   {
    "metadata": {},

tests/test_chemical_potentials.py

@@ -19,6 +19,7 @@
 from pymatgen.core.structure import Structure
 from test_analysis import if_present_rm
 from test_plotting import custom_mpl_image_compare
+from test_thermodynamics import _run_func_and_capture_stdout_warnings
 
 from doped import chemical_potentials
 from doped.utils.symmetry import get_primitive_structure
@@ -519,6 +520,7 @@ def test_structure_input(self, api_key):
 class ChemPotAnalyzerTestCase(unittest.TestCase):
     def setUp(self):
         self.EXAMPLE_DIR = os.path.join(cwd, "../examples")
+        self.DATA_DIR = os.path.join(cwd, "data")
         self.stable_system = "ZrO2"
         self.unstable_system = "Zr2O"
         self.extrinsic_species = "La"
@@ -547,6 +549,8 @@ def tearDown(self):
         for i in ["chempot_limits.csv", "CompetingPhases.csv", "input.dat"]:
             if_present_rm(i)
 
+        if_present_rm(os.path.join(self.DATA_DIR, "ZrO2_LaTeX_Tables/text.tex"))
+
     def test_cpa_csv(self):
         stable_cpa = chemical_potentials.CompetingPhasesAnalyzer(self.stable_system)
         stable_cpa.from_csv(self.zro2_csv_path)
@@ -767,53 +771,34 @@ def test_vaspruns_none_parsed(self):
         assert "No vasprun files have been parsed," in str(e.value)
 
     def test_latex_table(self):
-        cpa = chemical_potentials.CompetingPhasesAnalyzer(self.stable_system)
-        cpa.from_vaspruns(path=self.zro2_path, subfolder="relax", csv_path=self.zro2_csv_path)
+        cpa = chemical_potentials.CompetingPhasesAnalyzer(self.stable_system, self.zro2_path)
 
-        string = cpa.to_LaTeX_table(splits=1)
-        assert (
-            string[28:209]
-            == "\\caption{Formation energies per formula unit ($\\Delta E_f$) of \\ce{ZrO2} and all "
-            "competing phases, with k-meshes used in calculations. Only the lowest energy polymorphs "
-            "are included"
-        )
-        assert len(string) == 589
-        assert string.split("hline")[1] == "\nFormula & k-mesh & $\\Delta E_f$ (eV/fu) \\\\ \\"
-        assert string.split("hline")[2][2:45] == "\\ce{ZrO2} & 3$\\times$3$\\times$3 & -10.975 \\"
+        def _test_latex_table(cpa=cpa, ref_filename="default.tex", **kwargs):
+            out, text, w = _run_func_and_capture_stdout_warnings(cpa.to_LaTeX_table, **kwargs)
+            assert not out
+            assert not w
 
-        string = cpa.to_LaTeX_table(splits=2)
-        assert (
-            string[28:209]
-            == "\\caption{Formation energies per formula unit ($\\Delta E_f$) of \\ce{ZrO2} and all "
-            "competing phases, with k-meshes used in calculations. Only the lowest energy polymorphs "
-            "are included"
-        )
-        assert (
-            string.split("hline")[1]
-            == "\nFormula & k-mesh & $\\Delta E_f$ (eV/fu) & Formula & k-mesh & $\\Delta E_f$ ("
-            "eV/fu) \\\\ \\"
-        )
+            with open(f"{self.DATA_DIR}/ZrO2_LaTeX_Tables/test.tex", "w+") as f:
+                f.write(text)
 
-        assert string.split("hline")[2][2:45] == "\\ce{ZrO2} & 3$\\times$3$\\times$3 & -10.975 &"
-        assert len(string) == 586
+            with (
+                open(f"{self.DATA_DIR}/ZrO2_LaTeX_Tables/{ref_filename}") as reference_f,
+                open(f"{self.DATA_DIR}/ZrO2_LaTeX_Tables/test.tex") as test_f,
+            ):
+                assert reference_f.read() == test_f.read()
 
-        # test without kpoints:
-        for entry_dict in cpa.data:
-            entry_dict.pop("k-points")
-        string = cpa.to_LaTeX_table(splits=1)
-        assert (
-            string[28:173]
-            == "\\caption{Formation energies per formula unit ($\\Delta E_f$) of \\ce{ZrO2} and all "
-            "competing phases. Only the lowest energy polymorphs are included"
-        )
-        assert len(string) == 433
-        assert string.split("hline")[1] == "\nFormula & $\\Delta E_f$ (eV/fu) \\\\ \\"
-        assert string.split("hline")[2][2:23] == "\\ce{ZrO2} & -10.975 \\"
+        for kwargs, ref_filename in [
+            ({}, "default.tex"),
+            ({"splits": 2}, "splits_2.tex"),
+            ({"prune_polymorphs": False}, "no_prune.tex"),
+        ]:
+            _test_latex_table(ref_filename=ref_filename, **kwargs)
+
+        la_cpa = chemical_potentials.CompetingPhasesAnalyzer(self.stable_system, self.la_zro2_path)
+        _test_latex_table(la_cpa, "la_default.tex")
 
-        cpa_csv = chemical_potentials.CompetingPhasesAnalyzer(self.stable_system)
-        cpa_csv.from_csv(self.zro2_csv_path)
         with pytest.raises(ValueError):
-            cpa_csv.to_LaTeX_table(splits=3)
+            cpa.to_LaTeX_table(splits=3)
 
     def test_to_csv(self):
         self.tearDown()  # clear out previous csvs