Updated oxidation.py and its tests

.pre-commit-config.yaml

@@ -52,7 +52,7 @@ repos:
     rev: v2.3.0
     hooks:
       - id: codespell
-        stages: [commit, commit-msg]
+        stages: [pre-commit, commit-msg]
         args: [--toml, pyproject.toml]
         additional_dependencies:
           - tomli

smact/tests/files/oxidation_states_icsd24_consensus.txt

@@ -0,0 +1,109 @@
+#
+# Oxidation state set
+# Source: ICSD (2024), filtered for low commonality of reports
+#
+# Testing writing of ICSD 24 oxidation states list.
+#
+H -1 1
+He
+Li 1
+Be 2
+B -5 -3 -2 -1 1 2 3
+C -4 -3 -2 -1 1 2 3 4
+N -5 -4 -3 -2 -1 1 2 3 4 5
+O -2 -1 2
+F -1
+Ne
+Na 1
+Mg 2
+Al -3 3
+Si -4 -3 -2 -1 1 2 3 4
+P -4 -3 -2 -1 1 2 3 4 5
+S -2 -1 1 2 3 4 5 6
+Cl -1 1 3 4 5 7
+Ar
+K 1
+Ca 1 2
+Sc 1 2 3
+Ti 1 2 3 4
+V 1 2 3 4 5
+Cr 1 2 3 4 5 6
+Mn -1 1 2 3 4 5 6 7
+Fe -4 1 2 3 4 5 6
+Co -1 1 2 3 4 5
+Ni 1 2 3 4
+Cu 1 2 3 4
+Zn 1 2 3 4
+Ga -4 -3 1 2 3 4
+Ge -4 -3 -2 -1 1 2 3 4
+As -3 -2 -1 1 2 3 4 5
+Se -2 -1 1 2 3 4 5 6
+Br -1 1 3 5 7
+Kr 2
+Rb 1
+Sr 2 4
+Y 1 2 3 4
+Zr 1 2 3 4
+Nb 1 2 3 4 5 6
+Mo -1 1 2 3 4 5 6 7
+Tc 1 2 3 4 5 6 7
+Ru -1 1 2 3 4 5 6 7
+Rh -1 1 2 3 4 5
+Pd 1 2 3 4
+Ag 1 2 3
+Cd 1 2
+In -3 -2 -1 1 2 3
+Sn -4 -3 -2 -1 1 2 3 4
+Sb -3 -2 -1 1 2 3 4 5
+Te -3 -2 -1 1 2 3 4 5 6
+I -1 1 3 5 7
+Xe 2 4 6 8
+Cs 1
+Ba 2
+La 1 2 3 4
+Ce 2 3 4
+Pr 2 3 4
+Nd 2 3 4 5
+Pm 3
+Sm 2 3 4
+Eu 2 3 4 6
+Gd 2 3 4
+Tb 1 2 3 4
+Dy 2 3 4
+Ho 2 3
+Er 2 3 4
+Tm 2 3
+Yb 2 3 4
+Lu 2 3
+Hf 2 3 4
+Ta 1 2 3 4 5 6
+W 2 3 4 5 6
+Re 1 2 3 4 5 6 7
+Os 1 2 3 4 5 6 7 8
+Ir 1 2 3 4 5 6
+Pt -2 1 2 3 4 5 6
+Au -1 1 2 3 5
+Hg 1 2
+Tl -2 -1 1 2 3
+Pb -4 -1 1 2 3 4
+Bi -3 -2 -1 1 2 3 4 5
+Po 4
+At
+Rn
+Fr
+Ra 2
+Ac 3
+Th 2 3 4 5
+Pa 3 4 5
+U 2 3 4 5 6
+Np 2 3 4 5 6 7
+Pu 2 3 4 5 6 7
+Am 2 3 4 5 6
+Cm 3 4
+Bk 3 4
+Cf 3
+Es 3
+Fm
+Md
+No
+Lr

smact/tests/files/oxidation_states_icsd24_consensus_w_0.txt

@@ -0,0 +1,111 @@
+#
+# Oxidation state set
+# Source: ICSD (2024), filtered for low commonality of reports
+#
+# Testing writing of ICSD 24 oxidation states list.
+#
+# Includes oxidation state 0
+#
+H -1 0 1
+He 0
+Li 0 1
+Be 0 2
+B -5 -3 -2 -1 0 1 2 3
+C -4 -3 -2 -1 0 1 2 3 4
+N -5 -4 -3 -2 -1 0 1 2 3 4 5
+O -2 -1 0 2
+F -1 0
+Ne 0
+Na 0 1
+Mg 0 2
+Al -3 0 3
+Si -4 -3 -2 -1 0 1 2 3 4
+P -4 -3 -2 -1 0 1 2 3 4 5
+S -2 -1 0 1 2 3 4 5 6
+Cl -1 0 1 3 4 5 7
+Ar 0
+K 0 1
+Ca 0 1 2
+Sc 0 1 2 3
+Ti 0 1 2 3 4
+V 0 1 2 3 4 5
+Cr 0 1 2 3 4 5 6
+Mn -1 0 1 2 3 4 5 6 7
+Fe -4 0 1 2 3 4 5 6
+Co -1 0 1 2 3 4 5
+Ni 0 1 2 3 4
+Cu 0 1 2 3 4
+Zn 0 1 2 3 4
+Ga -4 -3 0 1 2 3 4
+Ge -4 -3 -2 -1 0 1 2 3 4
+As -3 -2 -1 0 1 2 3 4 5
+Se -2 -1 0 1 2 3 4 5 6
+Br -1 0 1 3 5 7
+Kr 0 2
+Rb 0 1
+Sr 0 2 4
+Y 0 1 2 3 4
+Zr 0 1 2 3 4
+Nb 0 1 2 3 4 5 6
+Mo -1 0 1 2 3 4 5 6 7
+Tc 0 1 2 3 4 5 6 7
+Ru -1 0 1 2 3 4 5 6 7
+Rh -1 0 1 2 3 4 5
+Pd 0 1 2 3 4
+Ag 0 1 2 3
+Cd 0 1 2
+In -3 -2 -1 0 1 2 3
+Sn -4 -3 -2 -1 0 1 2 3 4
+Sb -3 -2 -1 0 1 2 3 4 5
+Te -3 -2 -1 0 1 2 3 4 5 6
+I -1 0 1 3 5 7
+Xe 0 2 4 6 8
+Cs 0 1
+Ba 0 2
+La 0 1 2 3 4
+Ce 0 2 3 4
+Pr 0 2 3 4
+Nd 0 2 3 4 5
+Pm 3
+Sm 0 2 3 4
+Eu 0 2 3 4 6
+Gd 0 2 3 4
+Tb 0 1 2 3 4
+Dy 0 2 3 4
+Ho 0 2 3
+Er 0 2 3 4
+Tm 0 2 3
+Yb 0 2 3 4
+Lu 0 2 3
+Hf 0 2 3 4
+Ta 0 1 2 3 4 5 6
+W 0 2 3 4 5 6
+Re 0 1 2 3 4 5 6 7
+Os 0 1 2 3 4 5 6 7 8
+Ir 0 1 2 3 4 5 6
+Pt -2 0 1 2 3 4 5 6
+Au -1 0 1 2 3 5
+Hg 0 1 2
+Tl -2 -1 0 1 2 3
+Pb -4 -1 0 1 2 3 4
+Bi -3 -2 -1 0 1 2 3 4 5
+Po 0 4
+At
+Rn
+Fr
+Ra 2
+Ac 3
+Th 0 2 3 4 5
+Pa 0 3 4 5
+U 0 2 3 4 5 6
+Np 0 2 3 4 5 6 7
+Pu 0 2 3 4 5 6 7
+Am 0 2 3 4 5 6
+Cm 0 3 4
+Bk 0 3 4
+Cf 0 3
+Es 3
+Fm
+Md
+No
+Lr

smact/tests/test_utils.py

@@ -163,8 +163,8 @@ def test_download_compounds_with_mp_api(self):
 
 
 files_dir = os.path.join(os.path.dirname(os.path.realpath(__file__)), "files")
-TEST_ICSD_OX_STATES = os.path.join(files_dir, "test_icsd_oxidation_states_filter_1000.txt")
-TEST_ICSD_OX_STATES_W_ZERO = os.path.join(files_dir, "test_icsd_oxidation_states_filter_1000_w_0_ox_state.txt")
+TEST_ICSD_OX_STATES = os.path.join(files_dir, "oxidation_states_icsd24_consensus.txt")
+TEST_ICSD_OX_STATES_W_ZERO = os.path.join(files_dir, "oxidation_states_icsd24_consensus_w_0.txt")
 
 
 class OxidationStatesTest(unittest.TestCase):
@@ -178,43 +178,95 @@ def setUp(self):
     def test_oxidation_states_filter(self):
         self.assertIsInstance(self.ox_filter.ox_states_df, pd.DataFrame)
         threshold = 10
-        filtered_df = self.ox_filter.filter(threshold)
+        filtered_df = self.ox_filter.filter(consensus=threshold)
 
         self.assertIsInstance(filtered_df, pd.DataFrame)
         self.assertEqual(filtered_df.columns.tolist(), ["element", "oxidation_state"])
-        # self.assertEqual(filtered_df.loc[""])
 
     def test_oxidation_states_write(self):
-        threshold = 1000
+        self.maxDiff = None
+
         filename = "test_ox_states"
-        filename_w_zero = "test_ox_states_w_zero"
         comment = "Testing writing of ICSD 24 oxidation states list."
-        self.ox_filter.write(filename, threshold, comment=comment)
-        self.ox_filter.write(filename_w_zero, threshold, include_zero=True, comment=comment)
+        self.ox_filter.write(
+            filename,
+            comment=comment,
+            consensus=3,
+            include_zero=False,
+            commonality="low",
+        )
+
         self.assertTrue(os.path.exists(f"{filename}.txt"))
+        # Read the file and check its content
         with open(f"{filename}.txt") as f:
-            self.assertEqual(f.read(), self.test_ox_states)
-
-        self.assertTrue(os.path.exists(f"{filename}_w_zero.txt"))
-        with open(f"{filename}_w_zero.txt") as f:
-            self.assertEqual(f.read(), self.test_ox_states_w_zero)
-        # Clean up
+            content = f.read()
+        # Check if the comment is included in the file
+        self.assertIn(comment, content)
+        # Check if the file content matches the expected content
+        self.assertEqual(content, self.test_ox_states)
         os.remove(f"{filename}.txt")
-        os.remove(f"{filename}_w_zero.txt")
 
-    def test_oxidation_states_filter_species_list(self):
-        for threshold, length in [(0, 490), (5, 358), (50, 227)]:
-            species_list = self.ox_filter.get_species_list(threshold)
-            self.assertIsInstance(species_list, list)
-            self.assertEqual(len(species_list), length)
+        filename_w_zero = "test_ox_states_w_zero"
+        comment = "Testing writing of ICSD 24 oxidation states list."
+        self.ox_filter.write(
+            filename_w_zero,
+            comment=comment,
+            consensus=3,
+            include_zero=True,
+            commonality="low",
+        )
+
+        self.assertTrue(os.path.exists(f"{filename_w_zero}.txt"))
+        # Read the file and check its content
+        with open(f"{filename_w_zero}.txt") as f:
+            content = f.read()
+        # Check if the comment is included in the file
+        self.assertIn(comment, content)
+        # Check if the file content matches the expected content
+        self.assertEqual(content, self.test_ox_states_w_zero)
+        os.remove(f"{filename_w_zero}.txt")
+
+    def test_get_species_list(self):
+        # Test with default parameters
+        species_list = self.ox_filter.get_species_list()
+        self.assertIsInstance(species_list, list)
+        self.assertGreater(len(species_list), 0)  # Ensure the list is not empty
+
+        # Test with include_zero=True
+        species_list_with_zero = self.ox_filter.get_species_list(include_zero=True)
+        self.assertIsInstance(species_list_with_zero, list)
+        self.assertGreater(len(species_list_with_zero), 0)
+
+        # Test with include_one_oxidation_state=True
+        species_list_with_one = self.ox_filter.get_species_list(include_one_oxidation_state=True)
+        self.assertIsInstance(species_list_with_one, list)
+        self.assertGreater(len(species_list_with_one), 0)
+
+        # Test with different commonality levels
+        species_list_low = self.ox_filter.get_species_list(commonality="low")
+        self.assertIsInstance(species_list_low, list)
+        self.assertGreater(len(species_list_low), 0)
+
+        species_list_medium = self.ox_filter.get_species_list(commonality="medium")
+        self.assertIsInstance(species_list_medium, list)
+        self.assertGreater(len(species_list_medium), 0)
+
+        species_list_high = self.ox_filter.get_species_list(commonality="high")
+        self.assertIsInstance(species_list_high, list)
+        self.assertGreater(len(species_list_high), 0)
+
+        # Test with a specific consensus threshold
+        species_list_threshold = self.ox_filter.get_species_list(consensus=5)
+        self.assertIsInstance(species_list_threshold, list)
+        self.assertGreater(len(species_list_threshold), 0)
 
     def test_oxidation_states_filter_species_occurrences(self):
-        species_occurrences_df = self.ox_filter.get_species_occurrences_df()
+        species_occurrences_df = self.ox_filter.get_species_occurrences_df(consensus=1)
         self.assertIsInstance(species_occurrences_df, pd.DataFrame)
         self.assertEqual(
             species_occurrences_df.columns.tolist(),
-            ["species", "results_count"],
+            ["element", "species", "results_count", "species_proportion (%)"],
         )
-        self.assertEqual(species_occurrences_df.shape, (490, 2))
+        self.assertEqual(species_occurrences_df.shape, (490, 4))
         self.assertEqual(species_occurrences_df.iloc[0]["species"], "O2-")
         self.assertEqual(species_occurrences_df.iloc[0]["results_count"], 116910)

smact/utils/crystal_space/generate_composition_with_smact.py

@@ -72,7 +72,7 @@ def generate_composition_with_smact(
     # 2. generate all possible stoichiometric combinations
     print("#2. Generating all possible stoichiometric combinations...")
 
-    pool = multiprocessing.Pool(processes=multiprocessing.cpu_count() if num_processes is None else num_processes)
+    pool = multiprocessing.Pool(processes=(multiprocessing.cpu_count() if num_processes is None else num_processes))
     compounds = list(
         tqdm(
             pool.imap_unordered(
@@ -103,11 +103,15 @@ def generate_composition_with_smact(
     ]  # omit elements without Pauling electronegativity (e.g., He, Ne, Ar, ...)
     compounds_pauling = list(itertools.combinations(elements_pauling, num_elements))
 
-    pool = multiprocessing.Pool(processes=multiprocessing.cpu_count() if num_processes is None else num_processes)
+    pool = multiprocessing.Pool(processes=(multiprocessing.cpu_count() if num_processes is None else num_processes))
     results = list(
         tqdm(
             pool.imap_unordered(
-                partial(smact_filter, threshold=max_stoich, oxidation_states_set=oxidation_states_set),
+                partial(
+                    smact_filter,
+                    threshold=max_stoich,
+                    oxidation_states_set=oxidation_states_set,
+                ),
                 compounds_pauling,
             ),
             total=len(compounds_pauling),