dscribe and sklearn added under def, similarity_threshold set to .999 - tested vs example problem poscar

Author: efako

autoadsorbate/utils.py

@@ -641,7 +641,7 @@ def _filter_unique_sites_by_soap(
     site_df: pd.DataFrame,
     cutoff: float = 5.0,
     soap_params: dict = None,
-    similarity_threshold: float = 0.98
+    similarity_threshold: float = 0.999
 ) -> pd.DataFrame:
 
     """

scripts/aads_2025.ipynb

@@ -10,7 +10,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "id": "1b3f770d-d1a5-4498-a508-be4469a8970c",
    "metadata": {},
    "outputs": [],
@@ -21,7 +21,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 4,
    "id": "cd5c4cd6-d15b-4ad3-89b0-200610d1c960",
    "metadata": {},
    "outputs": [],
@@ -32,8 +32,8 @@
     "from ase.build.tools import sort as sort_atoms\n",
     "from matplotlib import colors as mcolors\n",
     "\n",
-    "import sys\n",
-    "sys.path.insert(0, '/home/djrm/git/hetcattoolbox')\n",
+    "# import sys\n",
+    "# sys.path.insert(0, '/home/djrm/git/hetcattoolbox')\n",
     "\n",
     "from glob import glob\n",
     "import pandas as pd\n",
@@ -45,7 +45,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 5,
    "id": "67a98c50-f0d3-49e4-a4d8-183afe68d572",
    "metadata": {},
    "outputs": [],
@@ -1842,6 +1842,60 @@
     "    minhop_trj+=read(file, index=':')\n",
     "len(minhop_trj)"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "381b0ed8",
+   "metadata": {},
+   "source": [
+    "### sym reduce debug"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "325fe48d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "len(s.site_df) = 72\n",
+      "len(xdf) = 3\n"
+     ]
+    }
+   ],
+   "source": [
+    "from pymatgen.core import Structure\n",
+    "from pymatgen.io.ase import AseAtomsAdaptor\n",
+    "from autoadsorbate.utils import _filter_unique_sites_by_soap\n",
+    "\n",
+    "structure = Structure.from_file(\"POSCAR\")\n",
+    "atoms = AseAtomsAdaptor.get_atoms(structure)\n",
+    "\n",
+    "s = Surface(atoms)\n",
+    "print(f'{len(s.site_df) = }')\n",
+    "\n",
+    "xdf = _filter_unique_sites_by_soap(s.atoms, s.site_df, similarity_threshold=0.999)\n",
+    "print(f'{len(xdf) = }')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1a1d5378",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5b99231b",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {