{ "cells": [ { "cell_type": "code", "execution_count": 14, "id": "9391dbcb", "metadata": {}, "outputs": [], "source": [ "import ase\n", "from ase import io\n", "import numpy as np\n", "import chemiscope\n", "import pandas as pd" ] }, { "cell_type": "code", "execution_count": 15, "id": "10fb366f", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
refcodemetaltotal_chargespin_multiplicityelem_nrm_oxd_elecCNgeometryrel_m
0KIPLIHCr0124055Square pyramidal0.836
1AYIZISCr0124056Octahedral0.848
2MISLABCr0124056Octahedral0.859
3KOQBATCr0124056Octahedral0.860
4VOWRAACr-1124056Octahedral0.856
\n", "
" ], "text/plain": [ " refcode metal total_charge spin_multiplicity elem_nr m_ox d_elec CN \\\n", "0 KIPLIH Cr 0 1 24 0 5 5 \n", "1 AYIZIS Cr 0 1 24 0 5 6 \n", "2 MISLAB Cr 0 1 24 0 5 6 \n", "3 KOQBAT Cr 0 1 24 0 5 6 \n", "4 VOWRAA Cr -1 1 24 0 5 6 \n", "\n", " geometry rel_m \n", "0 Square pyramidal 0.836 \n", "1 Octahedral 0.848 \n", "2 Octahedral 0.859 \n", "3 Octahedral 0.860 \n", "4 Octahedral 0.856 " ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_1 = pd.read_csv(\"property_2063.txt\",sep='\\t')\n", "df_1.head()" ] }, { "cell_type": "code", "execution_count": 16, "id": "64c2e198", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/home/ruben/anaconda3/lib/python3.8/site-packages/chemiscope/structures.py:278: UserWarning: the following structure properties properties are only defined for a subset of frames: ['-1', '-2', '-3', '-4', '-5', '0', '1', '2', '3', '4', '5', '6']; they will be ignored\n", " warnings.warn(\n" ] } ], "source": [ "mols_1 = []\n", "for structure in df_1[\"refcode\"]:\n", " mols_1.append(ase.io.read(f\"Ground_state_spin_dataset/{structure}.xyz\"))\n", "\n", "properties_1 = {}\n", "for key in df_1.keys():\n", " #print(key)\n", " units = None\n", " if key == \"refcode\" or key == \"name\":\n", " continue\n", "\n", " if \"total_charge\" in key:\n", " units = \"\"\n", "\n", " if \"spin_multiplicity\" in key:\n", " units = \"\"\n", "\n", " if \"elem_nr\" in key:\n", " units = \"\"\n", "\n", " if key == \"m_ox\":\n", " units = \"\"\n", "\n", " if key == \"d_elec\":\n", " units = \"electrons\"\n", " \n", " if key == \"CN\":\n", " units == \"\"\n", " \n", " if key == \"rel_m\":\n", " units == \"\"\n", " \n", " if units is not None:\n", " keydict = {\n", " \"target\": \"structure\",\n", " \"values\": df_1[f\"{key}\"].to_list(),\n", " \"units\": f\"{units}\",\n", " }\n", " else:\n", " continue\n", " properties_1[f\"{key}\"] = keydict\n", "\n", "chemiscope.write_input(\n", " path=f\"Ground_state_spin_dataset_chemiscope.json.gz\",\n", " frames=mols_1,\n", " properties=properties_1,\n", ")" ] }, { "cell_type": "code", "execution_count": 17, "id": "b3086ad5", "metadata": {}, "outputs": [], "source": [ "widget = chemiscope.show(mols_1, properties_1)" ] }, { "cell_type": "code", "execution_count": 18, "id": "098c19d3", "metadata": {}, "outputs": [ { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "0518e2ae986c45c5a2bb39b279944cd7", "version_major": 2, "version_minor": 0 }, "text/plain": [ "ChemiscopeWidget(value=None, data='{\"meta\": {\"name\": \" \"}, \"structures\": [{\"size\": 59, \"names\": [\"Cr\", \"O\", \"O…" ] }, "execution_count": 18, "metadata": {}, "output_type": "execute_result" } ], "source": [ "widget" ] }, { "cell_type": "code", "execution_count": 19, "id": "b707bb27", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
refcodemetaltotal_chargespin_multiplicityelem_nrm_oxd_elechapticity
0DIDSEQSc012130False
1EZUYUWSc012130False
2NURLAQSc012130False
3ZIGKOSSc012130False
4ACOJADTi032222False
\n", "
" ], "text/plain": [ " refcode metal total_charge spin_multiplicity elem_nr m_ox d_elec \\\n", "0 DIDSEQ Sc 0 1 21 3 0 \n", "1 EZUYUW Sc 0 1 21 3 0 \n", "2 NURLAQ Sc 0 1 21 3 0 \n", "3 ZIGKOS Sc 0 1 21 3 0 \n", "4 ACOJAD Ti 0 3 22 2 2 \n", "\n", " hapticity \n", "0 False \n", "1 False \n", "2 False \n", "3 False \n", "4 False " ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_2 = pd.read_csv(\"property_1838.txt\",sep='\\t')\n", "df_2.head()" ] }, { "cell_type": "code", "execution_count": 20, "id": "d5b4015f", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/home/ruben/anaconda3/lib/python3.8/site-packages/chemiscope/structures.py:278: UserWarning: the following structure properties properties are only defined for a subset of frames: ['-1', '-2', '-3', '-4', '0', '1', '2', '3', '4', '5', '6']; they will be ignored\n", " warnings.warn(\n" ] } ], "source": [ "mols_2 = []\n", "for structure in df_2[\"refcode\"]:\n", " mols_2.append(ase.io.read(f\"Supplementary_dataset/{structure}.xyz\"))\n", "\n", "properties_2 = {}\n", "for key in df_2.keys():\n", " #print(key)\n", " units = None\n", " if key == \"refcode\" or key == \"name\":\n", " continue\n", "\n", " if \"total_charge\" in key:\n", " units = \"\"\n", "\n", " if \"spin_multiplicity\" in key:\n", " units = \"\"\n", "\n", " if \"elem_nr\" in key:\n", " units = \"\"\n", "\n", " if key == \"m_ox\":\n", " units = \"\"\n", "\n", " if key == \"d_elec\":\n", " units = \"electrons\"\n", " \n", " if key == \"CN\":\n", " units == \"\"\n", " \n", " if key == \"rel_m\":\n", " units == \"\"\n", " \n", " if key == \"hapticity\":\n", " units == \"\"\n", " \n", " if key == \"hapttype\":\n", " units == \"\"\n", " \n", " if units is not None:\n", " keydict = {\n", " \"target\": \"structure\",\n", " \"values\": df_2[f\"{key}\"].to_list(),\n", " \"units\": f\"{units}\",\n", " }\n", " else:\n", " continue\n", " properties_2[f\"{key}\"] = keydict\n", "\n", "chemiscope.write_input(\n", " path=f\"Supplementary_dataset_chemiscope.json.gz\",\n", " frames=mols_2,\n", " properties=properties_2,\n", ")" ] }, { "cell_type": "code", "execution_count": null, "id": "5cb2d443", "metadata": {}, "outputs": [], "source": [ "\n", "\n" ] }, { "cell_type": "code", "execution_count": null, "id": "e7ffde49", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "fa7105fc", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "447712c8", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "8226984d", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "5db74c86", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "fdbdec69", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "9e3956fe", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "a61b141f", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "8458cc7f", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "dad0267d", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "02ad7df5", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "22b2a8c0", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "b3f6c7c0", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "6818d8c3", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "a387fbed", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "1b5e7e8a", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "cf083db1", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.8.13" } }, "nbformat": 4, "nbformat_minor": 5 }