{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [],
   "source": [
    "import qml "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {},
   "outputs": [],
   "source": [
    "from glob import glob\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [],
   "source": [
    "from rdkit import Chem"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "metadata": {},
   "outputs": [],
   "source": [
    "def read_sdf(sdf):\n",
    "    with open(sdf, \"r\") as f:\n",
    "        txt = f.read().rstrip()\n",
    "    return txt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_ncharges_coords(sdf):\n",
    "    mol = Chem.MolFromMolBlock(sdf)\n",
    "   #mol = Chem.AddHs(mol)\n",
    "    # rdkit molobj\n",
    "    ncharges = [atom.GetAtomicNum() for atom in mol.GetAtoms()]\n",
    "    conf = mol.GetConformer()\n",
    "    coords = np.asarray(conf.GetPositions())\n",
    "    return ncharges, coords"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['targets/qm9.sdf', 'targets/vitc.sdf', 'targets/vitd.sdf']"
      ]
     },
     "execution_count": 74,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "target_sdfs = sorted(glob(\"targets/*.sdf\"))\n",
    "target_sdfs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {},
   "outputs": [],
   "source": [
    "qm9_amons_files = sorted(glob(\"amons-qm9/*.sdf\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "metadata": {},
   "outputs": [],
   "source": [
    "qm9_amons_sdfs = [read_sdf(x) for x in qm9_amons_files]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "metadata": {},
   "outputs": [],
   "source": [
    "conf_data = [get_ncharges_coords(x) for x in qm9_amons_sdfs]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "metadata": {},
   "outputs": [],
   "source": [
    "ncharges_list, coords_list = zip(*conf_data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "metadata": {},
   "outputs": [],
   "source": [
    "qm9_ncharges = ncharges_list"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "metadata": {},
   "outputs": [],
   "source": [
    "qm9_reps = [np.array(qml.representations.generate_fchl_acsf(\n",
    "                                                ncharges_list[i],\n",
    "                                                coords_list[i],\n",
    "                                                elements=[6,7,8])) for i in \n",
    "       range(len(ncharges_list))]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/puck/anaconda3/envs/aqml/lib/python3.7/site-packages/ipykernel_launcher.py:1: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray\n",
      "  \"\"\"Entry point for launching an IPython kernel.\n"
     ]
    }
   ],
   "source": [
    "qm9_reps = np.array(qm9_reps)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1, 312)"
      ]
     },
     "execution_count": 82,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "qm9_reps[0].shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "metadata": {},
   "outputs": [],
   "source": [
    "qm9_amons_labels = [t.split(\"/\")[-1].split(\".sdf\")[0] for t in qm9_amons_files]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "metadata": {},
   "outputs": [],
   "source": [
    "vitc_amons_files = sorted(glob(\"amons-vitc/*.sdf\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "metadata": {},
   "outputs": [],
   "source": [
    "vitc_amons_sdfs = [read_sdf(x) for x in vitc_amons_files]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "metadata": {},
   "outputs": [],
   "source": [
    "conf_data = [get_ncharges_coords(x) for x in vitc_amons_sdfs]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "metadata": {},
   "outputs": [],
   "source": [
    "ncharges_list, coords_list = zip(*conf_data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "metadata": {},
   "outputs": [],
   "source": [
    "vitc_ncharges = ncharges_list"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "metadata": {},
   "outputs": [],
   "source": [
    "vitc_reps = [np.array(qml.representations.generate_fchl_acsf(\n",
    "                                                ncharges_list[i],\n",
    "                                                coords_list[i],\n",
    "                                                elements=[6,8])) for i in \n",
    "            range(len(ncharges_list))]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/puck/anaconda3/envs/aqml/lib/python3.7/site-packages/ipykernel_launcher.py:1: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray\n",
      "  \"\"\"Entry point for launching an IPython kernel.\n"
     ]
    }
   ],
   "source": [
    "vitc_reps = np.array(vitc_reps)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "metadata": {},
   "outputs": [],
   "source": [
    "vitc_amons_labels = [t.split(\"/\")[-1].split(\".sdf\")[0] for t in vitc_amons_files]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "metadata": {},
   "outputs": [],
   "source": [
    "vitd_amons_files = sorted(glob(\"amons-vitd/*.sdf\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "metadata": {},
   "outputs": [],
   "source": [
    "vitd_amons_sdfs = [read_sdf(x) for x in vitd_amons_files]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "metadata": {},
   "outputs": [],
   "source": [
    "conf_data = [get_ncharges_coords(x) for x in vitd_amons_sdfs]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "metadata": {},
   "outputs": [],
   "source": [
    "ncharges_list, coords_list = zip(*conf_data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "metadata": {},
   "outputs": [],
   "source": [
    "vitd_ncharges = ncharges_list"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "metadata": {},
   "outputs": [],
   "source": [
    "vitd_reps = [np.array(qml.representations.generate_fchl_acsf(\n",
    "                                                ncharges_list[i],\n",
    "                                                coords_list[i],\n",
    "                                                elements=[6,8])) for i \n",
    "            in range(len(ncharges_list))]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/puck/anaconda3/envs/aqml/lib/python3.7/site-packages/ipykernel_launcher.py:1: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray\n",
      "  \"\"\"Entry point for launching an IPython kernel.\n"
     ]
    }
   ],
   "source": [
    "vitd_reps = np.array(vitd_reps)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "metadata": {},
   "outputs": [],
   "source": [
    "vitd_amons_labels = [t.split(\"/\")[-1].split(\".sdf\")[0] for t in vitd_amons_files]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [],
   "source": [
    "# np save "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "metadata": {},
   "outputs": [],
   "source": [
    "np.savez(\"amons_FCHL_data.npz\", \n",
    "         vitd_amons_labels=vitd_amons_labels,\n",
    "         vitc_amons_labels=vitc_amons_labels,\n",
    "         qm9_amons_labels=qm9_amons_labels,\n",
    "         vitd_amons_ncharges=vitd_ncharges,\n",
    "         vitc_amons_ncharges=vitc_ncharges,\n",
    "         qm9_amons_ncharges=qm9_ncharges,\n",
    "         vitd_amons_reps=vitd_reps,\n",
    "         vitc_amons_reps=vitc_reps,\n",
    "         qm9_amons_reps=qm9_reps)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1, 168)"
      ]
     },
     "execution_count": 101,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "vitd_reps[0].shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.7.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}