{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "import h5py\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Explore the options used in the solver"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<KeysViewHDF5 ['cuda', 'hdf5file', 'opt', 'qmctorch_version', 'sampler', 'save_model', 'wf']>\n"
     ]
    }
   ],
   "source": [
    "with h5py.File('./hdf5/H2_adf_dzp_QMCTorch.hdf5', 'r') as f5:\n",
    "    print(f5['Solver'].keys())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<KeysViewHDF5 ['ao', 'atoms', 'configs', 'configs_method', 'cuda', 'fc', 'gradients', 'highest_occ_mo', 'include_all_mo', 'jastrow', 'jastrow_type', 'kinetic', 'kinetic_energy', 'kinetic_method', 'mo', 'mol', 'natom', 'nci', 'ndim', 'ndim_tot', 'nelec', 'nmo_opt', 'orb_confs', 'pool', 'training', 'use_backflow', 'use_jastrow']>\n"
     ]
    }
   ],
   "source": [
    "with h5py.File('./hdf5/H2_adf_dzp_QMCTorch.hdf5', 'r') as f5:\n",
    "    print(f5['Solver']['wf'].keys())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "b'single_double(2,2)'\n"
     ]
    }
   ],
   "source": [
    "with h5py.File('./hdf5/H2_adf_dzp_QMCTorch.hdf5', 'r') as f5:\n",
    "    print(f5['Solver']['wf']['configs_method'][()])"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Explore the results of the wave function optimization"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<KeysViewHDF5 ['ao.bas_exp', 'energy', 'fc.weight', 'geometry', 'jastrow.jastrow_kernel.weight', 'local_energy', 'mo.mo_modifier', 'models', 'qmctorch_version']>\n"
     ]
    }
   ],
   "source": [
    "with h5py.File('./hdf5/H2_adf_dzp_QMCTorch.hdf5', 'r') as f5:\n",
    "    print(f5['wf_opt'].keys())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "with h5py.File('./hdf5/H2_adf_dzp_QMCTorch.hdf5', 'r') as f5:\n",
    "    det_weigts = f5['wf_opt']['fc.weight'][()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x743fd87eddc0>,\n",
       " <matplotlib.lines.Line2D at 0x743fd87ede20>,\n",
       " <matplotlib.lines.Line2D at 0x743fd87ede50>,\n",
       " <matplotlib.lines.Line2D at 0x743fd87edf40>]"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(det_weigts.squeeze())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "qmctorch",
   "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": "3.8.0"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}