{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Experiment emulators"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np \n",
    "\n",
    "from olympus import Emulator\n",
    "from olympus import list_trained_emulators"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['wf3_NeuralNet', 'hplc_BayesNeuralNet', 'snar_BayesNeuralNet', 'n9_NeuralNet', 'hplc_NeuralNet', 'suzuki_BayesNeuralNet', 'bob_NeuralNet', 'pce10_BayesNeuralNet', 'fullerenes_BayesNeuralNet', 'alkox_NeuralNet', 'benzylation_NeuralNet', 'fullerenes_NeuralNet', 'alkox_BayesNeuralNet', 'snar_NeuralNet', 'n9_BayesNeuralNet', 'suzuki_NeuralNet', 'benzylation_BayesNeuralNet', 'pce10_NeuralNet', 'bob_BayesNeuralNet', 'wf3_BayesNeuralNet']\n"
     ]
    }
   ],
   "source": [
    "# checking trained emulators\n",
    "print(list_trained_emulators())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Here we will use `alkox_BayesNeuralNet`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[0;37m[INFO] Loading emulator using a BayesNeuralNet model for the dataset alkox...\n",
      "\u001b[0m"
     ]
    }
   ],
   "source": [
    "# initialize emulator\n",
    "emulator = Emulator(dataset='alkox', model='BayesNeuralNet')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<Emulator (Dataset(kind=alkox), model=\n",
      "--> batch_size:    50\n",
      "--> es_patience:   100\n",
      "--> hidden_act:    leaky_relu\n",
      "--> hidden_depth:  3\n",
      "--> hidden_nodes:  96\n",
      "--> kind:          BayesNeuralNet\n",
      "--> learning_rate: 0.001\n",
      "--> max_epochs:    100000\n",
      "--> out_act:       relu\n",
      "--> pred_int:      100\n",
      "--> reg:           0.01\n",
      "--> scope:         model)>\n"
     ]
    }
   ],
   "source": [
    "# print emulator information\n",
    "print(emulator)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "maximize\n"
     ]
    }
   ],
   "source": [
    "# check on goal\n",
    "print(emulator.get_goal())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[56.3565859]]\n"
     ]
    }
   ],
   "source": [
    "# run single prediction\n",
    "params = np.zeros(4)\n",
    "values = emulator.run(params)\n",
    "print(values)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[47.04858576]\n",
      " [35.74277879]\n",
      " [20.47608956]]\n"
     ]
    }
   ],
   "source": [
    "# run multiple predictions\n",
    "params = [np.zeros(4) + 0.0, \n",
    "          np.zeros(4) + 0.5, \n",
    "          np.zeros(4) + 1.0]\n",
    "values = emulator.run(params, num_samples = 5)\n",
    "print(values)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "olympus",
   "language": "python",
   "name": "olympus"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}