{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-12-23T15:38:53.675876Z",
     "start_time": "2018-12-23T15:38:53.616738Z"
    }
   },
   "outputs": [],
   "source": [
    "%reload_ext autoreload\n",
    "%autoreload 2\n",
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\",category =RuntimeWarning)\n",
    "import numpy as np\n",
    "import de2 as de\n",
    "import multiprocessing as mp\n",
    "import makeqx as mkq\n",
    "import oldqx as oqx\n",
    "\n",
    "\n",
    "def rndtop5(x):\n",
    "    return np.round(x*2.0)/2\n",
    "\n",
    "def tmm_wrapper2(arg):\n",
    "    args, kwargs = arg\n",
    "    return oqx.tmm_eval_wsweep(*args, **kwargs)\n",
    "\n",
    "def arc_par(pop, **kwargs):\n",
    "    jobs = []\n",
    "    pool=mp.Pool(90)\n",
    "    for indiv in pop:\n",
    "        #indiv = indiv.reshape((int(indiv.size/2), 2))\n",
    "        #indiv[:,1] = mkq.digitize_qx(indiv[:,1], dlevels=2)\n",
    "        indiv = rndtop5(indiv)\n",
    "        #indiv = indiv.flatten()\n",
    "        jobs.append((indiv, 0))\n",
    "    arg = [(j, kwargs) for j in jobs]\n",
    "    answ = np.array(pool.map(tmm_wrapper2, arg))\n",
    "    pool.close()\n",
    "    return answ\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-12-23T19:14:28.407811Z",
     "start_time": "2018-12-23T18:48:13.609264Z"
    }
   },
   "outputs": [],
   "source": [
    "dataset_size = 200000\n",
    "\n",
    "# parameters of the dataset\n",
    "num_layers = 16\n",
    "num_lpoints = 128\n",
    "# lam_min = 400.0\n",
    "# lam_max = 800.0\n",
    "d_min = 0.5\n",
    "d_max = 100\n",
    "\n",
    "lam_min = 400.0  # this is lam/d\n",
    "lam_max = 800.0       # this is lam/d\n",
    "\n",
    "lams = np.linspace(lam_min, lam_max, endpoint=True, num=num_lpoints)\n",
    "# lam_inv = np.linspace(1/lam_min, 1/lam_max, num=num_lpoints, endpoint=True)\n",
    "# lams = 1.0/lam_inv\n",
    "\n",
    "\n",
    "#lams = np.linspace(lam_low, lam_high, endpoint=True, num=lam_pts)\n",
    "#lam_inv = np.linspace(1/400.0, 1/800.0, num=num_lpoints, endpoint=True)\n",
    "#lams = 1.0/lam_inv\n",
    "dataset_X = np.random.uniform(0,1,num_layers*dataset_size).astype(float).reshape(dataset_size, num_layers)\n",
    "\n",
    "# for ds in dataset_X:\n",
    "#     ds = ds/np.sum(ds)\n",
    "\n",
    "#lams = np.linspace(lam_min, lam_max, num_lpoints, endpoint=True)\n",
    "dataset_Y = np.zeros((dataset_size,num_lpoints))\n",
    "\n",
    "dataset_Y = arc_par( d_min + (d_max - d_min)*dataset_X,  lam_low=lam_min, lam_high=lam_max, lam_pts = num_lpoints)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-12-23T19:19:42.741175Z",
     "start_time": "2018-12-23T19:19:42.609535Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(0, 100)"
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 460.8x403.2 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "from jupyterthemes import jtplot\n",
    "# currently installed theme will be used to\n",
    "# set plot style if no arguments provided\n",
    "jtplot.style()\n",
    "\n",
    "#plt.plot(dataset_Y[  0  ])\n",
    "plt.plot(lams, dataset_Y[  np.random.randint(0, 1000) ])\n",
    "\n",
    "plt.xlim([400,800])\n",
    "plt.ylim([0, 100])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-12-23T19:20:21.693949Z",
     "start_time": "2018-12-23T19:20:21.551102Z"
    }
   },
   "outputs": [],
   "source": [
    "import h5py\n",
    "h5f = h5py.File('./datasets/s16_d_siti_2.h5', 'w')\n",
    "h5f.create_dataset('sizes', data=dataset_X)\n",
    "h5f.create_dataset('spectrum', data=dataset_Y)\n",
    "h5f.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-12-23T13:34:10.538963Z",
     "start_time": "2018-12-23T13:34:10.522776Z"
    }
   },
   "outputs": [],
   "source": [
    "dataset_X.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-12-23T16:40:22.352387Z",
     "start_time": "2018-12-23T16:40:22.337616Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([400.        , 403.1496063 , 406.2992126 , 409.4488189 ,\n",
       "       412.5984252 , 415.7480315 , 418.8976378 , 422.04724409,\n",
       "       425.19685039, 428.34645669, 431.49606299, 434.64566929,\n",
       "       437.79527559, 440.94488189, 444.09448819, 447.24409449,\n",
       "       450.39370079, 453.54330709, 456.69291339, 459.84251969,\n",
       "       462.99212598, 466.14173228, 469.29133858, 472.44094488,\n",
       "       475.59055118, 478.74015748, 481.88976378, 485.03937008,\n",
       "       488.18897638, 491.33858268, 494.48818898, 497.63779528,\n",
       "       500.78740157, 503.93700787, 507.08661417, 510.23622047,\n",
       "       513.38582677, 516.53543307, 519.68503937, 522.83464567,\n",
       "       525.98425197, 529.13385827, 532.28346457, 535.43307087,\n",
       "       538.58267717, 541.73228346, 544.88188976, 548.03149606,\n",
       "       551.18110236, 554.33070866, 557.48031496, 560.62992126,\n",
       "       563.77952756, 566.92913386, 570.07874016, 573.22834646,\n",
       "       576.37795276, 579.52755906, 582.67716535, 585.82677165,\n",
       "       588.97637795, 592.12598425, 595.27559055, 598.42519685,\n",
       "       601.57480315, 604.72440945, 607.87401575, 611.02362205,\n",
       "       614.17322835, 617.32283465, 620.47244094, 623.62204724,\n",
       "       626.77165354, 629.92125984, 633.07086614, 636.22047244,\n",
       "       639.37007874, 642.51968504, 645.66929134, 648.81889764,\n",
       "       651.96850394, 655.11811024, 658.26771654, 661.41732283,\n",
       "       664.56692913, 667.71653543, 670.86614173, 674.01574803,\n",
       "       677.16535433, 680.31496063, 683.46456693, 686.61417323,\n",
       "       689.76377953, 692.91338583, 696.06299213, 699.21259843,\n",
       "       702.36220472, 705.51181102, 708.66141732, 711.81102362,\n",
       "       714.96062992, 718.11023622, 721.25984252, 724.40944882,\n",
       "       727.55905512, 730.70866142, 733.85826772, 737.00787402,\n",
       "       740.15748031, 743.30708661, 746.45669291, 749.60629921,\n",
       "       752.75590551, 755.90551181, 759.05511811, 762.20472441,\n",
       "       765.35433071, 768.50393701, 771.65354331, 774.80314961,\n",
       "       777.95275591, 781.1023622 , 784.2519685 , 787.4015748 ,\n",
       "       790.5511811 , 793.7007874 , 796.8503937 , 800.        ])"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lams"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "hide_input": false,
  "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": "3.7.0"
  },
  "varInspector": {
   "cols": {
    "lenName": 16,
    "lenType": 16,
    "lenVar": 40
   },
   "kernels_config": {
    "python": {
     "delete_cmd_postfix": "",
     "delete_cmd_prefix": "del ",
     "library": "var_list.py",
     "varRefreshCmd": "print(var_dic_list())"
    },
    "r": {
     "delete_cmd_postfix": ") ",
     "delete_cmd_prefix": "rm(",
     "library": "var_list.r",
     "varRefreshCmd": "cat(var_dic_list()) "
    }
   },
   "types_to_exclude": [
    "module",
    "function",
    "builtin_function_or_method",
    "instance",
    "_Feature"
   ],
   "window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}