{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-10-21T07:56:11.075394Z",
     "start_time": "2018-10-21T07:56:11.041609Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/hegder/anaconda3/lib/python3.7/site-packages/ipyparallel/client/client.py:459: RuntimeWarning: \n",
      "            Controller appears to be listening on localhost, but not on this machine.\n",
      "            If this is true, you should specify Client(...,sshserver='you@Gamma')\n",
      "            or instruct your controller to listen on an external IP.\n",
      "  RuntimeWarning)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[0, 1, 2, 3, 4, 5, 6, 7]"
      ]
     },
     "execution_count": 74,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import ipyparallel as ipp\n",
    "\n",
    "rc = ipp.Client()\n",
    "dview = rc[:]\n",
    "\n",
    "rc.ids"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-10-21T07:56:20.877563Z",
     "start_time": "2018-10-21T07:56:14.818972Z"
    },
    "attributes": {
     "classes": [],
     "id": "",
     "n": "413"
    },
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The autoreload extension is already loaded. To reload it, use:\n",
      "  %reload_ext autoreload\n",
      "Dataset has been loaded\n",
      "[stdout:0] Dataset has been loaded\n",
      "[stdout:1] Dataset has been loaded\n",
      "[stdout:2] Dataset has been loaded\n",
      "[stdout:3] Dataset has been loaded\n",
      "[stdout:4] Dataset has been loaded\n",
      "[stdout:5] Dataset has been loaded\n",
      "[stdout:6] Dataset has been loaded\n",
      "[stdout:7] Dataset has been loaded\n"
     ]
    }
   ],
   "source": [
    "%%px --local\n",
    "%load_ext autoreload\n",
    "%autoreload 2\n",
    "\n",
    "import numpy as np\n",
    "import mxnet as mx\n",
    "#import matplotlib.pyplot as plt\n",
    "import h5py\n",
    "from sklearn.model_selection import train_test_split\n",
    "# # # #import jtplot submodule from jupyterthemes\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",
    "#now load this dataset \n",
    "h5f = h5py.File('./datasets/s8_sio2tio2_v2.h5','r')\n",
    "X = h5f['sizes'][:]\n",
    "Y = h5f['spectrum'][:]\n",
    "\n",
    "#create a train - test split of the dataset\n",
    "x_train, x_test, y_train, y_test = train_test_split(X, Y, test_size=0.4, random_state=42)\n",
    "# normalize inputs \n",
    "#x_test = (x_test - 50)/20 \n",
    "\n",
    "print(\"Dataset has been loaded\")\n",
    "\n",
    "\n",
    "\n",
    "# # Step1: Load the model in MXNet\n",
    "\n",
    "# # # Use the same prefix and epoch parameters we used in save_mxnet_model API.\n",
    "sym, arg_params, aux_params = mx.model.load_checkpoint(prefix='./models/my_mod_convprel', epoch=0)\n",
    "\n",
    "# We use the data_names and data_shapes returned by save_mxnet_model API.\n",
    "mod = mx.mod.Module(symbol=sym, \n",
    "                    data_names=['/first_input6'], \n",
    "                    context=mx.gpu(), \n",
    "                    label_names=None)\n",
    "mod.bind(for_training=False, \n",
    "         data_shapes=[('/first_input6', (1,8))], \n",
    "         label_shapes=mod._label_shapes)\n",
    "mod.set_params(arg_params, aux_params, allow_missing=True)    \n",
    "\n",
    "\n",
    "#resnet - my_mod_bet   input_21\n",
    "#fullycon - my_mod_fullycon  first_input2\n",
    "#conv1d - my_mod_conv1d - first_input4\n",
    "#convprel - my_mod_convprel - first_input6"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-10-21T07:56:42.662949Z",
     "start_time": "2018-10-21T07:56:42.561201Z"
    },
    "code_folding": [],
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The autoreload extension is already loaded. To reload it, use:\n",
      "  %reload_ext autoreload\n",
      "[stdout:0] \n",
      "The autoreload extension is already loaded. To reload it, use:\n",
      "  %reload_ext autoreload\n",
      "[stdout:1] \n",
      "The autoreload extension is already loaded. To reload it, use:\n",
      "  %reload_ext autoreload\n",
      "[stdout:2] \n",
      "The autoreload extension is already loaded. To reload it, use:\n",
      "  %reload_ext autoreload\n",
      "[stdout:3] \n",
      "The autoreload extension is already loaded. To reload it, use:\n",
      "  %reload_ext autoreload\n",
      "[stdout:4] \n",
      "The autoreload extension is already loaded. To reload it, use:\n",
      "  %reload_ext autoreload\n",
      "[stdout:5] \n",
      "The autoreload extension is already loaded. To reload it, use:\n",
      "  %reload_ext autoreload\n",
      "[stdout:6] \n",
      "The autoreload extension is already loaded. To reload it, use:\n",
      "  %reload_ext autoreload\n",
      "[stdout:7] \n",
      "The autoreload extension is already loaded. To reload it, use:\n",
      "  %reload_ext autoreload\n"
     ]
    }
   ],
   "source": [
    "\n",
    "%%px --local\n",
    "%load_ext autoreload\n",
    "%autoreload 2\n",
    "\n",
    "\n",
    "#%%px --local\n",
    "import time\n",
    "import de2 as de\n",
    "import loss_defs as ld\n",
    "\n",
    "bnds = [(30, 70)]*8\n",
    "mats = np.array([3, 4, 3, 4, 3, 4, 3, 4])\n",
    "lams = np.linspace(300, 1200, 256)\n",
    "targ_spec = y_test[29]\n",
    "\n",
    "\n",
    "from sklearn.model_selection import ParameterGrid\n",
    "param_grid = {\n",
    "    'psize': [80, 160, 320], \n",
    "    'psnew': [20, 40],\n",
    "    'crossp': [0.4, 0.5, 0.6, 0.7, 0.8]\n",
    "      }\n",
    "grid = ParameterGrid(param_grid) \n",
    "\n",
    "def dE_stat(psize,psnew,its_first,its_second,mut,crossp):\n",
    "    return psize, psnew, crossp\n",
    "\n",
    "\n",
    "def de_stat(psize,psnew,its_first,its_second,mut,crossp):\n",
    "    run_time_tot = []\n",
    "    run_pmre = []\n",
    "    reps = 20\n",
    "    targ_spec2 = np.tile(targ_spec, (psize,1))\n",
    "    for rep in range(reps):\n",
    "#         print(rep)\n",
    "        start = time.time()\n",
    "        pop, f, b, hstry = de.de_g(\n",
    "            fobj=ld.mxmod_arr_loss, \n",
    "            bounds=bnds, \n",
    "            mut=mut,\n",
    "            crossp=crossp,\n",
    "            popsize=psize, \n",
    "            its=its_first, \n",
    "            target=targ_spec2, \n",
    "            mxmodel=mod) \n",
    "        marg = int(psnew/5)\n",
    "        pnew1 = pop[np.argsort(f)][:psnew-marg]\n",
    "        pnew2 = pop[np.argsort(f)][psnew-marg:psnew]\n",
    "        pnew = np.concatenate((pnew1, pnew2))\n",
    "        b, c, hstry = de.de_c(\n",
    "            fobj=ld.loss_func, \n",
    "            bounds=bnds, \n",
    "            pop=pnew, \n",
    "            history=hstry, \n",
    "            it_start=its_first, \n",
    "            mut=mut,\n",
    "            crossp=crossp,\n",
    "            popsize=psnew, \n",
    "            its=its_second, \n",
    "            target=targ_spec, \n",
    "            mats=mats, \n",
    "            lams=lams)\n",
    "        end = time.time()\n",
    "        run_time_tot.append((end - start)/60.0)\n",
    "        run_pmre.append(c)\n",
    "    return  np.mean(run_pmre), np.std(run_pmre), np.mean(run_time_tot)\n",
    "    \n",
    "    \n",
    "\n",
    "# pm, pstd, rmd =  de_stat(psize=80,psnew=10,its_first=500,its_second=100,mut=0.8,crossp=0.7)\n",
    "\n",
    "\n",
    "# pm, pstd, rmd\n",
    "\n",
    "\n",
    "\n",
    "# print(grid)\n",
    "# for mem in grid:\n",
    "#     for key in mem:\n",
    "#         print(key, mem[key])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-10-21T07:56:47.477288Z",
     "start_time": "2018-10-21T07:56:47.446944Z"
    }
   },
   "outputs": [],
   "source": [
    "\n",
    "def ff(x):\n",
    "    for pset in grid:\n",
    "#         print(x,pset)\n",
    "        pm, pstd, rmd = de_stat(psize=pset['psize'],\n",
    "                                psnew=pset['psnew'],\n",
    "                                its_first=500,\n",
    "                                its_second=300,\n",
    "                                mut=x,\n",
    "                                crossp=pset['crossp']\n",
    "                               )\n",
    "        print(pm)\n",
    "        print(pstd)\n",
    "        print(rmd)\n",
    "    \n",
    "\n",
    " \n",
    "#asyn = dview.map_async(ff,[0.5 ,0.6, 0.7, 0.8, 0.9, 1.0])\n",
    "#ff(0.5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 110,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-10-21T14:43:52.453854Z",
     "start_time": "2018-10-21T14:43:52.430772Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'crossp': 0.4, 'psize': 80, 'psnew': 20}\n",
      "{'crossp': 0.4, 'psize': 80, 'psnew': 40}\n",
      "{'crossp': 0.4, 'psize': 160, 'psnew': 20}\n",
      "{'crossp': 0.4, 'psize': 160, 'psnew': 40}\n",
      "{'crossp': 0.4, 'psize': 320, 'psnew': 20}\n",
      "{'crossp': 0.4, 'psize': 320, 'psnew': 40}\n",
      "{'crossp': 0.5, 'psize': 80, 'psnew': 20}\n",
      "{'crossp': 0.5, 'psize': 80, 'psnew': 40}\n",
      "{'crossp': 0.5, 'psize': 160, 'psnew': 20}\n",
      "{'crossp': 0.5, 'psize': 160, 'psnew': 40}\n",
      "{'crossp': 0.5, 'psize': 320, 'psnew': 20}\n",
      "{'crossp': 0.5, 'psize': 320, 'psnew': 40}\n",
      "{'crossp': 0.6, 'psize': 80, 'psnew': 20}\n",
      "{'crossp': 0.6, 'psize': 80, 'psnew': 40}\n",
      "{'crossp': 0.6, 'psize': 160, 'psnew': 20}\n",
      "{'crossp': 0.6, 'psize': 160, 'psnew': 40}\n",
      "{'crossp': 0.6, 'psize': 320, 'psnew': 20}\n",
      "{'crossp': 0.6, 'psize': 320, 'psnew': 40}\n",
      "{'crossp': 0.7, 'psize': 80, 'psnew': 20}\n",
      "{'crossp': 0.7, 'psize': 80, 'psnew': 40}\n",
      "{'crossp': 0.7, 'psize': 160, 'psnew': 20}\n",
      "{'crossp': 0.7, 'psize': 160, 'psnew': 40}\n",
      "{'crossp': 0.7, 'psize': 320, 'psnew': 20}\n",
      "{'crossp': 0.7, 'psize': 320, 'psnew': 40}\n",
      "{'crossp': 0.8, 'psize': 80, 'psnew': 20}\n",
      "{'crossp': 0.8, 'psize': 80, 'psnew': 40}\n",
      "{'crossp': 0.8, 'psize': 160, 'psnew': 20}\n",
      "{'crossp': 0.8, 'psize': 160, 'psnew': 40}\n",
      "{'crossp': 0.8, 'psize': 320, 'psnew': 20}\n",
      "{'crossp': 0.8, 'psize': 320, 'psnew': 40}\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "['1.1301009177342074\\n0.4433545102972204\\n1.9973992935816451\\n1.1978118829893494\\n0.5433340634490728\\n3.9798421380917235\\n1.185659489902775\\n0.5229318402795373\\n2.0346258413791656\\n1.0203257728233819\\n0.4328800961143291\\n3.9803607704242068\\n0.8853474755214226\\n0.39025710533254293\\n2.121337319811185\\n0.8745737336598876\\n0.40638905130018776\\n4.080368780096372\\n1.136967865218111\\n0.7886459836783719\\n1.98240611632665\\n',\n",
       " '1.7131988937392013\\n0.6082128954795456\\n2.0491744035482404\\n1.428553914278536\\n0.44388601231540326\\n4.026420084039371\\n1.5048834539525133\\n0.6004320686610364\\n2.070323901772499\\n1.3652300738904153\\n0.5752924032686485\\n4.047638735373815\\n1.2851497406207808\\n0.4712458455064607\\n2.1543499658505123\\n1.288555356129053\\n0.5452378126342693\\n4.131543535788855\\n',\n",
       " '2.0202662132221905\\n0.5519051815259742\\n2.0411330630381896\\n1.9525635908247334\\n0.4583166928303958\\n4.0116366086403525\\n1.7012429992895874\\n0.5010234174726487\\n2.05347172955672\\n1.7794735270108073\\n0.5739565246000088\\n4.039100284576416\\n1.902040312708279\\n0.590235390140152\\n2.148336291710535\\n1.6673563120526818\\n0.4281516235207753\\n4.117947609623273\\n',\n",
       " '2.602639688174307\\n0.6152539758296448\\n2.0382266837358474\\n2.3995031384104224\\n0.6499501393566456\\n3.994401550889015\\n2.259091084659232\\n0.602963186643796\\n2.056499874989192\\n2.2681213876612434\\n0.4265081657964298\\n4.004326575398446\\n2.3096017439957017\\n0.5134323378774367\\n2.1406100873152414\\n2.1120005176863494\\n0.5716520001785659\\n4.098231108983358\\n2.155047865321666\\n0.7828864333850875\\n2.000000069737434\\n',\n",
       " '2.6307611743968344\\n0.5994124514860908\\n2.056917774875959\\n2.9493241444314537\\n0.6988332871974442\\n4.03848379433155\\n2.67712050359448\\n0.633608073041573\\n2.090317832430203\\n2.4557335895738275\\n0.619746104257869\\n4.082432220975559\\n2.4134195710515063\\n0.4391665495051974\\n2.1765918880701065\\n2.5009232355992004\\n0.7942216982459094\\n4.158314067324002\\n',\n",
       " '2.9633835944933495\\n0.4875300123238345\\n2.0318510516484585\\n3.1881074389096407\\n0.8280600156469394\\n4.002757206956545\\n2.857410062376154\\n0.6435796953353261\\n2.059861578543981\\n2.6423645770530033\\n0.6120867705147262\\n4.032538525462151\\n2.7043254624645554\\n0.6426567614916722\\n2.1510924446582793\\n2.6640555496411666\\n0.38322716764518094\\n4.115076087315877\\n']"
      ]
     },
     "execution_count": 110,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    " for pset in grid:\n",
    "        print(pset)\n",
    "asyn.stdout"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-10-21T15:11:23.567612Z",
     "start_time": "2018-10-21T15:11:23.545535Z"
    }
   },
   "outputs": [],
   "source": [
    "\n",
    "\n",
    "outs=[]\n",
    "for out in asyn.stdout:\n",
    "    outs.append(out.splitlines())\n",
    "\n",
    "outs2 = sum(outs, [])\n",
    "\n",
    "outs_f = np.array([float(o)  for o in outs2])\n",
    "outs_f\n",
    "\n",
    "a =np.reshape(outs_f, (int(outs_f.size/3),3))\n",
    "pm = a[:,0]\n",
    "pstd = a[:,1]\n",
    "rmd = a[:,2]\n",
    "\n",
    "# vals = np.array([float(mem[:-1]) for mem in asyn.stdout])\n",
    "#asyn.stdout\n",
    "#asyn.stdout"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 114,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-10-21T15:11:27.651372Z",
     "start_time": "2018-10-21T15:11:27.630132Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1.13010092, 1.19781188, 1.18565949, 1.02032577, 0.88534748,\n",
       "       0.87457373, 1.13696787, 1.71319889, 1.42855391, 1.50488345,\n",
       "       1.36523007, 1.28514974, 1.28855536, 0.94324173, 2.02026621,\n",
       "       1.95256359, 1.701243  , 1.77947353, 1.90204031, 1.66735631,\n",
       "       1.46799337, 2.60263969, 2.39950314, 2.25909108, 2.26812139,\n",
       "       2.30960174, 2.11200052, 2.15504787, 2.63076117, 2.94932414,\n",
       "       2.6771205 , 2.45573359, 2.41341957, 2.50092324, 2.37576157,\n",
       "       2.96338359, 3.18810744, 2.85741006, 2.64236458, 2.70432546,\n",
       "       2.66405555, 2.73309118])"
      ]
     },
     "execution_count": 114,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-10-20T13:32:36.565912Z",
     "start_time": "2018-10-20T13:32:21.309964Z"
    },
    "attributes": {
     "classes": [],
     "id": "",
     "n": "414"
    },
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "import time\n",
    "import de2 as de\n",
    "import loss_defs as ld\n",
    "\n",
    "bnds = [(30, 70)]*8\n",
    "mats = np.array([3, 4, 3, 4, 3, 4, 3, 4])\n",
    "lams = np.linspace(300, 1200, 256)\n",
    "targ_spec = y_test[29]\n",
    "\n",
    "psize = 320\n",
    "targ_spec2 = np.tile(targ_spec, (psize,1))\n",
    "its_first = 500\n",
    "psnew = 20\n",
    "its_second = 300\n",
    "reps = 100\n",
    "\n",
    "\n",
    "run_hist = []\n",
    "run_time1 = []\n",
    "run_time2 = []\n",
    "run_time_tot = []\n",
    "run_pmre = []\n",
    "run_best = []\n",
    "\n",
    "for rep in range(reps):\n",
    "    print(\"iteration \", rep)\n",
    "    start = time.time()\n",
    "    pop, f, b, hstry = de.de_g(fobj=ld.mxmod_arr_loss, bounds=bnds, popsize=psize, its=its_first, target=targ_spec2, mxmodel=mod) \n",
    "    #pop, f, b, hstry = de2(fobj=mxmod_arr_loss, bounds=bnds, popsize=psize, its=its_first) \n",
    "    end1 = time.time()\n",
    "    marg = int(psnew/5)\n",
    "    pnew1 = pop[np.argsort(f)][:psnew-marg]\n",
    "    pnew2 = pop[np.argsort(f)][psnew-marg:psnew]\n",
    "    pnew = np.concatenate((pnew1, pnew2))\n",
    "    #b, c, hstry = de_stage2(fobj=loss_func, bounds=bnds, popint=pnew, history=hstry, itprev=its_first, popsize=psnew, its=its_second)\n",
    "   # b, c, hstry = de.de_c(fobj=loss_func, bounds=bnds,  popsize=80, its=500)\n",
    "    b, c, hstry = de.de_c(fobj=ld.loss_func, bounds=bnds, pop=pnew, history=hstry, it_start=its_first, popsize=psnew, its=its_second, target=targ_spec, mats=mats, lams=lams)\n",
    "    end = time.time()\n",
    "    run_time1.append((end1 - start)/60.0)\n",
    "    run_time2.append((end - end1)/60.0)\n",
    "    run_time_tot.append((end - start)/60.0)\n",
    "    run_pmre.append(c)\n",
    "    run_best.append(b)\n",
    "    run_hist.append(np.asarray(hstry))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-10-20T10:21:20.278082Z",
     "start_time": "2018-10-20T10:21:20.249204Z"
    }
   },
   "outputs": [],
   "source": [
    "pm, pstd, rm, rstd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-10-19T18:01:38.465084Z",
     "start_time": "2018-10-19T18:01:38.382183Z"
    }
   },
   "outputs": [],
   "source": [
    "# import jtplot module in notebook\n",
    "from jupyterthemes import jtplot\n",
    "\n",
    "# choose which theme to inherit plotting style from\n",
    "# onedork | grade3 | oceans16 | chesterish | monokai | solarizedl | solarizedd\n",
    "#jtplot.style(theme='monokai')\n",
    "\n",
    "# set \"context\" (paper, notebook, talk, poster)\n",
    "# scale font-size of ticklabels, legend, etc.\n",
    "# remove spines from x and y axes and make grid dashed\n",
    "#jtplot.style(context='talk', fscale=1.4, spines=False, gridlines='--')\n",
    "\n",
    "# turn on X- and Y-axis tick marks (default=False)\n",
    "# turn off the axis grid lines (default=True)\n",
    "# and set the default figure size\n",
    "#jtplot.style(ticks=True, grid=False, figsize=(6, 4.5))\n",
    "jtplot.style(grid=False, figsize=(4,2), fscale=0.7, s)\n",
    "# reset default matplotlib rcParams\n",
    "#jtplot.reset()\n",
    "plt.s\n",
    "plt.hist(run_pmre, bins=[0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 1.0, 2.5, 3], density=True, stacked=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-10-20T05:57:55.035771Z",
     "start_time": "2018-10-20T05:57:54.969003Z"
    }
   },
   "outputs": [],
   "source": [
    "fig, ax = plt.subplots()\n",
    "ax.hist(run_pmre, bins=np.linspace(0, 2, 33), density=True, stacked=True, histtype='stepfilled')\n",
    "ax.spines['top'].set_visible(False)\n",
    "ax.spines['right'].set_visible(False)\n",
    "ax.set_xlim(left=0.0)\n",
    "#ax.spines['bottom'].set_visible(False)\n",
    "#ax.spines['left'].set_visible(False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-10-20T15:36:41.834584Z",
     "start_time": "2018-10-20T15:36:41.830750Z"
    }
   },
   "outputs": [],
   "source": [
    "a =np.arange(9)\n",
    "a =np.reshape(a, (int(a.size/3),3))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-10-20T15:37:45.105731Z",
     "start_time": "2018-10-20T15:37:45.100307Z"
    }
   },
   "outputs": [],
   "source": [
    "a[:,0]"
   ]
  },
  {
   "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": "3.7.0"
  },
  "latex_envs": {
   "LaTeX_envs_menu_present": true,
   "autoclose": false,
   "autocomplete": true,
   "bibliofile": "biblio.bib",
   "cite_by": "apalike",
   "current_citInitial": 1,
   "eqLabelWithNumbers": true,
   "eqNumInitial": 1,
   "hotkeys": {
    "equation": "Ctrl-E",
    "itemize": "Ctrl-I"
   },
   "labels_anchors": false,
   "latex_user_defs": false,
   "report_style_numbering": false,
   "user_envs_cfg": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}