{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The autoreload extension is already loaded. To reload it, use:\n",
      "  %reload_ext autoreload\n"
     ]
    }
   ],
   "source": [
    "%load_ext autoreload\n",
    "%autoreload 2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(900096, 74)\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "\n",
    "datafile = 'data/21.csv'\n",
    "\n",
    "data = pd.read_csv(datafile, header=None)\n",
    "\n",
    "#and convert it to numpy array:\n",
    "npdata = np.array(data)\n",
    "\n",
    "print(npdata.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(59999, 120, 40)\n"
     ]
    }
   ],
   "source": [
    "window_data = [npdata[i:i+120, 0:40] for i in range(0, npdata.shape[0]-120, int(120/8))]\n",
    "del npdata\n",
    "data = np.reshape(window_data, (len(window_data), len(window_data[0][0]), len(window_data[0])))\n",
    "del window_data\n",
    "data = np.reshape(data, (len(data), len(data[0][0]), len(data[0])))\n",
    "# data = np.concatenate((data, data))\n",
    "print(data.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "targets = [43895, 33430, 42575, 1060, 11975]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Preprocessing:\n",
      "1730\n",
      "0:0\n",
      "1730\n",
      "999:59\n",
      "1730\n",
      "1998:70\n",
      "1730\n",
      "2997:78\n",
      "1730\n",
      "3996:81\n",
      "1730\n",
      "4995:81\n",
      "1730\n",
      "5994:81\n",
      "1730\n",
      "6993:84\n",
      "1730\n",
      "7992:84\n",
      "1730\n",
      "8991:84\n",
      "1730\n",
      "9990:84\n",
      "1730\n",
      "10989:84\n",
      "1730\n",
      "11988:84\n",
      "1730\n",
      "12987:84\n",
      "1730\n",
      "13986:91\n",
      "1730\n",
      "14985:91\n",
      "1730\n",
      "15984:91\n",
      "1730\n",
      "16983:91\n",
      "1730\n",
      "17982:91\n",
      "1730\n",
      "18981:91\n",
      "1730\n",
      "19980:95\n",
      "1730\n",
      "20979:95\n",
      "1730\n",
      "21978:95\n",
      "1730\n",
      "22977:95\n",
      "1730\n",
      "23976:95\n",
      "1730\n",
      "24975:95\n",
      "1730\n",
      "25974:95\n",
      "1730\n",
      "26973:99\n",
      "1730\n",
      "27972:99\n",
      "1730\n",
      "28971:99\n",
      "1730\n",
      "29970:99\n",
      "1730\n",
      "30969:102\n",
      "1730\n",
      "31968:102\n",
      "1730\n",
      "32967:103\n",
      "1730\n",
      "33966:105\n",
      "1730\n",
      "34965:105\n",
      "1730\n",
      "35964:105\n",
      "1730\n",
      "36963:105\n",
      "1730\n",
      "37962:109\n",
      "1730\n",
      "38961:110\n",
      "1730\n",
      "39960:114\n",
      "1730\n",
      "40959:114\n",
      "1730\n",
      "41958:115\n",
      "1730\n",
      "42957:116\n",
      "1730\n",
      "43956:116\n",
      "1730\n",
      "44955:116\n",
      "1730\n",
      "45954:122\n",
      "1730\n",
      "46953:126\n",
      "1730\n",
      "47952:126\n",
      "1730\n",
      "48951:126\n",
      "1730\n",
      "49950:128\n",
      "1730\n",
      "50949:128\n",
      "1730\n",
      "51948:128\n",
      "1730\n",
      "52947:128\n",
      "1730\n",
      "53946:130\n",
      "1730\n",
      "54945:134\n",
      "1730\n",
      "55944:134\n",
      "1730\n",
      "56943:134\n",
      "1730\n",
      "57942:143\n",
      "1730\n",
      "58941:143\n",
      "1730\n",
      "59940:145\n",
      "r = 1730\n",
      "0\n",
      "1\n",
      "2\n",
      "3\n",
      "4\n",
      "5\n",
      "6\n",
      "7\n",
      "8\n",
      "9\n",
      "10\n",
      "11\n",
      "12\n",
      "13\n",
      "14\n",
      "15\n",
      "16\n",
      "17\n",
      "18\n",
      "19\n",
      "20\n",
      "21\n",
      "22\n",
      "23\n",
      "24\n",
      "25\n",
      "26\n",
      "27\n",
      "28\n",
      "29\n",
      "30\n",
      "31\n",
      "32\n",
      "33\n",
      "34\n",
      "35\n",
      "36\n",
      "37\n",
      "38\n",
      "39\n",
      "40\n",
      "41\n",
      "42\n",
      "43\n",
      "44\n",
      "45\n",
      "46\n",
      "47\n",
      "48\n",
      "49\n",
      "50\n",
      "51\n",
      "52\n",
      "53\n",
      "54\n",
      "55\n",
      "56\n",
      "57\n",
      "58\n",
      "59\n",
      "60\n",
      "61\n",
      "62\n",
      "63\n",
      "64\n",
      "65\n",
      "66\n",
      "67\n",
      "68\n",
      "69\n",
      "70\n",
      "71\n",
      "72\n",
      "73\n",
      "74\n",
      "75\n",
      "76\n",
      "77\n",
      "78\n",
      "79\n",
      "80\n",
      "81\n",
      "82\n",
      "83\n",
      "84\n",
      "85\n",
      "86\n",
      "87\n",
      "88\n",
      "89\n",
      "90\n",
      "91\n",
      "92\n",
      "93\n",
      "94\n",
      "95\n",
      "96\n",
      "97\n",
      "98\n",
      "99\n",
      "100\n",
      "101\n",
      "102\n",
      "103\n",
      "104\n",
      "105\n",
      "106\n",
      "107\n",
      "108\n",
      "109\n",
      "110\n",
      "111\n",
      "112\n",
      "113\n",
      "114\n",
      "115\n",
      "116\n",
      "117\n",
      "118\n",
      "119\n",
      "120\n",
      "121\n",
      "122\n",
      "123\n",
      "124\n",
      "125\n",
      "126\n",
      "127\n",
      "128\n",
      "129\n",
      "130\n",
      "131\n",
      "132\n",
      "133\n",
      "134\n",
      "135\n",
      "136\n",
      "137\n",
      "138\n",
      "139\n",
      "140\n",
      "141\n",
      "142\n",
      "143\n",
      "144\n",
      "Mean: 16672.21312363323\n",
      "Stdev: 7180.272654591725\n",
      "Ratio mean: 0.9379277278060563\n",
      "Ratio stdev: 0.15076175892196642\n",
      "Theta: -1852.8903252134187\n",
      "r: 166.7221312363323\n",
      "Preprocessing time: 14.979660749435425\n",
      "Preprocessing done. Took 14.98 seconds (0.2 minutes).\n"
     ]
    }
   ],
   "source": [
    "import sys\n",
    "from time import time\n",
    "\n",
    "sys.path.insert(0, '../Flaskserver')\n",
    "import importlib\n",
    "from main import preprocess\n",
    "import _lsh\n",
    "\n",
    "topk_dtw = []\n",
    "\n",
    "print('Preprocessing:')\n",
    "t0 = time()\n",
    "r,a,sd = preprocess(data, 1730)\n",
    "print('Preprocessing done. Took {:.2f} seconds ({:.1f} minutes).'.format(time() - t0, (time() - t0) / 60))\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "doing lsh\n",
      "Target #0 done! Took 3.11 seconds (0.1 minutes).\n",
      "doing lsh\n",
      "Target #1 done! Took 2.91 seconds (0.0 minutes).\n",
      "doing lsh\n",
      "Target #2 done! Took 2.80 seconds (0.0 minutes).\n",
      "doing lsh\n",
      "Target #3 done! Took 2.82 seconds (0.0 minutes).\n",
      "doing lsh\n",
      "Target #4 done! Took 2.85 seconds (0.0 minutes).\n",
      "Done! Took 14.50 seconds (0.2 minutes).\n"
     ]
    }
   ],
   "source": [
    "t0 = time()\n",
    "for i, target in enumerate(targets):\n",
    "    t1 = time()\n",
    "    query = data[target]\n",
    "    print('doing lsh')\n",
    "    lsh_candidates, lsh_distances, _ = _lsh.lsh(data, query, r, a, sd)\n",
    "#     topk_dtw.append(candidates)\n",
    "    print('Target #{} done! Took {:.2f} seconds ({:.1f} minutes).'.format(i, time() - t1, (time() - t1) / 60))\n",
    "    \n",
    "# print(candidates[0:10])\n",
    "print('Done! Took {:.2f} seconds ({:.1f} minutes).'.format(time() - t0, (time() - t0) / 60))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Target #0 done! Took 5.99 seconds (0.1 minutes).\n",
      "Target #1 done! Took 5.71 seconds (0.1 minutes).\n",
      "Target #2 done! Took 5.76 seconds (0.1 minutes).\n",
      "Target #3 done! Took 5.65 seconds (0.1 minutes).\n",
      "Target #4 done! Took 5.84 seconds (0.1 minutes).\n",
      "Done! Took 28.96 seconds (0.5 minutes).\n",
      "[11975, 18529, 3579, 2144, 18528, 11974, 4602, 11976, 9108, 8084]\n"
     ]
    }
   ],
   "source": [
    "from scipy.spatial.distance import cdist\n",
    "from tslearn.metrics import dtw\n",
    "from time import time\n",
    "\n",
    "t0 = time()\n",
    "for i, target in enumerate(targets):\n",
    "    t1 = time()\n",
    "    query = data[target]\n",
    "    dtw_distances = [dtw(window, query, global_constraint='sakoe_chiba', sakoe_chiba_radius=int(0.05)) for window in data]\n",
    "    print('Target #{} done! Took {:.2f} seconds ({:.1f} minutes).'.format(i, time() - t1, (time() - t1) / 60))\n",
    "dtw_candidates = sorted(range(len(dtw_distances)), key=lambda k: dtw_distances[k])\n",
    "print('Done! Took {:.2f} seconds ({:.1f} minutes).'.format(time() - t0, (time() - t0) / 60))\n",
    "print(dtw_candidates[0:10])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[11975, 18529, 4602, 2144, 1325, 14433, 5421, 9108, 5217, 3579]\n"
     ]
    }
   ],
   "source": [
    "from collections import defaultdict\n",
    "\n",
    "dict = defaultdict(int)\n",
    "for l in range(len(lsh_candidates)):\n",
    "    for k in range(len(lsh_candidates[0])):\n",
    "        for i in range(len(lsh_candidates[0][0])):\n",
    "            dict[lsh_candidates[l][k][i]] += lsh_distances[l][k][i]\n",
    "sorted_dict = {k: v for k, v in sorted(dict.items(), key=lambda item: item[1])}\n",
    "candidates = list(sorted_dict.keys())\n",
    "print(candidates[0:10])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "20\n",
      "[11975, 18529, 3579, 2144, 18528, 11974, 4602, 11976, 9108, 8084, 4807, 1325, 14433, 5422, 9312, 5421, 4603, 18938, 3578, 9928]\n",
      "[11975, 18529, 4602, 2144, 1325, 14433, 5421, 9108, 5217, 3579, 18528, 8084, 4807, 3578, 4603, 59898, 9312, 15662, 4601, 11974]\n"
     ]
    }
   ],
   "source": [
    "accuracy = 0\n",
    "for index in dtw_candidates[0:20]:\n",
    "    if index in candidates:\n",
    "        accuracy += 1\n",
    "print(accuracy)\n",
    "accuracy = 0\n",
    "for index in dtw_candidates[0:20]:\n",
    "    if index in candidates[0:20]:\n",
    "        accuracy += 1\n",
    "print(accuracy)\n",
    "print(dtw_candidates[0:20])\n",
    "print(candidates[0:20])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "18218\n"
     ]
    }
   ],
   "source": [
    "print(len(candidates))"
   ]
  },
  {
   "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}