{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from time import time\n",
    "\n",
    "datafile = 'data/21.csv'\n",
    "\n",
    "N = 100\n",
    "T = 100\n",
    "M = 100000\n",
    "\n",
    "data = np.random.uniform(size=(M, T, N))\n",
    "\n",
    "#and convert it to numpy array:\n",
    "data = np.array(data, dtype = \"float32\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We sample a number of subwindows which will be used as query for the search algorithms"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[23484, 81670, 8609, 31051, 42832, 14303, 85653, 67886, 17319, 93188]\n"
     ]
    }
   ],
   "source": [
    "import random\n",
    "from time import time\n",
    "\n",
    "targets = random.sample(list(range(len(data))), 10)\n",
    "print(targets)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## PSEUDo"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "For the LSH algorithm some preprocessing is done to find the right LSH parameters."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Preprocessing:\n",
      "r = 100\n",
      "smaller\n",
      "r = 50.0\n",
      "smaller\n",
      "r = 25.0\n",
      "bigger\n",
      "r = 37.5\n",
      "bigger\n",
      "r = 43.75\n",
      "smaller\n",
      "r = 40.625\n",
      "bigger\n",
      "r = 42.1875\n",
      "smaller\n",
      "r = 41.40625\n",
      "smaller\n",
      "r = 41.015625\n",
      "Mean: 41.028657241907524\n",
      "Stdev: 0.16600796717920388\n",
      "Ratio mean: 0.9930308931432998\n",
      "Ratio stdev: 0.004133342888573115\n",
      "Theta: 40.60035668658518\n",
      "r: 3.7478993980502606\n",
      "Preprocessing time: 11.971427917480469\n",
      "Preprocessing done. Took 11.97 seconds (0.2 minutes).\n"
     ]
    }
   ],
   "source": [
    "import sys\n",
    "\n",
    "sys.path.insert(0, '../Flaskserver')\n",
    "import importlib\n",
    "from pseudo import preprocess\n",
    "import _lsh\n",
    "\n",
    "topk_dtw = []\n",
    "\n",
    "print('Preprocessing:')\n",
    "t0 = time()\n",
    "r,a,sd = preprocess(data, data.shape[2])\n",
    "print('Preprocessing done. Took {:.2f} seconds ({:.1f} minutes).'.format(time() - t0, (time() - t0) / 60))\n",
    "pseudo_preprocess_time = time() - t0"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now we run the LSH algorithm for all targets and calculate the most similar subwindows"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "doing lsh\n",
      "Target #0 done! Took 14.48 seconds (0.2 minutes).\n",
      "doing lsh\n",
      "Target #1 done! Took 14.31 seconds (0.2 minutes).\n",
      "doing lsh\n",
      "Target #2 done! Took 14.30 seconds (0.2 minutes).\n",
      "doing lsh\n",
      "Target #3 done! Took 14.17 seconds (0.2 minutes).\n",
      "doing lsh\n",
      "Target #4 done! Took 14.30 seconds (0.2 minutes).\n",
      "doing lsh\n",
      "Target #5 done! Took 14.31 seconds (0.2 minutes).\n",
      "doing lsh\n",
      "Target #6 done! Took 14.18 seconds (0.2 minutes).\n",
      "doing lsh\n",
      "Target #7 done! Took 13.75 seconds (0.2 minutes).\n",
      "doing lsh\n",
      "Target #8 done! Took 13.80 seconds (0.2 minutes).\n",
      "doing lsh\n",
      "Target #9 done! Took 14.17 seconds (0.2 minutes).\n",
      "Done! Took 141.76 seconds (2.4 minutes).\n"
     ]
    }
   ],
   "source": [
    "from collections import defaultdict\n",
    "t0 = time()\n",
    "total_lsh_times = []\n",
    "all_lsh_candidates = []\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, 0)\n",
    "#     topk_dtw.append(candidates)\n",
    "    dict = defaultdict(int)\n",
    "    for l in range(len(lsh_candidates)):\n",
    "        for k in range(len(lsh_candidates[0])):\n",
    "            for a in range(len(lsh_candidates[0][0])):\n",
    "                dict[lsh_candidates[l][k][a]] += lsh_distances[l][k][a]\n",
    "    sorted_dict = {k: v for k, v in sorted(dict.items(), key=lambda item: item[1])}\n",
    "    candidates = list(sorted_dict.keys())\n",
    "    total_lsh_times.append(time()-t1)\n",
    "    print('Target #{} done! Took {:.2f} seconds ({:.1f} minutes).'.format(i, time() - t1, (time() - t1) / 60))\n",
    "    all_lsh_candidates.append(candidates)\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": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "doing lsh\n",
      "Target #0 done! Took 9.85 seconds (0.2 minutes).\n",
      "doing lsh\n",
      "Target #1 done! Took 9.73 seconds (0.2 minutes).\n",
      "doing lsh\n",
      "Target #2 done! Took 9.58 seconds (0.2 minutes).\n",
      "doing lsh\n",
      "Target #3 done! Took 9.60 seconds (0.2 minutes).\n",
      "doing lsh\n",
      "Target #4 done! Took 9.84 seconds (0.2 minutes).\n",
      "doing lsh\n",
      "Target #5 done! Took 9.74 seconds (0.2 minutes).\n",
      "doing lsh\n"
     ]
    }
   ],
   "source": [
    "from collections import defaultdict\n",
    "t0 = time()\n",
    "total_lsh_times_ed = []\n",
    "all_lsh_candidates_ed = []\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, 1)\n",
    "#     topk_dtw.append(candidates)\n",
    "    dict = defaultdict(int)\n",
    "    for l in range(len(lsh_candidates)):\n",
    "        for k in range(len(lsh_candidates[0])):\n",
    "            for a in range(len(lsh_candidates[0][0])):\n",
    "                dict[lsh_candidates[l][k][a]] += lsh_distances[l][k][a]\n",
    "    sorted_dict = {k: v for k, v in sorted(dict.items(), key=lambda item: item[1])}\n",
    "    candidates = list(sorted_dict.keys())\n",
    "    total_lsh_times_ed.append(time()-t1)\n",
    "    print('Target #{} done! Took {:.2f} seconds ({:.1f} minutes).'.format(i, time() - t1, (time() - t1) / 60))\n",
    "    all_lsh_candidates_ed.append(candidates)\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": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "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
}