Baseline - GRU-GAN.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "a80a379b-932c-4401-8d76-b5ae5dedc6cc",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import random\n",
    "\n",
    "os.environ[\"CUDA_DEVICE_ORDER\"] = \"PCI_BUS_ID\";\n",
    "os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"1\"\n",
    "os.environ[\"TF_FORCE_GPU_ALLOW_GROWTH\"] = \"true\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "saving-behavior",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import tensorflow as tf\n",
    "\n",
    "from evaluator import evaluate\n",
    "from data_loader import load_kdd_cup_urc, load_yahoo_A1, load_yahoo_A2, load_yahoo_A3, load_yahoo_A4, load_power_demand # Univariate Datasets\n",
    "from data_loader import load_nasa, load_ecg, load_gesture, load_smd # Multivariate Datasets\n",
    "\n",
    "from tensorflow import keras\n",
    "from tensorflow.keras import layers\n",
    "from tqdm.notebook import tqdm\n",
    "\n",
    "# THESE LINES ARE FOR REPRODUCIBILITY\n",
    "random.seed(0)\n",
    "np.random.seed(0)\n",
    "tf.random.set_seed(0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "49c0a8e3-705d-429b-b7a0-c3c26a3a7b2b",
   "metadata": {},
   "outputs": [],
   "source": [
    "def train_gan(gan, dataset, batch_size, codings_size, dim, n_epochs=50):\n",
    "    generator, discriminator = gan.layers\n",
    "    for epoch in range(n_epochs):\n",
    "        for X_batch in dataset:\n",
    "            X_batch = tf.cast(X_batch, tf.float32)\n",
    "            # phase 1 - training the discriminator\n",
    "            noise = tf.random.normal(shape=[batch_size, codings_size, dim])\n",
    "            generated_images = generator(noise)\n",
    "            X_fake_and_real = tf.concat([generated_images, X_batch], axis=0)\n",
    "            y1 = tf.constant([[0.]] * batch_size + [[1.]] * batch_size)\n",
    "            discriminator.trainable = True\n",
    "            discriminator.train_on_batch(X_fake_and_real, y1)\n",
    "            # phase 2 - training the generator\n",
    "            noise = tf.random.normal(shape=[batch_size, codings_size, dim])\n",
    "            y2 = tf.constant([[1.]] * batch_size)\n",
    "            discriminator.trainable = False\n",
    "            gan.train_on_batch(noise, y2)\n",
    "            \n",
    "def get_gan(x_train):\n",
    "    generator = keras.models.Sequential([\n",
    "        layers.InputLayer(input_shape=(x_train.shape[1], x_train.shape[2])),\n",
    "        layers.GRU(128, return_sequences=True),\n",
    "        layers.Dropout(rate=0.2),\n",
    "        layers.GRU(64),\n",
    "        layers.RepeatVector(x_train.shape[1]),\n",
    "        layers.GRU(64, return_sequences=True),\n",
    "        layers.Dropout(rate=0.2),\n",
    "        layers.GRU(128),\n",
    "        layers.Dense(x_train.shape[1] * x_train.shape[2]),\n",
    "        layers.Reshape([x_train.shape[1], x_train.shape[2]])\n",
    "    ])\n",
    "\n",
    "    discriminator = keras.models.Sequential([\n",
    "        layers.InputLayer(input_shape=(x_train.shape[1], x_train.shape[2])),\n",
    "        keras.layers.GRU(64, return_sequences=True),\n",
    "        keras.layers.Dropout(0.2),\n",
    "        keras.layers.GRU(64),\n",
    "        keras.layers.Dropout(0.2),\n",
    "        keras.layers.Dense(1, activation=\"sigmoid\")\n",
    "    ])\n",
    "\n",
    "    gan = keras.models.Sequential([generator, discriminator])\n",
    "\n",
    "    discriminator.compile(loss=\"binary_crossentropy\", optimizer=\"adam\")\n",
    "    discriminator.trainable = False\n",
    "    gan.compile(loss=\"binary_crossentropy\", optimizer=\"adam\")\n",
    "    return gan"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fa97c067-d18d-4c06-ae1b-2cbfe88788b6",
   "metadata": {},
   "source": [
    "### Yahoo S5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "eight-partition",
   "metadata": {},
   "outputs": [],
   "source": [
    "total_scores = {'dataset': [], 'f1': [], 'pr_auc': [], 'roc_auc': []}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "71866d92-1163-4975-bb99-4302ccda66c3",
   "metadata": {
    "scrolled": true,
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "adcae96ee12e42258ef177104ba36947",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/67 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "5f80a1f59b384d989b5b3c1e38a54ae2",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/56 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "yahoo_A1 0.03738317383177589 0.00480769253887533 -0.0\n",
      "yahoo_A1 0.05504586610554703 0.014926318841405592 0.09546925238843343\n",
      "yahoo_A1 0.6666666074074105 0.35161276324797885 0.4999999911666669\n",
      "yahoo_A1 0.9999998500000123 0.0 0.9999998990476292\n",
      "yahoo_A1 0.03703703333333351 0.004761904990972433 -0.0\n",
      "yahoo_A1 0.03703703333333351 0.004761904990972433 -0.0\n",
      "yahoo_A1 0.7999999200000041 0.3607005639602226 0.9269840821859433\n",
      "yahoo_A1 0.9666666134444469 0.9410052576018082 0.9731111065431062\n",
      "yahoo_A1 0.9206348678256514 0.9375203532457317 0.9851111064288685\n",
      "yahoo_A1 0.8888888197530895 0.628148105828666 0.9514851247559559\n",
      "yahoo_A1 0.10810809768687688 0.007500000949671265 -0.0\n",
      "yahoo_A1 0.7499999343750033 0.43208311873845845 0.817749977641834\n",
      "yahoo_A1 0.9999999437500025 0.937499976331382 0.9999999926264044\n",
      "yahoo_A1 0.7999999200000041 0.38095234093123503 0.9607842660515213\n",
      "yahoo_A1 0.7499999343750033 0.41270435077147205 0.6446601792155406\n",
      "yahoo_A1 0.9999999409090937 0.9090908783316949 0.9999999898564595\n",
      "yahoo_A1 0.9047618505668963 0.7217838546622369 0.9498039155806868\n",
      "yahoo_A1 0.07339448820806381 0.004901961700966002 -0.0\n",
      "yahoo_A1 0.6666666000000033 0.30891845390310946 0.8055555207652523\n",
      "yahoo_A1 0.5714285142857172 0.30143523342150547 0.7980197782164827\n",
      "yahoo_A1 0.7999999200000041 0.3395638266794521 0.6666666438095247\n",
      "yahoo_A1 0.03636363272727291 0.009302526352111108 -0.0\n",
      "yahoo_A1 0.5263157340720269 0.28956753468813423 0.8579239638643188\n",
      "yahoo_A1 0.5454544932966067 0.20860657281836903 0.8353706154278152\n",
      "yahoo_A1 0.06249999355468753 0.016129030593132317 0.7142856421768782\n",
      "yahoo_A1 0.12499998805803669 0.022926022378748873 0.27346938127253706\n",
      "yahoo_A1 0.5128204696909958 0.3086444012454506 0.8535885080880019\n",
      "yahoo_A1 0.1333332871111258 0.030335175396260454 0.4460437535361238\n",
      "yahoo_A1 0.39999995200000177 0.02521269466587514 0.7504124737997904\n",
      "yahoo_A1 0.6666666074074105 0.5858332846607097 0.9884999662456678\n",
      "yahoo_A1 0.9090908553719035 0.7399605561051631 0.9237811695684204\n",
      "yahoo_A1 0.9999999250000032 0.7499999447916703 0.9999999740196083\n",
      "yahoo_A1 0.8888888323731168 0.7976722162434119 0.856366452579593\n",
      "yahoo_A1 0.14035086389658463 0.048526864239193834 0.2956450394286747\n",
      "yahoo_A1 0.666666577777783 0.005181486181496228 0.5408653529655162\n",
      "yahoo_A1 0.07272726558677738 0.0048543698400085 -0.0\n",
      "yahoo_A1 0.10810809768687688 0.005000001327171221 -0.0\n",
      "yahoo_A1 0.018691586898419075 0.0047169806559274234 -0.0\n",
      "yahoo_A1 0.09090908206611638 0.004950496190208909 -0.0\n",
      "yahoo_A1 0.6666666024691398 0.3653263630853105 0.7962871057054095\n",
      "yahoo_A1 0.7499999343750033 0.41450044186256163 0.6766990127912312\n",
      "yahoo_A1 0.12499998805803669 0.005050506538735456 -0.0\n",
      "yahoo_A1 0.12499998805803669 0.007812501078786125 0.030612241805498024\n",
      "yahoo_A1 0.07272726558677738 0.0048543698400085 -0.0\n",
      "yahoo_A1 0.9523808934240391 0.8272277744870896 0.9090908998695086\n",
      "yahoo_A1 0.03703703333333351 0.004761904990972433 -0.0\n",
      "yahoo_A1 0.6666666000000033 0.38104511125679835 0.8511326475420522\n",
      "yahoo_A1 0.0 0.0 -0.0\n",
      "yahoo_A1 0.666666577777783 0.4166665883127155 0.9901959779604099\n",
      "yahoo_A1 0.03703703333333351 0.004761904990972433 -0.0\n",
      "yahoo_A1 0.49999995416666926 0.2669074023395298 0.5072544571259631\n",
      "yahoo_A1 0.9565216809073751 0.9161324502522443 0.9990941933493409\n",
      "yahoo_A1 0.9473683612188393 0.8151441997894529 0.9431578838329334\n",
      "yahoo_A1 0.22033896307095824 0.049650386565623886 0.03382803753922417\n",
      "yahoo_A1 0.7999999200000041 0.42732693930963317 0.676980175392017\n",
      "yahoo_A1 0.068965503923902 0.019941076409018547 0.6690475568628178\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "c39d119e735d453cb1ca087d55ad93c2",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/100 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "8c77633f37544e218402d170471db53f",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/100 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "yahoo_A2 0.041450773099949295 0.0026881725513145803 -0.0\n",
      "yahoo_A2 0.041450773099949295 0.0026881725513145803 -0.0\n",
      "yahoo_A2 0.041450773099949295 0.0026881725513145803 -0.0\n",
      "yahoo_A2 0.06829267626412905 0.005194840631162036 -0.0\n",
      "yahoo_A2 0.015267174034147195 0.0038461534585799203 -0.0\n",
      "yahoo_A2 0.041450773099949295 0.0026881725513145803 -0.0\n",
      "yahoo_A2 0.06829267626412905 0.002604167445975811 -0.0\n",
      "yahoo_A2 0.015267174034147195 0.0038461534585799203 -0.0\n",
      "yahoo_A2 0.041450773099949295 0.0026881725513145803 -0.0\n",
      "yahoo_A2 0.06829267626412905 0.002604167445975811 -0.0\n",
      "yahoo_A2 0.015267174034147195 0.0038461534585799203 -0.0\n",
      "yahoo_A2 0.041450773099949295 0.0026881725513145803 -0.0\n",
      "yahoo_A2 0.06829267626412905 0.00775743327644073 0.25109073794845516\n",
      "yahoo_A2 0.06829267626412905 0.005194840631162036 -0.0\n",
      "yahoo_A2 0.015267174034147195 0.0038461534585799203 -0.0\n",
      "yahoo_A2 0.041450773099949295 0.0026881725513145803 -0.0\n",
      "yahoo_A2 0.4444444000000022 0.17648263206431553 0.8339441171644995\n",
      "yahoo_A2 0.02941176172145329 0.00746268580975726 0.492248012409115\n",
      "yahoo_A2 0.041450773099949295 0.0026881725513145803 -0.0\n",
      "yahoo_A2 0.06829267626412905 0.008306926357221453 0.19458986954617205\n",
      "yahoo_A2 0.015267174034147195 0.0038461534585799203 -0.0\n",
      "yahoo_A2 0.39999995200000177 0.024480257848516814 0.8281531191938678\n",
      "yahoo_A2 0.06829267626412905 0.0052016578210409324 0.002617800914859778\n",
      "yahoo_A2 0.015267174034147195 0.0038461534585799203 -0.0\n",
      "yahoo_A2 0.01694915083309394 0.004273503842501322 0.1007751836428109\n",
      "yahoo_A2 0.041450773099949295 0.0026881725513145803 -0.0\n",
      "yahoo_A2 0.14285710000001145 0.05518719697204028 0.8660558035641672\n",
      "yahoo_A2 0.015267174034147195 0.0038461534585799203 -0.0\n",
      "yahoo_A2 0.041450773099949295 0.0026881725513145803 -0.0\n",
      "yahoo_A2 0.06829267626412905 0.020078913206615402 0.3914485096000894\n",
      "yahoo_A2 0.015267174034147195 0.0038461534585799203 -0.0\n",
      "yahoo_A2 0.09523806984127565 0.03609788080247159 0.8747747078454731\n",
      "yahoo_A2 0.06829267626412905 0.005164093137128652 0.25130887997313855\n",
      "yahoo_A2 0.015267174034147195 0.0038461534585799203 -0.0\n",
      "yahoo_A2 0.041450773099949295 0.0026881725513145803 -0.0\n",
      "yahoo_A2 0.041450773099949295 0.008254723077237404 0.5202702189755347\n",
      "yahoo_A2 0.06829267626412905 0.0026041674459758115 -0.0\n",
      "yahoo_A2 0.015267174034147195 0.0038461534585799203 -0.0\n",
      "yahoo_A2 0.041450773099949295 0.0026881725513145803 -0.0\n",
      "yahoo_A2 0.06829267626412905 0.005194840655596054 -0.0\n",
      "yahoo_A2 0.015267174034147195 0.0038461534585799203 -0.0\n",
      "yahoo_A2 0.041450773099949295 0.0026881725513145803 -0.0\n",
      "yahoo_A2 0.06829267626412905 0.002604167530553369 -0.0\n",
      "yahoo_A2 0.015267174034147195 0.0038461534585799203 -0.0\n",
      "yahoo_A2 0.8571427836734729 0.5124999577380092 0.9229729436339795\n",
      "yahoo_A2 0.06829267626412905 0.002604167445975811 -0.0\n",
      "yahoo_A2 0.06829267626412905 0.0028089895331500324 0.07853402474073322\n",
      "yahoo_A2 0.015267174034147195 0.0038461534585799203 -0.0\n",
      "yahoo_A2 0.041450773099949295 0.0028409095837703163 0.05405404861943079\n",
      "yahoo_A2 0.4999999500000025 0.2699868658616783 0.8414048653102744\n",
      "yahoo_A2 0.015267174034147195 0.0038461534585799203 -0.0\n",
      "yahoo_A2 0.05633801991668414 0.01110597765710668 0.43558557071800236\n",
      "yahoo_A2 0.3333332777777854 0.07479771429355109 0.46145598487177303\n",
      "yahoo_A2 0.015267174034147195 0.0038461534585799203 -0.0\n",
      "yahoo_A2 0.39999995200000177 0.0045388534743955235 0.33378376744345134\n",
      "yahoo_A2 0.06829267626412905 0.005194840631162036 -0.0\n",
      "yahoo_A2 0.015267174034147195 0.0038461534585799203 -0.0\n",
      "yahoo_A2 0.015267174034147195 0.0038461534585799203 -0.0\n",
      "yahoo_A2 0.041450773099949295 0.0026881725513145803 -0.0\n",
      "yahoo_A2 0.06829267626412905 0.005194840631162036 -0.0\n",
      "yahoo_A2 0.9999998500000123 0.0 0.9999998992248162\n",
      "yahoo_A2 0.041450773099949295 0.0026881725513145803 -0.0\n",
      "yahoo_A2 0.8333332708333363 0.644542193245625 0.9770007334589019\n",
      "yahoo_A2 0.015267174034147195 0.0038461534585799203 -0.0\n",
      "yahoo_A2 0.041450773099949295 0.007918472241816629 0.04729729490686645\n",
      "yahoo_A2 0.06829267626412905 0.005102041258699844 0.23560207055727872\n",
      "yahoo_A2 0.9999998500000123 0.0 0.9999998992248162\n",
      "yahoo_A2 0.39999995200000177 0.0048963389341252295 0.3693693533889304\n",
      "yahoo_A2 0.6666666000000033 0.2572483909307982 0.586936919048353\n",
      "yahoo_A2 0.06829267626412905 0.002604167445975811 -0.0\n",
      "yahoo_A2 0.015267174034147195 0.0038461534585799203 -0.0\n",
      "yahoo_A2 0.041450773099949295 0.0026881725513145803 -0.0\n",
      "yahoo_A2 0.06829267626412905 0.007661622110957908 0.4136125459440084\n",
      "yahoo_A2 0.015267174034147195 0.0038461534585799203 -0.0\n",
      "yahoo_A2 0.041450773099949295 0.0026881725513145803 -0.0\n",
      "yahoo_A2 0.8333332708333363 0.5843069416796679 0.7894539898046454\n",
      "yahoo_A2 0.015267174034147195 0.0038461534585799203 -0.0\n",
      "yahoo_A2 0.041450773099949295 0.0026881725513145803 -0.0\n",
      "yahoo_A2 0.06829267626412905 0.011180155223709416 0.5523559930354172\n",
      "yahoo_A2 0.06829267626412905 0.002604167445975811 -0.0\n",
      "yahoo_A2 0.9999998500000123 0.0 0.9999998992248164\n",
      "yahoo_A2 0.041450773099949295 0.002702703209537798 0.00540540486194309\n",
      "yahoo_A2 0.5999999460000028 0.3071747247582527 0.5604337961174851\n",
      "yahoo_A2 0.015267174034147195 0.0038461534585799203 -0.0\n",
      "yahoo_A2 0.041450773099949295 0.0026881725513145803 -0.0\n",
      "yahoo_A2 0.4444444000000022 0.15111485053803828 0.35794065481637805\n",
      "yahoo_A2 0.015267174034147195 0.0038461534585799203 -0.0\n",
      "yahoo_A2 0.041450773099949295 0.0026881725513145803 -0.0\n",
      "yahoo_A2 0.06829267626412905 0.002604167445975811 -0.0\n",
      "yahoo_A2 0.015267174034147195 0.0038461534585799203 -0.0\n",
      "yahoo_A2 0.015267174034147195 0.0038461534585799203 -0.0\n",
      "yahoo_A2 0.9999999250000032 0.7499999447916703 0.9999999744594601\n",
      "yahoo_A2 0.06829267626412905 0.0026315797321078064 0.010471203135879091\n",
      "yahoo_A2 0.15384613727810673 0.04166666215277823 0.9147285899885917\n",
      "yahoo_A2 0.041450773099949295 0.0026881725513145803 -0.0\n",
      "yahoo_A2 0.06829267626412905 0.007462687085238345 0.654450215364166\n",
      "yahoo_A2 0.015267174034147195 0.0038461534585799203 -0.0\n",
      "yahoo_A2 0.39999995200000177 0.015919913128909488 0.7948197482171463\n",
      "yahoo_A2 0.28571425306122533 0.06031778160209355 0.6211605358674126\n",
      "yahoo_A2 0.015267174034147195 0.0038461534585799203 -0.0\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "977d5e2aa8d7442499e677964e630877",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/100 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "b1146ac6ab5b42328ee861f4392bf672",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/92 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "yahoo_A3 0.03174602857142873 0.004065040847075319 -0.0\n",
      "yahoo_A3 0.2222221975308647 0.03780108303333946 0.4923542547135603\n",
      "yahoo_A3 0.09230768336094745 0.004201681792727941 -0.0\n",
      "yahoo_A3 0.03174602857142873 0.004065040847075319 -0.0\n",
      "yahoo_A3 0.14925371730897866 0.004347827665800764 -0.0\n",
      "yahoo_A3 0.0624999938476567 0.008699633897400685 0.30624997193229436\n",
      "yahoo_A3 0.17647057188581453 0.013918775729983063 0.09876394430481163\n",
      "yahoo_A3 0.16666661388890391 0.022771735991232545 0.2724576162655733\n",
      "yahoo_A3 0.22222217283951495 0.03821479108419271 0.37372879329980757\n",
      "yahoo_A3 0.18181816198347142 0.01675838899215872 0.27043997982019824\n",
      "yahoo_A3 0.14925371730897866 0.03204090696920303 0.22733569514427907\n",
      "yahoo_A3 0.18181816198347142 0.029216649001128452 0.3092592527930398\n",
      "yahoo_A3 0.03174602857142873 0.004065040847075319 -0.0\n",
      "yahoo_A3 0.17647057188581453 0.009114960738280987 0.0973426816573804\n",
      "yahoo_A3 0.04724408980097991 0.004098361191078604 -0.0\n",
      "yahoo_A3 0.18181816198347142 0.02982207312185124 0.3665448268618582\n",
      "yahoo_A3 0.03174602857142873 0.004065040847075319 -0.0\n",
      "yahoo_A3 0.03174602857142873 0.004065040847075319 -0.0\n",
      "yahoo_A3 0.0624999938476567 0.0041322321806666834 -0.0\n",
      "yahoo_A3 0.03174602857142873 0.004065040847075319 -0.0\n",
      "yahoo_A3 0.39999993600000633 0.15476188668924606 0.9672130180596707\n",
      "yahoo_A3 0.7999999200000041 0.42261900463804797 0.6944444193287047\n",
      "yahoo_A3 0.28571425306122533 0.02511695243917064 0.3422316266141639\n",
      "yahoo_A3 0.09230768336094745 0.007352942057563918 0.4322033521761023\n",
      "yahoo_A3 0.03174602857142873 0.00526315796935869 0.23360653382491497\n",
      "yahoo_A3 0.22222217283951495 0.03803049847829482 0.30120055245131383\n",
      "yahoo_A3 0.0624999938476567 0.0041322321806666834 -0.0\n",
      "yahoo_A3 0.03174602857142873 0.004065040847075319 -0.0\n",
      "yahoo_A3 0.2499999437500102 0.04246872306352855 0.38715275816985084\n",
      "yahoo_A3 0.2666666133333427 0.049283338699499274 0.4068400963597029\n",
      "yahoo_A3 0.20289853219911938 0.02152080763753237 0.1629661219439768\n",
      "yahoo_A3 0.18181816198347142 0.029846593869704344 0.3010790811772779\n",
      "yahoo_A3 0.2222221975308647 0.017742072987987585 0.550287312495865\n",
      "yahoo_A3 0.13533833304313522 0.011853164185705832 0.12608695039760584\n",
      "yahoo_A3 0.22222217283951495 0.047795035002879196 0.5302259513613935\n",
      "yahoo_A3 0.18181816198347142 0.027906871640733424 0.30093287973970323\n",
      "yahoo_A3 0.28571425306122533 0.008639866452953093 0.2910310610566835\n",
      "yahoo_A3 0.12121210964187425 0.004273505647355304 -0.0\n",
      "yahoo_A3 0.0624999938476567 0.0041322321806666834 -0.0\n",
      "yahoo_A3 0.17647057188581453 0.0044247805153377435 -0.0\n",
      "yahoo_A3 0.04166666241319446 0.01063829739235382 0.6229507568664401\n",
      "yahoo_A3 0.12121210964187425 0.004310346197689935 0.008620688785671996\n",
      "yahoo_A3 0.03174602857142873 0.004065040847075319 -0.0\n",
      "yahoo_A3 0.09230768336094745 0.004201681792727941 -0.0\n",
      "yahoo_A3 0.2222221975308647 0.014904527433086491 0.26374178230154094\n",
      "yahoo_A3 0.17647057188581453 0.026199087516543814 0.21997944449626217\n",
      "yahoo_A3 0.1897810044434987 0.01390914057771422 0.11129620956401258\n",
      "yahoo_A3 0.12121210964187425 0.004273505647355304 -0.0\n",
      "yahoo_A3 0.03174602857142873 0.004065040847075319 -0.0\n",
      "yahoo_A3 0.0624999938476567 0.0041322321806666834 -0.0\n",
      "yahoo_A3 0.0624999938476567 0.0041322321806666834 -0.0\n",
      "yahoo_A3 0.09230768336094745 0.004201681792727941 -0.0\n",
      "yahoo_A3 0.09230768336094745 0.017747698332512 0.27542371897445295\n",
      "yahoo_A3 0.12121210964187425 0.004273505647355304 -0.0\n",
      "yahoo_A3 0.399999960000002 0.14973610021718511 0.5973111422195247\n",
      "yahoo_A3 0.2222221975308647 0.01096087660712255 0.2973624674537891\n",
      "yahoo_A3 0.28571425306122533 0.02451886232271968 0.29286721969778273\n",
      "yahoo_A3 0.047619038321996814 0.014724575263989226 0.6045081397709005\n",
      "yahoo_A3 0.14925371730897866 0.025517835636836753 0.4181634317634556\n",
      "yahoo_A3 0.153846101775164 0.02404689093352264 0.4563731175231446\n",
      "yahoo_A3 0.0624999938476567 0.004464286461326228 0.07499999285416731\n",
      "yahoo_A3 0.09230768336094745 0.004201681792727941 -0.0\n",
      "yahoo_A3 0.03174602857142873 0.004545454693254655 0.10655736630610156\n",
      "yahoo_A3 0.18181816198347142 0.014020822347024 0.2360014550747289\n",
      "yahoo_A3 0.18181816198347142 0.04061058789094987 0.6405684073206637\n",
      "yahoo_A3 0.17647057188581453 0.01599750347516496 0.13035713931019705\n",
      "yahoo_A3 0.0624999938476567 0.0041322321806666834 -0.0\n",
      "yahoo_A3 0.22857140800000167 0.016488269880952484 0.186665732904911\n",
      "yahoo_A3 0.13533833304313522 0.004504505965665374 0.04347825648393233\n",
      "yahoo_A3 0.666666577777783 0.011627905816938707 0.8278687780099505\n",
      "yahoo_A3 0.39999995200000177 0.0145465418871377 0.6670138317155725\n",
      "yahoo_A3 0.09230768336094745 0.004201681792727941 -0.0\n",
      "yahoo_A3 0.3636363272727291 0.15726574801557616 0.581958346571432\n",
      "yahoo_A3 0.12121210964187425 0.01188875270719579 0.24891213742192578\n",
      "yahoo_A3 0.03174602857142873 0.004065040847075319 -0.0\n",
      "yahoo_A3 0.03174602857142873 0.004065040847075319 -0.0\n",
      "yahoo_A3 0.0624999938476567 0.0041322321806666834 -0.0\n",
      "yahoo_A3 0.28571425306122533 0.012722597240485254 0.3392655226258586\n",
      "yahoo_A3 0.0624999938476567 0.0041322321806666834 -0.0\n",
      "yahoo_A3 0.12121210964187425 0.004273505647355304 -0.0\n",
      "yahoo_A3 0.3636363272727291 0.15447537796407565 0.41436506943534823\n",
      "yahoo_A3 0.12121210964187425 0.004273505647355304 -0.0\n",
      "yahoo_A3 0.363636317355376 0.11558182226657548 0.562181836659847\n",
      "yahoo_A3 0.39999995200000177 0.007192770191090994 0.3104166557482644\n",
      "yahoo_A3 0.0624999938476567 0.0041322321806666834 -0.0\n",
      "yahoo_A3 0.4444444000000022 0.16655880919938323 0.5557386867146679\n",
      "yahoo_A3 0.0624999938476567 0.004237288900619699 0.024999997479166938\n",
      "yahoo_A3 0.14925371730897866 0.02261956672567699 0.27353800352888646\n",
      "yahoo_A3 0.09230768336094745 0.004201681792727941 -0.0\n",
      "yahoo_A3 0.39999995200000177 0.009361903617503005 0.3444444313912043\n",
      "yahoo_A3 0.09230768336094745 0.004201681792727941 -0.0\n",
      "yahoo_A3 0.12121210964187425 0.004273505647355304 -0.0\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "2730c99677384143b9eca80c71a569ef",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/100 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "a12011af96624f1caf8eef0b115f52b1",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/82 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "yahoo_A4 0.09230768336094745 0.004201681792727941 -0.0\n",
      "yahoo_A4 0.03174602857142873 0.004065040847075319 -0.0\n",
      "yahoo_A4 0.0624999938476567 0.0041322321806666834 -0.0\n",
      "yahoo_A4 0.39999995200000177 0.012112396473658325 0.6059027288556178\n",
      "yahoo_A4 0.12121210964187425 0.010544783315222005 0.22068964342158073\n",
      "yahoo_A4 0.12499995156251753 0.016528677108842656 0.24015803706296296\n",
      "yahoo_A4 0.0624999938476567 0.006338433258920479 0.024999997895833487\n",
      "yahoo_A4 0.07751937227330145 0.008264463152590763 -0.0\n",
      "yahoo_A4 0.1999999480000115 0.03144884793326277 0.36370054703641314\n",
      "yahoo_A4 0.0624999938476567 0.01015005777444636 0.29583330556944715\n",
      "yahoo_A4 0.12121210964187425 0.004273505647355304 -0.0\n",
      "yahoo_A4 0.18181813223141666 0.03236661227983009 0.6211805041495997\n",
      "yahoo_A4 0.0624999938476567 0.011377274002312003 0.14305554962615766\n",
      "yahoo_A4 0.09230768336094745 0.004201681792727941 -0.0\n",
      "yahoo_A4 0.03174602857142873 0.004201680855047808 0.03278688194033898\n",
      "yahoo_A4 0.03174602857142873 0.004065040847075319 -0.0\n",
      "yahoo_A4 0.13533833304313522 0.004310346308505339 -0.0\n",
      "yahoo_A4 0.13333328177779635 0.037369184844649836 0.5584769885015449\n",
      "yahoo_A4 0.14925371730897866 0.004347827672227911 -0.0\n",
      "yahoo_A4 0.09230768336094745 0.004201681792727941 -0.0\n",
      "yahoo_A4 0.03174602857142873 0.004065040847075319 -0.0\n",
      "yahoo_A4 0.0624999938476567 0.0041322321806666834 -0.0\n",
      "yahoo_A4 0.09230768336094745 0.004201681792727941 -0.0\n",
      "yahoo_A4 0.03174602857142873 0.004065040847075319 -0.0\n",
      "yahoo_A4 0.0624999938476567 0.009997745533442211 0.0756944407818289\n",
      "yahoo_A4 0.09230768336094745 0.004201681792727941 -0.0\n",
      "yahoo_A4 0.20289853219911938 0.00450450641461874 -0.0\n",
      "yahoo_A4 0.03174602857142873 0.004065040847075319 -0.0\n",
      "yahoo_A4 0.14925371730897866 0.004347827665800764 -0.0\n",
      "yahoo_A4 0.18181816198347142 0.015255348772937254 0.20406919585444172\n",
      "yahoo_A4 0.0624999938476567 0.008230592218291049 -0.0\n",
      "yahoo_A4 0.09230768336094745 0.008453991722557138 0.19067795633558426\n",
      "yahoo_A4 0.03174602857142873 0.004065040847075319 -0.0\n",
      "yahoo_A4 0.0624999938476567 0.0041322321806666834 -0.0\n",
      "yahoo_A4 0.16666664861111138 0.017776164633075207 0.24747952962163772\n",
      "yahoo_A4 0.12121210964187425 0.005813954710534015 0.27155169717969946\n",
      "yahoo_A4 0.09230768336094745 0.005681819370475622 0.26271185104854994\n",
      "yahoo_A4 0.09230768336094745 0.00782879882536757 0.21186438753232012\n",
      "yahoo_A4 0.09230768336094745 0.004201681792727941 -0.0\n",
      "yahoo_A4 0.0624999938476567 0.0041322321806666834 -0.0\n",
      "yahoo_A4 0.28571425306122533 0.009227228538777131 0.3093926432810002\n",
      "yahoo_A4 0.015999998387200003 0.004032257658038542 -0.0\n",
      "yahoo_A4 0.10687021872851314 0.0234846088479054 0.4225783254352382\n",
      "yahoo_A4 0.0624999938476567 0.0041322321806666834 -0.0\n",
      "yahoo_A4 0.0624999938476567 0.00885774798298763 0.1940972085332766\n",
      "yahoo_A4 0.666666577777783 0.005291153222658941 0.6168032356624598\n",
      "yahoo_A4 0.0624999938476567 0.004464286471802226 0.07499999368750052\n",
      "yahoo_A4 0.4999999250000064 0.13281248692239683 0.7377048563625425\n",
      "yahoo_A4 0.07751937227330145 0.004166667630810862 -0.0\n",
      "yahoo_A4 0.22222216790124563 0.03271300814265773 0.3576388727633111\n",
      "yahoo_A4 0.3076922769230785 0.1299391727605724 0.40353598536847546\n",
      "yahoo_A4 0.12121210964187425 0.004310346197689935 0.008620688785671996\n",
      "yahoo_A4 0.03174602857142873 0.004065040847075319 -0.0\n",
      "yahoo_A4 0.03174602857142873 0.004065040847075319 -0.0\n",
      "yahoo_A4 0.09230768336094745 0.004201681792727941 -0.0\n",
      "yahoo_A4 0.0624999938476567 0.0041322321806666834 -0.0\n",
      "yahoo_A4 0.0624999938476567 0.004132232180666684 -0.0\n",
      "yahoo_A4 0.0624999938476567 0.0041322321806666834 -0.0\n",
      "yahoo_A4 0.03174602857142873 0.004098360849020119 0.008196720485084744\n",
      "yahoo_A4 0.12121210964187425 0.004273505647355304 -0.0\n",
      "yahoo_A4 0.0624999938476567 0.0041322321806666834 -0.0\n",
      "yahoo_A4 0.12121210964187425 0.015039588763919684 0.37011491894291054\n",
      "yahoo_A4 0.12499994843752003 0.018909613671578285 0.21330048630282056\n",
      "yahoo_A4 0.14925371730897866 0.004385966487244442 0.008771928939673802\n",
      "yahoo_A4 0.033898298419995226 0.008734119505694266 0.30327866983337937\n",
      "yahoo_A4 0.22222217283951495 0.04610503319658035 0.3730225857662714\n",
      "yahoo_A4 0.0624999938476567 0.0041322321806666834 -0.0\n",
      "yahoo_A4 0.03174602857142873 0.004065040847075319 -0.0\n",
      "yahoo_A4 0.17647057188581453 0.006718358159477833 0.02008928469188462\n",
      "yahoo_A4 0.12121210964187425 0.008510793143764456 0.002155172304176604\n",
      "yahoo_A4 0.03174602857142873 0.004065040847075319 -0.0\n",
      "yahoo_A4 0.16296294775308767 0.008917888097419396 0.10870205812922197\n",
      "yahoo_A4 0.363636317355376 0.09216180002497626 0.44266213917778324\n",
      "yahoo_A4 0.3157894216066558 0.07674293484320294 0.40441548076960643\n",
      "yahoo_A4 0.0624999938476567 0.006493507028068957 0.36666662969444813\n",
      "yahoo_A4 0.09230768336094745 0.0042016817989637975 -0.0\n",
      "yahoo_A4 0.39999995200000177 0.009434838712421954 0.4968749651675376\n",
      "yahoo_A4 0.09230768336094745 0.006620554132184649 0.05508474126687775\n",
      "yahoo_A4 0.0624999938476567 0.0041322321806666834 -0.0\n",
      "yahoo_A4 0.14925371730897866 0.007053430918814943 0.0767543783317951\n",
      "yahoo_A4 0.14925371730897866 0.017631130880058753 0.20066311070665177\n",
      "yahoo_A4 0.04724408980097991 0.0043478265969294745 0.05785123383648715\n"
     ]
    }
   ],
   "source": [
    "for loader in [load_yahoo_A1, load_yahoo_A2, load_yahoo_A3, load_yahoo_A4]:\n",
    "    datasets = loader(8, 4)\n",
    "    x_trains, x_tests, y_tests = datasets['x_train'], datasets['x_test'], datasets['y_test']\n",
    "    \n",
    "    for i in tqdm(range(len(x_trains))):\n",
    "        tf.keras.backend.clear_session()\n",
    "\n",
    "        X_train = x_trains[i]\n",
    "        X_test = x_tests[i]\n",
    "        \n",
    "        gan = get_gan(X_train)\n",
    "        dataset = tf.data.Dataset.from_tensor_slices(X_train)\n",
    "        dataset = dataset.batch(128, drop_remainder=True).prefetch(1)\n",
    "\n",
    "        train_gan(gan, dataset, 128, X_train.shape[1], X_train.shape[2])\n",
    "        \n",
    "        X_test_rec = gan.layers[0].predict(X_test)\n",
    "        scores = evaluate(X_test, X_test_rec, y_tests[i], is_reconstructed=True)\n",
    "    \n",
    "        total_scores['dataset'].append(loader.__name__.replace('load_', ''))\n",
    "        total_scores['f1'].append(np.max(scores['f1']))\n",
    "        total_scores['pr_auc'].append(scores['pr_auc'])\n",
    "        total_scores['roc_auc'].append(scores['roc_auc'])\n",
    "        print(loader.__name__.replace('load_', ''), np.max(scores['f1']), scores['pr_auc'], scores['roc_auc'])   "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "bd9e37fd-124c-4f5c-8f1f-a9d61a4b0315",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>f1</th>\n",
       "      <th>pr_auc</th>\n",
       "      <th>roc_auc</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>dataset</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>yahoo_A1</th>\n",
       "      <td>0.488035</td>\n",
       "      <td>0.299807</td>\n",
       "      <td>0.544554</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>yahoo_A2</th>\n",
       "      <td>0.149806</td>\n",
       "      <td>0.043063</td>\n",
       "      <td>0.206261</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>yahoo_A3</th>\n",
       "      <td>0.166101</td>\n",
       "      <td>0.026351</td>\n",
       "      <td>0.212825</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>yahoo_A4</th>\n",
       "      <td>0.123234</td>\n",
       "      <td>0.013497</td>\n",
       "      <td>0.136644</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                f1    pr_auc   roc_auc\n",
       "dataset                               \n",
       "yahoo_A1  0.488035  0.299807  0.544554\n",
       "yahoo_A2  0.149806  0.043063  0.206261\n",
       "yahoo_A3  0.166101  0.026351  0.212825\n",
       "yahoo_A4  0.123234  0.013497  0.136644"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "yahoo_results = pd.DataFrame(total_scores)\n",
    "yahoo_results.groupby('dataset').mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "19c0990b-6058-4a74-ab36-046a3417d85b",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "id": "8890a678-6116-4222-b0ff-395fcd7f41aa",
   "metadata": {},
   "source": [
    "### NASA"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "e4387a80-585a-488e-94a8-546f42d47632",
   "metadata": {},
   "outputs": [],
   "source": [
    "total_scores = {'dataset': [], 'f1': [], 'pr_auc': [], 'roc_auc': []}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "106a238d-c5cb-49e9-9764-b1bc37f09436",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "8614f5a9ac1140afb5432b7a7bcd059a",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/2 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "2b5e31450df24f4fa0a5c0484b211e9c",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/2 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "D1 0.2295534087061448 0.10054492275809881 0.3736609311633924\n",
      "D2 0.19498578202833744 0.36883052651740206 0.5131809255860225\n"
     ]
    }
   ],
   "source": [
    "for loader in [load_nasa]:\n",
    "    datasets = loader(8, 4)\n",
    "    x_trains, x_tests, y_tests = datasets['x_train'], datasets['x_test'], datasets['y_test']\n",
    "    \n",
    "    for i in tqdm(range(len(x_trains))):\n",
    "        tf.keras.backend.clear_session()\n",
    "\n",
    "        X_train = x_trains[i]\n",
    "        X_test = x_tests[i]\n",
    "        \n",
    "        gan = get_gan(X_train)\n",
    "        dataset = tf.data.Dataset.from_tensor_slices(X_train)\n",
    "        dataset = dataset.batch(128, drop_remainder=True).prefetch(1)\n",
    "\n",
    "        train_gan(gan, dataset, 128, X_train.shape[1], X_train.shape[2])\n",
    "        \n",
    "        X_test_rec = gan.layers[0].predict(X_test)\n",
    "        scores = evaluate(X_test, X_test_rec, y_tests[i], is_reconstructed=True)\n",
    "        \n",
    "        total_scores['dataset'].append(f'D{i+1}')\n",
    "        total_scores['f1'].append(np.max(scores['f1']))\n",
    "        total_scores['pr_auc'].append(scores['pr_auc'])\n",
    "        total_scores['roc_auc'].append(scores['roc_auc'])\n",
    "        print(f'D{i+1}', np.max(scores['f1']), scores['pr_auc'], scores['roc_auc'])   "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "abb7a6a5-3924-4a33-bc54-871559819602",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>f1</th>\n",
       "      <th>pr_auc</th>\n",
       "      <th>roc_auc</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>dataset</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>D1</th>\n",
       "      <td>0.229553</td>\n",
       "      <td>0.100545</td>\n",
       "      <td>0.373661</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>D2</th>\n",
       "      <td>0.194986</td>\n",
       "      <td>0.368831</td>\n",
       "      <td>0.513181</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               f1    pr_auc   roc_auc\n",
       "dataset                              \n",
       "D1       0.229553  0.100545  0.373661\n",
       "D2       0.194986  0.368831  0.513181"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "nasa_results = pd.DataFrame(total_scores)\n",
    "nasa_results.groupby('dataset').mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9ddf71c6-3db3-4653-9d94-7852977b9d16",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "id": "41754734-5c75-4caf-9069-fb3b39c7a0da",
   "metadata": {},
   "source": [
    "### SMD"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "60a26807-8359-42d4-82b4-9e1d37b6acaa",
   "metadata": {},
   "outputs": [],
   "source": [
    "total_scores = {'dataset': [], 'f1': [], 'pr_auc': [], 'roc_auc': []}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "41af318e-1b08-4cc9-a680-6b4a978544f2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "8c7e910a2f904c42baf65e1a8adcfc3e",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/28 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "8f1cb6b26188429eacc4d3377a9de000",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/28 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "smd 0.17627464443920743 0.5532991977145021 0.5087209301507045\n",
      "smd 0.5481480986310059 0.4259421627959828 0.8375471984832733\n",
      "smd 0.07773848243330729 0.059624174098404335 0.3868589298291686\n",
      "smd 0.09433961356354652 0.06895944573367709 0.33102278232655397\n",
      "smd 0.6551723644470901 0.6382942064942079 0.8864078011490509\n",
      "smd 0.8273877527484236 0.8265679846490493 0.8812277955484978\n",
      "smd 0.1906216415238548 0.1247017596178504 0.4679806759112928\n",
      "smd 0.2588235066758958 0.19629561233188014 0.586048432840561\n",
      "smd 0.34715816814779354 0.29463362114907016 0.7826940600216972\n",
      "smd 0.21837868410447125 0.2041617254668438 0.5088235636311222\n",
      "smd 0.34482754644768576 0.4159207787172737 0.8278167977193284\n",
      "smd 0.31284913550347165 0.23810251769053353 0.3752013740806507\n",
      "smd 0.2389609987006308 0.23474571424765706 0.7973527135463029\n",
      "smd 0.45751630398564924 0.3932709571190476 0.6612469380247212\n",
      "smd 0.6814158814550898 0.6113122055182829 0.8810666418082104\n",
      "smd 0.9629629106538662 0.9296134952390191 0.979060407943543\n",
      "smd 0.515199960674307 0.6695032910658268 0.6753119822946891\n",
      "smd 0.49557518220691027 0.6454617701005906 0.6666131701364144\n",
      "smd 0.8204081142632265 0.7280116593777102 0.8219163832251319\n",
      "smd 0.4473683798822749 0.36080222354708014 0.8901132994280294\n",
      "smd 0.12252250861387302 0.05244952150564719 0.5492608072434919\n",
      "smd 0.10701105487432305 0.04343778121480254 0.657824447199395\n",
      "smd 0.8391038194631708 0.8341141973394656 0.9118460242179138\n",
      "smd 0.3207546684585335 0.17957518066811617 0.7460801626124511\n",
      "smd 0.4565216959224993 0.3672883281285523 0.6179821721448302\n",
      "smd 0.14173227007254122 0.3213253986866291 0.6632863438946439\n",
      "smd 0.4746268156302125 0.4718927757276384 0.8766479980020385\n",
      "smd 0.47787606634819013 0.365769040735772 0.6621478859188258\n"
     ]
    }
   ],
   "source": [
    "for loader in [load_smd]:\n",
    "    datasets = loader(8, 4)\n",
    "    x_trains, x_tests, y_tests = datasets['x_train'], datasets['x_test'], datasets['y_test']\n",
    "    \n",
    "    for i in tqdm(range(len(x_trains))):\n",
    "        tf.keras.backend.clear_session()\n",
    "\n",
    "        X_train = x_trains[i]\n",
    "        X_test = x_tests[i]\n",
    "        \n",
    "        gan = get_gan(X_train)\n",
    "        dataset = tf.data.Dataset.from_tensor_slices(X_train)\n",
    "        dataset = dataset.batch(128, drop_remainder=True).prefetch(1)\n",
    "\n",
    "        train_gan(gan, dataset, 128, X_train.shape[1], X_train.shape[2])\n",
    "        \n",
    "        X_test_rec = gan.layers[0].predict(X_test)\n",
    "        scores = evaluate(X_test, X_test_rec, y_tests[i], is_reconstructed=True)\n",
    "\n",
    "        total_scores['dataset'].append(loader.__name__.replace('load_', ''))\n",
    "        total_scores['f1'].append(np.max(scores['f1']))\n",
    "        total_scores['pr_auc'].append(scores['pr_auc'])\n",
    "        total_scores['roc_auc'].append(scores['roc_auc'])\n",
    "        print(loader.__name__.replace('load_', ''), np.max(scores['f1']), scores['pr_auc'], scores['roc_auc'])   "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "23474773-bac1-4145-ac75-c1a686bca5c6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>f1</th>\n",
       "      <th>pr_auc</th>\n",
       "      <th>roc_auc</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>dataset</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>smd</th>\n",
       "      <td>0.414688</td>\n",
       "      <td>0.401967</td>\n",
       "      <td>0.694218</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               f1    pr_auc   roc_auc\n",
       "dataset                              \n",
       "smd      0.414688  0.401967  0.694218"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "smd_results = pd.DataFrame(total_scores)\n",
    "smd_results.groupby('dataset').mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f6df487f-7988-42e3-b3c6-905a1793ee6b",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "id": "1acf69c6-5136-40b1-a62e-0057ab6e8e79",
   "metadata": {},
   "source": [
    "### ECG"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "110fcd09-f039-43a6-a27a-3b05f17e24fd",
   "metadata": {},
   "outputs": [],
   "source": [
    "total_scores = {'dataset': [], 'f1': [], 'pr_auc': [], 'roc_auc': []}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "33e7998d-10e7-48c4-b2a4-c5e841abc77c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "06e0ef1fc29943199baebca5cd0dde6d",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/9 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "2f0331b1ddb6444dbe109f092e50caa9",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/9 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "D1 0.4210525813875098 0.3578865019087283 0.7668660624922247\n",
      "D2 0.4166666162344164 0.3424245336460199 0.7531017832194177\n",
      "D3 0.11734690745783838 0.05144644042821206 0.5301683670705016\n",
      "D4 0.24608498622184435 0.14999305654866596 0.5900093135255483\n",
      "D5 0.36792448340602174 0.23728753952082596 0.7083972332979065\n",
      "D6 0.20300749777105886 0.10099505348921684 0.5869722645103785\n",
      "D7 0.04649986871269535 0.016385874366508405 0.4171229992882579\n",
      "D8 0.18743959152484563 0.08171768584150915 0.4626302628521304\n",
      "D9 0.45519199456505577 0.29900534345303076 0.6721090239727271\n"
     ]
    }
   ],
   "source": [
    "for loader in [load_ecg]:\n",
    "    datasets = loader(4, 2)\n",
    "    x_trains, x_tests, y_tests = datasets['x_train'], datasets['x_test'], datasets['y_test']\n",
    "    \n",
    "    for i in tqdm(range(len(x_trains))):\n",
    "        tf.keras.backend.clear_session()\n",
    "\n",
    "        X_train = x_trains[i]\n",
    "        X_test = x_tests[i]\n",
    "        \n",
    "        gan = get_gan(X_train)\n",
    "        dataset = tf.data.Dataset.from_tensor_slices(X_train)\n",
    "        dataset = dataset.batch(128, drop_remainder=True).prefetch(1)\n",
    "\n",
    "        train_gan(gan, dataset, 128, X_train.shape[1], X_train.shape[2])\n",
    "        \n",
    "        X_test_rec = gan.layers[0].predict(X_test)\n",
    "        scores = evaluate(X_test, X_test_rec, y_tests[i], is_reconstructed=True)\n",
    "        \n",
    "        total_scores['dataset'].append(f'D{i+1}')\n",
    "        total_scores['f1'].append(np.max(scores['f1']))\n",
    "        total_scores['pr_auc'].append(scores['pr_auc'])\n",
    "        total_scores['roc_auc'].append(scores['roc_auc'])\n",
    "        print(f'D{i+1}', np.max(scores['f1']), scores['pr_auc'], scores['roc_auc'])  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "dd066703-fab4-4dc0-8e8f-57fc2a9a7ff4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>f1</th>\n",
       "      <th>pr_auc</th>\n",
       "      <th>roc_auc</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>dataset</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>D1</th>\n",
       "      <td>0.421053</td>\n",
       "      <td>0.357887</td>\n",
       "      <td>0.766866</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>D2</th>\n",
       "      <td>0.416667</td>\n",
       "      <td>0.342425</td>\n",
       "      <td>0.753102</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>D3</th>\n",
       "      <td>0.117347</td>\n",
       "      <td>0.051446</td>\n",
       "      <td>0.530168</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>D4</th>\n",
       "      <td>0.246085</td>\n",
       "      <td>0.149993</td>\n",
       "      <td>0.590009</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>D5</th>\n",
       "      <td>0.367924</td>\n",
       "      <td>0.237288</td>\n",
       "      <td>0.708397</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>D6</th>\n",
       "      <td>0.203007</td>\n",
       "      <td>0.100995</td>\n",
       "      <td>0.586972</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>D7</th>\n",
       "      <td>0.046500</td>\n",
       "      <td>0.016386</td>\n",
       "      <td>0.417123</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>D8</th>\n",
       "      <td>0.187440</td>\n",
       "      <td>0.081718</td>\n",
       "      <td>0.462630</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>D9</th>\n",
       "      <td>0.455192</td>\n",
       "      <td>0.299005</td>\n",
       "      <td>0.672109</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               f1    pr_auc   roc_auc\n",
       "dataset                              \n",
       "D1       0.421053  0.357887  0.766866\n",
       "D2       0.416667  0.342425  0.753102\n",
       "D3       0.117347  0.051446  0.530168\n",
       "D4       0.246085  0.149993  0.590009\n",
       "D5       0.367924  0.237288  0.708397\n",
       "D6       0.203007  0.100995  0.586972\n",
       "D7       0.046500  0.016386  0.417123\n",
       "D8       0.187440  0.081718  0.462630\n",
       "D9       0.455192  0.299005  0.672109"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ecg_results = pd.DataFrame(total_scores)\n",
    "ecg_results.groupby('dataset').mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bd5e9ccb-ba17-4936-81f4-c5b2a0435849",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "id": "32b55486-3ced-4ecd-8b4b-3e7faf10abe4",
   "metadata": {},
   "source": [
    "### Power Demand"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "83b22ae9-1df8-4d9c-8db1-e4f719476df5",
   "metadata": {},
   "outputs": [],
   "source": [
    "total_scores = {'dataset': [], 'f1': [], 'pr_auc': [], 'roc_auc': []}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "5ee504a8-18a9-45ec-ae6a-387138d55736",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "c768f6b88a01486fb13a673d726057bf",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/1 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "power_demand 0.4166666180555608 0.3270262158593743 0.6852466917759956\n"
     ]
    }
   ],
   "source": [
    "for loader in [load_power_demand]:\n",
    "    datasets = loader(16, 8)\n",
    "    x_trains, x_tests, y_tests = datasets['x_train'], datasets['x_test'], datasets['y_test']\n",
    "    \n",
    "    for i in tqdm(range(len(x_trains))):\n",
    "        tf.keras.backend.clear_session()\n",
    "\n",
    "        X_train = x_trains[i]\n",
    "        X_test = x_tests[i]\n",
    "        \n",
    "        gan = get_gan(X_train)\n",
    "        dataset = tf.data.Dataset.from_tensor_slices(X_train)\n",
    "        dataset = dataset.batch(128, drop_remainder=True).prefetch(1)\n",
    "\n",
    "        train_gan(gan, dataset, 128, X_train.shape[1], X_train.shape[2])\n",
    "        \n",
    "        X_test_rec = gan.layers[0].predict(X_test)\n",
    "        scores = evaluate(X_test, X_test_rec, y_tests[i], is_reconstructed=True)\n",
    "\n",
    "        total_scores['dataset'].append(loader.__name__.replace('load_', ''))\n",
    "        total_scores['f1'].append(np.max(scores['f1']))\n",
    "        total_scores['pr_auc'].append(scores['pr_auc'])\n",
    "        total_scores['roc_auc'].append(scores['roc_auc'])\n",
    "        print(loader.__name__.replace('load_', ''), np.max(scores['f1']), scores['pr_auc'], scores['roc_auc']) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "96a9ddc1-cd03-4d47-8586-d9ac8ac25dea",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>f1</th>\n",
       "      <th>pr_auc</th>\n",
       "      <th>roc_auc</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>dataset</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>power_demand</th>\n",
       "      <td>0.416667</td>\n",
       "      <td>0.327026</td>\n",
       "      <td>0.685247</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                    f1    pr_auc   roc_auc\n",
       "dataset                                   \n",
       "power_demand  0.416667  0.327026  0.685247"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "power_results = pd.DataFrame(total_scores)\n",
    "power_results.groupby('dataset').mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "fa4c3be7-4006-417e-bc75-76b7fba8a508",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "id": "21a2dd28-adbe-432c-9dfc-5fb478728d1b",
   "metadata": {},
   "source": [
    "### 2D Gesture"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "335b8cb2-b416-4850-8888-68af70886b73",
   "metadata": {},
   "outputs": [],
   "source": [
    "total_scores = {'dataset': [], 'f1': [], 'pr_auc': [], 'roc_auc': []}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "b1a951c6-fdc5-4b0c-be0b-244e57b4c024",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "63fce210c35e4fe293af677c8d6c0362",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/1 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "gesture 0.41320429272434867 0.2402366166809034 0.4903753928437219\n"
     ]
    }
   ],
   "source": [
    "for loader in [load_gesture]:\n",
    "    datasets = loader(4, 2)\n",
    "    x_trains, x_tests, y_tests = datasets['x_train'], datasets['x_test'], datasets['y_test']\n",
    "    \n",
    "    for i in tqdm(range(len(x_trains))):\n",
    "        tf.keras.backend.clear_session()\n",
    "\n",
    "        X_train = x_trains[i]\n",
    "        X_test = x_tests[i]\n",
    "        \n",
    "        gan = get_gan(X_train)\n",
    "        dataset = tf.data.Dataset.from_tensor_slices(X_train)\n",
    "        dataset = dataset.batch(128, drop_remainder=True).prefetch(1)\n",
    "\n",
    "        train_gan(gan, dataset, 128, X_train.shape[1], X_train.shape[2])\n",
    "        \n",
    "        X_test_rec = gan.layers[0].predict(X_test)\n",
    "        scores = evaluate(X_test, X_test_rec, y_tests[i], is_reconstructed=True)\n",
    "\n",
    "\n",
    "        total_scores['dataset'].append(loader.__name__.replace('load_', ''))\n",
    "        total_scores['f1'].append(np.max(scores['f1']))\n",
    "        total_scores['pr_auc'].append(scores['pr_auc'])\n",
    "        total_scores['roc_auc'].append(scores['roc_auc'])\n",
    "        print(loader.__name__.replace('load_', ''), np.max(scores['f1']), scores['pr_auc'], scores['roc_auc'])  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "689bf1c8-2e34-4d9a-8a64-e17cd0b7df40",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>f1</th>\n",
       "      <th>pr_auc</th>\n",
       "      <th>roc_auc</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>dataset</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>gesture</th>\n",
       "      <td>0.413204</td>\n",
       "      <td>0.240237</td>\n",
       "      <td>0.490375</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               f1    pr_auc   roc_auc\n",
       "dataset                              \n",
       "gesture  0.413204  0.240237  0.490375"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gesture_results = pd.DataFrame(total_scores)\n",
    "gesture_results.groupby('dataset').mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d12fde49-4a92-4e2c-9d8b-e77590499ced",
   "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": "3.7.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}