├── DDOS_CNN.ipynb
├── DDOS_SGD,_KNN,_Naive_Bayes.ipynb
├── DDOS_XGBoost.ipynb
├── DDOS_dataProcessing.ipynb
├── README.md
└── where_to_find_the_preprocessed_dataset.md


/DDOS_CNN.ipynb:
--------------------------------------------------------------------------------
   1 | {
   2 |   "nbformat": 4,
   3 |   "nbformat_minor": 0,
   4 |   "metadata": {
   5 |     "colab": {
   6 |       "name": "DDOS_CNN.ipynb",
   7 |       "provenance": [],
   8 |       "collapsed_sections": [],
   9 |       "authorship_tag": "ABX9TyPavcIoMzBgDmgzKpHYimZS",
  10 |       "include_colab_link": true
  11 |     },
  12 |     "kernelspec": {
  13 |       "name": "python3",
  14 |       "display_name": "Python 3"
  15 |     }
  16 |   },
  17 |   "cells": [
  18 |     {
  19 |       "cell_type": "markdown",
  20 |       "metadata": {
  21 |         "id": "view-in-github",
  22 |         "colab_type": "text"
  23 |       },
  24 |       "source": [
  25 |         "<a href=\"https://colab.research.google.com/github/mohak1/DDoS_Attack_Classification/blob/master/DDOS_CNN.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
  26 |       ]
  27 |     },
  28 |     {
  29 |       "cell_type": "code",
  30 |       "metadata": {
  31 |         "id": "xi2WzeFo5Emv",
  32 |         "colab_type": "code",
  33 |         "outputId": "22d20c94-12b3-47fc-bece-92508d7af59d",
  34 |         "colab": {
  35 |           "base_uri": "https://localhost:8080/",
  36 |           "height": 122
  37 |         }
  38 |       },
  39 |       "source": [
  40 |         "from google.colab import drive\n",
  41 |         "drive.mount('/content/drive')"
  42 |       ],
  43 |       "execution_count": 1,
  44 |       "outputs": [
  45 |         {
  46 |           "output_type": "stream",
  47 |           "text": [
  48 |             "Go to this URL in a browser: https://accounts.google.com/o/oauth2/auth?client_id=947318989803-6bn6qk8qdgf4n4g3pfee6491hc0brc4i.apps.googleusercontent.com&redirect_uri=urn%3aietf%3awg%3aoauth%3a2.0%3aoob&response_type=code&scope=email%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdocs.test%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdrive%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdrive.photos.readonly%20https%3a%2f%2fwww.googleapis.com%2fauth%2fpeopleapi.readonly\n",
  49 |             "\n",
  50 |             "Enter your authorization code:\n",
  51 |             "··········\n",
  52 |             "Mounted at /content/drive\n"
  53 |           ],
  54 |           "name": "stdout"
  55 |         }
  56 |       ]
  57 |     },
  58 |     {
  59 |       "cell_type": "code",
  60 |       "metadata": {
  61 |         "id": "MiEJKiYQ5LS9",
  62 |         "colab_type": "code",
  63 |         "outputId": "3c499ab5-02ef-4bb9-c60e-1d64b34eb816",
  64 |         "colab": {
  65 |           "base_uri": "https://localhost:8080/",
  66 |           "height": 80
  67 |         }
  68 |       },
  69 |       "source": [
  70 |         " #%tensorflow_version 2.x\n",
  71 |         "from sklearn.preprocessing import LabelEncoder\n",
  72 |         "from keras.models import Sequential\n",
  73 |         "from keras.layers import Dense, Dropout, Activation, Lambda, Flatten\n",
  74 |         "from keras.layers import Convolution1D, Dense, Dropout, MaxPooling1D, LSTM\n",
  75 |         "from sklearn.model_selection import train_test_split\n",
  76 |         "from sklearn.preprocessing import Normalizer\n",
  77 |         "from keras import callbacks\n",
  78 |         "from keras.callbacks import CSVLogger\n",
  79 |         "from keras.utils import to_categorical\n",
  80 |         "from keras.callbacks import ModelCheckpoint, EarlyStopping, ReduceLROnPlateau, CSVLogger\n",
  81 |         "import numpy as np\n",
  82 |         "np.random.seed(0)"
  83 |       ],
  84 |       "execution_count": 2,
  85 |       "outputs": [
  86 |         {
  87 |           "output_type": "stream",
  88 |           "text": [
  89 |             "Using TensorFlow backend.\n"
  90 |           ],
  91 |           "name": "stderr"
  92 |         },
  93 |         {
  94 |           "output_type": "display_data",
  95 |           "data": {
  96 |             "text/html": [
  97 |               "<p style=\"color: red;\">\n",
  98 |               "The default version of TensorFlow in Colab will soon switch to TensorFlow 2.x.<br>\n",
  99 |               "We recommend you <a href=\"https://www.tensorflow.org/guide/migrate\" target=\"_blank\">upgrade</a> now \n",
 100 |               "or ensure your notebook will continue to use TensorFlow 1.x via the <code>%tensorflow_version 1.x</code> magic:\n",
 101 |               "<a href=\"https://colab.research.google.com/notebooks/tensorflow_version.ipynb\" target=\"_blank\">more info</a>.</p>\n"
 102 |             ],
 103 |             "text/plain": [
 104 |               "<IPython.core.display.HTML object>"
 105 |             ]
 106 |           },
 107 |           "metadata": {
 108 |             "tags": []
 109 |           }
 110 |         }
 111 |       ]
 112 |     },
 113 |     {
 114 |       "cell_type": "code",
 115 |       "metadata": {
 116 |         "id": "U8Y02jOF5RN7",
 117 |         "colab_type": "code",
 118 |         "colab": {}
 119 |       },
 120 |       "source": [
 121 |         "#loading dataset\n",
 122 |         "import pandas as pd\n",
 123 |         "x = pd.read_csv(\"/content/drive/My Drive/dos_dataset/clean_5.csv\")\n",
 124 |         "y = pd.read_csv(\"/content/drive/My Drive/dos_dataset/y.csv\")\n",
 125 |         "y=y['Label']\n",
 126 |         "x=x.drop(['Label'], axis=1)\n",
 127 |         "\n",
 128 |         "#normalizing the data\n",
 129 |         "normalized_df=(x-x.mean())/x.std()"
 130 |       ],
 131 |       "execution_count": 0,
 132 |       "outputs": []
 133 |     },
 134 |     {
 135 |       "cell_type": "code",
 136 |       "metadata": {
 137 |         "id": "EjJebHdeDSDD",
 138 |         "colab_type": "code",
 139 |         "colab": {}
 140 |       },
 141 |       "source": [
 142 |         "normalized_df=normalized_df.drop(['Unnamed: 0'], axis=1)\n",
 143 |         "normalized_df=normalized_df.drop(['Unnamed: 0.1'], axis=1)\n",
 144 |         "normalized_df=normalized_df.drop(['Unnamed: 0.1.1'], axis=1)\n",
 145 |         "normalized_df=normalized_df.drop(['Flow Bytes/s'], axis=1)\n",
 146 |         "normalized_df=normalized_df.drop([' Flow Packets/s'], axis=1)\n"
 147 |       ],
 148 |       "execution_count": 0,
 149 |       "outputs": []
 150 |     },
 151 |     {
 152 |       "cell_type": "code",
 153 |       "metadata": {
 154 |         "id": "8ilKdvOK5UDd",
 155 |         "colab_type": "code",
 156 |         "outputId": "9573b97f-7d71-4de1-d5cc-e5ac7b5573c0",
 157 |         "colab": {
 158 |           "base_uri": "https://localhost:8080/",
 159 |           "height": 275
 160 |         }
 161 |       },
 162 |       "source": [
 163 |         "normalized_df.head()"
 164 |       ],
 165 |       "execution_count": 5,
 166 |       "outputs": [
 167 |         {
 168 |           "output_type": "execute_result",
 169 |           "data": {
 170 |             "text/html": [
 171 |               "<div>\n",
 172 |               "<style scoped>\n",
 173 |               "    .dataframe tbody tr th:only-of-type {\n",
 174 |               "        vertical-align: middle;\n",
 175 |               "    }\n",
 176 |               "\n",
 177 |               "    .dataframe tbody tr th {\n",
 178 |               "        vertical-align: top;\n",
 179 |               "    }\n",
 180 |               "\n",
 181 |               "    .dataframe thead th {\n",
 182 |               "        text-align: right;\n",
 183 |               "    }\n",
 184 |               "</style>\n",
 185 |               "<table border=\"1\" class=\"dataframe\">\n",
 186 |               "  <thead>\n",
 187 |               "    <tr style=\"text-align: right;\">\n",
 188 |               "      <th></th>\n",
 189 |               "      <th>Source Port</th>\n",
 190 |               "      <th>Destination IP</th>\n",
 191 |               "      <th>Destination Port</th>\n",
 192 |               "      <th>Protocol</th>\n",
 193 |               "      <th>Total Length of Fwd Packets</th>\n",
 194 |               "      <th>Fwd Packet Length Max</th>\n",
 195 |               "      <th>Fwd Packet Length Min</th>\n",
 196 |               "      <th>Fwd Packet Length Mean</th>\n",
 197 |               "      <th>Bwd Packet Length Max</th>\n",
 198 |               "      <th>Bwd Packet Length Min</th>\n",
 199 |               "      <th>Bwd Packet Length Mean</th>\n",
 200 |               "      <th>Bwd Packet Length Std</th>\n",
 201 |               "      <th>Flow IAT Mean</th>\n",
 202 |               "      <th>Flow IAT Std</th>\n",
 203 |               "      <th>Fwd IAT Mean</th>\n",
 204 |               "      <th>Fwd IAT Std</th>\n",
 205 |               "      <th>Fwd PSH Flags</th>\n",
 206 |               "      <th>Fwd Packets/s</th>\n",
 207 |               "      <th>Min Packet Length</th>\n",
 208 |               "      <th>Max Packet Length</th>\n",
 209 |               "      <th>Packet Length Mean</th>\n",
 210 |               "      <th>Packet Length Variance</th>\n",
 211 |               "      <th>RST Flag Count</th>\n",
 212 |               "      <th>ACK Flag Count</th>\n",
 213 |               "      <th>URG Flag Count</th>\n",
 214 |               "      <th>CWE Flag Count</th>\n",
 215 |               "      <th>Average Packet Size</th>\n",
 216 |               "      <th>Avg Fwd Segment Size</th>\n",
 217 |               "      <th>Avg Bwd Segment Size</th>\n",
 218 |               "      <th>Subflow Fwd Bytes</th>\n",
 219 |               "      <th>Init_Win_bytes_forward</th>\n",
 220 |               "      <th>Init_Win_bytes_backward</th>\n",
 221 |               "      <th>Idle Std</th>\n",
 222 |               "      <th>Inbound</th>\n",
 223 |               "    </tr>\n",
 224 |               "  </thead>\n",
 225 |               "  <tbody>\n",
 226 |               "    <tr>\n",
 227 |               "      <th>0</th>\n",
 228 |               "      <td>1.395596</td>\n",
 229 |               "      <td>0.157586</td>\n",
 230 |               "      <td>-0.607399</td>\n",
 231 |               "      <td>-2.031188</td>\n",
 232 |               "      <td>-0.725421</td>\n",
 233 |               "      <td>-0.954992</td>\n",
 234 |               "      <td>-0.935156</td>\n",
 235 |               "      <td>-0.945029</td>\n",
 236 |               "      <td>-0.050579</td>\n",
 237 |               "      <td>0.342849</td>\n",
 238 |               "      <td>0.015085</td>\n",
 239 |               "      <td>-0.076871</td>\n",
 240 |               "      <td>-0.178761</td>\n",
 241 |               "      <td>-0.175445</td>\n",
 242 |               "      <td>-0.178330</td>\n",
 243 |               "      <td>-0.168507</td>\n",
 244 |               "      <td>-0.090471</td>\n",
 245 |               "      <td>-1.335866</td>\n",
 246 |               "      <td>-0.935040</td>\n",
 247 |               "      <td>-0.940755</td>\n",
 248 |               "      <td>-0.948545</td>\n",
 249 |               "      <td>-0.069737</td>\n",
 250 |               "      <td>-0.090471</td>\n",
 251 |               "      <td>2.209740</td>\n",
 252 |               "      <td>-0.153371</td>\n",
 253 |               "      <td>-0.101473</td>\n",
 254 |               "      <td>-0.933777</td>\n",
 255 |               "      <td>-0.945029</td>\n",
 256 |               "      <td>0.015085</td>\n",
 257 |               "      <td>-0.725421</td>\n",
 258 |               "      <td>-0.054584</td>\n",
 259 |               "      <td>-0.057299</td>\n",
 260 |               "      <td>-0.162793</td>\n",
 261 |               "      <td>0.19758</td>\n",
 262 |               "    </tr>\n",
 263 |               "    <tr>\n",
 264 |               "      <th>1</th>\n",
 265 |               "      <td>0.347887</td>\n",
 266 |               "      <td>0.157586</td>\n",
 267 |               "      <td>-1.625958</td>\n",
 268 |               "      <td>-2.031188</td>\n",
 269 |               "      <td>-0.733744</td>\n",
 270 |               "      <td>-0.954992</td>\n",
 271 |               "      <td>-0.935156</td>\n",
 272 |               "      <td>-0.945029</td>\n",
 273 |               "      <td>-0.050579</td>\n",
 274 |               "      <td>0.342849</td>\n",
 275 |               "      <td>0.015085</td>\n",
 276 |               "      <td>-0.076871</td>\n",
 277 |               "      <td>-0.216151</td>\n",
 278 |               "      <td>-0.222876</td>\n",
 279 |               "      <td>-0.227006</td>\n",
 280 |               "      <td>-0.222546</td>\n",
 281 |               "      <td>-0.090471</td>\n",
 282 |               "      <td>-1.324001</td>\n",
 283 |               "      <td>-0.935040</td>\n",
 284 |               "      <td>-0.940755</td>\n",
 285 |               "      <td>-0.948545</td>\n",
 286 |               "      <td>-0.069737</td>\n",
 287 |               "      <td>-0.090471</td>\n",
 288 |               "      <td>2.209740</td>\n",
 289 |               "      <td>-0.153371</td>\n",
 290 |               "      <td>-0.101473</td>\n",
 291 |               "      <td>-0.933085</td>\n",
 292 |               "      <td>-0.945029</td>\n",
 293 |               "      <td>0.015085</td>\n",
 294 |               "      <td>-0.733744</td>\n",
 295 |               "      <td>7.027636</td>\n",
 296 |               "      <td>-0.057299</td>\n",
 297 |               "      <td>-0.162793</td>\n",
 298 |               "      <td>0.19758</td>\n",
 299 |               "    </tr>\n",
 300 |               "    <tr>\n",
 301 |               "      <th>2</th>\n",
 302 |               "      <td>1.196809</td>\n",
 303 |               "      <td>0.157586</td>\n",
 304 |               "      <td>-0.560525</td>\n",
 305 |               "      <td>-2.031188</td>\n",
 306 |               "      <td>-0.725421</td>\n",
 307 |               "      <td>-0.954992</td>\n",
 308 |               "      <td>-0.935156</td>\n",
 309 |               "      <td>-0.945029</td>\n",
 310 |               "      <td>-0.050579</td>\n",
 311 |               "      <td>0.342849</td>\n",
 312 |               "      <td>0.015085</td>\n",
 313 |               "      <td>-0.076871</td>\n",
 314 |               "      <td>-0.182709</td>\n",
 315 |               "      <td>-0.180450</td>\n",
 316 |               "      <td>-0.183461</td>\n",
 317 |               "      <td>-0.174204</td>\n",
 318 |               "      <td>-0.090471</td>\n",
 319 |               "      <td>-1.335864</td>\n",
 320 |               "      <td>-0.935040</td>\n",
 321 |               "      <td>-0.940755</td>\n",
 322 |               "      <td>-0.948545</td>\n",
 323 |               "      <td>-0.069737</td>\n",
 324 |               "      <td>-0.090471</td>\n",
 325 |               "      <td>2.209740</td>\n",
 326 |               "      <td>-0.153371</td>\n",
 327 |               "      <td>-0.101473</td>\n",
 328 |               "      <td>-0.933777</td>\n",
 329 |               "      <td>-0.945029</td>\n",
 330 |               "      <td>0.015085</td>\n",
 331 |               "      <td>-0.725421</td>\n",
 332 |               "      <td>-0.054584</td>\n",
 333 |               "      <td>-0.057299</td>\n",
 334 |               "      <td>-0.162793</td>\n",
 335 |               "      <td>0.19758</td>\n",
 336 |               "    </tr>\n",
 337 |               "    <tr>\n",
 338 |               "      <th>3</th>\n",
 339 |               "      <td>0.892029</td>\n",
 340 |               "      <td>0.157586</td>\n",
 341 |               "      <td>-1.562081</td>\n",
 342 |               "      <td>-2.031188</td>\n",
 343 |               "      <td>-0.725421</td>\n",
 344 |               "      <td>-0.954992</td>\n",
 345 |               "      <td>-0.935156</td>\n",
 346 |               "      <td>-0.945029</td>\n",
 347 |               "      <td>-0.050579</td>\n",
 348 |               "      <td>0.342849</td>\n",
 349 |               "      <td>0.015085</td>\n",
 350 |               "      <td>-0.076871</td>\n",
 351 |               "      <td>-0.186161</td>\n",
 352 |               "      <td>-0.184840</td>\n",
 353 |               "      <td>-0.187948</td>\n",
 354 |               "      <td>-0.179186</td>\n",
 355 |               "      <td>-0.090471</td>\n",
 356 |               "      <td>-1.335861</td>\n",
 357 |               "      <td>-0.935040</td>\n",
 358 |               "      <td>-0.940755</td>\n",
 359 |               "      <td>-0.948545</td>\n",
 360 |               "      <td>-0.069737</td>\n",
 361 |               "      <td>-0.090471</td>\n",
 362 |               "      <td>2.209740</td>\n",
 363 |               "      <td>-0.153371</td>\n",
 364 |               "      <td>-0.101473</td>\n",
 365 |               "      <td>-0.933777</td>\n",
 366 |               "      <td>-0.945029</td>\n",
 367 |               "      <td>0.015085</td>\n",
 368 |               "      <td>-0.725421</td>\n",
 369 |               "      <td>-0.054584</td>\n",
 370 |               "      <td>-0.057299</td>\n",
 371 |               "      <td>-0.162793</td>\n",
 372 |               "      <td>0.19758</td>\n",
 373 |               "    </tr>\n",
 374 |               "    <tr>\n",
 375 |               "      <th>4</th>\n",
 376 |               "      <td>-0.914218</td>\n",
 377 |               "      <td>0.157586</td>\n",
 378 |               "      <td>0.169285</td>\n",
 379 |               "      <td>0.489985</td>\n",
 380 |               "      <td>-0.424394</td>\n",
 381 |               "      <td>-0.494002</td>\n",
 382 |               "      <td>-0.472024</td>\n",
 383 |               "      <td>-0.480570</td>\n",
 384 |               "      <td>-0.085259</td>\n",
 385 |               "      <td>-0.138378</td>\n",
 386 |               "      <td>-0.095478</td>\n",
 387 |               "      <td>-0.076871</td>\n",
 388 |               "      <td>-0.216208</td>\n",
 389 |               "      <td>-0.222934</td>\n",
 390 |               "      <td>-0.227005</td>\n",
 391 |               "      <td>-0.222546</td>\n",
 392 |               "      <td>-0.090471</td>\n",
 393 |               "      <td>-0.610670</td>\n",
 394 |               "      <td>-0.471885</td>\n",
 395 |               "      <td>-0.494875</td>\n",
 396 |               "      <td>-0.483551</td>\n",
 397 |               "      <td>-0.069737</td>\n",
 398 |               "      <td>-0.090471</td>\n",
 399 |               "      <td>-0.452542</td>\n",
 400 |               "      <td>-0.153371</td>\n",
 401 |               "      <td>-0.101473</td>\n",
 402 |               "      <td>-0.467788</td>\n",
 403 |               "      <td>-0.480570</td>\n",
 404 |               "      <td>-0.095478</td>\n",
 405 |               "      <td>-0.424394</td>\n",
 406 |               "      <td>-0.362285</td>\n",
 407 |               "      <td>-0.057771</td>\n",
 408 |               "      <td>-0.162793</td>\n",
 409 |               "      <td>0.19758</td>\n",
 410 |               "    </tr>\n",
 411 |               "  </tbody>\n",
 412 |               "</table>\n",
 413 |               "</div>"
 414 |             ],
 415 |             "text/plain": [
 416 |               "    Source Port   Destination IP  ...   Idle Std   Inbound\n",
 417 |               "0      1.395596         0.157586  ...  -0.162793   0.19758\n",
 418 |               "1      0.347887         0.157586  ...  -0.162793   0.19758\n",
 419 |               "2      1.196809         0.157586  ...  -0.162793   0.19758\n",
 420 |               "3      0.892029         0.157586  ...  -0.162793   0.19758\n",
 421 |               "4     -0.914218         0.157586  ...  -0.162793   0.19758\n",
 422 |               "\n",
 423 |               "[5 rows x 34 columns]"
 424 |             ]
 425 |           },
 426 |           "metadata": {
 427 |             "tags": []
 428 |           },
 429 |           "execution_count": 5
 430 |         }
 431 |       ]
 432 |     },
 433 |     {
 434 |       "cell_type": "code",
 435 |       "metadata": {
 436 |         "id": "rEREKWdKiFB2",
 437 |         "colab_type": "code",
 438 |         "outputId": "27c8a91c-19b4-4711-fd89-edb774c80b91",
 439 |         "colab": {
 440 |           "base_uri": "https://localhost:8080/",
 441 |           "height": 34
 442 |         }
 443 |       },
 444 |       "source": [
 445 |         "y.nunique()"
 446 |       ],
 447 |       "execution_count": 6,
 448 |       "outputs": [
 449 |         {
 450 |           "output_type": "execute_result",
 451 |           "data": {
 452 |             "text/plain": [
 453 |               "8"
 454 |             ]
 455 |           },
 456 |           "metadata": {
 457 |             "tags": []
 458 |           },
 459 |           "execution_count": 6
 460 |         }
 461 |       ]
 462 |     },
 463 |     {
 464 |       "cell_type": "code",
 465 |       "metadata": {
 466 |         "id": "zBx1ZPpAKMZ1",
 467 |         "colab_type": "code",
 468 |         "outputId": "1741d9b4-3727-4e2c-9288-9ffc9329362d",
 469 |         "colab": {
 470 |           "base_uri": "https://localhost:8080/",
 471 |           "height": 204
 472 |         }
 473 |       },
 474 |       "source": [
 475 |         "y = pd.get_dummies(y,prefix=['Label'])\n",
 476 |         "y.head()"
 477 |       ],
 478 |       "execution_count": 7,
 479 |       "outputs": [
 480 |         {
 481 |           "output_type": "execute_result",
 482 |           "data": {
 483 |             "text/html": [
 484 |               "<div>\n",
 485 |               "<style scoped>\n",
 486 |               "    .dataframe tbody tr th:only-of-type {\n",
 487 |               "        vertical-align: middle;\n",
 488 |               "    }\n",
 489 |               "\n",
 490 |               "    .dataframe tbody tr th {\n",
 491 |               "        vertical-align: top;\n",
 492 |               "    }\n",
 493 |               "\n",
 494 |               "    .dataframe thead th {\n",
 495 |               "        text-align: right;\n",
 496 |               "    }\n",
 497 |               "</style>\n",
 498 |               "<table border=\"1\" class=\"dataframe\">\n",
 499 |               "  <thead>\n",
 500 |               "    <tr style=\"text-align: right;\">\n",
 501 |               "      <th></th>\n",
 502 |               "      <th>['Label']_0</th>\n",
 503 |               "      <th>['Label']_1</th>\n",
 504 |               "      <th>['Label']_2</th>\n",
 505 |               "      <th>['Label']_3</th>\n",
 506 |               "      <th>['Label']_4</th>\n",
 507 |               "      <th>['Label']_5</th>\n",
 508 |               "      <th>['Label']_6</th>\n",
 509 |               "      <th>['Label']_7</th>\n",
 510 |               "    </tr>\n",
 511 |               "  </thead>\n",
 512 |               "  <tbody>\n",
 513 |               "    <tr>\n",
 514 |               "      <th>0</th>\n",
 515 |               "      <td>0</td>\n",
 516 |               "      <td>0</td>\n",
 517 |               "      <td>1</td>\n",
 518 |               "      <td>0</td>\n",
 519 |               "      <td>0</td>\n",
 520 |               "      <td>0</td>\n",
 521 |               "      <td>0</td>\n",
 522 |               "      <td>0</td>\n",
 523 |               "    </tr>\n",
 524 |               "    <tr>\n",
 525 |               "      <th>1</th>\n",
 526 |               "      <td>0</td>\n",
 527 |               "      <td>0</td>\n",
 528 |               "      <td>1</td>\n",
 529 |               "      <td>0</td>\n",
 530 |               "      <td>0</td>\n",
 531 |               "      <td>0</td>\n",
 532 |               "      <td>0</td>\n",
 533 |               "      <td>0</td>\n",
 534 |               "    </tr>\n",
 535 |               "    <tr>\n",
 536 |               "      <th>2</th>\n",
 537 |               "      <td>0</td>\n",
 538 |               "      <td>0</td>\n",
 539 |               "      <td>1</td>\n",
 540 |               "      <td>0</td>\n",
 541 |               "      <td>0</td>\n",
 542 |               "      <td>0</td>\n",
 543 |               "      <td>0</td>\n",
 544 |               "      <td>0</td>\n",
 545 |               "    </tr>\n",
 546 |               "    <tr>\n",
 547 |               "      <th>3</th>\n",
 548 |               "      <td>0</td>\n",
 549 |               "      <td>0</td>\n",
 550 |               "      <td>1</td>\n",
 551 |               "      <td>0</td>\n",
 552 |               "      <td>0</td>\n",
 553 |               "      <td>0</td>\n",
 554 |               "      <td>0</td>\n",
 555 |               "      <td>0</td>\n",
 556 |               "    </tr>\n",
 557 |               "    <tr>\n",
 558 |               "      <th>4</th>\n",
 559 |               "      <td>0</td>\n",
 560 |               "      <td>0</td>\n",
 561 |               "      <td>1</td>\n",
 562 |               "      <td>0</td>\n",
 563 |               "      <td>0</td>\n",
 564 |               "      <td>0</td>\n",
 565 |               "      <td>0</td>\n",
 566 |               "      <td>0</td>\n",
 567 |               "    </tr>\n",
 568 |               "  </tbody>\n",
 569 |               "</table>\n",
 570 |               "</div>"
 571 |             ],
 572 |             "text/plain": [
 573 |               "   ['Label']_0  ['Label']_1  ['Label']_2  ...  ['Label']_5  ['Label']_6  ['Label']_7\n",
 574 |               "0            0            0            1  ...            0            0            0\n",
 575 |               "1            0            0            1  ...            0            0            0\n",
 576 |               "2            0            0            1  ...            0            0            0\n",
 577 |               "3            0            0            1  ...            0            0            0\n",
 578 |               "4            0            0            1  ...            0            0            0\n",
 579 |               "\n",
 580 |               "[5 rows x 8 columns]"
 581 |             ]
 582 |           },
 583 |           "metadata": {
 584 |             "tags": []
 585 |           },
 586 |           "execution_count": 7
 587 |         }
 588 |       ]
 589 |     },
 590 |     {
 591 |       "cell_type": "code",
 592 |       "metadata": {
 593 |         "id": "yXU3qYsqMecD",
 594 |         "colab_type": "code",
 595 |         "colab": {}
 596 |       },
 597 |       "source": [
 598 |         "from sklearn.model_selection import train_test_split\n",
 599 |         "X_train, X_test, y_train, y_test = train_test_split(normalized_df, y, test_size=0.25, random_state=0)\n",
 600 |         "y_train = np.array(y_train)"
 601 |       ],
 602 |       "execution_count": 0,
 603 |       "outputs": []
 604 |     },
 605 |     {
 606 |       "cell_type": "code",
 607 |       "metadata": {
 608 |         "id": "uXSDDA5b5biN",
 609 |         "colab_type": "code",
 610 |         "colab": {}
 611 |       },
 612 |       "source": [
 613 |         "y_train = np.array(y_train)\n",
 614 |         "y_test = np.array(y_test)\n",
 615 |         "X_train = np.array(X_train)\n",
 616 |         "X_test = np.array(X_test)\n",
 617 |         "X_train = np.reshape(X_train, (X_train.shape[0],X_train.shape[1],1))\n",
 618 |         "X_test = np.reshape(X_test, (X_test.shape[0],X_test.shape[1],1))"
 619 |       ],
 620 |       "execution_count": 0,
 621 |       "outputs": []
 622 |     },
 623 |     {
 624 |       "cell_type": "code",
 625 |       "metadata": {
 626 |         "id": "8AjyOGQX5eNt",
 627 |         "colab_type": "code",
 628 |         "outputId": "e8750d79-c2d8-4fd9-8540-352d01275a78",
 629 |         "colab": {
 630 |           "base_uri": "https://localhost:8080/",
 631 |           "height": 34
 632 |         }
 633 |       },
 634 |       "source": [
 635 |         "print('xtrain={}, ytrain={}, xtest={}, ytest={}'.format(X_train.shape,y_train.shape,X_test.shape,y_test.shape))"
 636 |       ],
 637 |       "execution_count": 10,
 638 |       "outputs": [
 639 |         {
 640 |           "output_type": "stream",
 641 |           "text": [
 642 |             "xtrain=(934348, 34, 1), ytrain=(934348, 8), xtest=(311450, 34, 1), ytest=(311450, 8)\n"
 643 |           ],
 644 |           "name": "stdout"
 645 |         }
 646 |       ]
 647 |     },
 648 |     {
 649 |       "cell_type": "code",
 650 |       "metadata": {
 651 |         "id": "2uy2mGjoMrDg",
 652 |         "colab_type": "code",
 653 |         "colab": {}
 654 |       },
 655 |       "source": [
 656 |         "from keras import optimizers\n",
 657 |         "sgd = optimizers.SGD(lr=0.009, decay=1e-6, momentum=0.9, nesterov=True)"
 658 |       ],
 659 |       "execution_count": 0,
 660 |       "outputs": []
 661 |     },
 662 |     {
 663 |       "cell_type": "code",
 664 |       "metadata": {
 665 |         "id": "eDumRGb15k19",
 666 |         "colab_type": "code",
 667 |         "colab": {}
 668 |       },
 669 |       "source": [
 670 |         "model = Sequential()\n",
 671 |         "model.add(Convolution1D(64, 3, activation=\"relu\", input_shape=(34,1)))\n",
 672 |         "model.add(Convolution1D(32, 3, activation=\"relu\"))\n",
 673 |         "#model.add(MaxPooling1D(pool_size=2))\n",
 674 |         "#model.add(Convolution1D(128, 3, activation=\"relu\"))\n",
 675 |         "#model.add(Convolution1D(128, 3, activation=\"relu\"))\n",
 676 |         "model.add(MaxPooling1D(pool_size=2))\n",
 677 |         "#model.add(Dropout(rate=0.3))\n",
 678 |         "model.add(Flatten())\n",
 679 |         "#model.add(Dense(30, activation=\"softmax\"))\n",
 680 |         "#model.add(Dense(10, activation=\"softmax\"))\n",
 681 |         "model.add(Dense(8))\n",
 682 |         "\n"
 683 |       ],
 684 |       "execution_count": 0,
 685 |       "outputs": []
 686 |     },
 687 |     {
 688 |       "cell_type": "code",
 689 |       "metadata": {
 690 |         "id": "AWBHKfGKM431",
 691 |         "colab_type": "code",
 692 |         "outputId": "9ce118f3-626c-4b95-bdc1-57653bce4776",
 693 |         "colab": {
 694 |           "base_uri": "https://localhost:8080/",
 695 |           "height": 921
 696 |         }
 697 |       },
 698 |       "source": [
 699 |         "model.compile(loss=\"mean_absolute_error\", optimizer=\"SGD\", metrics=['accuracy'])\n",
 700 |         "\n",
 701 |         "model.fit(X_train, y_train, epochs=20, batch_size=10, validation_data=(X_test, y_test))"
 702 |       ],
 703 |       "execution_count": 0,
 704 |       "outputs": [
 705 |         {
 706 |           "output_type": "stream",
 707 |           "text": [
 708 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:1033: The name tf.assign_add is deprecated. Please use tf.compat.v1.assign_add instead.\n",
 709 |             "\n",
 710 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:1020: The name tf.assign is deprecated. Please use tf.compat.v1.assign instead.\n",
 711 |             "\n",
 712 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:3005: The name tf.Session is deprecated. Please use tf.compat.v1.Session instead.\n",
 713 |             "\n",
 714 |             "Train on 934348 samples, validate on 311450 samples\n",
 715 |             "Epoch 1/20\n",
 716 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:190: The name tf.get_default_session is deprecated. Please use tf.compat.v1.get_default_session instead.\n",
 717 |             "\n",
 718 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:197: The name tf.ConfigProto is deprecated. Please use tf.compat.v1.ConfigProto instead.\n",
 719 |             "\n",
 720 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:207: The name tf.global_variables is deprecated. Please use tf.compat.v1.global_variables instead.\n",
 721 |             "\n",
 722 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:216: The name tf.is_variable_initialized is deprecated. Please use tf.compat.v1.is_variable_initialized instead.\n",
 723 |             "\n",
 724 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:223: The name tf.variables_initializer is deprecated. Please use tf.compat.v1.variables_initializer instead.\n",
 725 |             "\n",
 726 |             "934348/934348 [==============================] - 251s 268us/step - loss: 0.0641 - acc: 0.7995 - val_loss: 0.0566 - val_acc: 0.8215\n",
 727 |             "Epoch 2/20\n",
 728 |             "934348/934348 [==============================] - 250s 267us/step - loss: 0.0533 - acc: 0.8234 - val_loss: 0.0513 - val_acc: 0.8190\n",
 729 |             "Epoch 3/20\n",
 730 |             "934348/934348 [==============================] - 250s 267us/step - loss: 0.0509 - acc: 0.8227 - val_loss: 0.0509 - val_acc: 0.8215\n",
 731 |             "Epoch 4/20\n",
 732 |             "934348/934348 [==============================] - 247s 264us/step - loss: 0.0496 - acc: 0.8235 - val_loss: 0.0497 - val_acc: 0.8231\n",
 733 |             "Epoch 5/20\n",
 734 |             "934348/934348 [==============================] - 248s 265us/step - loss: 0.0488 - acc: 0.8239 - val_loss: 0.0487 - val_acc: 0.8232\n",
 735 |             "Epoch 6/20\n",
 736 |             "934348/934348 [==============================] - 247s 265us/step - loss: 0.0482 - acc: 0.8244 - val_loss: 0.0476 - val_acc: 0.8232\n",
 737 |             "Epoch 7/20\n",
 738 |             "934348/934348 [==============================] - 249s 266us/step - loss: 0.0477 - acc: 0.8248 - val_loss: 0.0482 - val_acc: 0.8232\n",
 739 |             "Epoch 8/20\n",
 740 |             " 50410/934348 [>.............................] - ETA: 3:18 - loss: 0.0481 - acc: 0.8231"
 741 |           ],
 742 |           "name": "stdout"
 743 |         },
 744 |         {
 745 |           "output_type": "error",
 746 |           "ename": "KeyboardInterrupt",
 747 |           "evalue": "ignored",
 748 |           "traceback": [
 749 |             "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
 750 |             "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
 751 |             "\u001b[0;32m<ipython-input-30-c92d71de67a2>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcompile\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mloss\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"mean_absolute_error\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0moptimizer\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"SGD\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmetrics\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'accuracy'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      2\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 3\u001b[0;31m \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX_train\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_train\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mepochs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m20\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbatch_size\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m10\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalidation_data\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX_test\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_test\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
 752 |             "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/keras/engine/training.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_freq, max_queue_size, workers, use_multiprocessing, **kwargs)\u001b[0m\n\u001b[1;32m   1176\u001b[0m                                         \u001b[0msteps_per_epoch\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0msteps_per_epoch\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1177\u001b[0m                                         \u001b[0mvalidation_steps\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mvalidation_steps\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1178\u001b[0;31m                                         validation_freq=validation_freq)\n\u001b[0m\u001b[1;32m   1179\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1180\u001b[0m     def evaluate(self,\n",
 753 |             "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/keras/engine/training_arrays.py\u001b[0m in \u001b[0;36mfit_loop\u001b[0;34m(model, fit_function, fit_inputs, out_labels, batch_size, epochs, verbose, callbacks, val_function, val_inputs, shuffle, callback_metrics, initial_epoch, steps_per_epoch, validation_steps, validation_freq)\u001b[0m\n\u001b[1;32m    202\u001b[0m                     \u001b[0mins_batch\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mins_batch\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtoarray\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    203\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 204\u001b[0;31m                 \u001b[0mouts\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfit_function\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mins_batch\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    205\u001b[0m                 \u001b[0mouts\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mto_list\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mouts\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    206\u001b[0m                 \u001b[0;32mfor\u001b[0m \u001b[0ml\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mo\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mzip\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mout_labels\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mouts\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
 754 |             "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, inputs)\u001b[0m\n\u001b[1;32m   2977\u001b[0m                     \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_legacy_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2978\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2979\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2980\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2981\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mpy_any\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mis_tensor\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mx\u001b[0m \u001b[0;32min\u001b[0m \u001b[0minputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
 755 |             "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py\u001b[0m in \u001b[0;36m_call\u001b[0;34m(self, inputs)\u001b[0m\n\u001b[1;32m   2935\u001b[0m             \u001b[0mfetched\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_callable_fn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0marray_vals\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrun_metadata\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrun_metadata\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2936\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2937\u001b[0;31m             \u001b[0mfetched\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_callable_fn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0marray_vals\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2938\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mfetched\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0moutputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2939\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
 756 |             "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/client/session.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1470\u001b[0m         ret = tf_session.TF_SessionRunCallable(self._session._session,\n\u001b[1;32m   1471\u001b[0m                                                \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_handle\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1472\u001b[0;31m                                                run_metadata_ptr)\n\u001b[0m\u001b[1;32m   1473\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mrun_metadata\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1474\u001b[0m           \u001b[0mproto_data\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtf_session\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mTF_GetBuffer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrun_metadata_ptr\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
 757 |             "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
 758 |           ]
 759 |         }
 760 |       ]
 761 |     },
 762 |     {
 763 |       "cell_type": "code",
 764 |       "metadata": {
 765 |         "id": "QJBkErPzm9im",
 766 |         "colab_type": "code",
 767 |         "outputId": "df42b31f-d3c6-4a2e-9c7b-e86454f43e2d",
 768 |         "colab": {
 769 |           "base_uri": "https://localhost:8080/",
 770 |           "height": 595
 771 |         }
 772 |       },
 773 |       "source": [
 774 |         "m = Sequential()\n",
 775 |         "m.add(Convolution1D(128, 3, activation=\"relu\", input_shape=(34,1)))\n",
 776 |         "m.add(Convolution1D(64, 3, activation=\"relu\"))\n",
 777 |         "m.add(MaxPooling1D(pool_size=2))\n",
 778 |         "#model.add(Dropout(rate=0.3))\n",
 779 |         "#m.add(LSTM(500))\n",
 780 |         "m.add(Flatten())\n",
 781 |         "m.add(Dense(8))\n",
 782 |         "\n",
 783 |         "\n",
 784 |         "m.compile(loss=\"mean_absolute_error\", optimizer=\"adam\", metrics=['accuracy'])\n",
 785 |         "m.fit(X_train, y_train, epochs=20, batch_size=10, validation_data=(X_test, y_test))"
 786 |       ],
 787 |       "execution_count": 0,
 788 |       "outputs": [
 789 |         {
 790 |           "output_type": "stream",
 791 |           "text": [
 792 |             "Train on 934348 samples, validate on 311450 samples\n",
 793 |             "Epoch 1/20\n",
 794 |             "934348/934348 [==============================] - 430s 460us/step - loss: 0.0475 - acc: 0.8276 - val_loss: 0.0453 - val_acc: 0.8297\n",
 795 |             "Epoch 2/20\n",
 796 |             "934348/934348 [==============================] - 430s 460us/step - loss: 0.0443 - acc: 0.8361 - val_loss: 0.0430 - val_acc: 0.8385\n",
 797 |             "Epoch 3/20\n",
 798 |             "934348/934348 [==============================] - 429s 459us/step - loss: 0.0437 - acc: 0.8377 - val_loss: 0.0436 - val_acc: 0.8333\n",
 799 |             "Epoch 4/20\n",
 800 |             "934348/934348 [==============================] - 431s 461us/step - loss: 0.0429 - acc: 0.8391 - val_loss: 0.0424 - val_acc: 0.8393\n",
 801 |             "Epoch 5/20\n",
 802 |             "934348/934348 [==============================] - 429s 459us/step - loss: 0.0425 - acc: 0.8395 - val_loss: 0.0433 - val_acc: 0.8340\n",
 803 |             "Epoch 6/20\n",
 804 |             "934348/934348 [==============================] - 429s 459us/step - loss: 0.0423 - acc: 0.8397 - val_loss: 0.0431 - val_acc: 0.8384\n",
 805 |             "Epoch 7/20\n",
 806 |             "279910/934348 [=======>......................] - ETA: 4:24 - loss: 0.0424 - acc: 0.8392"
 807 |           ],
 808 |           "name": "stdout"
 809 |         },
 810 |         {
 811 |           "output_type": "error",
 812 |           "ename": "KeyboardInterrupt",
 813 |           "evalue": "ignored",
 814 |           "traceback": [
 815 |             "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
 816 |             "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
 817 |             "\u001b[0;32m<ipython-input-31-6f92c837056c>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     10\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     11\u001b[0m \u001b[0mm\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcompile\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mloss\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"mean_absolute_error\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0moptimizer\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"adam\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmetrics\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'accuracy'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 12\u001b[0;31m \u001b[0mm\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX_train\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_train\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mepochs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m20\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbatch_size\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m10\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalidation_data\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX_test\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_test\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
 818 |             "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/keras/engine/training.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_freq, max_queue_size, workers, use_multiprocessing, **kwargs)\u001b[0m\n\u001b[1;32m   1176\u001b[0m                                         \u001b[0msteps_per_epoch\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0msteps_per_epoch\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1177\u001b[0m                                         \u001b[0mvalidation_steps\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mvalidation_steps\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1178\u001b[0;31m                                         validation_freq=validation_freq)\n\u001b[0m\u001b[1;32m   1179\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1180\u001b[0m     def evaluate(self,\n",
 819 |             "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/keras/engine/training_arrays.py\u001b[0m in \u001b[0;36mfit_loop\u001b[0;34m(model, fit_function, fit_inputs, out_labels, batch_size, epochs, verbose, callbacks, val_function, val_inputs, shuffle, callback_metrics, initial_epoch, steps_per_epoch, validation_steps, validation_freq)\u001b[0m\n\u001b[1;32m    202\u001b[0m                     \u001b[0mins_batch\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mins_batch\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtoarray\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    203\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 204\u001b[0;31m                 \u001b[0mouts\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfit_function\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mins_batch\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    205\u001b[0m                 \u001b[0mouts\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mto_list\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mouts\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    206\u001b[0m                 \u001b[0;32mfor\u001b[0m \u001b[0ml\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mo\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mzip\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mout_labels\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mouts\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
 820 |             "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, inputs)\u001b[0m\n\u001b[1;32m   2977\u001b[0m                     \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_legacy_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2978\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2979\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2980\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2981\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mpy_any\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mis_tensor\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mx\u001b[0m \u001b[0;32min\u001b[0m \u001b[0minputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
 821 |             "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py\u001b[0m in \u001b[0;36m_call\u001b[0;34m(self, inputs)\u001b[0m\n\u001b[1;32m   2935\u001b[0m             \u001b[0mfetched\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_callable_fn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0marray_vals\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrun_metadata\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrun_metadata\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2936\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2937\u001b[0;31m             \u001b[0mfetched\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_callable_fn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0marray_vals\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2938\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mfetched\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0moutputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2939\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
 822 |             "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/client/session.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1470\u001b[0m         ret = tf_session.TF_SessionRunCallable(self._session._session,\n\u001b[1;32m   1471\u001b[0m                                                \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_handle\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1472\u001b[0;31m                                                run_metadata_ptr)\n\u001b[0m\u001b[1;32m   1473\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mrun_metadata\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1474\u001b[0m           \u001b[0mproto_data\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtf_session\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mTF_GetBuffer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrun_metadata_ptr\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
 823 |             "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
 824 |           ]
 825 |         }
 826 |       ]
 827 |     },
 828 |     {
 829 |       "cell_type": "code",
 830 |       "metadata": {
 831 |         "id": "rlwondpcztdH",
 832 |         "colab_type": "code",
 833 |         "outputId": "727f85ab-1d7a-4241-b58e-cd114797f771",
 834 |         "colab": {
 835 |           "base_uri": "https://localhost:8080/",
 836 |           "height": 1000
 837 |         }
 838 |       },
 839 |       "source": [
 840 |         "m2 = Sequential()\n",
 841 |         "m2.add(Convolution1D(64, 3, activation=\"relu\", input_shape=(34,1)))\n",
 842 |         "m2.add(Convolution1D(32, 3, activation=\"relu\"))\n",
 843 |         "m2.add(MaxPooling1D(pool_size=2))\n",
 844 |         "m2.add(Flatten())\n",
 845 |         "m2.add(Dense(8))\n",
 846 |         "\n",
 847 |         "\n",
 848 |         "m2.compile(loss=\"mean_absolute_error\", optimizer=\"adam\", metrics=['accuracy'])\n",
 849 |         "m2.fit(X_train, y_train, epochs=20, batch_size=10, validation_data=(X_test, y_test))"
 850 |       ],
 851 |       "execution_count": 0,
 852 |       "outputs": [
 853 |         {
 854 |           "output_type": "stream",
 855 |           "text": [
 856 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:66: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.\n",
 857 |             "\n",
 858 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:541: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.\n",
 859 |             "\n",
 860 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:4432: The name tf.random_uniform is deprecated. Please use tf.random.uniform instead.\n",
 861 |             "\n",
 862 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:4267: The name tf.nn.max_pool is deprecated. Please use tf.nn.max_pool2d instead.\n",
 863 |             "\n",
 864 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/optimizers.py:793: The name tf.train.Optimizer is deprecated. Please use tf.compat.v1.train.Optimizer instead.\n",
 865 |             "\n",
 866 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:1033: The name tf.assign_add is deprecated. Please use tf.compat.v1.assign_add instead.\n",
 867 |             "\n",
 868 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:1020: The name tf.assign is deprecated. Please use tf.compat.v1.assign instead.\n",
 869 |             "\n",
 870 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:3005: The name tf.Session is deprecated. Please use tf.compat.v1.Session instead.\n",
 871 |             "\n",
 872 |             "Train on 934348 samples, validate on 311450 samples\n",
 873 |             "Epoch 1/20\n",
 874 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:190: The name tf.get_default_session is deprecated. Please use tf.compat.v1.get_default_session instead.\n",
 875 |             "\n",
 876 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:197: The name tf.ConfigProto is deprecated. Please use tf.compat.v1.ConfigProto instead.\n",
 877 |             "\n",
 878 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:207: The name tf.global_variables is deprecated. Please use tf.compat.v1.global_variables instead.\n",
 879 |             "\n",
 880 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:216: The name tf.is_variable_initialized is deprecated. Please use tf.compat.v1.is_variable_initialized instead.\n",
 881 |             "\n",
 882 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:223: The name tf.variables_initializer is deprecated. Please use tf.compat.v1.variables_initializer instead.\n",
 883 |             "\n",
 884 |             "934348/934348 [==============================] - 268s 287us/step - loss: 0.0472 - acc: 0.8289 - val_loss: 0.0437 - val_acc: 0.8392\n",
 885 |             "Epoch 2/20\n",
 886 |             "934348/934348 [==============================] - 266s 285us/step - loss: 0.0436 - acc: 0.8360 - val_loss: 0.0436 - val_acc: 0.8325\n",
 887 |             "Epoch 3/20\n",
 888 |             "934348/934348 [==============================] - 271s 290us/step - loss: 0.0431 - acc: 0.8367 - val_loss: 0.0468 - val_acc: 0.8170\n",
 889 |             "Epoch 4/20\n",
 890 |             "934348/934348 [==============================] - 275s 295us/step - loss: 0.0429 - acc: 0.8376 - val_loss: 0.0423 - val_acc: 0.8379\n",
 891 |             "Epoch 5/20\n",
 892 |             "934348/934348 [==============================] - 265s 284us/step - loss: 0.0425 - acc: 0.8386 - val_loss: 0.0432 - val_acc: 0.8327\n",
 893 |             "Epoch 6/20\n",
 894 |             "934348/934348 [==============================] - 263s 282us/step - loss: 0.0423 - acc: 0.8388 - val_loss: 0.0425 - val_acc: 0.8381\n",
 895 |             "Epoch 7/20\n",
 896 |             "934348/934348 [==============================] - 263s 281us/step - loss: 0.0423 - acc: 0.8386 - val_loss: 0.0419 - val_acc: 0.8383\n",
 897 |             "Epoch 8/20\n",
 898 |             "934348/934348 [==============================] - 261s 279us/step - loss: 0.0422 - acc: 0.8386 - val_loss: 0.0426 - val_acc: 0.8374\n",
 899 |             "Epoch 9/20\n",
 900 |             "934348/934348 [==============================] - 259s 278us/step - loss: 0.0424 - acc: 0.8380 - val_loss: 0.0428 - val_acc: 0.8380\n",
 901 |             "Epoch 10/20\n",
 902 |             "934348/934348 [==============================] - 263s 282us/step - loss: 0.0422 - acc: 0.8382 - val_loss: 0.0416 - val_acc: 0.8392\n",
 903 |             "Epoch 11/20\n",
 904 |             "934348/934348 [==============================] - 263s 281us/step - loss: 0.0422 - acc: 0.8384 - val_loss: 0.0422 - val_acc: 0.8370\n",
 905 |             "Epoch 12/20\n",
 906 |             "934348/934348 [==============================] - 266s 284us/step - loss: 0.0423 - acc: 0.8381 - val_loss: 0.0422 - val_acc: 0.8374\n",
 907 |             "Epoch 13/20\n",
 908 |             "934348/934348 [==============================] - 271s 290us/step - loss: 0.0422 - acc: 0.8384 - val_loss: 0.0439 - val_acc: 0.8337\n",
 909 |             "Epoch 14/20\n",
 910 |             "934348/934348 [==============================] - 273s 293us/step - loss: 0.0421 - acc: 0.8385 - val_loss: 0.0417 - val_acc: 0.8384\n",
 911 |             "Epoch 15/20\n",
 912 |             "934348/934348 [==============================] - 268s 287us/step - loss: 0.0421 - acc: 0.8384 - val_loss: 0.0414 - val_acc: 0.8393\n",
 913 |             "Epoch 16/20\n",
 914 |             "934348/934348 [==============================] - 267s 286us/step - loss: 0.0423 - acc: 0.8385 - val_loss: 0.0418 - val_acc: 0.8386\n",
 915 |             "Epoch 17/20\n",
 916 |             "934348/934348 [==============================] - 261s 279us/step - loss: 0.0419 - acc: 0.8392 - val_loss: 0.0417 - val_acc: 0.8396\n",
 917 |             "Epoch 18/20\n",
 918 |             "934348/934348 [==============================] - 263s 281us/step - loss: 0.0423 - acc: 0.8382 - val_loss: 0.0418 - val_acc: 0.8384\n",
 919 |             "Epoch 19/20\n",
 920 |             "934348/934348 [==============================] - 264s 283us/step - loss: 0.0423 - acc: 0.8389 - val_loss: 0.0416 - val_acc: 0.8404\n",
 921 |             "Epoch 20/20\n",
 922 |             "934348/934348 [==============================] - 265s 284us/step - loss: 0.0425 - acc: 0.8373 - val_loss: 0.0423 - val_acc: 0.8389\n"
 923 |           ],
 924 |           "name": "stdout"
 925 |         },
 926 |         {
 927 |           "output_type": "execute_result",
 928 |           "data": {
 929 |             "text/plain": [
 930 |               "<keras.callbacks.History at 0x7f516f1d92b0>"
 931 |             ]
 932 |           },
 933 |           "metadata": {
 934 |             "tags": []
 935 |           },
 936 |           "execution_count": 11
 937 |         }
 938 |       ]
 939 |     },
 940 |     {
 941 |       "cell_type": "code",
 942 |       "metadata": {
 943 |         "id": "LkSMdt3q9ffc",
 944 |         "colab_type": "code",
 945 |         "colab": {
 946 |           "base_uri": "https://localhost:8080/",
 947 |           "height": 1000
 948 |         },
 949 |         "outputId": "d72a4f3f-b045-4813-b8fd-d6cc06c657ba"
 950 |       },
 951 |       "source": [
 952 |         "m2 = Sequential()\n",
 953 |         "m2.add(Convolution1D(64, 3, activation=\"relu\", input_shape=(34,1)))\n",
 954 |         "m2.add(Convolution1D(32, 3, activation=\"relu\"))\n",
 955 |         "m2.add(MaxPooling1D(pool_size=2))\n",
 956 |         "m2.add(Flatten())\n",
 957 |         "m2.add(Dense(8))\n",
 958 |         "\n",
 959 |         "\n",
 960 |         "m2.compile(loss=\"mean_absolute_error\", optimizer=\"adam\", metrics=['accuracy'])\n",
 961 |         "m2.fit(X_train, y_train, epochs=20, batch_size=10, validation_data=(X_test, y_test))"
 962 |       ],
 963 |       "execution_count": 11,
 964 |       "outputs": [
 965 |         {
 966 |           "output_type": "stream",
 967 |           "text": [
 968 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:66: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.\n",
 969 |             "\n",
 970 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:541: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.\n",
 971 |             "\n",
 972 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:4432: The name tf.random_uniform is deprecated. Please use tf.random.uniform instead.\n",
 973 |             "\n",
 974 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:4267: The name tf.nn.max_pool is deprecated. Please use tf.nn.max_pool2d instead.\n",
 975 |             "\n",
 976 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/optimizers.py:793: The name tf.train.Optimizer is deprecated. Please use tf.compat.v1.train.Optimizer instead.\n",
 977 |             "\n",
 978 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:1033: The name tf.assign_add is deprecated. Please use tf.compat.v1.assign_add instead.\n",
 979 |             "\n",
 980 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:1020: The name tf.assign is deprecated. Please use tf.compat.v1.assign instead.\n",
 981 |             "\n",
 982 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:3005: The name tf.Session is deprecated. Please use tf.compat.v1.Session instead.\n",
 983 |             "\n",
 984 |             "Train on 934348 samples, validate on 311450 samples\n",
 985 |             "Epoch 1/20\n",
 986 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:190: The name tf.get_default_session is deprecated. Please use tf.compat.v1.get_default_session instead.\n",
 987 |             "\n",
 988 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:197: The name tf.ConfigProto is deprecated. Please use tf.compat.v1.ConfigProto instead.\n",
 989 |             "\n",
 990 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:207: The name tf.global_variables is deprecated. Please use tf.compat.v1.global_variables instead.\n",
 991 |             "\n",
 992 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:216: The name tf.is_variable_initialized is deprecated. Please use tf.compat.v1.is_variable_initialized instead.\n",
 993 |             "\n",
 994 |             "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:223: The name tf.variables_initializer is deprecated. Please use tf.compat.v1.variables_initializer instead.\n",
 995 |             "\n",
 996 |             "934348/934348 [==============================] - 253s 271us/step - loss: 0.0471 - acc: 0.8291 - val_loss: 0.0438 - val_acc: 0.8373\n",
 997 |             "Epoch 2/20\n",
 998 |             "934348/934348 [==============================] - 248s 265us/step - loss: 0.0436 - acc: 0.8357 - val_loss: 0.0438 - val_acc: 0.8374\n",
 999 |             "Epoch 3/20\n",
1000 |             "934348/934348 [==============================] - 247s 265us/step - loss: 0.0432 - acc: 0.8354 - val_loss: 0.0445 - val_acc: 0.8389\n",
1001 |             "Epoch 4/20\n",
1002 |             "934348/934348 [==============================] - 248s 266us/step - loss: 0.0430 - acc: 0.8365 - val_loss: 0.0432 - val_acc: 0.8377\n",
1003 |             "Epoch 5/20\n",
1004 |             "934348/934348 [==============================] - 247s 264us/step - loss: 0.0428 - acc: 0.8367 - val_loss: 0.0437 - val_acc: 0.8315\n",
1005 |             "Epoch 6/20\n",
1006 |             "934348/934348 [==============================] - 250s 267us/step - loss: 0.0428 - acc: 0.8369 - val_loss: 0.0432 - val_acc: 0.8378\n",
1007 |             "Epoch 7/20\n",
1008 |             " 19780/934348 [..............................] - ETA: 3:33 - loss: 0.0421 - acc: 0.8395"
1009 |           ],
1010 |           "name": "stdout"
1011 |         },
1012 |         {
1013 |           "output_type": "error",
1014 |           "ename": "KeyboardInterrupt",
1015 |           "evalue": "ignored",
1016 |           "traceback": [
1017 |             "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
1018 |             "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
1019 |             "\u001b[0;32m<ipython-input-11-46e664b9d0ae>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      8\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      9\u001b[0m \u001b[0mm2\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcompile\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mloss\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"mean_absolute_error\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0moptimizer\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"adam\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmetrics\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'accuracy'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 10\u001b[0;31m \u001b[0mm2\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX_train\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_train\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mepochs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m20\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbatch_size\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m10\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalidation_data\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX_test\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_test\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
1020 |             "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/keras/engine/training.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_freq, max_queue_size, workers, use_multiprocessing, **kwargs)\u001b[0m\n\u001b[1;32m   1176\u001b[0m                                         \u001b[0msteps_per_epoch\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0msteps_per_epoch\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1177\u001b[0m                                         \u001b[0mvalidation_steps\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mvalidation_steps\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1178\u001b[0;31m                                         validation_freq=validation_freq)\n\u001b[0m\u001b[1;32m   1179\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1180\u001b[0m     def evaluate(self,\n",
1021 |             "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/keras/engine/training_arrays.py\u001b[0m in \u001b[0;36mfit_loop\u001b[0;34m(model, fit_function, fit_inputs, out_labels, batch_size, epochs, verbose, callbacks, val_function, val_inputs, shuffle, callback_metrics, initial_epoch, steps_per_epoch, validation_steps, validation_freq)\u001b[0m\n\u001b[1;32m    202\u001b[0m                     \u001b[0mins_batch\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mins_batch\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtoarray\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    203\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 204\u001b[0;31m                 \u001b[0mouts\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfit_function\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mins_batch\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    205\u001b[0m                 \u001b[0mouts\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mto_list\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mouts\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    206\u001b[0m                 \u001b[0;32mfor\u001b[0m \u001b[0ml\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mo\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mzip\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mout_labels\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mouts\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
1022 |             "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, inputs)\u001b[0m\n\u001b[1;32m   2977\u001b[0m                     \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_legacy_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2978\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2979\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2980\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2981\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mpy_any\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mis_tensor\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mx\u001b[0m \u001b[0;32min\u001b[0m \u001b[0minputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
1023 |             "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py\u001b[0m in \u001b[0;36m_call\u001b[0;34m(self, inputs)\u001b[0m\n\u001b[1;32m   2935\u001b[0m             \u001b[0mfetched\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_callable_fn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0marray_vals\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrun_metadata\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrun_metadata\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2936\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2937\u001b[0;31m             \u001b[0mfetched\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_callable_fn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0marray_vals\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2938\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mfetched\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0moutputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2939\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
1024 |             "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/client/session.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1470\u001b[0m         ret = tf_session.TF_SessionRunCallable(self._session._session,\n\u001b[1;32m   1471\u001b[0m                                                \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_handle\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1472\u001b[0;31m                                                run_metadata_ptr)\n\u001b[0m\u001b[1;32m   1473\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mrun_metadata\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1474\u001b[0m           \u001b[0mproto_data\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtf_session\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mTF_GetBuffer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrun_metadata_ptr\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
1025 |             "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
1026 |           ]
1027 |         }
1028 |       ]
1029 |     },
1030 |     {
1031 |       "cell_type": "code",
1032 |       "metadata": {
1033 |         "id": "frzX_kXg9i7C",
1034 |         "colab_type": "code",
1035 |         "colab": {}
1036 |       },
1037 |       "source": [
1038 |         "#save to folder\n",
1039 |         "m2.save(\"/content/drive/My Drive/dos_dataset/final_cnn_m2.h5\")"
1040 |       ],
1041 |       "execution_count": 0,
1042 |       "outputs": []
1043 |     },
1044 |     {
1045 |       "cell_type": "code",
1046 |       "metadata": {
1047 |         "id": "M3-DWLWPbLk4",
1048 |         "colab_type": "code",
1049 |         "colab": {}
1050 |       },
1051 |       "source": [
1052 |         "y_pred = m2.predict(X_test)"
1053 |       ],
1054 |       "execution_count": 0,
1055 |       "outputs": []
1056 |     },
1057 |     {
1058 |       "cell_type": "code",
1059 |       "metadata": {
1060 |         "id": "0cNO8st5uc9G",
1061 |         "colab_type": "code",
1062 |         "colab": {}
1063 |       },
1064 |       "source": [
1065 |         "a = (y_pred > 0.5)\n",
1066 |         "b = (y_test > 0.5) "
1067 |       ],
1068 |       "execution_count": 0,
1069 |       "outputs": []
1070 |     },
1071 |     {
1072 |       "cell_type": "code",
1073 |       "metadata": {
1074 |         "id": "AtDc4wLdzaBi",
1075 |         "colab_type": "code",
1076 |         "colab": {}
1077 |       },
1078 |       "source": [
1079 |         "b=np.argmax(y_test, axis=1)"
1080 |       ],
1081 |       "execution_count": 0,
1082 |       "outputs": []
1083 |     },
1084 |     {
1085 |       "cell_type": "code",
1086 |       "metadata": {
1087 |         "id": "ppJB_LMjzFr3",
1088 |         "colab_type": "code",
1089 |         "outputId": "d307ee6e-945a-4f26-b5f5-f0166a820d03",
1090 |         "colab": {
1091 |           "base_uri": "https://localhost:8080/",
1092 |           "height": 34
1093 |         }
1094 |       },
1095 |       "source": [
1096 |         "a=np.argmax(y_pred, axis=1)\n",
1097 |         "a[2]"
1098 |       ],
1099 |       "execution_count": 16,
1100 |       "outputs": [
1101 |         {
1102 |           "output_type": "execute_result",
1103 |           "data": {
1104 |             "text/plain": [
1105 |               "1"
1106 |             ]
1107 |           },
1108 |           "metadata": {
1109 |             "tags": []
1110 |           },
1111 |           "execution_count": 16
1112 |         }
1113 |       ]
1114 |     },
1115 |     {
1116 |       "cell_type": "code",
1117 |       "metadata": {
1118 |         "id": "xouyY6kCbC-s",
1119 |         "colab_type": "code",
1120 |         "outputId": "a1a19d7b-dbce-499f-d696-a5e97fc7aa46",
1121 |         "colab": {
1122 |           "base_uri": "https://localhost:8080/",
1123 |           "height": 564
1124 |         }
1125 |       },
1126 |       "source": [
1127 |         "from sklearn import metrics\n",
1128 |         "from sklearn.metrics import accuracy_score\n",
1129 |         "from sklearn.metrics import f1_score\n",
1130 |         "\n",
1131 |         "print('Convolution Neural Network')\n",
1132 |         "\n",
1133 |         "print('Accuracy: %f' % (accuracy_score(a, b)*100))\n",
1134 |         "print(\"Confusion Matrix =\\n\", metrics.confusion_matrix(b, a, labels=None, \n",
1135 |         "                                              sample_weight=None))\n",
1136 |         "print(\"Recall =\", metrics.recall_score(b, a, labels=None, \n",
1137 |         "                                             pos_label=1, average='weighted', \n",
1138 |         "                                             sample_weight=None))\n",
1139 |         "print(\"Classification Report =\\n\", metrics.classification_report(b, a, \n",
1140 |         "                                                                 labels=None, \n",
1141 |         "                                                                 target_names=None, \n",
1142 |         "                                                                 sample_weight=None, \n",
1143 |         "                                                                 digits=2, \n",
1144 |         "                                                                 output_dict=False))\n",
1145 |         "\n",
1146 |         "print(\"F1 Score = \",f1_score(a, b, average='macro'))"
1147 |       ],
1148 |       "execution_count": 18,
1149 |       "outputs": [
1150 |         {
1151 |           "output_type": "stream",
1152 |           "text": [
1153 |             "Convolution Neural Network\n",
1154 |             "Accuracy: 83.924225\n",
1155 |             "Confusion Matrix =\n",
1156 |             " [[14222    58     6    11     6    18     0     0]\n",
1157 |             " [    9 48066     2    12  1588     0    85     0]\n",
1158 |             " [   10     3 49270   530     6     3     0     0]\n",
1159 |             " [    2     0  1143 48551    29     0   550     0]\n",
1160 |             " [  163 43372     0   123  3197     0    63     0]\n",
1161 |             " [    9     0     0     2     0 49651     2     0]\n",
1162 |             " [    9     9     0  1714    10     0 48425     0]\n",
1163 |             " [   49     0     0    30     4     0   438     0]]\n",
1164 |             "Recall = 0.8392422539733505\n"
1165 |           ],
1166 |           "name": "stdout"
1167 |         },
1168 |         {
1169 |           "output_type": "stream",
1170 |           "text": [
1171 |             "/usr/local/lib/python3.6/dist-packages/sklearn/metrics/_classification.py:1272: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
1172 |             "  _warn_prf(average, modifier, msg_start, len(result))\n"
1173 |           ],
1174 |           "name": "stderr"
1175 |         },
1176 |         {
1177 |           "output_type": "stream",
1178 |           "text": [
1179 |             "Classification Report =\n",
1180 |             "               precision    recall  f1-score   support\n",
1181 |             "\n",
1182 |             "           0       0.98      0.99      0.99     14321\n",
1183 |             "           1       0.53      0.97      0.68     49762\n",
1184 |             "           2       0.98      0.99      0.98     49822\n",
1185 |             "           3       0.95      0.97      0.96     50275\n",
1186 |             "           4       0.66      0.07      0.12     46918\n",
1187 |             "           5       1.00      1.00      1.00     49664\n",
1188 |             "           6       0.98      0.97      0.97     50167\n",
1189 |             "           7       0.00      0.00      0.00       521\n",
1190 |             "\n",
1191 |             "    accuracy                           0.84    311450\n",
1192 |             "   macro avg       0.76      0.74      0.71    311450\n",
1193 |             "weighted avg       0.86      0.84      0.80    311450\n",
1194 |             "\n",
1195 |             "F1 Score =  0.713088426198137\n"
1196 |           ],
1197 |           "name": "stdout"
1198 |         }
1199 |       ]
1200 |     }
1201 |   ]
1202 | }


--------------------------------------------------------------------------------
/DDOS_XGBoost.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |   "nbformat": 4,
  3 |   "nbformat_minor": 0,
  4 |   "metadata": {
  5 |     "colab": {
  6 |       "name": "DDOS_XGBoost.ipynb",
  7 |       "provenance": [],
  8 |       "include_colab_link": true
  9 |     },
 10 |     "kernelspec": {
 11 |       "name": "python3",
 12 |       "display_name": "Python 3"
 13 |     }
 14 |   },
 15 |   "cells": [
 16 |     {
 17 |       "cell_type": "markdown",
 18 |       "metadata": {
 19 |         "id": "view-in-github",
 20 |         "colab_type": "text"
 21 |       },
 22 |       "source": [
 23 |         "<a href=\"https://colab.research.google.com/github/mohak1/DDoS_Attack_Classification/blob/master/DDOS_XGBoost.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
 24 |       ]
 25 |     },
 26 |     {
 27 |       "cell_type": "code",
 28 |       "metadata": {
 29 |         "id": "lnz8kF7JX4kO",
 30 |         "colab_type": "code",
 31 |         "outputId": "770c4510-44fa-4bc6-9453-1fd699bb5e2f",
 32 |         "colab": {
 33 |           "base_uri": "https://localhost:8080/",
 34 |           "height": 122
 35 |         }
 36 |       },
 37 |       "source": [
 38 |         "from google.colab import drive\n",
 39 |         "drive.mount('/content/drive')"
 40 |       ],
 41 |       "execution_count": 1,
 42 |       "outputs": [
 43 |         {
 44 |           "output_type": "stream",
 45 |           "text": [
 46 |             "Go to this URL in a browser: https://accounts.google.com/o/oauth2/auth?client_id=947318989803-6bn6qk8qdgf4n4g3pfee6491hc0brc4i.apps.googleusercontent.com&redirect_uri=urn%3aietf%3awg%3aoauth%3a2.0%3aoob&response_type=code&scope=email%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdocs.test%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdrive%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdrive.photos.readonly%20https%3a%2f%2fwww.googleapis.com%2fauth%2fpeopleapi.readonly\n",
 47 |             "\n",
 48 |             "Enter your authorization code:\n",
 49 |             "··········\n",
 50 |             "Mounted at /content/drive\n"
 51 |           ],
 52 |           "name": "stdout"
 53 |         }
 54 |       ]
 55 |     },
 56 |     {
 57 |       "cell_type": "code",
 58 |       "metadata": {
 59 |         "id": "oS-BDuLOX_vC",
 60 |         "colab_type": "code",
 61 |         "outputId": "93f21e0b-74f2-4ae4-9090-646930fc37f6",
 62 |         "colab": {
 63 |           "base_uri": "https://localhost:8080/",
 64 |           "height": 80
 65 |         }
 66 |       },
 67 |       "source": [
 68 |         " #%tensorflow_version 2.x\n",
 69 |         "from sklearn.preprocessing import LabelEncoder\n",
 70 |         "from keras.models import Sequential\n",
 71 |         "from keras.layers import Dense, Dropout, Activation, Lambda, Flatten\n",
 72 |         "from keras.layers import Convolution1D, Dense, Dropout, MaxPooling1D, LSTM\n",
 73 |         "from sklearn.model_selection import train_test_split\n",
 74 |         "from sklearn.preprocessing import Normalizer\n",
 75 |         "from keras import callbacks\n",
 76 |         "from keras.callbacks import CSVLogger\n",
 77 |         "from keras.utils import to_categorical\n",
 78 |         "from keras.callbacks import ModelCheckpoint, EarlyStopping, ReduceLROnPlateau, CSVLogger\n",
 79 |         "import numpy as np\n",
 80 |         "np.random.seed(0)"
 81 |       ],
 82 |       "execution_count": 2,
 83 |       "outputs": [
 84 |         {
 85 |           "output_type": "stream",
 86 |           "text": [
 87 |             "Using TensorFlow backend.\n"
 88 |           ],
 89 |           "name": "stderr"
 90 |         },
 91 |         {
 92 |           "output_type": "display_data",
 93 |           "data": {
 94 |             "text/html": [
 95 |               "<p style=\"color: red;\">\n",
 96 |               "The default version of TensorFlow in Colab will soon switch to TensorFlow 2.x.<br>\n",
 97 |               "We recommend you <a href=\"https://www.tensorflow.org/guide/migrate\" target=\"_blank\">upgrade</a> now \n",
 98 |               "or ensure your notebook will continue to use TensorFlow 1.x via the <code>%tensorflow_version 1.x</code> magic:\n",
 99 |               "<a href=\"https://colab.research.google.com/notebooks/tensorflow_version.ipynb\" target=\"_blank\">more info</a>.</p>\n"
100 |             ],
101 |             "text/plain": [
102 |               "<IPython.core.display.HTML object>"
103 |             ]
104 |           },
105 |           "metadata": {
106 |             "tags": []
107 |           }
108 |         }
109 |       ]
110 |     },
111 |     {
112 |       "cell_type": "code",
113 |       "metadata": {
114 |         "id": "UhGqcdZLX_z7",
115 |         "colab_type": "code",
116 |         "outputId": "5c5c57f9-c6b8-4957-b6de-9706ccb87521",
117 |         "colab": {
118 |           "base_uri": "https://localhost:8080/",
119 |           "height": 275
120 |         }
121 |       },
122 |       "source": [
123 |         "#loading dataset\n",
124 |         "import pandas as pd\n",
125 |         "x = pd.read_csv(\"/content/drive/My Drive/dos_dataset/clean_5.csv\")\n",
126 |         "y = pd.read_csv(\"/content/drive/My Drive/dos_dataset/y.csv\")\n",
127 |         "y=y['Label']\n",
128 |         "x=x.drop(['Label'], axis=1)\n",
129 |         "\n",
130 |         "#normalizing the data\n",
131 |         "normalized_df=(x-x.mean())/x.std()\n",
132 |         "\n",
133 |         "normalized_df=normalized_df.drop(['Unnamed: 0'], axis=1)\n",
134 |         "normalized_df=normalized_df.drop(['Unnamed: 0.1'], axis=1)\n",
135 |         "normalized_df=normalized_df.drop(['Unnamed: 0.1.1'], axis=1)\n",
136 |         "normalized_df=normalized_df.drop(['Flow Bytes/s'], axis=1)\n",
137 |         "normalized_df=normalized_df.drop([' Flow Packets/s'], axis=1)\n",
138 |         "\n",
139 |         "y = pd.get_dummies(y,prefix=['Label'], drop_first=True)\n",
140 |         "\n",
141 |         "normalized_df.head()"
142 |       ],
143 |       "execution_count": 3,
144 |       "outputs": [
145 |         {
146 |           "output_type": "execute_result",
147 |           "data": {
148 |             "text/html": [
149 |               "<div>\n",
150 |               "<style scoped>\n",
151 |               "    .dataframe tbody tr th:only-of-type {\n",
152 |               "        vertical-align: middle;\n",
153 |               "    }\n",
154 |               "\n",
155 |               "    .dataframe tbody tr th {\n",
156 |               "        vertical-align: top;\n",
157 |               "    }\n",
158 |               "\n",
159 |               "    .dataframe thead th {\n",
160 |               "        text-align: right;\n",
161 |               "    }\n",
162 |               "</style>\n",
163 |               "<table border=\"1\" class=\"dataframe\">\n",
164 |               "  <thead>\n",
165 |               "    <tr style=\"text-align: right;\">\n",
166 |               "      <th></th>\n",
167 |               "      <th>Source Port</th>\n",
168 |               "      <th>Destination IP</th>\n",
169 |               "      <th>Destination Port</th>\n",
170 |               "      <th>Protocol</th>\n",
171 |               "      <th>Total Length of Fwd Packets</th>\n",
172 |               "      <th>Fwd Packet Length Max</th>\n",
173 |               "      <th>Fwd Packet Length Min</th>\n",
174 |               "      <th>Fwd Packet Length Mean</th>\n",
175 |               "      <th>Bwd Packet Length Max</th>\n",
176 |               "      <th>Bwd Packet Length Min</th>\n",
177 |               "      <th>Bwd Packet Length Mean</th>\n",
178 |               "      <th>Bwd Packet Length Std</th>\n",
179 |               "      <th>Flow IAT Mean</th>\n",
180 |               "      <th>Flow IAT Std</th>\n",
181 |               "      <th>Fwd IAT Mean</th>\n",
182 |               "      <th>Fwd IAT Std</th>\n",
183 |               "      <th>Fwd PSH Flags</th>\n",
184 |               "      <th>Fwd Packets/s</th>\n",
185 |               "      <th>Min Packet Length</th>\n",
186 |               "      <th>Max Packet Length</th>\n",
187 |               "      <th>Packet Length Mean</th>\n",
188 |               "      <th>Packet Length Variance</th>\n",
189 |               "      <th>RST Flag Count</th>\n",
190 |               "      <th>ACK Flag Count</th>\n",
191 |               "      <th>URG Flag Count</th>\n",
192 |               "      <th>CWE Flag Count</th>\n",
193 |               "      <th>Average Packet Size</th>\n",
194 |               "      <th>Avg Fwd Segment Size</th>\n",
195 |               "      <th>Avg Bwd Segment Size</th>\n",
196 |               "      <th>Subflow Fwd Bytes</th>\n",
197 |               "      <th>Init_Win_bytes_forward</th>\n",
198 |               "      <th>Init_Win_bytes_backward</th>\n",
199 |               "      <th>Idle Std</th>\n",
200 |               "      <th>Inbound</th>\n",
201 |               "    </tr>\n",
202 |               "  </thead>\n",
203 |               "  <tbody>\n",
204 |               "    <tr>\n",
205 |               "      <th>0</th>\n",
206 |               "      <td>1.395596</td>\n",
207 |               "      <td>0.157586</td>\n",
208 |               "      <td>-0.607399</td>\n",
209 |               "      <td>-2.031188</td>\n",
210 |               "      <td>-0.725421</td>\n",
211 |               "      <td>-0.954992</td>\n",
212 |               "      <td>-0.935156</td>\n",
213 |               "      <td>-0.945029</td>\n",
214 |               "      <td>-0.050579</td>\n",
215 |               "      <td>0.342849</td>\n",
216 |               "      <td>0.015085</td>\n",
217 |               "      <td>-0.076871</td>\n",
218 |               "      <td>-0.178761</td>\n",
219 |               "      <td>-0.175445</td>\n",
220 |               "      <td>-0.178330</td>\n",
221 |               "      <td>-0.168507</td>\n",
222 |               "      <td>-0.090471</td>\n",
223 |               "      <td>-1.335866</td>\n",
224 |               "      <td>-0.935040</td>\n",
225 |               "      <td>-0.940755</td>\n",
226 |               "      <td>-0.948545</td>\n",
227 |               "      <td>-0.069737</td>\n",
228 |               "      <td>-0.090471</td>\n",
229 |               "      <td>2.209740</td>\n",
230 |               "      <td>-0.153371</td>\n",
231 |               "      <td>-0.101473</td>\n",
232 |               "      <td>-0.933777</td>\n",
233 |               "      <td>-0.945029</td>\n",
234 |               "      <td>0.015085</td>\n",
235 |               "      <td>-0.725421</td>\n",
236 |               "      <td>-0.054584</td>\n",
237 |               "      <td>-0.057299</td>\n",
238 |               "      <td>-0.162793</td>\n",
239 |               "      <td>0.19758</td>\n",
240 |               "    </tr>\n",
241 |               "    <tr>\n",
242 |               "      <th>1</th>\n",
243 |               "      <td>0.347887</td>\n",
244 |               "      <td>0.157586</td>\n",
245 |               "      <td>-1.625958</td>\n",
246 |               "      <td>-2.031188</td>\n",
247 |               "      <td>-0.733744</td>\n",
248 |               "      <td>-0.954992</td>\n",
249 |               "      <td>-0.935156</td>\n",
250 |               "      <td>-0.945029</td>\n",
251 |               "      <td>-0.050579</td>\n",
252 |               "      <td>0.342849</td>\n",
253 |               "      <td>0.015085</td>\n",
254 |               "      <td>-0.076871</td>\n",
255 |               "      <td>-0.216151</td>\n",
256 |               "      <td>-0.222876</td>\n",
257 |               "      <td>-0.227006</td>\n",
258 |               "      <td>-0.222546</td>\n",
259 |               "      <td>-0.090471</td>\n",
260 |               "      <td>-1.324001</td>\n",
261 |               "      <td>-0.935040</td>\n",
262 |               "      <td>-0.940755</td>\n",
263 |               "      <td>-0.948545</td>\n",
264 |               "      <td>-0.069737</td>\n",
265 |               "      <td>-0.090471</td>\n",
266 |               "      <td>2.209740</td>\n",
267 |               "      <td>-0.153371</td>\n",
268 |               "      <td>-0.101473</td>\n",
269 |               "      <td>-0.933085</td>\n",
270 |               "      <td>-0.945029</td>\n",
271 |               "      <td>0.015085</td>\n",
272 |               "      <td>-0.733744</td>\n",
273 |               "      <td>7.027636</td>\n",
274 |               "      <td>-0.057299</td>\n",
275 |               "      <td>-0.162793</td>\n",
276 |               "      <td>0.19758</td>\n",
277 |               "    </tr>\n",
278 |               "    <tr>\n",
279 |               "      <th>2</th>\n",
280 |               "      <td>1.196809</td>\n",
281 |               "      <td>0.157586</td>\n",
282 |               "      <td>-0.560525</td>\n",
283 |               "      <td>-2.031188</td>\n",
284 |               "      <td>-0.725421</td>\n",
285 |               "      <td>-0.954992</td>\n",
286 |               "      <td>-0.935156</td>\n",
287 |               "      <td>-0.945029</td>\n",
288 |               "      <td>-0.050579</td>\n",
289 |               "      <td>0.342849</td>\n",
290 |               "      <td>0.015085</td>\n",
291 |               "      <td>-0.076871</td>\n",
292 |               "      <td>-0.182709</td>\n",
293 |               "      <td>-0.180450</td>\n",
294 |               "      <td>-0.183461</td>\n",
295 |               "      <td>-0.174204</td>\n",
296 |               "      <td>-0.090471</td>\n",
297 |               "      <td>-1.335864</td>\n",
298 |               "      <td>-0.935040</td>\n",
299 |               "      <td>-0.940755</td>\n",
300 |               "      <td>-0.948545</td>\n",
301 |               "      <td>-0.069737</td>\n",
302 |               "      <td>-0.090471</td>\n",
303 |               "      <td>2.209740</td>\n",
304 |               "      <td>-0.153371</td>\n",
305 |               "      <td>-0.101473</td>\n",
306 |               "      <td>-0.933777</td>\n",
307 |               "      <td>-0.945029</td>\n",
308 |               "      <td>0.015085</td>\n",
309 |               "      <td>-0.725421</td>\n",
310 |               "      <td>-0.054584</td>\n",
311 |               "      <td>-0.057299</td>\n",
312 |               "      <td>-0.162793</td>\n",
313 |               "      <td>0.19758</td>\n",
314 |               "    </tr>\n",
315 |               "    <tr>\n",
316 |               "      <th>3</th>\n",
317 |               "      <td>0.892029</td>\n",
318 |               "      <td>0.157586</td>\n",
319 |               "      <td>-1.562081</td>\n",
320 |               "      <td>-2.031188</td>\n",
321 |               "      <td>-0.725421</td>\n",
322 |               "      <td>-0.954992</td>\n",
323 |               "      <td>-0.935156</td>\n",
324 |               "      <td>-0.945029</td>\n",
325 |               "      <td>-0.050579</td>\n",
326 |               "      <td>0.342849</td>\n",
327 |               "      <td>0.015085</td>\n",
328 |               "      <td>-0.076871</td>\n",
329 |               "      <td>-0.186161</td>\n",
330 |               "      <td>-0.184840</td>\n",
331 |               "      <td>-0.187948</td>\n",
332 |               "      <td>-0.179186</td>\n",
333 |               "      <td>-0.090471</td>\n",
334 |               "      <td>-1.335861</td>\n",
335 |               "      <td>-0.935040</td>\n",
336 |               "      <td>-0.940755</td>\n",
337 |               "      <td>-0.948545</td>\n",
338 |               "      <td>-0.069737</td>\n",
339 |               "      <td>-0.090471</td>\n",
340 |               "      <td>2.209740</td>\n",
341 |               "      <td>-0.153371</td>\n",
342 |               "      <td>-0.101473</td>\n",
343 |               "      <td>-0.933777</td>\n",
344 |               "      <td>-0.945029</td>\n",
345 |               "      <td>0.015085</td>\n",
346 |               "      <td>-0.725421</td>\n",
347 |               "      <td>-0.054584</td>\n",
348 |               "      <td>-0.057299</td>\n",
349 |               "      <td>-0.162793</td>\n",
350 |               "      <td>0.19758</td>\n",
351 |               "    </tr>\n",
352 |               "    <tr>\n",
353 |               "      <th>4</th>\n",
354 |               "      <td>-0.914218</td>\n",
355 |               "      <td>0.157586</td>\n",
356 |               "      <td>0.169285</td>\n",
357 |               "      <td>0.489985</td>\n",
358 |               "      <td>-0.424394</td>\n",
359 |               "      <td>-0.494002</td>\n",
360 |               "      <td>-0.472024</td>\n",
361 |               "      <td>-0.480570</td>\n",
362 |               "      <td>-0.085259</td>\n",
363 |               "      <td>-0.138378</td>\n",
364 |               "      <td>-0.095478</td>\n",
365 |               "      <td>-0.076871</td>\n",
366 |               "      <td>-0.216208</td>\n",
367 |               "      <td>-0.222934</td>\n",
368 |               "      <td>-0.227005</td>\n",
369 |               "      <td>-0.222546</td>\n",
370 |               "      <td>-0.090471</td>\n",
371 |               "      <td>-0.610670</td>\n",
372 |               "      <td>-0.471885</td>\n",
373 |               "      <td>-0.494875</td>\n",
374 |               "      <td>-0.483551</td>\n",
375 |               "      <td>-0.069737</td>\n",
376 |               "      <td>-0.090471</td>\n",
377 |               "      <td>-0.452542</td>\n",
378 |               "      <td>-0.153371</td>\n",
379 |               "      <td>-0.101473</td>\n",
380 |               "      <td>-0.467788</td>\n",
381 |               "      <td>-0.480570</td>\n",
382 |               "      <td>-0.095478</td>\n",
383 |               "      <td>-0.424394</td>\n",
384 |               "      <td>-0.362285</td>\n",
385 |               "      <td>-0.057771</td>\n",
386 |               "      <td>-0.162793</td>\n",
387 |               "      <td>0.19758</td>\n",
388 |               "    </tr>\n",
389 |               "  </tbody>\n",
390 |               "</table>\n",
391 |               "</div>"
392 |             ],
393 |             "text/plain": [
394 |               "    Source Port   Destination IP  ...   Idle Std   Inbound\n",
395 |               "0      1.395596         0.157586  ...  -0.162793   0.19758\n",
396 |               "1      0.347887         0.157586  ...  -0.162793   0.19758\n",
397 |               "2      1.196809         0.157586  ...  -0.162793   0.19758\n",
398 |               "3      0.892029         0.157586  ...  -0.162793   0.19758\n",
399 |               "4     -0.914218         0.157586  ...  -0.162793   0.19758\n",
400 |               "\n",
401 |               "[5 rows x 34 columns]"
402 |             ]
403 |           },
404 |           "metadata": {
405 |             "tags": []
406 |           },
407 |           "execution_count": 3
408 |         }
409 |       ]
410 |     },
411 |     {
412 |       "cell_type": "code",
413 |       "metadata": {
414 |         "id": "dJTE1lD8YhDQ",
415 |         "colab_type": "code",
416 |         "outputId": "7b8f40e8-f9b5-4408-9249-c420ae9d740a",
417 |         "colab": {
418 |           "base_uri": "https://localhost:8080/",
419 |           "height": 119
420 |         }
421 |       },
422 |       "source": [
423 |         "y = pd.read_csv(\"/content/drive/My Drive/dos_dataset/y.csv\")\n",
424 |         "y=y['Label']\n",
425 |         "y.head()"
426 |       ],
427 |       "execution_count": 4,
428 |       "outputs": [
429 |         {
430 |           "output_type": "execute_result",
431 |           "data": {
432 |             "text/plain": [
433 |               "0    2\n",
434 |               "1    2\n",
435 |               "2    2\n",
436 |               "3    2\n",
437 |               "4    2\n",
438 |               "Name: Label, dtype: int64"
439 |             ]
440 |           },
441 |           "metadata": {
442 |             "tags": []
443 |           },
444 |           "execution_count": 4
445 |         }
446 |       ]
447 |     },
448 |     {
449 |       "cell_type": "code",
450 |       "metadata": {
451 |         "id": "XDBQEpsTX_3b",
452 |         "colab_type": "code",
453 |         "outputId": "0ee5cbde-c3be-4a0e-b3e7-8952e21b6d02",
454 |         "colab": {
455 |           "base_uri": "https://localhost:8080/",
456 |           "height": 34
457 |         }
458 |       },
459 |       "source": [
460 |         "from sklearn.model_selection import train_test_split\n",
461 |         "X_train, X_test, y_train, y_test = train_test_split(normalized_df, y, test_size=0.3, random_state=0)\n",
462 |         "y_train = np.array(y_train)\n",
463 |         "\n",
464 |         "y_train = np.array(y_train)\n",
465 |         "y_test = np.array(y_test)\n",
466 |         "X_train = np.array(X_train)\n",
467 |         "X_test = np.array(X_test)\n",
468 |         "X_train = np.reshape(X_train, (X_train.shape[0],X_train.shape[1]))\n",
469 |         "X_test = np.reshape(X_test, (X_test.shape[0],X_test.shape[1]))\n",
470 |         "\n",
471 |         "print('xtrain={}, ytrain={}, xtest={}, ytest={}'.format(X_train.shape,y_train.shape,X_test.shape,y_test.shape))"
472 |       ],
473 |       "execution_count": 5,
474 |       "outputs": [
475 |         {
476 |           "output_type": "stream",
477 |           "text": [
478 |             "xtrain=(872058, 34), ytrain=(872058,), xtest=(373740, 34), ytest=(373740,)\n"
479 |           ],
480 |           "name": "stdout"
481 |         }
482 |       ]
483 |     },
484 |     {
485 |       "cell_type": "markdown",
486 |       "metadata": {
487 |         "id": "a7ZM193PagA5",
488 |         "colab_type": "text"
489 |       },
490 |       "source": [
491 |         "**XGBoost**\n",
492 |         "\n",
493 |         "> with metrics\n",
494 |         "\n"
495 |       ]
496 |     },
497 |     {
498 |       "cell_type": "code",
499 |       "metadata": {
500 |         "id": "phVeKBGYamO-",
501 |         "colab_type": "code",
502 |         "outputId": "22c659dd-7f91-4b0c-be67-5c9dfe1897a3",
503 |         "colab": {
504 |           "base_uri": "https://localhost:8080/",
505 |           "height": 68
506 |         }
507 |       },
508 |       "source": [
509 |         "!pip install xgboost"
510 |       ],
511 |       "execution_count": 6,
512 |       "outputs": [
513 |         {
514 |           "output_type": "stream",
515 |           "text": [
516 |             "Requirement already satisfied: xgboost in /usr/local/lib/python3.6/dist-packages (0.90)\n",
517 |             "Requirement already satisfied: numpy in /usr/local/lib/python3.6/dist-packages (from xgboost) (1.17.5)\n",
518 |             "Requirement already satisfied: scipy in /usr/local/lib/python3.6/dist-packages (from xgboost) (1.4.1)\n"
519 |           ],
520 |           "name": "stdout"
521 |         }
522 |       ]
523 |     },
524 |     {
525 |       "cell_type": "code",
526 |       "metadata": {
527 |         "id": "9ZE9XYK6AzKO",
528 |         "colab_type": "code",
529 |         "colab": {}
530 |       },
531 |       "source": [
532 |         "from xgboost import XGBClassifier\n",
533 |         "model = XGBClassifier()\n",
534 |         "model.fit(X_train, y_train)\n",
535 |         "\n",
536 |         "import pickle\n",
537 |         "pickle.dump(model, open(\"/content/drive/My Drive/dos_dataset/final_xgb.pickle.dat\", \"wb\"))"
538 |       ],
539 |       "execution_count": 0,
540 |       "outputs": []
541 |     },
542 |     {
543 |       "cell_type": "code",
544 |       "metadata": {
545 |         "id": "tVRI3zWqGJD1",
546 |         "colab_type": "code",
547 |         "colab": {}
548 |       },
549 |       "source": [
550 |         "y_pred=model.predict(X_test)"
551 |       ],
552 |       "execution_count": 0,
553 |       "outputs": []
554 |     },
555 |     {
556 |       "cell_type": "code",
557 |       "metadata": {
558 |         "id": "8RrZdXa8Fz2C",
559 |         "colab_type": "code",
560 |         "outputId": "3aef8cd0-6990-488b-8fac-bcfd93ddb686",
561 |         "colab": {
562 |           "base_uri": "https://localhost:8080/",
563 |           "height": 34
564 |         }
565 |       },
566 |       "source": [
567 |         "y_train.shape"
568 |       ],
569 |       "execution_count": 10,
570 |       "outputs": [
571 |         {
572 |           "output_type": "execute_result",
573 |           "data": {
574 |             "text/plain": [
575 |               "(872058,)"
576 |             ]
577 |           },
578 |           "metadata": {
579 |             "tags": []
580 |           },
581 |           "execution_count": 10
582 |         }
583 |       ]
584 |     },
585 |     {
586 |       "cell_type": "code",
587 |       "metadata": {
588 |         "id": "854hNxDbao_c",
589 |         "colab_type": "code",
590 |         "outputId": "9da28dd8-ce69-4883-df42-ab3c4d3c9692",
591 |         "colab": {
592 |           "base_uri": "https://localhost:8080/",
593 |           "height": 510
594 |         }
595 |       },
596 |       "source": [
597 |         "from sklearn import metrics\n",
598 |         "from sklearn.metrics import f1_score\n",
599 |         "print('XGBoost Classifier')\n",
600 |         "\n",
601 |         "print('Accuracy = ', metrics.accuracy_score(y_test, y_pred)*100)\n",
602 |         "print(\"Confusion Matrix =\\n\", metrics.confusion_matrix(y_test, y_pred, labels=None, \n",
603 |         "                                              sample_weight=None))\n",
604 |         "print(\"Recall =\", metrics.recall_score(y_test, y_pred, labels=None, \n",
605 |         "                                             pos_label=1, average='weighted', \n",
606 |         "                                             sample_weight=None))\n",
607 |         "print(\"Classification Report =\\n\", metrics.classification_report(y_test, y_pred, \n",
608 |         "                                                                 labels=None, \n",
609 |         "                                                                 target_names=None, \n",
610 |         "                                                                 sample_weight=None, \n",
611 |         "                                                                 digits=2, \n",
612 |         "                                                                 output_dict=False))\n",
613 |         "\n",
614 |         "print(\"F1 Score = \",f1_score(y_test, y_pred, average='macro'))"
615 |       ],
616 |       "execution_count": 15,
617 |       "outputs": [
618 |         {
619 |           "output_type": "stream",
620 |           "text": [
621 |             "XGBoost Classifier\n",
622 |             "Accuracy =  89.29871033338685\n",
623 |             "Confusion Matrix =\n",
624 |             " [[17136     0     0     0     0     0     0     0]\n",
625 |             " [    1 56298     6     0  3467     0     0     1]\n",
626 |             " [    0     0 59645    42    17     5     0     0]\n",
627 |             " [    2     1    24 60168    22     0   199     0]\n",
628 |             " [   11 34241     8    68 21904     1     0    16]\n",
629 |             " [    1     0     0     2     1 59765     2     0]\n",
630 |             " [    1     0     0  1621    11     0 58430    19]\n",
631 |             " [    1     0     0    20    55     0   129   399]]\n",
632 |             "Recall = 0.8929871033338684\n",
633 |             "Classification Report =\n",
634 |             "               precision    recall  f1-score   support\n",
635 |             "\n",
636 |             "           0       1.00      1.00      1.00     17136\n",
637 |             "           1       0.62      0.94      0.75     59773\n",
638 |             "           2       1.00      1.00      1.00     59709\n",
639 |             "           3       0.97      1.00      0.98     60416\n",
640 |             "           4       0.86      0.39      0.54     56249\n",
641 |             "           5       1.00      1.00      1.00     59771\n",
642 |             "           6       0.99      0.97      0.98     60082\n",
643 |             "           7       0.92      0.66      0.77       604\n",
644 |             "\n",
645 |             "    accuracy                           0.89    373740\n",
646 |             "   macro avg       0.92      0.87      0.88    373740\n",
647 |             "weighted avg       0.91      0.89      0.88    373740\n",
648 |             "\n",
649 |             "F1 Score =  0.8773342009066785\n"
650 |           ],
651 |           "name": "stdout"
652 |         }
653 |       ]
654 |     }
655 |   ]
656 | }


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | # Detection-and-Classification-of-Distributed-DDoS-Attacks
2 | This repository contains ipython notebooks which were used for detection and classification of Distributed Denial of Service (DDoS) attacks. The dataset used in this study is called 'DDoS Evaluation Dataset (CICDDoS2019)' which was obtained from Canadian Institute for Cybersecurity. The dataset contains thousands of synthesized DDoS attack scenarios which are based on actual attacks attacks that were reported in 2019. The results from this study have been used in a research work hence give a citation if you are using these notebooks/results from this repository.
3 | 
4 | Link to the paper: https://link.springer.com/chapter/10.1007%2F978-981-15-9647-6_78
5 | 


--------------------------------------------------------------------------------
/where_to_find_the_preprocessed_dataset.md:
--------------------------------------------------------------------------------
 1 | Orinal dataset can be found on Canadian Institute for Cybersecurity website:
 2 | https://www.unb.ca/cic/datasets/ddos-2019.html (the download link at the end of the page is dead)
 3 | 
 4 | ~~The datasets used in the pre-processing IPython Notebook (DDOS_dataProcessing.ipynb) can be downloaded from the following link:~~
 5 | ~~https://drive.google.com/drive/folders/1BBCAAL7I4xKwRQJ8Joziqi28PccBQGOi?usp=sharing~~
 6 | ________________________________________________________________________________________
 7 | Update (Jan, 2022):
 8 | 
 9 | The datasets are in two parts and can be found here:
10 | ~~https://drive.google.com/drive/folders/1BBCAAL7I4xKwRQJ8Joziqi28PccBQGOi?usp=sharing~~
11 | ~~https://drive.google.com/drive/folders/1-0nrb9K4mwgpeLqRr7jrsTYVockLQm2J?usp=sharing~~
12 | There has been some changes in the way this data was stored during the project and necessary changes will be required in the ipnb files to read the datasets correctly. Please note that this project is no longer maintained so I won't be updating the ipython notebooks 
13 | 
14 | ________________________________________________________________________________________
15 | Update (Jan, 2024):
16 | 
17 | Unfortunately the dataset download link on the Canadian Institute for Cybersecurity website is down (at the time of writing) and I've lost access to my uni google drive where I had uploaded the two-part dataset, so those URLs are also no longer working.
18 | 
19 | Not all is lost though as the original dataset is available on Kaggle (here's the download link: https://www.kaggle.com/datasets/rodrigorosasilva/cic-ddos2019-30gb-full-dataset-csv-files). You can download the dataset from there and run it through the `DDOS_dataProcessing.ipynb` file and store the resulting "cleaned" files. You'll need these processed data files to run the rest of the ipython notebooks.
20 | 
21 | As previously stated, this repo is not actively maintained but feel free to raise an issue if you have any questions and I will try to get back to you with an answer. Thanks :)
22 | 


--------------------------------------------------------------------------------