├── README.md
├── test.csv
└── timeseries Forecasting.ipynb


/README.md:
--------------------------------------------------------------------------------
1 | 
2 | 


--------------------------------------------------------------------------------
/test.csv:
--------------------------------------------------------------------------------
 1 | Date,High,Low,Close,Adj Close
 2 | 2021-09-30,107.089996,102.949997,103.029999,102.939865
 3 | 2021-10-01,106.389999,103.66999799999999,105.82,105.727425
 4 | 2021-10-04,107.08000200000001,104.599998,104.900002,104.808235
 5 | 2021-10-05,106.0,103.75,104.900002,104.808235
 6 | 2021-10-06,104.41999799999999,102.059998,104.33000200000001,104.238731
 7 | 2021-10-07,106.529999,104.33000200000001,105.510002,105.417702
 8 | 2021-10-08,106.220001,104.660004,104.720001,104.628387
 9 | 2021-10-11,105.760002,103.970001,104.08000200000001,103.98895300000001
10 | 2021-10-12,104.040001,101.559998,102.720001,102.630142
11 | 2021-10-13,103.199997,101.18,102.360001,102.270454
12 | 2021-10-14,103.650002,102.370003,102.739998,102.650116
13 | 2021-10-15,105.900002,103.190002,104.410004,104.318665
14 | 2021-10-18,104.57,103.040001,104.120003,104.028915
15 | 2021-10-19,104.970001,103.58000200000001,104.730003,104.638382
16 | 2021-10-20,106.019997,103.870003,106.0,105.90727199999999
17 | 2021-10-21,106.389999,103.010002,103.150002,103.059761
18 | 2021-10-22,104.510002,102.550003,104.050003,103.958977
19 | 2021-10-25,105.989998,103.33000200000001,105.300003,105.20788600000002
20 | 2021-10-26,110.970001,105.220001,107.440002,107.34600800000001
21 | 2021-10-27,108.279999,103.690002,103.849998,103.759148
22 | 2021-10-28,105.379997,103.099998,105.260002,105.167915
23 | 2021-10-29,105.239998,104.120003,104.870003,104.77825899999999
24 | 2021-11-01,106.769997,105.279999,106.230003,106.13707
25 | 2021-11-02,107.139999,105.300003,106.690002,106.59666399999999
26 | 2021-11-03,106.339996,104.82,105.970001,105.877296
27 | 2021-11-04,106.400002,104.290001,105.209999,105.117958
28 | 2021-11-05,109.650002,106.849998,108.739998,108.64486699999999
29 | 2021-11-08,110.309998,108.32,108.41999799999999,108.32515
30 | 2021-11-09,116.16999799999999,110.480003,111.290001,111.19264199999999
31 | 2021-11-10,112.68,108.110001,108.959999,108.864677


--------------------------------------------------------------------------------
/timeseries Forecasting.ipynb:
--------------------------------------------------------------------------------
   1 | {
   2 |  "cells": [
   3 |   {
   4 |    "cell_type": "code",
   5 |    "execution_count": 1,
   6 |    "id": "27e86681",
   7 |    "metadata": {},
   8 |    "outputs": [],
   9 |    "source": [
  10 |     "import numpy as np\n",
  11 |     "from tensorflow.keras.models import Sequential\n",
  12 |     "from tensorflow.keras.layers import LSTM\n",
  13 |     "from tensorflow.keras.layers import Dense, Dropout\n",
  14 |     "import pandas as pd\n",
  15 |     "from matplotlib import pyplot as plt\n",
  16 |     "from sklearn.preprocessing import MinMaxScaler\n",
  17 |     "import seaborn as sns"
  18 |    ]
  19 |   },
  20 |   {
  21 |    "cell_type": "code",
  22 |    "execution_count": 2,
  23 |    "id": "59a416cd",
  24 |    "metadata": {},
  25 |    "outputs": [],
  26 |    "source": [
  27 |     "df=pd.read_csv(\"train.csv\",parse_dates=[\"Date\"],index_col=[0])"
  28 |    ]
  29 |   },
  30 |   {
  31 |    "cell_type": "code",
  32 |    "execution_count": 3,
  33 |    "id": "ab54faea",
  34 |    "metadata": {},
  35 |    "outputs": [
  36 |     {
  37 |      "name": "stdout",
  38 |      "output_type": "stream",
  39 |      "text": [
  40 |       "None\n"
  41 |      ]
  42 |     }
  43 |    ],
  44 |    "source": [
  45 |     "print(df.index.freq)"
  46 |    ]
  47 |   },
  48 |   {
  49 |    "cell_type": "code",
  50 |    "execution_count": 4,
  51 |    "id": "9d69a828",
  52 |    "metadata": {},
  53 |    "outputs": [
  54 |     {
  55 |      "data": {
  56 |       "text/plain": [
  57 |        "(5203, 5)"
  58 |       ]
  59 |      },
  60 |      "execution_count": 4,
  61 |      "metadata": {},
  62 |      "output_type": "execute_result"
  63 |     }
  64 |    ],
  65 |    "source": [
  66 |     "df.shape"
  67 |    ]
  68 |   },
  69 |   {
  70 |    "cell_type": "code",
  71 |    "execution_count": 5,
  72 |    "id": "1fe6f18e",
  73 |    "metadata": {},
  74 |    "outputs": [
  75 |     {
  76 |      "data": {
  77 |       "text/html": [
  78 |        "<div>\n",
  79 |        "<style scoped>\n",
  80 |        "    .dataframe tbody tr th:only-of-type {\n",
  81 |        "        vertical-align: middle;\n",
  82 |        "    }\n",
  83 |        "\n",
  84 |        "    .dataframe tbody tr th {\n",
  85 |        "        vertical-align: top;\n",
  86 |        "    }\n",
  87 |        "\n",
  88 |        "    .dataframe thead th {\n",
  89 |        "        text-align: right;\n",
  90 |        "    }\n",
  91 |        "</style>\n",
  92 |        "<table border=\"1\" class=\"dataframe\">\n",
  93 |        "  <thead>\n",
  94 |        "    <tr style=\"text-align: right;\">\n",
  95 |        "      <th></th>\n",
  96 |        "      <th>Open</th>\n",
  97 |        "      <th>High</th>\n",
  98 |        "      <th>Low</th>\n",
  99 |        "      <th>Close</th>\n",
 100 |        "      <th>Adj Close</th>\n",
 101 |        "    </tr>\n",
 102 |        "    <tr>\n",
 103 |        "      <th>Date</th>\n",
 104 |        "      <th></th>\n",
 105 |        "      <th></th>\n",
 106 |        "      <th></th>\n",
 107 |        "      <th></th>\n",
 108 |        "      <th></th>\n",
 109 |        "    </tr>\n",
 110 |        "  </thead>\n",
 111 |        "  <tbody>\n",
 112 |        "    <tr>\n",
 113 |        "      <th>2001-01-25</th>\n",
 114 |        "      <td>356.730774</td>\n",
 115 |        "      <td>362.980774</td>\n",
 116 |        "      <td>352.403839</td>\n",
 117 |        "      <td>353.365387</td>\n",
 118 |        "      <td>197.122452</td>\n",
 119 |        "    </tr>\n",
 120 |        "    <tr>\n",
 121 |        "      <th>2001-01-26</th>\n",
 122 |        "      <td>357.211548</td>\n",
 123 |        "      <td>360.096161</td>\n",
 124 |        "      <td>342.788452</td>\n",
 125 |        "      <td>343.269226</td>\n",
 126 |        "      <td>191.490234</td>\n",
 127 |        "    </tr>\n",
 128 |        "    <tr>\n",
 129 |        "      <th>2001-01-29</th>\n",
 130 |        "      <td>345.153839</td>\n",
 131 |        "      <td>355.769226</td>\n",
 132 |        "      <td>338.461548</td>\n",
 133 |        "      <td>341.384613</td>\n",
 134 |        "      <td>190.439011</td>\n",
 135 |        "    </tr>\n",
 136 |        "    <tr>\n",
 137 |        "      <th>2001-01-30</th>\n",
 138 |        "      <td>344.307678</td>\n",
 139 |        "      <td>355.923065</td>\n",
 140 |        "      <td>341.692322</td>\n",
 141 |        "      <td>355.769226</td>\n",
 142 |        "      <td>198.463318</td>\n",
 143 |        "    </tr>\n",
 144 |        "    <tr>\n",
 145 |        "      <th>2001-01-31</th>\n",
 146 |        "      <td>359.615387</td>\n",
 147 |        "      <td>361.153839</td>\n",
 148 |        "      <td>350.461548</td>\n",
 149 |        "      <td>353.692322</td>\n",
 150 |        "      <td>197.304749</td>\n",
 151 |        "    </tr>\n",
 152 |        "  </tbody>\n",
 153 |        "</table>\n",
 154 |        "</div>"
 155 |       ],
 156 |       "text/plain": [
 157 |        "                  Open        High         Low       Close   Adj Close\n",
 158 |        "Date                                                                  \n",
 159 |        "2001-01-25  356.730774  362.980774  352.403839  353.365387  197.122452\n",
 160 |        "2001-01-26  357.211548  360.096161  342.788452  343.269226  191.490234\n",
 161 |        "2001-01-29  345.153839  355.769226  338.461548  341.384613  190.439011\n",
 162 |        "2001-01-30  344.307678  355.923065  341.692322  355.769226  198.463318\n",
 163 |        "2001-01-31  359.615387  361.153839  350.461548  353.692322  197.304749"
 164 |       ]
 165 |      },
 166 |      "execution_count": 5,
 167 |      "metadata": {},
 168 |      "output_type": "execute_result"
 169 |     }
 170 |    ],
 171 |    "source": [
 172 |     "df.head()"
 173 |    ]
 174 |   },
 175 |   {
 176 |    "cell_type": "code",
 177 |    "execution_count": 6,
 178 |    "id": "750dae9a",
 179 |    "metadata": {},
 180 |    "outputs": [
 181 |     {
 182 |      "data": {
 183 |       "text/html": [
 184 |        "<div>\n",
 185 |        "<style scoped>\n",
 186 |        "    .dataframe tbody tr th:only-of-type {\n",
 187 |        "        vertical-align: middle;\n",
 188 |        "    }\n",
 189 |        "\n",
 190 |        "    .dataframe tbody tr th {\n",
 191 |        "        vertical-align: top;\n",
 192 |        "    }\n",
 193 |        "\n",
 194 |        "    .dataframe thead th {\n",
 195 |        "        text-align: right;\n",
 196 |        "    }\n",
 197 |        "</style>\n",
 198 |        "<table border=\"1\" class=\"dataframe\">\n",
 199 |        "  <thead>\n",
 200 |        "    <tr style=\"text-align: right;\">\n",
 201 |        "      <th></th>\n",
 202 |        "      <th>Open</th>\n",
 203 |        "      <th>High</th>\n",
 204 |        "      <th>Low</th>\n",
 205 |        "      <th>Close</th>\n",
 206 |        "      <th>Adj Close</th>\n",
 207 |        "    </tr>\n",
 208 |        "    <tr>\n",
 209 |        "      <th>Date</th>\n",
 210 |        "      <th></th>\n",
 211 |        "      <th></th>\n",
 212 |        "      <th></th>\n",
 213 |        "      <th></th>\n",
 214 |        "      <th></th>\n",
 215 |        "    </tr>\n",
 216 |        "  </thead>\n",
 217 |        "  <tbody>\n",
 218 |        "    <tr>\n",
 219 |        "      <th>2021-09-23</th>\n",
 220 |        "      <td>99.529999</td>\n",
 221 |        "      <td>104.080002</td>\n",
 222 |        "      <td>99.519997</td>\n",
 223 |        "      <td>102.959999</td>\n",
 224 |        "      <td>102.789993</td>\n",
 225 |        "    </tr>\n",
 226 |        "    <tr>\n",
 227 |        "      <th>2021-09-24</th>\n",
 228 |        "      <td>102.660004</td>\n",
 229 |        "      <td>104.199997</td>\n",
 230 |        "      <td>102.599998</td>\n",
 231 |        "      <td>103.800003</td>\n",
 232 |        "      <td>103.709198</td>\n",
 233 |        "    </tr>\n",
 234 |        "    <tr>\n",
 235 |        "      <th>2021-09-27</th>\n",
 236 |        "      <td>104.550003</td>\n",
 237 |        "      <td>106.330002</td>\n",
 238 |        "      <td>104.389999</td>\n",
 239 |        "      <td>105.349998</td>\n",
 240 |        "      <td>105.257835</td>\n",
 241 |        "    </tr>\n",
 242 |        "    <tr>\n",
 243 |        "      <th>2021-09-28</th>\n",
 244 |        "      <td>105.290001</td>\n",
 245 |        "      <td>106.750000</td>\n",
 246 |        "      <td>104.730003</td>\n",
 247 |        "      <td>105.730003</td>\n",
 248 |        "      <td>105.637512</td>\n",
 249 |        "    </tr>\n",
 250 |        "    <tr>\n",
 251 |        "      <th>2021-09-29</th>\n",
 252 |        "      <td>106.000000</td>\n",
 253 |        "      <td>107.000000</td>\n",
 254 |        "      <td>105.309998</td>\n",
 255 |        "      <td>106.279999</td>\n",
 256 |        "      <td>106.187027</td>\n",
 257 |        "    </tr>\n",
 258 |        "  </tbody>\n",
 259 |        "</table>\n",
 260 |        "</div>"
 261 |       ],
 262 |       "text/plain": [
 263 |        "                  Open        High         Low       Close   Adj Close\n",
 264 |        "Date                                                                  \n",
 265 |        "2021-09-23   99.529999  104.080002   99.519997  102.959999  102.789993\n",
 266 |        "2021-09-24  102.660004  104.199997  102.599998  103.800003  103.709198\n",
 267 |        "2021-09-27  104.550003  106.330002  104.389999  105.349998  105.257835\n",
 268 |        "2021-09-28  105.290001  106.750000  104.730003  105.730003  105.637512\n",
 269 |        "2021-09-29  106.000000  107.000000  105.309998  106.279999  106.187027"
 270 |       ]
 271 |      },
 272 |      "execution_count": 6,
 273 |      "metadata": {},
 274 |      "output_type": "execute_result"
 275 |     }
 276 |    ],
 277 |    "source": [
 278 |     "df.tail()"
 279 |    ]
 280 |   },
 281 |   {
 282 |    "cell_type": "code",
 283 |    "execution_count": 7,
 284 |    "id": "9f685196",
 285 |    "metadata": {},
 286 |    "outputs": [],
 287 |    "source": [
 288 |     "test_split=round(len(df)*0.20)"
 289 |    ]
 290 |   },
 291 |   {
 292 |    "cell_type": "code",
 293 |    "execution_count": 8,
 294 |    "id": "c435d2e4",
 295 |    "metadata": {},
 296 |    "outputs": [
 297 |     {
 298 |      "data": {
 299 |       "text/plain": [
 300 |        "1041"
 301 |       ]
 302 |      },
 303 |      "execution_count": 8,
 304 |      "metadata": {},
 305 |      "output_type": "execute_result"
 306 |     }
 307 |    ],
 308 |    "source": [
 309 |     "test_split"
 310 |    ]
 311 |   },
 312 |   {
 313 |    "cell_type": "code",
 314 |    "execution_count": 9,
 315 |    "id": "6815e6cf",
 316 |    "metadata": {},
 317 |    "outputs": [],
 318 |    "source": [
 319 |     "df_for_training=df[:-1041]\n",
 320 |     "df_for_testing=df[-1041:]"
 321 |    ]
 322 |   },
 323 |   {
 324 |    "cell_type": "code",
 325 |    "execution_count": 10,
 326 |    "id": "164f3e06",
 327 |    "metadata": {},
 328 |    "outputs": [
 329 |     {
 330 |      "name": "stdout",
 331 |      "output_type": "stream",
 332 |      "text": [
 333 |       "(4162, 5)\n",
 334 |       "(1041, 5)\n"
 335 |      ]
 336 |     }
 337 |    ],
 338 |    "source": [
 339 |     "print(df_for_training.shape)\n",
 340 |     "print(df_for_testing.shape)"
 341 |    ]
 342 |   },
 343 |   {
 344 |    "cell_type": "code",
 345 |    "execution_count": 11,
 346 |    "id": "4a86012c",
 347 |    "metadata": {},
 348 |    "outputs": [],
 349 |    "source": [
 350 |     "scaler = MinMaxScaler(feature_range=(0,1))\n",
 351 |     "df_for_training_scaled = scaler.fit_transform(df_for_training)"
 352 |    ]
 353 |   },
 354 |   {
 355 |    "cell_type": "code",
 356 |    "execution_count": 12,
 357 |    "id": "5697bff5",
 358 |    "metadata": {},
 359 |    "outputs": [],
 360 |    "source": [
 361 |     "df_for_testing_scaled=scaler.transform(df_for_testing)"
 362 |    ]
 363 |   },
 364 |   {
 365 |    "cell_type": "code",
 366 |    "execution_count": 13,
 367 |    "id": "d33a6b6e",
 368 |    "metadata": {},
 369 |    "outputs": [
 370 |     {
 371 |      "data": {
 372 |       "text/plain": [
 373 |        "array([[0.85398707, 0.86281807, 0.85292546, 0.8403402 , 0.82180889],\n",
 374 |        "       [0.85533406, 0.85473269, 0.82623316, 0.8122593 , 0.79289309],\n",
 375 |        "       [0.82155169, 0.84260459, 0.81422168, 0.80701755, 0.78749611],\n",
 376 |        "       ...,\n",
 377 |        "       [0.40689652, 0.40362224, 0.41960282, 0.40436458, 0.7632948 ],\n",
 378 |        "       [0.40517242, 0.39995691, 0.41832161, 0.4075738 , 0.76889077],\n",
 379 |        "       [0.40862067, 0.39974127, 0.41426436, 0.39880189, 0.75359571]])"
 380 |       ]
 381 |      },
 382 |      "execution_count": 13,
 383 |      "metadata": {},
 384 |      "output_type": "execute_result"
 385 |     }
 386 |    ],
 387 |    "source": [
 388 |     "df_for_training_scaled"
 389 |    ]
 390 |   },
 391 |   {
 392 |    "cell_type": "code",
 393 |    "execution_count": 14,
 394 |    "id": "03b668b1",
 395 |    "metadata": {},
 396 |    "outputs": [
 397 |     {
 398 |      "data": {
 399 |       "text/plain": [
 400 |        "(4162, 5)"
 401 |       ]
 402 |      },
 403 |      "execution_count": 14,
 404 |      "metadata": {},
 405 |      "output_type": "execute_result"
 406 |     }
 407 |    ],
 408 |    "source": [
 409 |     "df_for_training_scaled.shape"
 410 |    ]
 411 |   },
 412 |   {
 413 |    "cell_type": "code",
 414 |    "execution_count": 15,
 415 |    "id": "88390259",
 416 |    "metadata": {},
 417 |    "outputs": [
 418 |     {
 419 |      "data": {
 420 |       "text/plain": [
 421 |        "(1041, 5)"
 422 |       ]
 423 |      },
 424 |      "execution_count": 15,
 425 |      "metadata": {},
 426 |      "output_type": "execute_result"
 427 |     }
 428 |    ],
 429 |    "source": [
 430 |     "df_for_testing_scaled.shape"
 431 |    ]
 432 |   },
 433 |   {
 434 |    "cell_type": "code",
 435 |    "execution_count": 16,
 436 |    "id": "b6a58026",
 437 |    "metadata": {},
 438 |    "outputs": [],
 439 |    "source": [
 440 |     "def createXY(dataset,n_past):\n",
 441 |     "    dataX = []\n",
 442 |     "    dataY = []\n",
 443 |     "    for i in range(n_past, len(dataset)):\n",
 444 |     "            dataX.append(dataset[i - n_past:i, 0:dataset.shape[1]])\n",
 445 |     "            dataY.append(dataset[i,0])\n",
 446 |     "    return np.array(dataX),np.array(dataY)        "
 447 |    ]
 448 |   },
 449 |   {
 450 |    "cell_type": "code",
 451 |    "execution_count": 17,
 452 |    "id": "18b62d65",
 453 |    "metadata": {},
 454 |    "outputs": [],
 455 |    "source": [
 456 |     "trainX,trainY=createXY(df_for_training_scaled,30)"
 457 |    ]
 458 |   },
 459 |   {
 460 |    "cell_type": "code",
 461 |    "execution_count": 18,
 462 |    "id": "8d694c12",
 463 |    "metadata": {},
 464 |    "outputs": [
 465 |     {
 466 |      "data": {
 467 |       "text/plain": [
 468 |        "(4132, 30, 5)"
 469 |       ]
 470 |      },
 471 |      "execution_count": 18,
 472 |      "metadata": {},
 473 |      "output_type": "execute_result"
 474 |     }
 475 |    ],
 476 |    "source": [
 477 |     "trainX.shape"
 478 |    ]
 479 |   },
 480 |   {
 481 |    "cell_type": "code",
 482 |    "execution_count": null,
 483 |    "id": "2795bf2a",
 484 |    "metadata": {},
 485 |    "outputs": [],
 486 |    "source": []
 487 |   },
 488 |   {
 489 |    "cell_type": "code",
 490 |    "execution_count": 19,
 491 |    "id": "184bfdb6",
 492 |    "metadata": {},
 493 |    "outputs": [],
 494 |    "source": [
 495 |     "testX,testY=createXY(df_for_testing_scaled,30)"
 496 |    ]
 497 |   },
 498 |   {
 499 |    "cell_type": "code",
 500 |    "execution_count": 20,
 501 |    "id": "5e77d396",
 502 |    "metadata": {},
 503 |    "outputs": [
 504 |     {
 505 |      "data": {
 506 |       "text/plain": [
 507 |        "array([[0.85398707, 0.86281807, 0.85292546, 0.8403402 , 0.82180889],\n",
 508 |        "       [0.85533406, 0.85473269, 0.82623316, 0.8122593 , 0.79289309],\n",
 509 |        "       [0.82155169, 0.84260459, 0.81422168, 0.80701755, 0.78749611],\n",
 510 |        "       [0.81918098, 0.84303579, 0.82319031, 0.8470261 , 0.8286929 ],\n",
 511 |        "       [0.86206895, 0.85769729, 0.84753366, 0.84124952, 0.8227448 ],\n",
 512 |        "       [0.85668106, 0.85295391, 0.85479397, 0.84659822, 0.82825271],\n",
 513 |        "       [0.85129307, 0.85661925, 0.85372629, 0.84766796, 0.82935384],\n",
 514 |        "       [0.8540948 , 0.88249248, 0.85799703, 0.88125807, 0.86394198],\n",
 515 |        "       [0.88577588, 0.88227684, 0.88255396, 0.87590928, 0.85843431],\n",
 516 |        "       [0.88189657, 0.87602422, 0.87016871, 0.86200256, 0.84411479],\n",
 517 |        "       [0.88362063, 0.88357053, 0.87892376, 0.86606763, 0.84829995],\n",
 518 |        "       [0.87047413, 0.86200956, 0.84390347, 0.8344031 , 0.81569511],\n",
 519 |        "       [0.83857758, 0.87645542, 0.84966903, 0.87398378, 0.85645156],\n",
 520 |        "       [0.88168102, 0.88012075, 0.88105913, 0.86649551, 0.84874037],\n",
 521 |        "       [0.87090514, 0.86287196, 0.85949177, 0.84724008, 0.82891342],\n",
 522 |        "       [0.85237065, 0.88249248, 0.8601324 , 0.88403941, 0.86680588],\n",
 523 |        "       [0.85668106, 0.86589053, 0.86248134, 0.8630723 , 0.84521599],\n",
 524 |        "       [0.87176726, 0.8870203 , 0.88191333, 0.87783486, 0.86041721],\n",
 525 |        "       [0.88254305, 0.89003888, 0.88298101, 0.86949083, 0.85182511],\n",
 526 |        "       [0.875     , 0.86955587, 0.85821051, 0.86521178, 0.84741896],\n",
 527 |        "       [0.85775864, 0.85877534, 0.83600253, 0.84552848, 0.82715127],\n",
 528 |        "       [0.86745685, 0.88055195, 0.86120008, 0.88403941, 0.86680588],\n",
 529 |        "       [0.87780172, 0.88033639, 0.87828313, 0.88446729, 0.86724607],\n",
 530 |        "       [0.88900862, 0.88551106, 0.84838778, 0.85237489, 0.83420073],\n",
 531 |        "       [0.83512929, 0.83872361, 0.83365367, 0.83975181, 0.82120263],\n",
 532 |        "       [0.83189656, 0.82988361, 0.82532568, 0.81108261, 0.79168158],\n",
 533 |        "       [0.81896551, 0.82341526, 0.82703399, 0.82199401, 0.80649534],\n",
 534 |        "       [0.85129307, 0.85015098, 0.84240872, 0.8292683 , 0.81401255],\n",
 535 |        "       [0.83448273, 0.84282023, 0.84561178, 0.84124952, 0.82639405],\n",
 536 |        "       [0.84913791, 0.84497632, 0.83557547, 0.83889605, 0.82396218]])"
 537 |       ]
 538 |      },
 539 |      "execution_count": 20,
 540 |      "metadata": {},
 541 |      "output_type": "execute_result"
 542 |     }
 543 |    ],
 544 |    "source": [
 545 |     "trainX[0]"
 546 |    ]
 547 |   },
 548 |   {
 549 |    "cell_type": "code",
 550 |    "execution_count": 21,
 551 |    "id": "bdaf6a49",
 552 |    "metadata": {},
 553 |    "outputs": [
 554 |     {
 555 |      "name": "stdout",
 556 |      "output_type": "stream",
 557 |      "text": [
 558 |       "trainX Shape--  (4132, 30, 5)\n",
 559 |       "trainY Shape--  (4132,)\n"
 560 |      ]
 561 |     }
 562 |    ],
 563 |    "source": [
 564 |     "print(\"trainX Shape-- \",trainX.shape)\n",
 565 |     "print(\"trainY Shape-- \",trainY.shape)"
 566 |    ]
 567 |   },
 568 |   {
 569 |    "cell_type": "code",
 570 |    "execution_count": 22,
 571 |    "id": "0c78e7db",
 572 |    "metadata": {},
 573 |    "outputs": [
 574 |     {
 575 |      "name": "stdout",
 576 |      "output_type": "stream",
 577 |      "text": [
 578 |       "testX Shape--  (1011, 30, 5)\n",
 579 |       "testY Shape--  (1011,)\n"
 580 |      ]
 581 |     }
 582 |    ],
 583 |    "source": [
 584 |     "print(\"testX Shape-- \",testX.shape)\n",
 585 |     "print(\"testY Shape-- \",testY.shape)"
 586 |    ]
 587 |   },
 588 |   {
 589 |    "cell_type": "code",
 590 |    "execution_count": 23,
 591 |    "id": "cbf9d2df",
 592 |    "metadata": {},
 593 |    "outputs": [
 594 |     {
 595 |      "name": "stdout",
 596 |      "output_type": "stream",
 597 |      "text": [
 598 |       "trainX[0]-- \n",
 599 |       " [[0.85398707 0.86281807 0.85292546 0.8403402  0.82180889]\n",
 600 |       " [0.85533406 0.85473269 0.82623316 0.8122593  0.79289309]\n",
 601 |       " [0.82155169 0.84260459 0.81422168 0.80701755 0.78749611]\n",
 602 |       " [0.81918098 0.84303579 0.82319031 0.8470261  0.8286929 ]\n",
 603 |       " [0.86206895 0.85769729 0.84753366 0.84124952 0.8227448 ]\n",
 604 |       " [0.85668106 0.85295391 0.85479397 0.84659822 0.82825271]\n",
 605 |       " [0.85129307 0.85661925 0.85372629 0.84766796 0.82935384]\n",
 606 |       " [0.8540948  0.88249248 0.85799703 0.88125807 0.86394198]\n",
 607 |       " [0.88577588 0.88227684 0.88255396 0.87590928 0.85843431]\n",
 608 |       " [0.88189657 0.87602422 0.87016871 0.86200256 0.84411479]\n",
 609 |       " [0.88362063 0.88357053 0.87892376 0.86606763 0.84829995]\n",
 610 |       " [0.87047413 0.86200956 0.84390347 0.8344031  0.81569511]\n",
 611 |       " [0.83857758 0.87645542 0.84966903 0.87398378 0.85645156]\n",
 612 |       " [0.88168102 0.88012075 0.88105913 0.86649551 0.84874037]\n",
 613 |       " [0.87090514 0.86287196 0.85949177 0.84724008 0.82891342]\n",
 614 |       " [0.85237065 0.88249248 0.8601324  0.88403941 0.86680588]\n",
 615 |       " [0.85668106 0.86589053 0.86248134 0.8630723  0.84521599]\n",
 616 |       " [0.87176726 0.8870203  0.88191333 0.87783486 0.86041721]\n",
 617 |       " [0.88254305 0.89003888 0.88298101 0.86949083 0.85182511]\n",
 618 |       " [0.875      0.86955587 0.85821051 0.86521178 0.84741896]\n",
 619 |       " [0.85775864 0.85877534 0.83600253 0.84552848 0.82715127]\n",
 620 |       " [0.86745685 0.88055195 0.86120008 0.88403941 0.86680588]\n",
 621 |       " [0.87780172 0.88033639 0.87828313 0.88446729 0.86724607]\n",
 622 |       " [0.88900862 0.88551106 0.84838778 0.85237489 0.83420073]\n",
 623 |       " [0.83512929 0.83872361 0.83365367 0.83975181 0.82120263]\n",
 624 |       " [0.83189656 0.82988361 0.82532568 0.81108261 0.79168158]\n",
 625 |       " [0.81896551 0.82341526 0.82703399 0.82199401 0.80649534]\n",
 626 |       " [0.85129307 0.85015098 0.84240872 0.8292683  0.81401255]\n",
 627 |       " [0.83448273 0.84282023 0.84561178 0.84124952 0.82639405]\n",
 628 |       " [0.84913791 0.84497632 0.83557547 0.83889605 0.82396218]]\n",
 629 |       "\n",
 630 |       "trainY[0]--  0.8297413960482309\n"
 631 |      ]
 632 |     }
 633 |    ],
 634 |    "source": [
 635 |     "print(\"trainX[0]-- \\n\",trainX[0])\n",
 636 |     "print(\"\\ntrainY[0]-- \",trainY[0])"
 637 |    ]
 638 |   },
 639 |   {
 640 |    "cell_type": "code",
 641 |    "execution_count": 24,
 642 |    "id": "a5892e85",
 643 |    "metadata": {},
 644 |    "outputs": [
 645 |     {
 646 |      "data": {
 647 |       "text/plain": [
 648 |        "0.8297413960482309"
 649 |       ]
 650 |      },
 651 |      "execution_count": 24,
 652 |      "metadata": {},
 653 |      "output_type": "execute_result"
 654 |     }
 655 |    ],
 656 |    "source": [
 657 |     "trainY[0]"
 658 |    ]
 659 |   },
 660 |   {
 661 |    "cell_type": "code",
 662 |    "execution_count": 25,
 663 |    "id": "713712db",
 664 |    "metadata": {},
 665 |    "outputs": [
 666 |     {
 667 |      "data": {
 668 |       "text/plain": [
 669 |        "(4132,)"
 670 |       ]
 671 |      },
 672 |      "execution_count": 25,
 673 |      "metadata": {},
 674 |      "output_type": "execute_result"
 675 |     }
 676 |    ],
 677 |    "source": [
 678 |     "trainY.shape"
 679 |    ]
 680 |   },
 681 |   {
 682 |    "cell_type": "code",
 683 |    "execution_count": 26,
 684 |    "id": "d165e52b",
 685 |    "metadata": {},
 686 |    "outputs": [],
 687 |    "source": [
 688 |     "from keras.wrappers.scikit_learn import KerasRegressor\n",
 689 |     "from sklearn.model_selection import GridSearchCV"
 690 |    ]
 691 |   },
 692 |   {
 693 |    "cell_type": "code",
 694 |    "execution_count": 27,
 695 |    "id": "42ffe2bf",
 696 |    "metadata": {},
 697 |    "outputs": [
 698 |     {
 699 |      "name": "stderr",
 700 |      "output_type": "stream",
 701 |      "text": [
 702 |       "C:\\Users\\SUJAN~1.ISL\\AppData\\Local\\Temp/ipykernel_11732/1694479593.py:11: DeprecationWarning: KerasRegressor is deprecated, use Sci-Keras (https://github.com/adriangb/scikeras) instead.\n",
 703 |       "  grid_model = KerasRegressor(build_fn=build_model,verbose=1,validation_data=(testX,testY))\n"
 704 |      ]
 705 |     }
 706 |    ],
 707 |    "source": [
 708 |     "def build_model(optimizer):\n",
 709 |     "    grid_model = Sequential()\n",
 710 |     "    grid_model.add(LSTM(50,return_sequences=True,input_shape=(30,5)))\n",
 711 |     "    grid_model.add(LSTM(50))\n",
 712 |     "    grid_model.add(Dropout(0.2))\n",
 713 |     "    grid_model.add(Dense(1))\n",
 714 |     "\n",
 715 |     "    grid_model.compile(loss = 'mse',optimizer = optimizer)\n",
 716 |     "    return grid_model\n",
 717 |     "\n",
 718 |     "grid_model = KerasRegressor(build_fn=build_model,verbose=1,validation_data=(testX,testY))\n",
 719 |     "parameters = {'batch_size' : [16,20],\n",
 720 |     "              'epochs' : [8,10],\n",
 721 |     "              'optimizer' : ['adam','Adadelta'] }\n",
 722 |     "\n",
 723 |     "grid_search  = GridSearchCV(estimator = grid_model,\n",
 724 |     "                            param_grid = parameters,\n",
 725 |     "                            cv = 2)"
 726 |    ]
 727 |   },
 728 |   {
 729 |    "cell_type": "code",
 730 |    "execution_count": 28,
 731 |    "id": "1fc54625",
 732 |    "metadata": {},
 733 |    "outputs": [
 734 |     {
 735 |      "name": "stdout",
 736 |      "output_type": "stream",
 737 |      "text": [
 738 |       "Epoch 1/8\n",
 739 |       "130/130 [==============================] - 6s 23ms/step - loss: 0.0045 - val_loss: 0.0024\n",
 740 |       "Epoch 2/8\n",
 741 |       "130/130 [==============================] - 2s 17ms/step - loss: 0.0012 - val_loss: 0.0017\n",
 742 |       "Epoch 3/8\n",
 743 |       "130/130 [==============================] - 2s 18ms/step - loss: 9.0876e-04 - val_loss: 0.0014\n",
 744 |       "Epoch 4/8\n",
 745 |       "130/130 [==============================] - 2s 17ms/step - loss: 8.8440e-04 - val_loss: 0.0016\n",
 746 |       "Epoch 5/8\n",
 747 |       "130/130 [==============================] - 2s 18ms/step - loss: 8.2294e-04 - val_loss: 0.0018\n",
 748 |       "Epoch 6/8\n",
 749 |       "130/130 [==============================] - 2s 18ms/step - loss: 7.0709e-04 - val_loss: 0.0013\n",
 750 |       "Epoch 7/8\n",
 751 |       "130/130 [==============================] - 2s 18ms/step - loss: 8.3741e-04 - val_loss: 0.0011\n",
 752 |       "Epoch 8/8\n",
 753 |       "130/130 [==============================] - 2s 18ms/step - loss: 7.1207e-04 - val_loss: 0.0017\n",
 754 |       "130/130 [==============================] - 1s 6ms/step - loss: 0.0061\n",
 755 |       "Epoch 1/8\n",
 756 |       "130/130 [==============================] - 6s 25ms/step - loss: 0.0111 - val_loss: 0.0011\n",
 757 |       "Epoch 2/8\n",
 758 |       "130/130 [==============================] - 3s 19ms/step - loss: 0.0029 - val_loss: 5.4374e-04\n",
 759 |       "Epoch 3/8\n",
 760 |       "130/130 [==============================] - 2s 19ms/step - loss: 0.0026 - val_loss: 6.5927e-04\n",
 761 |       "Epoch 4/8\n",
 762 |       "130/130 [==============================] - 2s 19ms/step - loss: 0.0024 - val_loss: 1.5511e-04\n",
 763 |       "Epoch 5/8\n",
 764 |       "130/130 [==============================] - 2s 18ms/step - loss: 0.0024 - val_loss: 1.4759e-04\n",
 765 |       "Epoch 6/8\n",
 766 |       "130/130 [==============================] - 2s 18ms/step - loss: 0.0021 - val_loss: 2.3574e-04\n",
 767 |       "Epoch 7/8\n",
 768 |       "130/130 [==============================] - 2s 19ms/step - loss: 0.0021 - val_loss: 2.6727e-04\n",
 769 |       "Epoch 8/8\n",
 770 |       "130/130 [==============================] - 2s 18ms/step - loss: 0.0019 - val_loss: 1.3201e-04\n",
 771 |       "130/130 [==============================] - 1s 6ms/step - loss: 1.3788e-04\n",
 772 |       "Epoch 1/8\n",
 773 |       "130/130 [==============================] - 6s 23ms/step - loss: 0.0619 - val_loss: 0.0053\n",
 774 |       "Epoch 2/8\n",
 775 |       "130/130 [==============================] - 2s 18ms/step - loss: 0.0558 - val_loss: 0.0043\n",
 776 |       "Epoch 3/8\n",
 777 |       "130/130 [==============================] - 2s 18ms/step - loss: 0.0489 - val_loss: 0.0033\n",
 778 |       "Epoch 4/8\n",
 779 |       "130/130 [==============================] - 2s 18ms/step - loss: 0.0416 - val_loss: 0.0025\n",
 780 |       "Epoch 5/8\n",
 781 |       "130/130 [==============================] - 2s 18ms/step - loss: 0.0354 - val_loss: 0.0018\n",
 782 |       "Epoch 6/8\n",
 783 |       "130/130 [==============================] - 2s 18ms/step - loss: 0.0285 - val_loss: 0.0013\n",
 784 |       "Epoch 7/8\n",
 785 |       "130/130 [==============================] - 2s 18ms/step - loss: 0.0225 - val_loss: 9.9643e-04\n",
 786 |       "Epoch 8/8\n",
 787 |       "130/130 [==============================] - 2s 18ms/step - loss: 0.0178 - val_loss: 9.0072e-04\n",
 788 |       "130/130 [==============================] - 1s 5ms/step - loss: 0.0809\n",
 789 |       "Epoch 1/8\n",
 790 |       "130/130 [==============================] - 6s 24ms/step - loss: 0.3296 - val_loss: 0.0131\n",
 791 |       "Epoch 2/8\n",
 792 |       "130/130 [==============================] - 2s 19ms/step - loss: 0.3091 - val_loss: 0.0113\n",
 793 |       "Epoch 3/8\n",
 794 |       "130/130 [==============================] - 2s 19ms/step - loss: 0.2856 - val_loss: 0.0095\n",
 795 |       "Epoch 4/8\n",
 796 |       "130/130 [==============================] - 2s 19ms/step - loss: 0.2617 - val_loss: 0.0078\n",
 797 |       "Epoch 5/8\n",
 798 |       "130/130 [==============================] - 2s 19ms/step - loss: 0.2376 - val_loss: 0.0062\n",
 799 |       "Epoch 6/8\n",
 800 |       "130/130 [==============================] - 2s 19ms/step - loss: 0.2149 - val_loss: 0.0048\n",
 801 |       "Epoch 7/8\n",
 802 |       "130/130 [==============================] - 2s 19ms/step - loss: 0.1906 - val_loss: 0.0035\n",
 803 |       "Epoch 8/8\n",
 804 |       "130/130 [==============================] - 2s 18ms/step - loss: 0.1665 - val_loss: 0.0025\n",
 805 |       "130/130 [==============================] - 1s 6ms/step - loss: 0.0406\n",
 806 |       "Epoch 1/10\n",
 807 |       "130/130 [==============================] - 6s 25ms/step - loss: 0.0050 - val_loss: 0.0024\n",
 808 |       "Epoch 2/10\n",
 809 |       "130/130 [==============================] - 3s 20ms/step - loss: 0.0012 - val_loss: 0.0033\n",
 810 |       "Epoch 3/10\n",
 811 |       "130/130 [==============================] - 3s 20ms/step - loss: 0.0010 - val_loss: 0.0024\n",
 812 |       "Epoch 4/10\n",
 813 |       "130/130 [==============================] - 3s 19ms/step - loss: 8.7333e-04 - val_loss: 0.0017\n",
 814 |       "Epoch 5/10\n",
 815 |       "130/130 [==============================] - 3s 20ms/step - loss: 9.6562e-04 - val_loss: 0.0026\n",
 816 |       "Epoch 6/10\n",
 817 |       "130/130 [==============================] - 3s 20ms/step - loss: 7.7910e-04 - val_loss: 0.0011\n",
 818 |       "Epoch 7/10\n",
 819 |       "130/130 [==============================] - 3s 19ms/step - loss: 8.4658e-04 - val_loss: 0.0012\n",
 820 |       "Epoch 8/10\n",
 821 |       "130/130 [==============================] - 3s 19ms/step - loss: 7.0317e-04 - val_loss: 0.0016\n",
 822 |       "Epoch 9/10\n",
 823 |       "130/130 [==============================] - 3s 20ms/step - loss: 6.8117e-04 - val_loss: 0.0014\n",
 824 |       "Epoch 10/10\n",
 825 |       "130/130 [==============================] - 3s 20ms/step - loss: 6.4499e-04 - val_loss: 9.2790e-04\n",
 826 |       "130/130 [==============================] - 1s 7ms/step - loss: 0.0093\n",
 827 |       "Epoch 1/10\n",
 828 |       "130/130 [==============================] - 6s 23ms/step - loss: 0.0140 - val_loss: 6.1009e-04\n",
 829 |       "Epoch 2/10\n",
 830 |       "130/130 [==============================] - 2s 19ms/step - loss: 0.0029 - val_loss: 3.5661e-04\n",
 831 |       "Epoch 3/10\n",
 832 |       "130/130 [==============================] - 2s 18ms/step - loss: 0.0028 - val_loss: 4.1601e-04\n",
 833 |       "Epoch 4/10\n",
 834 |       "130/130 [==============================] - 2s 18ms/step - loss: 0.0026 - val_loss: 1.4354e-04\n",
 835 |       "Epoch 5/10\n",
 836 |       "130/130 [==============================] - 2s 18ms/step - loss: 0.0023 - val_loss: 2.6037e-04\n",
 837 |       "Epoch 6/10\n",
 838 |       "130/130 [==============================] - 2s 19ms/step - loss: 0.0022 - val_loss: 5.0231e-04\n",
 839 |       "Epoch 7/10\n",
 840 |       "130/130 [==============================] - 2s 18ms/step - loss: 0.0023 - val_loss: 1.4798e-04\n",
 841 |       "Epoch 8/10\n",
 842 |       "130/130 [==============================] - 2s 19ms/step - loss: 0.0020 - val_loss: 1.6298e-04\n",
 843 |       "Epoch 9/10\n",
 844 |       "130/130 [==============================] - 2s 19ms/step - loss: 0.0018 - val_loss: 1.5584e-04\n",
 845 |       "Epoch 10/10\n",
 846 |       "130/130 [==============================] - 2s 18ms/step - loss: 0.0018 - val_loss: 1.3824e-04\n",
 847 |       "130/130 [==============================] - 1s 6ms/step - loss: 1.3508e-04\n",
 848 |       "Epoch 1/10\n",
 849 |       "130/130 [==============================] - 6s 24ms/step - loss: 0.1327 - val_loss: 0.0152\n",
 850 |       "Epoch 2/10\n",
 851 |       "130/130 [==============================] - 2s 19ms/step - loss: 0.1190 - val_loss: 0.0130\n",
 852 |       "Epoch 3/10\n",
 853 |       "130/130 [==============================] - 2s 19ms/step - loss: 0.1055 - val_loss: 0.0108\n",
 854 |       "Epoch 4/10\n",
 855 |       "130/130 [==============================] - 2s 19ms/step - loss: 0.0930 - val_loss: 0.0088\n",
 856 |       "Epoch 5/10\n",
 857 |       "130/130 [==============================] - 3s 19ms/step - loss: 0.0805 - val_loss: 0.0070\n",
 858 |       "Epoch 6/10\n",
 859 |       "130/130 [==============================] - 3s 19ms/step - loss: 0.0690 - val_loss: 0.0054\n",
 860 |       "Epoch 7/10\n",
 861 |       "130/130 [==============================] - 2s 19ms/step - loss: 0.0570 - val_loss: 0.0040\n",
 862 |       "Epoch 8/10\n",
 863 |       "130/130 [==============================] - 2s 19ms/step - loss: 0.0476 - val_loss: 0.0029\n",
 864 |       "Epoch 9/10\n",
 865 |       "130/130 [==============================] - 3s 19ms/step - loss: 0.0380 - val_loss: 0.0020\n",
 866 |       "Epoch 10/10\n",
 867 |       "130/130 [==============================] - 3s 20ms/step - loss: 0.0298 - val_loss: 0.0014\n",
 868 |       "130/130 [==============================] - 1s 7ms/step - loss: 0.0926\n",
 869 |       "Epoch 1/10\n",
 870 |       "130/130 [==============================] - 6s 26ms/step - loss: 0.1676 - val_loss: 0.0062\n",
 871 |       "Epoch 2/10\n",
 872 |       "130/130 [==============================] - 3s 19ms/step - loss: 0.1418 - val_loss: 0.0047\n",
 873 |       "Epoch 3/10\n",
 874 |       "130/130 [==============================] - 3s 20ms/step - loss: 0.1201 - val_loss: 0.0034\n",
 875 |       "Epoch 4/10\n",
 876 |       "130/130 [==============================] - 3s 19ms/step - loss: 0.1034 - val_loss: 0.0023\n",
 877 |       "Epoch 5/10\n",
 878 |       "130/130 [==============================] - 3s 20ms/step - loss: 0.0823 - val_loss: 0.0014\n",
 879 |       "Epoch 6/10\n",
 880 |       "130/130 [==============================] - 3s 20ms/step - loss: 0.0659 - val_loss: 8.7395e-04\n",
 881 |       "Epoch 7/10\n",
 882 |       "130/130 [==============================] - 2s 19ms/step - loss: 0.0519 - val_loss: 6.4540e-04\n",
 883 |       "Epoch 8/10\n",
 884 |       "130/130 [==============================] - 2s 19ms/step - loss: 0.0410 - val_loss: 7.2971e-04\n",
 885 |       "Epoch 9/10\n",
 886 |       "130/130 [==============================] - 2s 19ms/step - loss: 0.0296 - val_loss: 0.0011\n",
 887 |       "Epoch 10/10\n",
 888 |       "130/130 [==============================] - 3s 20ms/step - loss: 0.0234 - val_loss: 0.0017\n",
 889 |       "130/130 [==============================] - 1s 7ms/step - loss: 8.2772e-04\n",
 890 |       "Epoch 1/8\n",
 891 |       "104/104 [==============================] - 5s 25ms/step - loss: 0.0041 - val_loss: 0.0011\n",
 892 |       "Epoch 2/8\n",
 893 |       "104/104 [==============================] - 2s 19ms/step - loss: 0.0012 - val_loss: 9.3332e-04\n",
 894 |       "Epoch 3/8\n",
 895 |       "104/104 [==============================] - 2s 19ms/step - loss: 9.8285e-04 - val_loss: 8.4572e-04\n",
 896 |       "Epoch 4/8\n",
 897 |       "104/104 [==============================] - 2s 20ms/step - loss: 9.3753e-04 - val_loss: 9.7374e-04\n",
 898 |       "Epoch 5/8\n",
 899 |       "104/104 [==============================] - 2s 19ms/step - loss: 8.6342e-04 - val_loss: 8.9776e-04\n",
 900 |       "Epoch 6/8\n",
 901 |       "104/104 [==============================] - 2s 19ms/step - loss: 8.4445e-04 - val_loss: 0.0011\n",
 902 |       "Epoch 7/8\n",
 903 |       "104/104 [==============================] - 2s 19ms/step - loss: 7.8490e-04 - val_loss: 5.4684e-04\n",
 904 |       "Epoch 8/8\n",
 905 |       "104/104 [==============================] - 2s 19ms/step - loss: 6.7601e-04 - val_loss: 5.3758e-04\n",
 906 |       "104/104 [==============================] - 1s 6ms/step - loss: 0.0045\n",
 907 |       "Epoch 1/8\n",
 908 |       "104/104 [==============================] - 6s 25ms/step - loss: 0.0162 - val_loss: 0.0028\n",
 909 |       "Epoch 2/8\n",
 910 |       "104/104 [==============================] - 2s 20ms/step - loss: 0.0035 - val_loss: 6.2902e-04\n",
 911 |       "Epoch 3/8\n",
 912 |       "104/104 [==============================] - 2s 19ms/step - loss: 0.0028 - val_loss: 3.7858e-04\n",
 913 |       "Epoch 4/8\n",
 914 |       "104/104 [==============================] - 2s 19ms/step - loss: 0.0028 - val_loss: 3.3770e-04\n",
 915 |       "Epoch 5/8\n",
 916 |       "104/104 [==============================] - 2s 19ms/step - loss: 0.0028 - val_loss: 4.2632e-04\n",
 917 |       "Epoch 6/8\n",
 918 |       "104/104 [==============================] - 2s 19ms/step - loss: 0.0024 - val_loss: 2.2002e-04\n",
 919 |       "Epoch 7/8\n",
 920 |       "104/104 [==============================] - 2s 19ms/step - loss: 0.0026 - val_loss: 4.0730e-04\n",
 921 |       "Epoch 8/8\n",
 922 |       "104/104 [==============================] - 2s 19ms/step - loss: 0.0021 - val_loss: 1.6472e-04\n",
 923 |       "104/104 [==============================] - 1s 6ms/step - loss: 1.4469e-04\n",
 924 |       "Epoch 1/8\n",
 925 |       "104/104 [==============================] - 5s 27ms/step - loss: 0.0387 - val_loss: 0.0030\n",
 926 |       "Epoch 2/8\n",
 927 |       "104/104 [==============================] - 2s 19ms/step - loss: 0.0350 - val_loss: 0.0022\n",
 928 |       "Epoch 3/8\n",
 929 |       "104/104 [==============================] - 2s 19ms/step - loss: 0.0287 - val_loss: 0.0016\n",
 930 |       "Epoch 4/8\n",
 931 |       "104/104 [==============================] - 2s 19ms/step - loss: 0.0245 - val_loss: 0.0012\n",
 932 |       "Epoch 5/8\n",
 933 |       "104/104 [==============================] - 2s 19ms/step - loss: 0.0203 - val_loss: 8.2166e-04\n",
 934 |       "Epoch 6/8\n",
 935 |       "104/104 [==============================] - 2s 19ms/step - loss: 0.0170 - val_loss: 6.1919e-04\n",
 936 |       "Epoch 7/8\n",
 937 |       "104/104 [==============================] - 2s 20ms/step - loss: 0.0137 - val_loss: 5.3654e-04\n",
 938 |       "Epoch 8/8\n",
 939 |       "104/104 [==============================] - 2s 19ms/step - loss: 0.0118 - val_loss: 5.5950e-04\n",
 940 |       "104/104 [==============================] - 1s 6ms/step - loss: 0.0437\n",
 941 |       "Epoch 1/8\n",
 942 |       "104/104 [==============================] - 5s 25ms/step - loss: 0.4360 - val_loss: 0.0241\n",
 943 |       "Epoch 2/8\n",
 944 |       "104/104 [==============================] - 2s 19ms/step - loss: 0.4077 - val_loss: 0.0217\n",
 945 |       "Epoch 3/8\n",
 946 |       "104/104 [==============================] - 2s 19ms/step - loss: 0.3787 - val_loss: 0.0192\n",
 947 |       "Epoch 4/8\n",
 948 |       "104/104 [==============================] - 2s 19ms/step - loss: 0.3537 - val_loss: 0.0168\n",
 949 |       "Epoch 5/8\n",
 950 |       "104/104 [==============================] - 2s 19ms/step - loss: 0.3256 - val_loss: 0.0145\n",
 951 |       "Epoch 6/8\n",
 952 |       "104/104 [==============================] - 2s 19ms/step - loss: 0.2958 - val_loss: 0.0123\n",
 953 |       "Epoch 7/8\n",
 954 |       "104/104 [==============================] - 2s 19ms/step - loss: 0.2700 - val_loss: 0.0101\n",
 955 |       "Epoch 8/8\n",
 956 |       "104/104 [==============================] - 2s 19ms/step - loss: 0.2415 - val_loss: 0.0082\n",
 957 |       "104/104 [==============================] - 1s 7ms/step - loss: 0.0798\n",
 958 |       "Epoch 1/10\n",
 959 |       "104/104 [==============================] - 6s 25ms/step - loss: 0.0048 - val_loss: 0.0033\n",
 960 |       "Epoch 2/10\n",
 961 |       "104/104 [==============================] - 2s 19ms/step - loss: 0.0012 - val_loss: 0.0020\n",
 962 |       "Epoch 3/10\n",
 963 |       "104/104 [==============================] - 2s 19ms/step - loss: 0.0012 - val_loss: 0.0022\n",
 964 |       "Epoch 4/10\n",
 965 |       "104/104 [==============================] - 2s 19ms/step - loss: 9.3055e-04 - val_loss: 0.0019\n",
 966 |       "Epoch 5/10\n",
 967 |       "104/104 [==============================] - 2s 19ms/step - loss: 8.9744e-04 - val_loss: 0.0021\n",
 968 |       "Epoch 6/10\n",
 969 |       "104/104 [==============================] - 2s 19ms/step - loss: 8.1779e-04 - val_loss: 0.0014\n",
 970 |       "Epoch 7/10\n",
 971 |       "104/104 [==============================] - 2s 23ms/step - loss: 8.1245e-04 - val_loss: 0.0020\n",
 972 |       "Epoch 8/10\n",
 973 |       "104/104 [==============================] - 2s 24ms/step - loss: 8.0051e-04 - val_loss: 0.0022\n",
 974 |       "Epoch 9/10\n",
 975 |       "104/104 [==============================] - 2s 21ms/step - loss: 6.9432e-04 - val_loss: 0.0015\n",
 976 |       "Epoch 10/10\n",
 977 |       "104/104 [==============================] - 2s 22ms/step - loss: 6.2016e-04 - val_loss: 0.0013\n",
 978 |       "104/104 [==============================] - 1s 7ms/step - loss: 0.0104\n",
 979 |       "Epoch 1/10\n",
 980 |       "104/104 [==============================] - 6s 28ms/step - loss: 0.0130 - val_loss: 4.6528e-04\n",
 981 |       "Epoch 2/10\n",
 982 |       "104/104 [==============================] - 2s 20ms/step - loss: 0.0031 - val_loss: 4.5892e-04\n",
 983 |       "Epoch 3/10\n",
 984 |       "104/104 [==============================] - 2s 20ms/step - loss: 0.0028 - val_loss: 3.2218e-04\n",
 985 |       "Epoch 4/10\n",
 986 |       "104/104 [==============================] - 2s 20ms/step - loss: 0.0027 - val_loss: 1.8599e-04\n",
 987 |       "Epoch 5/10\n",
 988 |       "104/104 [==============================] - 2s 22ms/step - loss: 0.0025 - val_loss: 1.9228e-04\n",
 989 |       "Epoch 6/10\n",
 990 |       "104/104 [==============================] - 2s 22ms/step - loss: 0.0027 - val_loss: 1.8521e-04\n",
 991 |       "Epoch 7/10\n",
 992 |       "104/104 [==============================] - 2s 22ms/step - loss: 0.0024 - val_loss: 1.5056e-04\n",
 993 |       "Epoch 8/10\n",
 994 |       "104/104 [==============================] - 2s 23ms/step - loss: 0.0020 - val_loss: 3.5268e-04\n",
 995 |       "Epoch 9/10\n",
 996 |       "104/104 [==============================] - 2s 21ms/step - loss: 0.0021 - val_loss: 2.0168e-04\n",
 997 |       "Epoch 10/10\n",
 998 |       "104/104 [==============================] - 2s 23ms/step - loss: 0.0020 - val_loss: 1.3420e-04\n",
 999 |       "104/104 [==============================] - 1s 6ms/step - loss: 1.5619e-04\n",
1000 |       "Epoch 1/10\n",
1001 |       "104/104 [==============================] - 5s 25ms/step - loss: 0.1901 - val_loss: 0.0253\n",
1002 |       "Epoch 2/10\n",
1003 |       "104/104 [==============================] - 2s 19ms/step - loss: 0.1784 - val_loss: 0.0230\n",
1004 |       "Epoch 3/10\n",
1005 |       "104/104 [==============================] - 2s 21ms/step - loss: 0.1643 - val_loss: 0.0209\n",
1006 |       "Epoch 4/10\n",
1007 |       "104/104 [==============================] - 2s 20ms/step - loss: 0.1531 - val_loss: 0.0187\n",
1008 |       "Epoch 5/10\n",
1009 |       "104/104 [==============================] - 2s 22ms/step - loss: 0.1419 - val_loss: 0.0166\n",
1010 |       "Epoch 6/10\n",
1011 |       "104/104 [==============================] - 2s 20ms/step - loss: 0.1297 - val_loss: 0.0145\n",
1012 |       "Epoch 7/10\n",
1013 |       "104/104 [==============================] - 2s 21ms/step - loss: 0.1159 - val_loss: 0.0126\n",
1014 |       "Epoch 8/10\n",
1015 |       "104/104 [==============================] - 2s 21ms/step - loss: 0.1060 - val_loss: 0.0108\n",
1016 |       "Epoch 9/10\n",
1017 |       "104/104 [==============================] - 3s 28ms/step - loss: 0.0945 - val_loss: 0.0091\n",
1018 |       "Epoch 10/10\n",
1019 |       "104/104 [==============================] - 3s 25ms/step - loss: 0.0833 - val_loss: 0.0075\n",
1020 |       "104/104 [==============================] - 1s 5ms/step - loss: 0.2128\n",
1021 |       "Epoch 1/10\n",
1022 |       "104/104 [==============================] - 6s 25ms/step - loss: 0.3825 - val_loss: 0.0222\n",
1023 |       "Epoch 2/10\n",
1024 |       "104/104 [==============================] - 2s 19ms/step - loss: 0.3530 - val_loss: 0.0197\n",
1025 |       "Epoch 3/10\n",
1026 |       "104/104 [==============================] - 2s 21ms/step - loss: 0.3224 - val_loss: 0.0173\n",
1027 |       "Epoch 4/10\n",
1028 |       "104/104 [==============================] - 2s 22ms/step - loss: 0.2969 - val_loss: 0.0149\n",
1029 |       "Epoch 5/10\n",
1030 |       "104/104 [==============================] - 2s 22ms/step - loss: 0.2642 - val_loss: 0.0126\n",
1031 |       "Epoch 6/10\n",
1032 |       "104/104 [==============================] - 2s 23ms/step - loss: 0.2371 - val_loss: 0.0104\n",
1033 |       "Epoch 7/10\n",
1034 |       "104/104 [==============================] - 3s 24ms/step - loss: 0.2087 - val_loss: 0.0084\n",
1035 |       "Epoch 8/10\n",
1036 |       "104/104 [==============================] - 2s 23ms/step - loss: 0.1806 - val_loss: 0.0065\n",
1037 |       "Epoch 9/10\n",
1038 |       "104/104 [==============================] - 2s 22ms/step - loss: 0.1530 - val_loss: 0.0049\n",
1039 |       "Epoch 10/10\n",
1040 |       "104/104 [==============================] - 2s 22ms/step - loss: 0.1281 - val_loss: 0.0035\n",
1041 |       "104/104 [==============================] - 1s 6ms/step - loss: 0.0401\n",
1042 |       "Epoch 1/8\n",
1043 |       "207/207 [==============================] - 7s 21ms/step - loss: 0.0069 - val_loss: 2.0161e-04\n",
1044 |       "Epoch 2/8\n",
1045 |       "207/207 [==============================] - 4s 19ms/step - loss: 0.0019 - val_loss: 3.6436e-04\n",
1046 |       "Epoch 3/8\n",
1047 |       "207/207 [==============================] - 4s 20ms/step - loss: 0.0017 - val_loss: 1.9528e-04\n",
1048 |       "Epoch 4/8\n",
1049 |       "207/207 [==============================] - 4s 20ms/step - loss: 0.0016 - val_loss: 2.2016e-04\n",
1050 |       "Epoch 5/8\n"
1051 |      ]
1052 |     },
1053 |     {
1054 |      "name": "stdout",
1055 |      "output_type": "stream",
1056 |      "text": [
1057 |       "207/207 [==============================] - 4s 20ms/step - loss: 0.0014 - val_loss: 2.0823e-04\n",
1058 |       "Epoch 6/8\n",
1059 |       "207/207 [==============================] - 4s 20ms/step - loss: 0.0014 - val_loss: 1.4749e-04\n",
1060 |       "Epoch 7/8\n",
1061 |       "207/207 [==============================] - 4s 20ms/step - loss: 0.0013 - val_loss: 1.3235e-04\n",
1062 |       "Epoch 8/8\n",
1063 |       "207/207 [==============================] - 4s 20ms/step - loss: 0.0012 - val_loss: 1.1994e-04\n"
1064 |      ]
1065 |     }
1066 |    ],
1067 |    "source": [
1068 |     "grid_search = grid_search.fit(trainX,trainY)"
1069 |    ]
1070 |   },
1071 |   {
1072 |    "cell_type": "code",
1073 |    "execution_count": 29,
1074 |    "id": "a9e26e10",
1075 |    "metadata": {},
1076 |    "outputs": [
1077 |     {
1078 |      "data": {
1079 |       "text/plain": [
1080 |        "{'batch_size': 20, 'epochs': 8, 'optimizer': 'adam'}"
1081 |       ]
1082 |      },
1083 |      "execution_count": 29,
1084 |      "metadata": {},
1085 |      "output_type": "execute_result"
1086 |     }
1087 |    ],
1088 |    "source": [
1089 |     "grid_search.best_params_"
1090 |    ]
1091 |   },
1092 |   {
1093 |    "cell_type": "code",
1094 |    "execution_count": 30,
1095 |    "id": "d6851ffc",
1096 |    "metadata": {},
1097 |    "outputs": [],
1098 |    "source": [
1099 |     "my_model=grid_search.best_estimator_.model"
1100 |    ]
1101 |   },
1102 |   {
1103 |    "cell_type": "code",
1104 |    "execution_count": 31,
1105 |    "id": "9f0b2e50",
1106 |    "metadata": {},
1107 |    "outputs": [
1108 |     {
1109 |      "data": {
1110 |       "text/plain": [
1111 |        "<keras.engine.sequential.Sequential at 0x20bd0704b20>"
1112 |       ]
1113 |      },
1114 |      "execution_count": 31,
1115 |      "metadata": {},
1116 |      "output_type": "execute_result"
1117 |     }
1118 |    ],
1119 |    "source": [
1120 |     "my_model"
1121 |    ]
1122 |   },
1123 |   {
1124 |    "cell_type": "code",
1125 |    "execution_count": 32,
1126 |    "id": "eeb97d64",
1127 |    "metadata": {},
1128 |    "outputs": [],
1129 |    "source": [
1130 |     "prediction=my_model.predict(testX)"
1131 |    ]
1132 |   },
1133 |   {
1134 |    "cell_type": "code",
1135 |    "execution_count": 33,
1136 |    "id": "8699c0d3",
1137 |    "metadata": {},
1138 |    "outputs": [
1139 |     {
1140 |      "name": "stdout",
1141 |      "output_type": "stream",
1142 |      "text": [
1143 |       "prediction\n",
1144 |       " [[0.36429983]\n",
1145 |       " [0.36749688]\n",
1146 |       " [0.37060487]\n",
1147 |       " ...\n",
1148 |       " [0.1306538 ]\n",
1149 |       " [0.13263184]\n",
1150 |       " [0.13514471]]\n",
1151 |       "\n",
1152 |       "Prediction Shape- (1011, 1)\n"
1153 |      ]
1154 |     }
1155 |    ],
1156 |    "source": [
1157 |     "print(\"prediction\\n\", prediction)\n",
1158 |     "print(\"\\nPrediction Shape-\",prediction.shape)"
1159 |    ]
1160 |   },
1161 |   {
1162 |    "cell_type": "code",
1163 |    "execution_count": 34,
1164 |    "id": "2be6090a",
1165 |    "metadata": {},
1166 |    "outputs": [
1167 |     {
1168 |      "data": {
1169 |       "text/plain": [
1170 |        "(1011, 1)"
1171 |       ]
1172 |      },
1173 |      "execution_count": 34,
1174 |      "metadata": {},
1175 |      "output_type": "execute_result"
1176 |     }
1177 |    ],
1178 |    "source": [
1179 |     "prediction.shape"
1180 |    ]
1181 |   },
1182 |   {
1183 |    "cell_type": "code",
1184 |    "execution_count": 35,
1185 |    "id": "c8c654a6",
1186 |    "metadata": {},
1187 |    "outputs": [
1188 |     {
1189 |      "ename": "ValueError",
1190 |      "evalue": "non-broadcastable output operand with shape (1011,1) doesn't match the broadcast shape (1011,5)",
1191 |      "output_type": "error",
1192 |      "traceback": [
1193 |       "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
1194 |       "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
1195 |       "\u001b[1;32mC:\\Users\\SUJAN~1.ISL\\AppData\\Local\\Temp/ipykernel_11732/1176355301.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mscaler\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0minverse_transform\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mprediction\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
1196 |       "\u001b[1;32m~\\.conda\\envs\\env1\\lib\\site-packages\\sklearn\\preprocessing\\_data.py\u001b[0m in \u001b[0;36minverse_transform\u001b[1;34m(self, X)\u001b[0m\n\u001b[0;32m    527\u001b[0m         )\n\u001b[0;32m    528\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 529\u001b[1;33m         \u001b[0mX\u001b[0m \u001b[1;33m-=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmin_\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    530\u001b[0m         \u001b[0mX\u001b[0m \u001b[1;33m/=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mscale_\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    531\u001b[0m         \u001b[1;32mreturn\u001b[0m \u001b[0mX\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
1197 |       "\u001b[1;31mValueError\u001b[0m: non-broadcastable output operand with shape (1011,1) doesn't match the broadcast shape (1011,5)"
1198 |      ]
1199 |     }
1200 |    ],
1201 |    "source": [
1202 |     "scaler.inverse_transform(prediction)"
1203 |    ]
1204 |   },
1205 |   {
1206 |    "cell_type": "code",
1207 |    "execution_count": 36,
1208 |    "id": "44862c61",
1209 |    "metadata": {},
1210 |    "outputs": [],
1211 |    "source": [
1212 |     "prediction_copies_array = np.repeat(prediction,5, axis=-1)"
1213 |    ]
1214 |   },
1215 |   {
1216 |    "cell_type": "code",
1217 |    "execution_count": 37,
1218 |    "id": "1dbd500f",
1219 |    "metadata": {},
1220 |    "outputs": [
1221 |     {
1222 |      "data": {
1223 |       "text/plain": [
1224 |        "(1011, 5)"
1225 |       ]
1226 |      },
1227 |      "execution_count": 37,
1228 |      "metadata": {},
1229 |      "output_type": "execute_result"
1230 |     }
1231 |    ],
1232 |    "source": [
1233 |     "prediction_copies_array.shape"
1234 |    ]
1235 |   },
1236 |   {
1237 |    "cell_type": "code",
1238 |    "execution_count": 38,
1239 |    "id": "3b00bd6e",
1240 |    "metadata": {},
1241 |    "outputs": [
1242 |     {
1243 |      "data": {
1244 |       "text/plain": [
1245 |        "array([[0.36429983, 0.36429983, 0.36429983, 0.36429983, 0.36429983],\n",
1246 |        "       [0.36749688, 0.36749688, 0.36749688, 0.36749688, 0.36749688],\n",
1247 |        "       [0.37060487, 0.37060487, 0.37060487, 0.37060487, 0.37060487],\n",
1248 |        "       ...,\n",
1249 |        "       [0.1306538 , 0.1306538 , 0.1306538 , 0.1306538 , 0.1306538 ],\n",
1250 |        "       [0.13263184, 0.13263184, 0.13263184, 0.13263184, 0.13263184],\n",
1251 |        "       [0.13514471, 0.13514471, 0.13514471, 0.13514471, 0.13514471]],\n",
1252 |        "      dtype=float32)"
1253 |       ]
1254 |      },
1255 |      "execution_count": 38,
1256 |      "metadata": {},
1257 |      "output_type": "execute_result"
1258 |     }
1259 |    ],
1260 |    "source": [
1261 |     "prediction_copies_array"
1262 |    ]
1263 |   },
1264 |   {
1265 |    "cell_type": "code",
1266 |    "execution_count": 39,
1267 |    "id": "84f2780a",
1268 |    "metadata": {},
1269 |    "outputs": [],
1270 |    "source": [
1271 |     "pred=scaler.inverse_transform(np.reshape(prediction_copies_array,(len(prediction),5)))[:,0]"
1272 |    ]
1273 |   },
1274 |   {
1275 |    "cell_type": "code",
1276 |    "execution_count": 40,
1277 |    "id": "2c86afce",
1278 |    "metadata": {},
1279 |    "outputs": [
1280 |     {
1281 |      "data": {
1282 |       "text/plain": [
1283 |        "array([181.9501  , 183.09119 , 184.20052 , ...,  98.556435,  99.26244 ,\n",
1284 |        "       100.15935 ], dtype=float32)"
1285 |       ]
1286 |      },
1287 |      "execution_count": 40,
1288 |      "metadata": {},
1289 |      "output_type": "execute_result"
1290 |     }
1291 |    ],
1292 |    "source": [
1293 |     "pred"
1294 |    ]
1295 |   },
1296 |   {
1297 |    "cell_type": "code",
1298 |    "execution_count": 41,
1299 |    "id": "4ec05dff",
1300 |    "metadata": {},
1301 |    "outputs": [],
1302 |    "source": [
1303 |     "original_copies_array = np.repeat(testY,5, axis=-1)\n",
1304 |     "\n",
1305 |     "original_copies_array.shape\n",
1306 |     "\n",
1307 |     "original=scaler.inverse_transform(np.reshape(original_copies_array,(len(testY),5)))[:,0]"
1308 |    ]
1309 |   },
1310 |   {
1311 |    "cell_type": "code",
1312 |    "execution_count": 42,
1313 |    "id": "442e0222",
1314 |    "metadata": {},
1315 |    "outputs": [
1316 |     {
1317 |      "data": {
1318 |       "text/plain": [
1319 |        "array([181.9501  , 183.09119 , 184.20052 , ...,  98.556435,  99.26244 ,\n",
1320 |        "       100.15935 ], dtype=float32)"
1321 |       ]
1322 |      },
1323 |      "execution_count": 42,
1324 |      "metadata": {},
1325 |      "output_type": "execute_result"
1326 |     }
1327 |    ],
1328 |    "source": [
1329 |     "pred"
1330 |    ]
1331 |   },
1332 |   {
1333 |    "cell_type": "code",
1334 |    "execution_count": 43,
1335 |    "id": "cecfd7bf",
1336 |    "metadata": {},
1337 |    "outputs": [
1338 |     {
1339 |      "name": "stdout",
1340 |      "output_type": "stream",
1341 |      "text": [
1342 |       "Pred Values--  [181.9501   183.09119  184.20052  ...  98.556435  99.26244  100.15935 ]\n",
1343 |       "\n",
1344 |       "Original Values--  [191.692307 193.461533 192.307693 ... 104.550003 105.290001 106.      ]\n"
1345 |      ]
1346 |     }
1347 |    ],
1348 |    "source": [
1349 |     "print(\"Pred Values-- \" ,pred)\n",
1350 |     "print(\"\\nOriginal Values-- \",original)"
1351 |    ]
1352 |   },
1353 |   {
1354 |    "cell_type": "code",
1355 |    "execution_count": null,
1356 |    "id": "b1986d23",
1357 |    "metadata": {},
1358 |    "outputs": [],
1359 |    "source": []
1360 |   },
1361 |   {
1362 |    "cell_type": "code",
1363 |    "execution_count": 44,
1364 |    "id": "07e37414",
1365 |    "metadata": {},
1366 |    "outputs": [],
1367 |    "source": [
1368 |     "import matplotlib.pyplot as plt"
1369 |    ]
1370 |   },
1371 |   {
1372 |    "cell_type": "code",
1373 |    "execution_count": 45,
1374 |    "id": "bfa9b94b",
1375 |    "metadata": {},
1376 |    "outputs": [
1377 |     {
1378 |      "data": {
1379 |       "image/png": "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\n",
1380 |       "text/plain": [
1381 |        "<Figure size 432x288 with 1 Axes>"
1382 |       ]
1383 |      },
1384 |      "metadata": {
1385 |       "needs_background": "light"
1386 |      },
1387 |      "output_type": "display_data"
1388 |     }
1389 |    ],
1390 |    "source": [
1391 |     "plt.plot(original, color = 'red', label = 'Real  Stock Price')\n",
1392 |     "plt.plot(pred, color = 'blue', label = 'Predicted  Stock Price')\n",
1393 |     "plt.title(' Stock Price Prediction')\n",
1394 |     "plt.xlabel('Time')\n",
1395 |     "plt.ylabel(' Stock Price')\n",
1396 |     "plt.legend()\n",
1397 |     "plt.show()"
1398 |    ]
1399 |   },
1400 |   {
1401 |    "cell_type": "code",
1402 |    "execution_count": null,
1403 |    "id": "441ddb80",
1404 |    "metadata": {},
1405 |    "outputs": [],
1406 |    "source": []
1407 |   },
1408 |   {
1409 |    "cell_type": "code",
1410 |    "execution_count": 99,
1411 |    "id": "3a095e22",
1412 |    "metadata": {},
1413 |    "outputs": [],
1414 |    "source": [
1415 |     "df_30_days_past=df.iloc[-30:,:]"
1416 |    ]
1417 |   },
1418 |   {
1419 |    "cell_type": "code",
1420 |    "execution_count": 100,
1421 |    "id": "451dafea",
1422 |    "metadata": {},
1423 |    "outputs": [
1424 |     {
1425 |      "data": {
1426 |       "text/html": [
1427 |        "<div>\n",
1428 |        "<style scoped>\n",
1429 |        "    .dataframe tbody tr th:only-of-type {\n",
1430 |        "        vertical-align: middle;\n",
1431 |        "    }\n",
1432 |        "\n",
1433 |        "    .dataframe tbody tr th {\n",
1434 |        "        vertical-align: top;\n",
1435 |        "    }\n",
1436 |        "\n",
1437 |        "    .dataframe thead th {\n",
1438 |        "        text-align: right;\n",
1439 |        "    }\n",
1440 |        "</style>\n",
1441 |        "<table border=\"1\" class=\"dataframe\">\n",
1442 |        "  <thead>\n",
1443 |        "    <tr style=\"text-align: right;\">\n",
1444 |        "      <th></th>\n",
1445 |        "      <th>Open</th>\n",
1446 |        "      <th>High</th>\n",
1447 |        "      <th>Low</th>\n",
1448 |        "      <th>Close</th>\n",
1449 |        "      <th>Adj Close</th>\n",
1450 |        "    </tr>\n",
1451 |        "    <tr>\n",
1452 |        "      <th>Date</th>\n",
1453 |        "      <th></th>\n",
1454 |        "      <th></th>\n",
1455 |        "      <th></th>\n",
1456 |        "      <th></th>\n",
1457 |        "      <th></th>\n",
1458 |        "    </tr>\n",
1459 |        "  </thead>\n",
1460 |        "  <tbody>\n",
1461 |        "    <tr>\n",
1462 |        "      <th>2021-08-18</th>\n",
1463 |        "      <td>101.080002</td>\n",
1464 |        "      <td>103.470001</td>\n",
1465 |        "      <td>100.760002</td>\n",
1466 |        "      <td>101.410004</td>\n",
1467 |        "      <td>101.242561</td>\n",
1468 |        "    </tr>\n",
1469 |        "    <tr>\n",
1470 |        "      <th>2021-08-19</th>\n",
1471 |        "      <td>100.000000</td>\n",
1472 |        "      <td>100.820000</td>\n",
1473 |        "      <td>98.599998</td>\n",
1474 |        "      <td>99.419998</td>\n",
1475 |        "      <td>99.255844</td>\n",
1476 |        "    </tr>\n",
1477 |        "    <tr>\n",
1478 |        "      <th>2021-08-20</th>\n",
1479 |        "      <td>99.589996</td>\n",
1480 |        "      <td>100.669998</td>\n",
1481 |        "      <td>99.099998</td>\n",
1482 |        "      <td>100.050003</td>\n",
1483 |        "      <td>99.884804</td>\n",
1484 |        "    </tr>\n",
1485 |        "    <tr>\n",
1486 |        "      <th>2021-08-23</th>\n",
1487 |        "      <td>100.599998</td>\n",
1488 |        "      <td>101.480003</td>\n",
1489 |        "      <td>100.269997</td>\n",
1490 |        "      <td>100.970001</td>\n",
1491 |        "      <td>100.803284</td>\n",
1492 |        "    </tr>\n",
1493 |        "    <tr>\n",
1494 |        "      <th>2021-08-24</th>\n",
1495 |        "      <td>101.290001</td>\n",
1496 |        "      <td>103.510002</td>\n",
1497 |        "      <td>101.059998</td>\n",
1498 |        "      <td>103.269997</td>\n",
1499 |        "      <td>103.099487</td>\n",
1500 |        "    </tr>\n",
1501 |        "    <tr>\n",
1502 |        "      <th>2021-08-25</th>\n",
1503 |        "      <td>103.360001</td>\n",
1504 |        "      <td>105.129997</td>\n",
1505 |        "      <td>102.550003</td>\n",
1506 |        "      <td>104.699997</td>\n",
1507 |        "      <td>104.527122</td>\n",
1508 |        "    </tr>\n",
1509 |        "    <tr>\n",
1510 |        "      <th>2021-08-26</th>\n",
1511 |        "      <td>104.459999</td>\n",
1512 |        "      <td>104.620003</td>\n",
1513 |        "      <td>102.839996</td>\n",
1514 |        "      <td>103.379997</td>\n",
1515 |        "      <td>103.209305</td>\n",
1516 |        "    </tr>\n",
1517 |        "    <tr>\n",
1518 |        "      <th>2021-08-27</th>\n",
1519 |        "      <td>103.900002</td>\n",
1520 |        "      <td>106.150002</td>\n",
1521 |        "      <td>103.900002</td>\n",
1522 |        "      <td>106.089996</td>\n",
1523 |        "      <td>105.914825</td>\n",
1524 |        "    </tr>\n",
1525 |        "    <tr>\n",
1526 |        "      <th>2021-08-30</th>\n",
1527 |        "      <td>106.330002</td>\n",
1528 |        "      <td>106.459999</td>\n",
1529 |        "      <td>104.800003</td>\n",
1530 |        "      <td>105.190002</td>\n",
1531 |        "      <td>105.016312</td>\n",
1532 |        "    </tr>\n",
1533 |        "    <tr>\n",
1534 |        "      <th>2021-08-31</th>\n",
1535 |        "      <td>104.940002</td>\n",
1536 |        "      <td>106.360001</td>\n",
1537 |        "      <td>104.459999</td>\n",
1538 |        "      <td>105.410004</td>\n",
1539 |        "      <td>105.235954</td>\n",
1540 |        "    </tr>\n",
1541 |        "    <tr>\n",
1542 |        "      <th>2021-09-01</th>\n",
1543 |        "      <td>105.360001</td>\n",
1544 |        "      <td>105.470001</td>\n",
1545 |        "      <td>103.260002</td>\n",
1546 |        "      <td>103.660004</td>\n",
1547 |        "      <td>103.488846</td>\n",
1548 |        "    </tr>\n",
1549 |        "    <tr>\n",
1550 |        "      <th>2021-09-02</th>\n",
1551 |        "      <td>104.000000</td>\n",
1552 |        "      <td>106.339996</td>\n",
1553 |        "      <td>103.980003</td>\n",
1554 |        "      <td>106.260002</td>\n",
1555 |        "      <td>106.084557</td>\n",
1556 |        "    </tr>\n",
1557 |        "    <tr>\n",
1558 |        "      <th>2021-09-03</th>\n",
1559 |        "      <td>106.000000</td>\n",
1560 |        "      <td>107.360001</td>\n",
1561 |        "      <td>104.080002</td>\n",
1562 |        "      <td>104.750000</td>\n",
1563 |        "      <td>104.577042</td>\n",
1564 |        "    </tr>\n",
1565 |        "    <tr>\n",
1566 |        "      <th>2021-09-07</th>\n",
1567 |        "      <td>104.500000</td>\n",
1568 |        "      <td>104.940002</td>\n",
1569 |        "      <td>102.309998</td>\n",
1570 |        "      <td>103.290001</td>\n",
1571 |        "      <td>103.119453</td>\n",
1572 |        "    </tr>\n",
1573 |        "    <tr>\n",
1574 |        "      <th>2021-09-08</th>\n",
1575 |        "      <td>102.949997</td>\n",
1576 |        "      <td>104.730003</td>\n",
1577 |        "      <td>100.419998</td>\n",
1578 |        "      <td>102.580002</td>\n",
1579 |        "      <td>102.410629</td>\n",
1580 |        "    </tr>\n",
1581 |        "    <tr>\n",
1582 |        "      <th>2021-09-09</th>\n",
1583 |        "      <td>102.360001</td>\n",
1584 |        "      <td>104.919998</td>\n",
1585 |        "      <td>102.110001</td>\n",
1586 |        "      <td>103.290001</td>\n",
1587 |        "      <td>103.119453</td>\n",
1588 |        "    </tr>\n",
1589 |        "    <tr>\n",
1590 |        "      <th>2021-09-10</th>\n",
1591 |        "      <td>103.290001</td>\n",
1592 |        "      <td>103.949997</td>\n",
1593 |        "      <td>101.779999</td>\n",
1594 |        "      <td>102.000000</td>\n",
1595 |        "      <td>101.831581</td>\n",
1596 |        "    </tr>\n",
1597 |        "    <tr>\n",
1598 |        "      <th>2021-09-13</th>\n",
1599 |        "      <td>102.650002</td>\n",
1600 |        "      <td>104.860001</td>\n",
1601 |        "      <td>102.019997</td>\n",
1602 |        "      <td>104.459999</td>\n",
1603 |        "      <td>104.287521</td>\n",
1604 |        "    </tr>\n",
1605 |        "    <tr>\n",
1606 |        "      <th>2021-09-14</th>\n",
1607 |        "      <td>104.540001</td>\n",
1608 |        "      <td>104.550003</td>\n",
1609 |        "      <td>100.070000</td>\n",
1610 |        "      <td>100.379997</td>\n",
1611 |        "      <td>100.214256</td>\n",
1612 |        "    </tr>\n",
1613 |        "    <tr>\n",
1614 |        "      <th>2021-09-15</th>\n",
1615 |        "      <td>100.790001</td>\n",
1616 |        "      <td>102.470001</td>\n",
1617 |        "      <td>100.690002</td>\n",
1618 |        "      <td>102.160004</td>\n",
1619 |        "      <td>101.991325</td>\n",
1620 |        "    </tr>\n",
1621 |        "    <tr>\n",
1622 |        "      <th>2021-09-16</th>\n",
1623 |        "      <td>102.389999</td>\n",
1624 |        "      <td>102.699997</td>\n",
1625 |        "      <td>100.820000</td>\n",
1626 |        "      <td>101.339996</td>\n",
1627 |        "      <td>101.172668</td>\n",
1628 |        "    </tr>\n",
1629 |        "    <tr>\n",
1630 |        "      <th>2021-09-17</th>\n",
1631 |        "      <td>101.150002</td>\n",
1632 |        "      <td>101.860001</td>\n",
1633 |        "      <td>100.129997</td>\n",
1634 |        "      <td>100.470001</td>\n",
1635 |        "      <td>100.304115</td>\n",
1636 |        "    </tr>\n",
1637 |        "    <tr>\n",
1638 |        "      <th>2021-09-20</th>\n",
1639 |        "      <td>98.500000</td>\n",
1640 |        "      <td>99.870003</td>\n",
1641 |        "      <td>97.269997</td>\n",
1642 |        "      <td>99.809998</td>\n",
1643 |        "      <td>99.645195</td>\n",
1644 |        "    </tr>\n",
1645 |        "    <tr>\n",
1646 |        "      <th>2021-09-21</th>\n",
1647 |        "      <td>99.900002</td>\n",
1648 |        "      <td>99.989998</td>\n",
1649 |        "      <td>96.209999</td>\n",
1650 |        "      <td>96.820000</td>\n",
1651 |        "      <td>96.660133</td>\n",
1652 |        "    </tr>\n",
1653 |        "    <tr>\n",
1654 |        "      <th>2021-09-22</th>\n",
1655 |        "      <td>97.669998</td>\n",
1656 |        "      <td>99.029999</td>\n",
1657 |        "      <td>97.660004</td>\n",
1658 |        "      <td>98.540001</td>\n",
1659 |        "      <td>98.377296</td>\n",
1660 |        "    </tr>\n",
1661 |        "    <tr>\n",
1662 |        "      <th>2021-09-23</th>\n",
1663 |        "      <td>99.529999</td>\n",
1664 |        "      <td>104.080002</td>\n",
1665 |        "      <td>99.519997</td>\n",
1666 |        "      <td>102.959999</td>\n",
1667 |        "      <td>102.789993</td>\n",
1668 |        "    </tr>\n",
1669 |        "    <tr>\n",
1670 |        "      <th>2021-09-24</th>\n",
1671 |        "      <td>102.660004</td>\n",
1672 |        "      <td>104.199997</td>\n",
1673 |        "      <td>102.599998</td>\n",
1674 |        "      <td>103.800003</td>\n",
1675 |        "      <td>103.709198</td>\n",
1676 |        "    </tr>\n",
1677 |        "    <tr>\n",
1678 |        "      <th>2021-09-27</th>\n",
1679 |        "      <td>104.550003</td>\n",
1680 |        "      <td>106.330002</td>\n",
1681 |        "      <td>104.389999</td>\n",
1682 |        "      <td>105.349998</td>\n",
1683 |        "      <td>105.257835</td>\n",
1684 |        "    </tr>\n",
1685 |        "    <tr>\n",
1686 |        "      <th>2021-09-28</th>\n",
1687 |        "      <td>105.290001</td>\n",
1688 |        "      <td>106.750000</td>\n",
1689 |        "      <td>104.730003</td>\n",
1690 |        "      <td>105.730003</td>\n",
1691 |        "      <td>105.637512</td>\n",
1692 |        "    </tr>\n",
1693 |        "    <tr>\n",
1694 |        "      <th>2021-09-29</th>\n",
1695 |        "      <td>106.000000</td>\n",
1696 |        "      <td>107.000000</td>\n",
1697 |        "      <td>105.309998</td>\n",
1698 |        "      <td>106.279999</td>\n",
1699 |        "      <td>106.187027</td>\n",
1700 |        "    </tr>\n",
1701 |        "  </tbody>\n",
1702 |        "</table>\n",
1703 |        "</div>"
1704 |       ],
1705 |       "text/plain": [
1706 |        "                  Open        High         Low       Close   Adj Close\n",
1707 |        "Date                                                                  \n",
1708 |        "2021-08-18  101.080002  103.470001  100.760002  101.410004  101.242561\n",
1709 |        "2021-08-19  100.000000  100.820000   98.599998   99.419998   99.255844\n",
1710 |        "2021-08-20   99.589996  100.669998   99.099998  100.050003   99.884804\n",
1711 |        "2021-08-23  100.599998  101.480003  100.269997  100.970001  100.803284\n",
1712 |        "2021-08-24  101.290001  103.510002  101.059998  103.269997  103.099487\n",
1713 |        "2021-08-25  103.360001  105.129997  102.550003  104.699997  104.527122\n",
1714 |        "2021-08-26  104.459999  104.620003  102.839996  103.379997  103.209305\n",
1715 |        "2021-08-27  103.900002  106.150002  103.900002  106.089996  105.914825\n",
1716 |        "2021-08-30  106.330002  106.459999  104.800003  105.190002  105.016312\n",
1717 |        "2021-08-31  104.940002  106.360001  104.459999  105.410004  105.235954\n",
1718 |        "2021-09-01  105.360001  105.470001  103.260002  103.660004  103.488846\n",
1719 |        "2021-09-02  104.000000  106.339996  103.980003  106.260002  106.084557\n",
1720 |        "2021-09-03  106.000000  107.360001  104.080002  104.750000  104.577042\n",
1721 |        "2021-09-07  104.500000  104.940002  102.309998  103.290001  103.119453\n",
1722 |        "2021-09-08  102.949997  104.730003  100.419998  102.580002  102.410629\n",
1723 |        "2021-09-09  102.360001  104.919998  102.110001  103.290001  103.119453\n",
1724 |        "2021-09-10  103.290001  103.949997  101.779999  102.000000  101.831581\n",
1725 |        "2021-09-13  102.650002  104.860001  102.019997  104.459999  104.287521\n",
1726 |        "2021-09-14  104.540001  104.550003  100.070000  100.379997  100.214256\n",
1727 |        "2021-09-15  100.790001  102.470001  100.690002  102.160004  101.991325\n",
1728 |        "2021-09-16  102.389999  102.699997  100.820000  101.339996  101.172668\n",
1729 |        "2021-09-17  101.150002  101.860001  100.129997  100.470001  100.304115\n",
1730 |        "2021-09-20   98.500000   99.870003   97.269997   99.809998   99.645195\n",
1731 |        "2021-09-21   99.900002   99.989998   96.209999   96.820000   96.660133\n",
1732 |        "2021-09-22   97.669998   99.029999   97.660004   98.540001   98.377296\n",
1733 |        "2021-09-23   99.529999  104.080002   99.519997  102.959999  102.789993\n",
1734 |        "2021-09-24  102.660004  104.199997  102.599998  103.800003  103.709198\n",
1735 |        "2021-09-27  104.550003  106.330002  104.389999  105.349998  105.257835\n",
1736 |        "2021-09-28  105.290001  106.750000  104.730003  105.730003  105.637512\n",
1737 |        "2021-09-29  106.000000  107.000000  105.309998  106.279999  106.187027"
1738 |       ]
1739 |      },
1740 |      "execution_count": 100,
1741 |      "metadata": {},
1742 |      "output_type": "execute_result"
1743 |     }
1744 |    ],
1745 |    "source": [
1746 |     "df_30_days_past"
1747 |    ]
1748 |   },
1749 |   {
1750 |    "cell_type": "code",
1751 |    "execution_count": 103,
1752 |    "id": "92497be0",
1753 |    "metadata": {},
1754 |    "outputs": [
1755 |     {
1756 |      "data": {
1757 |       "text/plain": [
1758 |        "(30, 4)"
1759 |       ]
1760 |      },
1761 |      "execution_count": 103,
1762 |      "metadata": {},
1763 |      "output_type": "execute_result"
1764 |     }
1765 |    ],
1766 |    "source": [
1767 |     "df_30_days_future=pd.read_csv(\"test.csv\",parse_dates=[\"Date\"],index_col=[0])\n",
1768 |     "df_30_days_future.shape"
1769 |    ]
1770 |   },
1771 |   {
1772 |    "cell_type": "code",
1773 |    "execution_count": 112,
1774 |    "id": "7004371c",
1775 |    "metadata": {},
1776 |    "outputs": [
1777 |     {
1778 |      "data": {
1779 |       "text/html": [
1780 |        "<div>\n",
1781 |        "<style scoped>\n",
1782 |        "    .dataframe tbody tr th:only-of-type {\n",
1783 |        "        vertical-align: middle;\n",
1784 |        "    }\n",
1785 |        "\n",
1786 |        "    .dataframe tbody tr th {\n",
1787 |        "        vertical-align: top;\n",
1788 |        "    }\n",
1789 |        "\n",
1790 |        "    .dataframe thead th {\n",
1791 |        "        text-align: right;\n",
1792 |        "    }\n",
1793 |        "</style>\n",
1794 |        "<table border=\"1\" class=\"dataframe\">\n",
1795 |        "  <thead>\n",
1796 |        "    <tr style=\"text-align: right;\">\n",
1797 |        "      <th></th>\n",
1798 |        "      <th>Open</th>\n",
1799 |        "      <th>High</th>\n",
1800 |        "      <th>Low</th>\n",
1801 |        "      <th>Close</th>\n",
1802 |        "      <th>Adj Close</th>\n",
1803 |        "    </tr>\n",
1804 |        "    <tr>\n",
1805 |        "      <th>Date</th>\n",
1806 |        "      <th></th>\n",
1807 |        "      <th></th>\n",
1808 |        "      <th></th>\n",
1809 |        "      <th></th>\n",
1810 |        "      <th></th>\n",
1811 |        "    </tr>\n",
1812 |        "  </thead>\n",
1813 |        "  <tbody>\n",
1814 |        "    <tr>\n",
1815 |        "      <th>2021-09-30</th>\n",
1816 |        "      <td>0</td>\n",
1817 |        "      <td>107.089996</td>\n",
1818 |        "      <td>102.949997</td>\n",
1819 |        "      <td>103.029999</td>\n",
1820 |        "      <td>102.939865</td>\n",
1821 |        "    </tr>\n",
1822 |        "    <tr>\n",
1823 |        "      <th>2021-10-01</th>\n",
1824 |        "      <td>0</td>\n",
1825 |        "      <td>106.389999</td>\n",
1826 |        "      <td>103.669998</td>\n",
1827 |        "      <td>105.820000</td>\n",
1828 |        "      <td>105.727425</td>\n",
1829 |        "    </tr>\n",
1830 |        "    <tr>\n",
1831 |        "      <th>2021-10-04</th>\n",
1832 |        "      <td>0</td>\n",
1833 |        "      <td>107.080002</td>\n",
1834 |        "      <td>104.599998</td>\n",
1835 |        "      <td>104.900002</td>\n",
1836 |        "      <td>104.808235</td>\n",
1837 |        "    </tr>\n",
1838 |        "    <tr>\n",
1839 |        "      <th>2021-10-05</th>\n",
1840 |        "      <td>0</td>\n",
1841 |        "      <td>106.000000</td>\n",
1842 |        "      <td>103.750000</td>\n",
1843 |        "      <td>104.900002</td>\n",
1844 |        "      <td>104.808235</td>\n",
1845 |        "    </tr>\n",
1846 |        "    <tr>\n",
1847 |        "      <th>2021-10-06</th>\n",
1848 |        "      <td>0</td>\n",
1849 |        "      <td>104.419998</td>\n",
1850 |        "      <td>102.059998</td>\n",
1851 |        "      <td>104.330002</td>\n",
1852 |        "      <td>104.238731</td>\n",
1853 |        "    </tr>\n",
1854 |        "    <tr>\n",
1855 |        "      <th>2021-10-07</th>\n",
1856 |        "      <td>0</td>\n",
1857 |        "      <td>106.529999</td>\n",
1858 |        "      <td>104.330002</td>\n",
1859 |        "      <td>105.510002</td>\n",
1860 |        "      <td>105.417702</td>\n",
1861 |        "    </tr>\n",
1862 |        "    <tr>\n",
1863 |        "      <th>2021-10-08</th>\n",
1864 |        "      <td>0</td>\n",
1865 |        "      <td>106.220001</td>\n",
1866 |        "      <td>104.660004</td>\n",
1867 |        "      <td>104.720001</td>\n",
1868 |        "      <td>104.628387</td>\n",
1869 |        "    </tr>\n",
1870 |        "    <tr>\n",
1871 |        "      <th>2021-10-11</th>\n",
1872 |        "      <td>0</td>\n",
1873 |        "      <td>105.760002</td>\n",
1874 |        "      <td>103.970001</td>\n",
1875 |        "      <td>104.080002</td>\n",
1876 |        "      <td>103.988953</td>\n",
1877 |        "    </tr>\n",
1878 |        "    <tr>\n",
1879 |        "      <th>2021-10-12</th>\n",
1880 |        "      <td>0</td>\n",
1881 |        "      <td>104.040001</td>\n",
1882 |        "      <td>101.559998</td>\n",
1883 |        "      <td>102.720001</td>\n",
1884 |        "      <td>102.630142</td>\n",
1885 |        "    </tr>\n",
1886 |        "    <tr>\n",
1887 |        "      <th>2021-10-13</th>\n",
1888 |        "      <td>0</td>\n",
1889 |        "      <td>103.199997</td>\n",
1890 |        "      <td>101.180000</td>\n",
1891 |        "      <td>102.360001</td>\n",
1892 |        "      <td>102.270454</td>\n",
1893 |        "    </tr>\n",
1894 |        "    <tr>\n",
1895 |        "      <th>2021-10-14</th>\n",
1896 |        "      <td>0</td>\n",
1897 |        "      <td>103.650002</td>\n",
1898 |        "      <td>102.370003</td>\n",
1899 |        "      <td>102.739998</td>\n",
1900 |        "      <td>102.650116</td>\n",
1901 |        "    </tr>\n",
1902 |        "    <tr>\n",
1903 |        "      <th>2021-10-15</th>\n",
1904 |        "      <td>0</td>\n",
1905 |        "      <td>105.900002</td>\n",
1906 |        "      <td>103.190002</td>\n",
1907 |        "      <td>104.410004</td>\n",
1908 |        "      <td>104.318665</td>\n",
1909 |        "    </tr>\n",
1910 |        "    <tr>\n",
1911 |        "      <th>2021-10-18</th>\n",
1912 |        "      <td>0</td>\n",
1913 |        "      <td>104.570000</td>\n",
1914 |        "      <td>103.040001</td>\n",
1915 |        "      <td>104.120003</td>\n",
1916 |        "      <td>104.028915</td>\n",
1917 |        "    </tr>\n",
1918 |        "    <tr>\n",
1919 |        "      <th>2021-10-19</th>\n",
1920 |        "      <td>0</td>\n",
1921 |        "      <td>104.970001</td>\n",
1922 |        "      <td>103.580002</td>\n",
1923 |        "      <td>104.730003</td>\n",
1924 |        "      <td>104.638382</td>\n",
1925 |        "    </tr>\n",
1926 |        "    <tr>\n",
1927 |        "      <th>2021-10-20</th>\n",
1928 |        "      <td>0</td>\n",
1929 |        "      <td>106.019997</td>\n",
1930 |        "      <td>103.870003</td>\n",
1931 |        "      <td>106.000000</td>\n",
1932 |        "      <td>105.907272</td>\n",
1933 |        "    </tr>\n",
1934 |        "    <tr>\n",
1935 |        "      <th>2021-10-21</th>\n",
1936 |        "      <td>0</td>\n",
1937 |        "      <td>106.389999</td>\n",
1938 |        "      <td>103.010002</td>\n",
1939 |        "      <td>103.150002</td>\n",
1940 |        "      <td>103.059761</td>\n",
1941 |        "    </tr>\n",
1942 |        "    <tr>\n",
1943 |        "      <th>2021-10-22</th>\n",
1944 |        "      <td>0</td>\n",
1945 |        "      <td>104.510002</td>\n",
1946 |        "      <td>102.550003</td>\n",
1947 |        "      <td>104.050003</td>\n",
1948 |        "      <td>103.958977</td>\n",
1949 |        "    </tr>\n",
1950 |        "    <tr>\n",
1951 |        "      <th>2021-10-25</th>\n",
1952 |        "      <td>0</td>\n",
1953 |        "      <td>105.989998</td>\n",
1954 |        "      <td>103.330002</td>\n",
1955 |        "      <td>105.300003</td>\n",
1956 |        "      <td>105.207886</td>\n",
1957 |        "    </tr>\n",
1958 |        "    <tr>\n",
1959 |        "      <th>2021-10-26</th>\n",
1960 |        "      <td>0</td>\n",
1961 |        "      <td>110.970001</td>\n",
1962 |        "      <td>105.220001</td>\n",
1963 |        "      <td>107.440002</td>\n",
1964 |        "      <td>107.346008</td>\n",
1965 |        "    </tr>\n",
1966 |        "    <tr>\n",
1967 |        "      <th>2021-10-27</th>\n",
1968 |        "      <td>0</td>\n",
1969 |        "      <td>108.279999</td>\n",
1970 |        "      <td>103.690002</td>\n",
1971 |        "      <td>103.849998</td>\n",
1972 |        "      <td>103.759148</td>\n",
1973 |        "    </tr>\n",
1974 |        "    <tr>\n",
1975 |        "      <th>2021-10-28</th>\n",
1976 |        "      <td>0</td>\n",
1977 |        "      <td>105.379997</td>\n",
1978 |        "      <td>103.099998</td>\n",
1979 |        "      <td>105.260002</td>\n",
1980 |        "      <td>105.167915</td>\n",
1981 |        "    </tr>\n",
1982 |        "    <tr>\n",
1983 |        "      <th>2021-10-29</th>\n",
1984 |        "      <td>0</td>\n",
1985 |        "      <td>105.239998</td>\n",
1986 |        "      <td>104.120003</td>\n",
1987 |        "      <td>104.870003</td>\n",
1988 |        "      <td>104.778259</td>\n",
1989 |        "    </tr>\n",
1990 |        "    <tr>\n",
1991 |        "      <th>2021-11-01</th>\n",
1992 |        "      <td>0</td>\n",
1993 |        "      <td>106.769997</td>\n",
1994 |        "      <td>105.279999</td>\n",
1995 |        "      <td>106.230003</td>\n",
1996 |        "      <td>106.137070</td>\n",
1997 |        "    </tr>\n",
1998 |        "    <tr>\n",
1999 |        "      <th>2021-11-02</th>\n",
2000 |        "      <td>0</td>\n",
2001 |        "      <td>107.139999</td>\n",
2002 |        "      <td>105.300003</td>\n",
2003 |        "      <td>106.690002</td>\n",
2004 |        "      <td>106.596664</td>\n",
2005 |        "    </tr>\n",
2006 |        "    <tr>\n",
2007 |        "      <th>2021-11-03</th>\n",
2008 |        "      <td>0</td>\n",
2009 |        "      <td>106.339996</td>\n",
2010 |        "      <td>104.820000</td>\n",
2011 |        "      <td>105.970001</td>\n",
2012 |        "      <td>105.877296</td>\n",
2013 |        "    </tr>\n",
2014 |        "    <tr>\n",
2015 |        "      <th>2021-11-04</th>\n",
2016 |        "      <td>0</td>\n",
2017 |        "      <td>106.400002</td>\n",
2018 |        "      <td>104.290001</td>\n",
2019 |        "      <td>105.209999</td>\n",
2020 |        "      <td>105.117958</td>\n",
2021 |        "    </tr>\n",
2022 |        "    <tr>\n",
2023 |        "      <th>2021-11-05</th>\n",
2024 |        "      <td>0</td>\n",
2025 |        "      <td>109.650002</td>\n",
2026 |        "      <td>106.849998</td>\n",
2027 |        "      <td>108.739998</td>\n",
2028 |        "      <td>108.644867</td>\n",
2029 |        "    </tr>\n",
2030 |        "    <tr>\n",
2031 |        "      <th>2021-11-08</th>\n",
2032 |        "      <td>0</td>\n",
2033 |        "      <td>110.309998</td>\n",
2034 |        "      <td>108.320000</td>\n",
2035 |        "      <td>108.419998</td>\n",
2036 |        "      <td>108.325150</td>\n",
2037 |        "    </tr>\n",
2038 |        "    <tr>\n",
2039 |        "      <th>2021-11-09</th>\n",
2040 |        "      <td>0</td>\n",
2041 |        "      <td>116.169998</td>\n",
2042 |        "      <td>110.480003</td>\n",
2043 |        "      <td>111.290001</td>\n",
2044 |        "      <td>111.192642</td>\n",
2045 |        "    </tr>\n",
2046 |        "    <tr>\n",
2047 |        "      <th>2021-11-10</th>\n",
2048 |        "      <td>0</td>\n",
2049 |        "      <td>112.680000</td>\n",
2050 |        "      <td>108.110001</td>\n",
2051 |        "      <td>108.959999</td>\n",
2052 |        "      <td>108.864677</td>\n",
2053 |        "    </tr>\n",
2054 |        "  </tbody>\n",
2055 |        "</table>\n",
2056 |        "</div>"
2057 |       ],
2058 |       "text/plain": [
2059 |        "            Open        High         Low       Close   Adj Close\n",
2060 |        "Date                                                            \n",
2061 |        "2021-09-30     0  107.089996  102.949997  103.029999  102.939865\n",
2062 |        "2021-10-01     0  106.389999  103.669998  105.820000  105.727425\n",
2063 |        "2021-10-04     0  107.080002  104.599998  104.900002  104.808235\n",
2064 |        "2021-10-05     0  106.000000  103.750000  104.900002  104.808235\n",
2065 |        "2021-10-06     0  104.419998  102.059998  104.330002  104.238731\n",
2066 |        "2021-10-07     0  106.529999  104.330002  105.510002  105.417702\n",
2067 |        "2021-10-08     0  106.220001  104.660004  104.720001  104.628387\n",
2068 |        "2021-10-11     0  105.760002  103.970001  104.080002  103.988953\n",
2069 |        "2021-10-12     0  104.040001  101.559998  102.720001  102.630142\n",
2070 |        "2021-10-13     0  103.199997  101.180000  102.360001  102.270454\n",
2071 |        "2021-10-14     0  103.650002  102.370003  102.739998  102.650116\n",
2072 |        "2021-10-15     0  105.900002  103.190002  104.410004  104.318665\n",
2073 |        "2021-10-18     0  104.570000  103.040001  104.120003  104.028915\n",
2074 |        "2021-10-19     0  104.970001  103.580002  104.730003  104.638382\n",
2075 |        "2021-10-20     0  106.019997  103.870003  106.000000  105.907272\n",
2076 |        "2021-10-21     0  106.389999  103.010002  103.150002  103.059761\n",
2077 |        "2021-10-22     0  104.510002  102.550003  104.050003  103.958977\n",
2078 |        "2021-10-25     0  105.989998  103.330002  105.300003  105.207886\n",
2079 |        "2021-10-26     0  110.970001  105.220001  107.440002  107.346008\n",
2080 |        "2021-10-27     0  108.279999  103.690002  103.849998  103.759148\n",
2081 |        "2021-10-28     0  105.379997  103.099998  105.260002  105.167915\n",
2082 |        "2021-10-29     0  105.239998  104.120003  104.870003  104.778259\n",
2083 |        "2021-11-01     0  106.769997  105.279999  106.230003  106.137070\n",
2084 |        "2021-11-02     0  107.139999  105.300003  106.690002  106.596664\n",
2085 |        "2021-11-03     0  106.339996  104.820000  105.970001  105.877296\n",
2086 |        "2021-11-04     0  106.400002  104.290001  105.209999  105.117958\n",
2087 |        "2021-11-05     0  109.650002  106.849998  108.739998  108.644867\n",
2088 |        "2021-11-08     0  110.309998  108.320000  108.419998  108.325150\n",
2089 |        "2021-11-09     0  116.169998  110.480003  111.290001  111.192642\n",
2090 |        "2021-11-10     0  112.680000  108.110001  108.959999  108.864677"
2091 |       ]
2092 |      },
2093 |      "execution_count": 112,
2094 |      "metadata": {},
2095 |      "output_type": "execute_result"
2096 |     }
2097 |    ],
2098 |    "source": [
2099 |     "df_30_days_future"
2100 |    ]
2101 |   },
2102 |   {
2103 |    "cell_type": "code",
2104 |    "execution_count": 104,
2105 |    "id": "20277ef8",
2106 |    "metadata": {},
2107 |    "outputs": [],
2108 |    "source": [
2109 |     "df_30_days_future[\"Open\"]=0\n",
2110 |     "df_30_days_future=df_30_days_future[[\"Open\",\"High\",\"Low\",\"Close\",\"Adj Close\"]]\n",
2111 |     "old_scaled_array=scaler.transform(df_30_days_past)\n",
2112 |     "new_scaled_array=scaler.transform(df_30_days_future)\n",
2113 |     "new_scaled_df=pd.DataFrame(new_scaled_array)\n",
2114 |     "new_scaled_df.iloc[:,0]=np.nan\n",
2115 |     "full_df=pd.concat([pd.DataFrame(old_scaled_array),new_scaled_df]).reset_index().drop([\"index\"],axis=1)"
2116 |    ]
2117 |   },
2118 |   {
2119 |    "cell_type": "code",
2120 |    "execution_count": 105,
2121 |    "id": "0dcb1ee5",
2122 |    "metadata": {},
2123 |    "outputs": [
2124 |     {
2125 |      "data": {
2126 |       "text/plain": [
2127 |        "(60, 5)"
2128 |       ]
2129 |      },
2130 |      "execution_count": 105,
2131 |      "metadata": {},
2132 |      "output_type": "execute_result"
2133 |     }
2134 |    ],
2135 |    "source": [
2136 |     "full_df.shape"
2137 |    ]
2138 |   },
2139 |   {
2140 |    "cell_type": "code",
2141 |    "execution_count": 106,
2142 |    "id": "88cfa224",
2143 |    "metadata": {},
2144 |    "outputs": [
2145 |     {
2146 |      "data": {
2147 |       "text/html": [
2148 |        "<div>\n",
2149 |        "<style scoped>\n",
2150 |        "    .dataframe tbody tr th:only-of-type {\n",
2151 |        "        vertical-align: middle;\n",
2152 |        "    }\n",
2153 |        "\n",
2154 |        "    .dataframe tbody tr th {\n",
2155 |        "        vertical-align: top;\n",
2156 |        "    }\n",
2157 |        "\n",
2158 |        "    .dataframe thead th {\n",
2159 |        "        text-align: right;\n",
2160 |        "    }\n",
2161 |        "</style>\n",
2162 |        "<table border=\"1\" class=\"dataframe\">\n",
2163 |        "  <thead>\n",
2164 |        "    <tr style=\"text-align: right;\">\n",
2165 |        "      <th></th>\n",
2166 |        "      <th>0</th>\n",
2167 |        "      <th>1</th>\n",
2168 |        "      <th>2</th>\n",
2169 |        "      <th>3</th>\n",
2170 |        "      <th>4</th>\n",
2171 |        "    </tr>\n",
2172 |        "  </thead>\n",
2173 |        "  <tbody>\n",
2174 |        "    <tr>\n",
2175 |        "      <th>55</th>\n",
2176 |        "      <td>NaN</td>\n",
2177 |        "      <td>0.143640</td>\n",
2178 |        "      <td>0.164162</td>\n",
2179 |        "      <td>0.150135</td>\n",
2180 |        "      <td>0.349458</td>\n",
2181 |        "    </tr>\n",
2182 |        "    <tr>\n",
2183 |        "      <th>56</th>\n",
2184 |        "      <td>NaN</td>\n",
2185 |        "      <td>0.152749</td>\n",
2186 |        "      <td>0.171268</td>\n",
2187 |        "      <td>0.159953</td>\n",
2188 |        "      <td>0.367565</td>\n",
2189 |        "    </tr>\n",
2190 |        "    <tr>\n",
2191 |        "      <th>57</th>\n",
2192 |        "      <td>NaN</td>\n",
2193 |        "      <td>0.154599</td>\n",
2194 |        "      <td>0.175349</td>\n",
2195 |        "      <td>0.159063</td>\n",
2196 |        "      <td>0.365924</td>\n",
2197 |        "    </tr>\n",
2198 |        "    <tr>\n",
2199 |        "      <th>58</th>\n",
2200 |        "      <td>NaN</td>\n",
2201 |        "      <td>0.171024</td>\n",
2202 |        "      <td>0.181345</td>\n",
2203 |        "      <td>0.167045</td>\n",
2204 |        "      <td>0.380645</td>\n",
2205 |        "    </tr>\n",
2206 |        "    <tr>\n",
2207 |        "      <th>59</th>\n",
2208 |        "      <td>NaN</td>\n",
2209 |        "      <td>0.161242</td>\n",
2210 |        "      <td>0.174766</td>\n",
2211 |        "      <td>0.160565</td>\n",
2212 |        "      <td>0.368694</td>\n",
2213 |        "    </tr>\n",
2214 |        "  </tbody>\n",
2215 |        "</table>\n",
2216 |        "</div>"
2217 |       ],
2218 |       "text/plain": [
2219 |        "     0         1         2         3         4\n",
2220 |        "55 NaN  0.143640  0.164162  0.150135  0.349458\n",
2221 |        "56 NaN  0.152749  0.171268  0.159953  0.367565\n",
2222 |        "57 NaN  0.154599  0.175349  0.159063  0.365924\n",
2223 |        "58 NaN  0.171024  0.181345  0.167045  0.380645\n",
2224 |        "59 NaN  0.161242  0.174766  0.160565  0.368694"
2225 |       ]
2226 |      },
2227 |      "execution_count": 106,
2228 |      "metadata": {},
2229 |      "output_type": "execute_result"
2230 |     }
2231 |    ],
2232 |    "source": [
2233 |     "full_df.tail()"
2234 |    ]
2235 |   },
2236 |   {
2237 |    "cell_type": "code",
2238 |    "execution_count": 107,
2239 |    "id": "e8cc462a",
2240 |    "metadata": {},
2241 |    "outputs": [
2242 |     {
2243 |      "data": {
2244 |       "text/plain": [
2245 |        "(60, 5)"
2246 |       ]
2247 |      },
2248 |      "execution_count": 107,
2249 |      "metadata": {},
2250 |      "output_type": "execute_result"
2251 |     }
2252 |    ],
2253 |    "source": [
2254 |     "full_df.shape"
2255 |    ]
2256 |   },
2257 |   {
2258 |    "cell_type": "code",
2259 |    "execution_count": 114,
2260 |    "id": "48bf070f",
2261 |    "metadata": {},
2262 |    "outputs": [],
2263 |    "source": [
2264 |     "full_df_scaled_array=full_df.values"
2265 |    ]
2266 |   },
2267 |   {
2268 |    "cell_type": "code",
2269 |    "execution_count": 115,
2270 |    "id": "91fdcf82",
2271 |    "metadata": {},
2272 |    "outputs": [
2273 |     {
2274 |      "data": {
2275 |       "text/plain": [
2276 |        "(60, 5)"
2277 |       ]
2278 |      },
2279 |      "execution_count": 115,
2280 |      "metadata": {},
2281 |      "output_type": "execute_result"
2282 |     }
2283 |    ],
2284 |    "source": [
2285 |     "full_df_scaled_array.shape"
2286 |    ]
2287 |   },
2288 |   {
2289 |    "cell_type": "code",
2290 |    "execution_count": 116,
2291 |    "id": "547622aa",
2292 |    "metadata": {},
2293 |    "outputs": [],
2294 |    "source": [
2295 |     "all_data=[]\n",
2296 |     "time_step=30\n",
2297 |     "for i in range(time_step,len(full_df_scaled_array)):\n",
2298 |     "    data_x=[]\n",
2299 |     "    data_x.append(full_df_scaled_array[i-time_step:i,0:full_df_scaled_array.shape[1]])\n",
2300 |     "    data_x=np.array(data_x)\n",
2301 |     "    prediction=my_model.predict(data_x)\n",
2302 |     "    all_data.append(prediction)\n",
2303 |     "    full_df.iloc[i,0]=prediction"
2304 |    ]
2305 |   },
2306 |   {
2307 |    "cell_type": "code",
2308 |    "execution_count": 117,
2309 |    "id": "05929d50",
2310 |    "metadata": {},
2311 |    "outputs": [
2312 |     {
2313 |      "data": {
2314 |       "text/plain": [
2315 |        "[array([[0.1378213]], dtype=float32),\n",
2316 |        " array([[0.13945529]], dtype=float32),\n",
2317 |        " array([[0.14068112]], dtype=float32),\n",
2318 |        " array([[0.14162877]], dtype=float32),\n",
2319 |        " array([[0.14216018]], dtype=float32),\n",
2320 |        " array([[0.14206707]], dtype=float32),\n",
2321 |        " array([[0.1421535]], dtype=float32),\n",
2322 |        " array([[0.14225037]], dtype=float32),\n",
2323 |        " array([[0.14217126]], dtype=float32),\n",
2324 |        " array([[0.14150538]], dtype=float32),\n",
2325 |        " array([[0.14047278]], dtype=float32),\n",
2326 |        " array([[0.13954498]], dtype=float32),\n",
2327 |        " array([[0.13914707]], dtype=float32),\n",
2328 |        " array([[0.13891666]], dtype=float32),\n",
2329 |        " array([[0.13893819]], dtype=float32),\n",
2330 |        " array([[0.13930015]], dtype=float32),\n",
2331 |        " array([[0.13948296]], dtype=float32),\n",
2332 |        " array([[0.13946058]], dtype=float32),\n",
2333 |        " array([[0.13963053]], dtype=float32),\n",
2334 |        " array([[0.14062819]], dtype=float32),\n",
2335 |        " array([[0.14126904]], dtype=float32),\n",
2336 |        " array([[0.14153312]], dtype=float32),\n",
2337 |        " array([[0.1416432]], dtype=float32),\n",
2338 |        " array([[0.14201452]], dtype=float32),\n",
2339 |        " array([[0.14254372]], dtype=float32),\n",
2340 |        " array([[0.14292328]], dtype=float32),\n",
2341 |        " array([[0.14306733]], dtype=float32),\n",
2342 |        " array([[0.14389662]], dtype=float32),\n",
2343 |        " array([[0.14515653]], dtype=float32),\n",
2344 |        " array([[0.14742556]], dtype=float32)]"
2345 |       ]
2346 |      },
2347 |      "execution_count": 117,
2348 |      "metadata": {},
2349 |      "output_type": "execute_result"
2350 |     }
2351 |    ],
2352 |    "source": [
2353 |     "all_data"
2354 |    ]
2355 |   },
2356 |   {
2357 |    "cell_type": "code",
2358 |    "execution_count": 118,
2359 |    "id": "379cf40a",
2360 |    "metadata": {},
2361 |    "outputs": [],
2362 |    "source": [
2363 |     "new_array=np.array(all_data)\n",
2364 |     "new_array=new_array.reshape(-1,1)\n",
2365 |     "prediction_copies_array = np.repeat(new_array,5, axis=-1)\n",
2366 |     "y_pred_future_30_days = scaler.inverse_transform(np.reshape(prediction_copies_array,(len(new_array),5)))[:,0]"
2367 |    ]
2368 |   },
2369 |   {
2370 |    "cell_type": "code",
2371 |    "execution_count": 119,
2372 |    "id": "4ab9307c",
2373 |    "metadata": {
2374 |     "scrolled": true
2375 |    },
2376 |    "outputs": [
2377 |     {
2378 |      "data": {
2379 |       "text/plain": [
2380 |        "array([101.11468 , 101.69789 , 102.135414, 102.473656, 102.66332 ,\n",
2381 |        "       102.6301  , 102.66094 , 102.69551 , 102.66728 , 102.4296  ,\n",
2382 |        "       102.06105 , 101.7299  , 101.58788 , 101.50563 , 101.51332 ,\n",
2383 |        "       101.64251 , 101.70776 , 101.69977 , 101.76044 , 102.11652 ,\n",
2384 |        "       102.34525 , 102.43951 , 102.478806, 102.61133 , 102.80022 ,\n",
2385 |        "       102.93569 , 102.98711 , 103.2831  , 103.732796, 104.54266 ],\n",
2386 |        "      dtype=float32)"
2387 |       ]
2388 |      },
2389 |      "execution_count": 119,
2390 |      "metadata": {},
2391 |      "output_type": "execute_result"
2392 |     }
2393 |    ],
2394 |    "source": [
2395 |     "y_pred_future_30_days"
2396 |    ]
2397 |   },
2398 |   {
2399 |    "cell_type": "code",
2400 |    "execution_count": null,
2401 |    "id": "265bfef0",
2402 |    "metadata": {},
2403 |    "outputs": [],
2404 |    "source": []
2405 |   },
2406 |   {
2407 |    "cell_type": "code",
2408 |    "execution_count": null,
2409 |    "id": "eed9c5c8",
2410 |    "metadata": {},
2411 |    "outputs": [],
2412 |    "source": [
2413 |     "from tensorflow.keras.models import Model\n",
2414 |     "from tensorflow.keras.models import load_model"
2415 |    ]
2416 |   },
2417 |   {
2418 |    "cell_type": "code",
2419 |    "execution_count": null,
2420 |    "id": "0ede34e7",
2421 |    "metadata": {},
2422 |    "outputs": [],
2423 |    "source": [
2424 |     "mymodel.save('Model_future_value.h5')\n",
2425 |     "print('Model Saved!')"
2426 |    ]
2427 |   },
2428 |   {
2429 |    "cell_type": "code",
2430 |    "execution_count": null,
2431 |    "id": "4f12ddc7",
2432 |    "metadata": {},
2433 |    "outputs": [],
2434 |    "source": [
2435 |     "scaler"
2436 |    ]
2437 |   },
2438 |   {
2439 |    "cell_type": "code",
2440 |    "execution_count": null,
2441 |    "id": "13f766d0",
2442 |    "metadata": {},
2443 |    "outputs": [],
2444 |    "source": [
2445 |     "import pickle\n",
2446 |     "scalerfile = 'scaler_model_future_value.pkl'\n",
2447 |     "pickle.dump(scaler, open(scalerfile, 'wb'))"
2448 |    ]
2449 |   },
2450 |   {
2451 |    "cell_type": "markdown",
2452 |    "id": "dcbe5698",
2453 |    "metadata": {},
2454 |    "source": [
2455 |     "# END!!!!"
2456 |    ]
2457 |   }
2458 |  ],
2459 |  "metadata": {
2460 |   "kernelspec": {
2461 |    "display_name": "Python 3 (ipykernel)",
2462 |    "language": "python",
2463 |    "name": "python3"
2464 |   },
2465 |   "language_info": {
2466 |    "codemirror_mode": {
2467 |     "name": "ipython",
2468 |     "version": 3
2469 |    },
2470 |    "file_extension": ".py",
2471 |    "mimetype": "text/x-python",
2472 |    "name": "python",
2473 |    "nbconvert_exporter": "python",
2474 |    "pygments_lexer": "ipython3",
2475 |    "version": "3.9.7"
2476 |   }
2477 |  },
2478 |  "nbformat": 4,
2479 |  "nbformat_minor": 5
2480 | }
2481 | 


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