├── README.md └── STOCK_PRED.ipynb /README.md: -------------------------------------------------------------------------------- 1 | # Stock_pred 2 | This is a stock market prediction project that can predict the future 30 days stock prices of various companies 3 | -------------------------------------------------------------------------------- /STOCK_PRED.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "code", 5 | "execution_count": 1, 6 | "id": "52d244d5", 7 | "metadata": {}, 8 | "outputs": [], 9 | "source": [ 10 | "import pandas as pd" 11 | ] 12 | }, 13 | { 14 | "cell_type": "code", 15 | "execution_count": 2, 16 | "id": "d468c25e", 17 | "metadata": { 18 | "scrolled": false 19 | }, 20 | "outputs": [ 21 | { 22 | "name": "stdout", 23 | "output_type": "stream", 24 | "text": [ 25 | "Requirement already satisfied: pandas_datareader in c:\\users\\hp\\anaconda3\\lib\\site-packages (0.10.0)\n", 26 | "Requirement already satisfied: pandas>=0.23 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from pandas_datareader) (1.2.4)\n", 27 | "Requirement already satisfied: lxml in c:\\users\\hp\\anaconda3\\lib\\site-packages (from pandas_datareader) (4.6.3)\n", 28 | "Requirement already satisfied: requests>=2.19.0 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from pandas_datareader) (2.25.1)\n", 29 | "Requirement already satisfied: pytz>=2017.3 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from pandas>=0.23->pandas_datareader) (2021.1)\n", 30 | "Requirement already satisfied: python-dateutil>=2.7.3 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from pandas>=0.23->pandas_datareader) (2.8.1)\n", 31 | "Requirement already satisfied: numpy>=1.16.5 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from pandas>=0.23->pandas_datareader) (1.20.1)\n", 32 | "Requirement already satisfied: six>=1.5 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from python-dateutil>=2.7.3->pandas>=0.23->pandas_datareader) (1.15.0)\n", 33 | "Requirement already satisfied: chardet<5,>=3.0.2 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from requests>=2.19.0->pandas_datareader) (4.0.0)\n", 34 | "Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from requests>=2.19.0->pandas_datareader) (2020.12.5)\n", 35 | "Requirement already satisfied: idna<3,>=2.5 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from requests>=2.19.0->pandas_datareader) (2.10)\n", 36 | "Requirement already satisfied: urllib3<1.27,>=1.21.1 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from requests>=2.19.0->pandas_datareader) (1.26.4)\n" 37 | ] 38 | } 39 | ], 40 | "source": [ 41 | "!pip install pandas_datareader" 42 | ] 43 | }, 44 | { 45 | "cell_type": "code", 46 | "execution_count": 3, 47 | "id": "188406a1", 48 | "metadata": {}, 49 | "outputs": [], 50 | "source": [ 51 | "import pandas_datareader as pdr\n", 52 | "import numpy as np" 53 | ] 54 | }, 55 | { 56 | "cell_type": "code", 57 | "execution_count": 4, 58 | "id": "9ea3fe9c", 59 | "metadata": {}, 60 | "outputs": [], 61 | "source": [ 62 | "df = pd.read_csv(r\"C:\\Users\\hp\\Desktop\\Untitled Folder\\AAPL_data.csv\")" 63 | ] 64 | }, 65 | { 66 | "cell_type": "code", 67 | "execution_count": 5, 68 | "id": "57307495", 69 | "metadata": {}, 70 | "outputs": [ 71 | { 72 | "data": { 73 | "text/plain": [ 74 | "" 88 | ] 89 | }, 90 | "execution_count": 5, 91 | "metadata": {}, 92 | "output_type": "execute_result" 93 | } 94 | ], 95 | "source": [ 96 | "df.head" 97 | ] 98 | }, 99 | { 100 | "cell_type": "code", 101 | "execution_count": 6, 102 | "id": "369203fb", 103 | "metadata": {}, 104 | "outputs": [], 105 | "source": [ 106 | "df2=df.reset_index()[\"close\"]" 107 | ] 108 | }, 109 | { 110 | "cell_type": "code", 111 | "execution_count": 7, 112 | "id": "6b8cbaae", 113 | "metadata": {}, 114 | "outputs": [ 115 | { 116 | "data": { 117 | "text/plain": [ 118 | "0 67.8542\n", 119 | "1 68.5614\n", 120 | "2 66.8428\n", 121 | "3 66.7156\n", 122 | "4 66.6556\n", 123 | " ... \n", 124 | "1254 167.7800\n", 125 | "1255 160.5000\n", 126 | "1256 156.4900\n", 127 | "1257 163.0300\n", 128 | "1258 159.5400\n", 129 | "Name: close, Length: 1259, dtype: float64" 130 | ] 131 | }, 132 | "execution_count": 7, 133 | "metadata": {}, 134 | "output_type": "execute_result" 135 | } 136 | ], 137 | "source": [ 138 | "df2" 139 | ] 140 | }, 141 | { 142 | "cell_type": "code", 143 | "execution_count": 8, 144 | "id": "fce2367b", 145 | "metadata": { 146 | "scrolled": true 147 | }, 148 | "outputs": [ 149 | { 150 | "data": { 151 | "text/plain": [ 152 | "[]" 153 | ] 154 | }, 155 | "execution_count": 8, 156 | "metadata": {}, 157 | "output_type": "execute_result" 158 | }, 159 | { 160 | "data": { 161 | "image/png": "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\n", 162 | "text/plain": [ 163 | "
" 164 | ] 165 | }, 166 | "metadata": { 167 | "needs_background": "light" 168 | }, 169 | "output_type": "display_data" 170 | } 171 | ], 172 | "source": [ 173 | "import matplotlib.pyplot as plt\n", 174 | "plt.plot(df2)" 175 | ] 176 | }, 177 | { 178 | "cell_type": "code", 179 | "execution_count": 9, 180 | "id": "3aaeb60b", 181 | "metadata": {}, 182 | "outputs": [], 183 | "source": [ 184 | "from sklearn.preprocessing import MinMaxScaler" 185 | ] 186 | }, 187 | { 188 | "cell_type": "code", 189 | "execution_count": 10, 190 | "id": "b011f836", 191 | "metadata": {}, 192 | "outputs": [], 193 | "source": [ 194 | "scaler = MinMaxScaler(feature_range=(0,1))\n", 195 | "df2=scaler.fit_transform(np.array(df2).reshape(-1,1))" 196 | ] 197 | }, 198 | { 199 | "cell_type": "code", 200 | "execution_count": 11, 201 | "id": "405f4478", 202 | "metadata": {}, 203 | "outputs": [ 204 | { 205 | "data": { 206 | "text/plain": [ 207 | "(1259, 7)" 208 | ] 209 | }, 210 | "execution_count": 11, 211 | "metadata": {}, 212 | "output_type": "execute_result" 213 | } 214 | ], 215 | "source": [ 216 | "df.shape" 217 | ] 218 | }, 219 | { 220 | "cell_type": "code", 221 | "execution_count": 12, 222 | "id": "a4053dc4", 223 | "metadata": {}, 224 | "outputs": [ 225 | { 226 | "data": { 227 | "text/plain": [ 228 | "array([[0.0977103 ],\n", 229 | " [0.103438 ],\n", 230 | " [0.08951884],\n", 231 | " ...,\n", 232 | " [0.81558288],\n", 233 | " [0.86855117],\n", 234 | " [0.84028522]])" 235 | ] 236 | }, 237 | "execution_count": 12, 238 | "metadata": {}, 239 | "output_type": "execute_result" 240 | } 241 | ], 242 | "source": [ 243 | "df2" 244 | ] 245 | }, 246 | { 247 | "cell_type": "code", 248 | "execution_count": 13, 249 | "id": "137a0ace", 250 | "metadata": {}, 251 | "outputs": [], 252 | "source": [ 253 | "#lets split the data into train and test\n", 254 | "training_size = int(len(df2)*0.65)\n", 255 | "test_size = len(df2)-training_size\n", 256 | "train_data,test_data= df2[0:training_size,:],df2[training_size:len(df2),:1]" 257 | ] 258 | }, 259 | { 260 | "cell_type": "code", 261 | "execution_count": 14, 262 | "id": "fd96ae61", 263 | "metadata": {}, 264 | "outputs": [ 265 | { 266 | "data": { 267 | "text/plain": [ 268 | "(818, 441)" 269 | ] 270 | }, 271 | "execution_count": 14, 272 | "metadata": {}, 273 | "output_type": "execute_result" 274 | } 275 | ], 276 | "source": [ 277 | "training_size,test_size" 278 | ] 279 | }, 280 | { 281 | "cell_type": "code", 282 | "execution_count": 15, 283 | "id": "45979e05", 284 | "metadata": {}, 285 | "outputs": [], 286 | "source": [ 287 | "# converting an array of values into a dataset matrix\n", 288 | "import numpy\n", 289 | "def create_dataset(dataset, time_step=1):\n", 290 | " dataX, dataY = [], []\n", 291 | " for i in range(len(dataset)-time_step-1):\n", 292 | " a = dataset[i:(i+time_step), 0] \n", 293 | " dataX.append(a)\n", 294 | " dataY.append(dataset[i + time_step, 0])\n", 295 | " return numpy.array(dataX), numpy.array(dataY)" 296 | ] 297 | }, 298 | { 299 | "cell_type": "code", 300 | "execution_count": 16, 301 | "id": "5a8568d9", 302 | "metadata": {}, 303 | "outputs": [ 304 | { 305 | "name": "stdout", 306 | "output_type": "stream", 307 | "text": [ 308 | "(717, 100)\n", 309 | "(717,)\n" 310 | ] 311 | }, 312 | { 313 | "data": { 314 | "text/plain": [ 315 | "(None, None)" 316 | ] 317 | }, 318 | "execution_count": 16, 319 | "metadata": {}, 320 | "output_type": "execute_result" 321 | } 322 | ], 323 | "source": [ 324 | "time_step = 100\n", 325 | "X_train, y_train = create_dataset(train_data, time_step)\n", 326 | "X_test, ytest = create_dataset(test_data, time_step)\n", 327 | "print(X_train.shape), print(y_train.shape)" 328 | ] 329 | }, 330 | { 331 | "cell_type": "code", 332 | "execution_count": 17, 333 | "id": "60070d48", 334 | "metadata": {}, 335 | "outputs": [ 336 | { 337 | "name": "stdout", 338 | "output_type": "stream", 339 | "text": [ 340 | "(340, 100)\n", 341 | "(340,)\n" 342 | ] 343 | }, 344 | { 345 | "data": { 346 | "text/plain": [ 347 | "(None, None)" 348 | ] 349 | }, 350 | "execution_count": 17, 351 | "metadata": {}, 352 | "output_type": "execute_result" 353 | } 354 | ], 355 | "source": [ 356 | "print(X_test.shape), print(ytest.shape)" 357 | ] 358 | }, 359 | { 360 | "cell_type": "code", 361 | "execution_count": 18, 362 | "id": "a19b02e0", 363 | "metadata": {}, 364 | "outputs": [], 365 | "source": [ 366 | "X_train =X_train.reshape(X_train.shape[0],X_train.shape[1] , 1)\n", 367 | "X_test = X_test.reshape(X_test.shape[0],X_test.shape[1] , 1)" 368 | ] 369 | }, 370 | { 371 | "cell_type": "code", 372 | "execution_count": 19, 373 | "id": "2fc2a6d6", 374 | "metadata": {}, 375 | "outputs": [], 376 | "source": [ 377 | "### Create the Stacked LSTM model\n", 378 | "from tensorflow.keras.models import Sequential\n", 379 | "from tensorflow.keras.layers import Dense\n", 380 | "from tensorflow.keras.layers import LSTM" 381 | ] 382 | }, 383 | { 384 | "cell_type": "code", 385 | "execution_count": 20, 386 | "id": "35f28536", 387 | "metadata": {}, 388 | "outputs": [], 389 | "source": [ 390 | "model=Sequential()\n", 391 | "model.add(LSTM(50,return_sequences=True,input_shape=(100,1)))\n", 392 | "model.add(LSTM(50,return_sequences=True))\n", 393 | "model.add(LSTM(50))\n", 394 | "model.add(Dense(1))\n", 395 | "model.compile(loss='mean_squared_error',optimizer='adam')" 396 | ] 397 | }, 398 | { 399 | "cell_type": "code", 400 | "execution_count": 21, 401 | "id": "18e043a3", 402 | "metadata": {}, 403 | "outputs": [ 404 | { 405 | "name": "stdout", 406 | "output_type": "stream", 407 | "text": [ 408 | "Model: \"sequential\"\n", 409 | "_________________________________________________________________\n", 410 | " Layer (type) Output Shape Param # \n", 411 | "=================================================================\n", 412 | " lstm (LSTM) (None, 100, 50) 10400 \n", 413 | " \n", 414 | " lstm_1 (LSTM) (None, 100, 50) 20200 \n", 415 | " \n", 416 | " lstm_2 (LSTM) (None, 50) 20200 \n", 417 | " \n", 418 | " dense (Dense) (None, 1) 51 \n", 419 | " \n", 420 | "=================================================================\n", 421 | "Total params: 50,851\n", 422 | "Trainable params: 50,851\n", 423 | "Non-trainable params: 0\n", 424 | "_________________________________________________________________\n" 425 | ] 426 | } 427 | ], 428 | "source": [ 429 | "model.summary()" 430 | ] 431 | }, 432 | { 433 | "cell_type": "code", 434 | "execution_count": 22, 435 | "id": "c8ee2d14", 436 | "metadata": {}, 437 | "outputs": [ 438 | { 439 | "name": "stdout", 440 | "output_type": "stream", 441 | "text": [ 442 | "Epoch 1/100\n", 443 | "12/12 [==============================] - 30s 463ms/step - loss: 0.0427 - val_loss: 0.0558\n", 444 | "Epoch 2/100\n", 445 | "12/12 [==============================] - 3s 251ms/step - loss: 0.0074 - val_loss: 0.0048\n", 446 | "Epoch 3/100\n", 447 | "12/12 [==============================] - 3s 263ms/step - loss: 0.0035 - val_loss: 0.0127\n", 448 | "Epoch 4/100\n", 449 | "12/12 [==============================] - 3s 253ms/step - loss: 0.0020 - val_loss: 0.0106\n", 450 | "Epoch 5/100\n", 451 | "12/12 [==============================] - 3s 237ms/step - loss: 0.0015 - val_loss: 0.0046\n", 452 | "Epoch 6/100\n", 453 | "12/12 [==============================] - 3s 242ms/step - loss: 0.0014 - val_loss: 0.0023\n", 454 | "Epoch 7/100\n", 455 | "12/12 [==============================] - 3s 239ms/step - loss: 0.0013 - val_loss: 0.0025\n", 456 | "Epoch 8/100\n", 457 | "12/12 [==============================] - 3s 240ms/step - loss: 0.0014 - val_loss: 0.0047\n", 458 | "Epoch 9/100\n", 459 | "12/12 [==============================] - 3s 252ms/step - loss: 0.0013 - val_loss: 0.0044\n", 460 | "Epoch 10/100\n", 461 | "12/12 [==============================] - 3s 240ms/step - loss: 0.0012 - val_loss: 0.0030\n", 462 | "Epoch 11/100\n", 463 | "12/12 [==============================] - 3s 241ms/step - loss: 0.0012 - val_loss: 0.0039\n", 464 | "Epoch 12/100\n", 465 | "12/12 [==============================] - 3s 237ms/step - loss: 0.0012 - val_loss: 0.0026\n", 466 | "Epoch 13/100\n", 467 | "12/12 [==============================] - 3s 240ms/step - loss: 0.0012 - val_loss: 0.0025\n", 468 | "Epoch 14/100\n", 469 | "12/12 [==============================] - 3s 246ms/step - loss: 0.0012 - val_loss: 0.0026\n", 470 | "Epoch 15/100\n", 471 | "12/12 [==============================] - 3s 236ms/step - loss: 0.0011 - val_loss: 0.0023\n", 472 | "Epoch 16/100\n", 473 | "12/12 [==============================] - 3s 239ms/step - loss: 0.0011 - val_loss: 0.0031\n", 474 | "Epoch 17/100\n", 475 | "12/12 [==============================] - 3s 237ms/step - loss: 0.0011 - val_loss: 0.0041\n", 476 | "Epoch 18/100\n", 477 | "12/12 [==============================] - 3s 242ms/step - loss: 0.0011 - val_loss: 0.0032\n", 478 | "Epoch 19/100\n", 479 | "12/12 [==============================] - 3s 246ms/step - loss: 0.0011 - val_loss: 0.0028\n", 480 | "Epoch 20/100\n", 481 | "12/12 [==============================] - 3s 255ms/step - loss: 0.0010 - val_loss: 0.0027\n", 482 | "Epoch 21/100\n", 483 | "12/12 [==============================] - 3s 242ms/step - loss: 9.7665e-04 - val_loss: 0.0022\n", 484 | "Epoch 22/100\n", 485 | "12/12 [==============================] - 3s 252ms/step - loss: 9.6788e-04 - val_loss: 0.0032\n", 486 | "Epoch 23/100\n", 487 | "12/12 [==============================] - 3s 261ms/step - loss: 9.7661e-04 - val_loss: 0.0019\n", 488 | "Epoch 24/100\n", 489 | "12/12 [==============================] - 3s 266ms/step - loss: 0.0010 - val_loss: 0.0040\n", 490 | "Epoch 25/100\n", 491 | "12/12 [==============================] - 3s 252ms/step - loss: 0.0011 - val_loss: 0.0054\n", 492 | "Epoch 26/100\n", 493 | "12/12 [==============================] - 3s 251ms/step - loss: 9.7677e-04 - val_loss: 0.0015\n", 494 | "Epoch 27/100\n", 495 | "12/12 [==============================] - 3s 252ms/step - loss: 8.8213e-04 - val_loss: 0.0063\n", 496 | "Epoch 28/100\n", 497 | "12/12 [==============================] - 3s 257ms/step - loss: 0.0010 - val_loss: 0.0019\n", 498 | "Epoch 29/100\n", 499 | "12/12 [==============================] - 3s 252ms/step - loss: 9.2592e-04 - val_loss: 0.0033\n", 500 | "Epoch 30/100\n", 501 | "12/12 [==============================] - 3s 278ms/step - loss: 8.2296e-04 - val_loss: 0.0027\n", 502 | "Epoch 31/100\n", 503 | "12/12 [==============================] - 3s 282ms/step - loss: 8.1438e-04 - val_loss: 0.0031\n", 504 | "Epoch 32/100\n", 505 | "12/12 [==============================] - 3s 244ms/step - loss: 7.8608e-04 - val_loss: 0.0042\n", 506 | "Epoch 33/100\n", 507 | "12/12 [==============================] - 3s 245ms/step - loss: 8.0877e-04 - val_loss: 0.0030\n", 508 | "Epoch 34/100\n", 509 | "12/12 [==============================] - 3s 261ms/step - loss: 7.9552e-04 - val_loss: 0.0013\n", 510 | "Epoch 35/100\n", 511 | "12/12 [==============================] - 3s 216ms/step - loss: 8.9732e-04 - val_loss: 0.0059\n", 512 | "Epoch 36/100\n", 513 | "12/12 [==============================] - 3s 229ms/step - loss: 7.8582e-04 - val_loss: 0.0016\n", 514 | "Epoch 37/100\n", 515 | "12/12 [==============================] - 3s 224ms/step - loss: 7.4947e-04 - val_loss: 0.0052\n", 516 | "Epoch 38/100\n", 517 | "12/12 [==============================] - 2s 202ms/step - loss: 7.8442e-04 - val_loss: 0.0020\n", 518 | "Epoch 39/100\n", 519 | "12/12 [==============================] - 2s 208ms/step - loss: 7.2167e-04 - val_loss: 0.0027\n", 520 | "Epoch 40/100\n", 521 | "12/12 [==============================] - 2s 210ms/step - loss: 7.2534e-04 - val_loss: 0.0024\n", 522 | "Epoch 41/100\n", 523 | "12/12 [==============================] - 3s 212ms/step - loss: 7.3448e-04 - val_loss: 0.0028\n", 524 | "Epoch 42/100\n", 525 | "12/12 [==============================] - 3s 224ms/step - loss: 7.0229e-04 - val_loss: 0.0028\n", 526 | "Epoch 43/100\n", 527 | "12/12 [==============================] - 2s 201ms/step - loss: 7.6169e-04 - val_loss: 0.0028\n", 528 | "Epoch 44/100\n", 529 | "12/12 [==============================] - 3s 212ms/step - loss: 7.1072e-04 - val_loss: 0.0024\n", 530 | "Epoch 45/100\n", 531 | "12/12 [==============================] - 2s 199ms/step - loss: 7.0569e-04 - val_loss: 0.0016\n", 532 | "Epoch 46/100\n", 533 | "12/12 [==============================] - 2s 204ms/step - loss: 7.5866e-04 - val_loss: 0.0026\n", 534 | "Epoch 47/100\n", 535 | "12/12 [==============================] - 2s 207ms/step - loss: 6.7575e-04 - val_loss: 0.0015\n", 536 | "Epoch 48/100\n", 537 | "12/12 [==============================] - 2s 205ms/step - loss: 6.9837e-04 - val_loss: 0.0022\n", 538 | "Epoch 49/100\n", 539 | "12/12 [==============================] - 3s 216ms/step - loss: 6.4168e-04 - val_loss: 0.0013\n", 540 | "Epoch 50/100\n", 541 | "12/12 [==============================] - 2s 205ms/step - loss: 6.4000e-04 - val_loss: 0.0042\n", 542 | "Epoch 51/100\n", 543 | "12/12 [==============================] - 2s 204ms/step - loss: 8.3667e-04 - val_loss: 0.0011\n", 544 | "Epoch 52/100\n", 545 | "12/12 [==============================] - 3s 213ms/step - loss: 6.4200e-04 - val_loss: 0.0054\n", 546 | "Epoch 53/100\n", 547 | "12/12 [==============================] - 3s 217ms/step - loss: 7.4340e-04 - val_loss: 0.0013\n", 548 | "Epoch 54/100\n", 549 | "12/12 [==============================] - 2s 210ms/step - loss: 6.3283e-04 - val_loss: 0.0017\n", 550 | "Epoch 55/100\n", 551 | "12/12 [==============================] - 3s 225ms/step - loss: 6.3931e-04 - val_loss: 0.0014\n", 552 | "Epoch 56/100\n", 553 | "12/12 [==============================] - 3s 253ms/step - loss: 6.4166e-04 - val_loss: 0.0013\n", 554 | "Epoch 57/100\n", 555 | "12/12 [==============================] - 3s 245ms/step - loss: 6.2991e-04 - val_loss: 0.0027\n", 556 | "Epoch 58/100\n", 557 | "12/12 [==============================] - 3s 248ms/step - loss: 6.1198e-04 - val_loss: 0.0014\n", 558 | "Epoch 59/100\n", 559 | "12/12 [==============================] - 3s 252ms/step - loss: 6.6360e-04 - val_loss: 0.0015\n", 560 | "Epoch 60/100\n", 561 | "12/12 [==============================] - 3s 249ms/step - loss: 5.9901e-04 - val_loss: 0.0022\n", 562 | "Epoch 61/100\n", 563 | "12/12 [==============================] - 3s 252ms/step - loss: 5.9428e-04 - val_loss: 9.5535e-04\n", 564 | "Epoch 62/100\n", 565 | "12/12 [==============================] - 3s 239ms/step - loss: 6.1475e-04 - val_loss: 0.0020\n", 566 | "Epoch 63/100\n", 567 | "12/12 [==============================] - 3s 239ms/step - loss: 5.8649e-04 - val_loss: 0.0020\n", 568 | "Epoch 64/100\n", 569 | "12/12 [==============================] - 3s 236ms/step - loss: 5.8447e-04 - val_loss: 0.0014\n", 570 | "Epoch 65/100\n", 571 | "12/12 [==============================] - 3s 245ms/step - loss: 5.8174e-04 - val_loss: 0.0013\n", 572 | "Epoch 66/100\n", 573 | "12/12 [==============================] - 3s 248ms/step - loss: 5.7608e-04 - val_loss: 0.0022\n", 574 | "Epoch 67/100\n", 575 | "12/12 [==============================] - 3s 238ms/step - loss: 6.7440e-04 - val_loss: 0.0055\n", 576 | "Epoch 68/100\n", 577 | "12/12 [==============================] - 3s 248ms/step - loss: 6.9157e-04 - val_loss: 0.0021\n", 578 | "Epoch 69/100\n", 579 | "12/12 [==============================] - 3s 241ms/step - loss: 6.4901e-04 - val_loss: 7.8301e-04\n", 580 | "Epoch 70/100\n", 581 | "12/12 [==============================] - 3s 237ms/step - loss: 6.0322e-04 - val_loss: 9.8244e-04\n", 582 | "Epoch 71/100\n", 583 | "12/12 [==============================] - 3s 239ms/step - loss: 5.6397e-04 - val_loss: 0.0023\n", 584 | "Epoch 72/100\n", 585 | "12/12 [==============================] - 3s 250ms/step - loss: 5.5574e-04 - val_loss: 0.0017\n", 586 | "Epoch 73/100\n", 587 | "12/12 [==============================] - 3s 239ms/step - loss: 5.5656e-04 - val_loss: 9.6552e-04\n", 588 | "Epoch 74/100\n", 589 | "12/12 [==============================] - 3s 239ms/step - loss: 5.9065e-04 - val_loss: 6.2092e-04\n", 590 | "Epoch 75/100\n", 591 | "12/12 [==============================] - 3s 246ms/step - loss: 5.6792e-04 - val_loss: 0.0010\n", 592 | "Epoch 76/100\n", 593 | "12/12 [==============================] - 3s 250ms/step - loss: 5.3962e-04 - val_loss: 0.0024\n", 594 | "Epoch 77/100\n", 595 | "12/12 [==============================] - 3s 245ms/step - loss: 5.7385e-04 - val_loss: 7.7966e-04\n", 596 | "Epoch 78/100\n", 597 | "12/12 [==============================] - 3s 257ms/step - loss: 5.7701e-04 - val_loss: 6.5986e-04\n", 598 | "Epoch 79/100\n", 599 | "12/12 [==============================] - 3s 245ms/step - loss: 5.3020e-04 - val_loss: 0.0013\n", 600 | "Epoch 80/100\n", 601 | "12/12 [==============================] - 3s 244ms/step - loss: 5.3075e-04 - val_loss: 0.0013\n", 602 | "Epoch 81/100\n", 603 | "12/12 [==============================] - 3s 239ms/step - loss: 5.3846e-04 - val_loss: 0.0021\n", 604 | "Epoch 82/100\n", 605 | "12/12 [==============================] - 3s 244ms/step - loss: 5.3333e-04 - val_loss: 0.0026\n", 606 | "Epoch 83/100\n", 607 | "12/12 [==============================] - 3s 257ms/step - loss: 5.8573e-04 - val_loss: 6.8453e-04\n", 608 | "Epoch 84/100\n", 609 | "12/12 [==============================] - 3s 236ms/step - loss: 5.9757e-04 - val_loss: 8.4274e-04\n", 610 | "Epoch 85/100\n", 611 | "12/12 [==============================] - 3s 243ms/step - loss: 5.0940e-04 - val_loss: 0.0012\n", 612 | "Epoch 86/100\n", 613 | "12/12 [==============================] - 3s 247ms/step - loss: 4.9212e-04 - val_loss: 0.0011\n", 614 | "Epoch 87/100\n", 615 | "12/12 [==============================] - 3s 240ms/step - loss: 4.8176e-04 - val_loss: 5.6637e-04\n", 616 | "Epoch 88/100\n", 617 | "12/12 [==============================] - 3s 251ms/step - loss: 4.9069e-04 - val_loss: 0.0024\n", 618 | "Epoch 89/100\n", 619 | "12/12 [==============================] - 3s 248ms/step - loss: 6.1907e-04 - val_loss: 0.0011\n", 620 | "Epoch 90/100\n", 621 | "12/12 [==============================] - 3s 242ms/step - loss: 5.1750e-04 - val_loss: 6.0290e-04\n", 622 | "Epoch 91/100\n", 623 | "12/12 [==============================] - 3s 242ms/step - loss: 5.6843e-04 - val_loss: 0.0048\n", 624 | "Epoch 92/100\n", 625 | "12/12 [==============================] - 3s 239ms/step - loss: 6.6094e-04 - val_loss: 0.0014\n", 626 | "Epoch 93/100\n", 627 | "12/12 [==============================] - 3s 247ms/step - loss: 5.0419e-04 - val_loss: 5.5629e-04\n", 628 | "Epoch 94/100\n", 629 | "12/12 [==============================] - 3s 260ms/step - loss: 5.0335e-04 - val_loss: 8.7860e-04\n", 630 | "Epoch 95/100\n", 631 | "12/12 [==============================] - 3s 249ms/step - loss: 4.7738e-04 - val_loss: 0.0019\n", 632 | "Epoch 96/100\n", 633 | "12/12 [==============================] - 3s 244ms/step - loss: 5.2874e-04 - val_loss: 5.1267e-04\n", 634 | "Epoch 97/100\n", 635 | "12/12 [==============================] - 3s 248ms/step - loss: 4.9798e-04 - val_loss: 9.2158e-04\n", 636 | "Epoch 98/100\n", 637 | "12/12 [==============================] - 3s 250ms/step - loss: 4.7022e-04 - val_loss: 8.5403e-04\n", 638 | "Epoch 99/100\n", 639 | "12/12 [==============================] - 3s 266ms/step - loss: 4.5296e-04 - val_loss: 0.0012\n", 640 | "Epoch 100/100\n", 641 | "12/12 [==============================] - 3s 244ms/step - loss: 4.5106e-04 - val_loss: 4.7737e-04\n" 642 | ] 643 | }, 644 | { 645 | "data": { 646 | "text/plain": [ 647 | "" 648 | ] 649 | }, 650 | "execution_count": 22, 651 | "metadata": {}, 652 | "output_type": "execute_result" 653 | } 654 | ], 655 | "source": [ 656 | "model.fit(X_train,y_train,validation_data=(X_test,ytest),epochs=100,batch_size=64,verbose=1)" 657 | ] 658 | }, 659 | { 660 | "cell_type": "code", 661 | "execution_count": 23, 662 | "id": "890e9022", 663 | "metadata": {}, 664 | "outputs": [], 665 | "source": [ 666 | "import tensorflow as tf" 667 | ] 668 | }, 669 | { 670 | "cell_type": "code", 671 | "execution_count": 24, 672 | "id": "7c829d2e", 673 | "metadata": {}, 674 | "outputs": [], 675 | "source": [ 676 | "train_predict=model.predict(X_train)\n", 677 | "test_predict=model.predict(X_test)" 678 | ] 679 | }, 680 | { 681 | "cell_type": "code", 682 | "execution_count": 25, 683 | "id": "78aafa65", 684 | "metadata": {}, 685 | "outputs": [], 686 | "source": [ 687 | "train_predict=scaler.inverse_transform(train_predict)\n", 688 | "test_predict=scaler.inverse_transform(test_predict)" 689 | ] 690 | }, 691 | { 692 | "cell_type": "code", 693 | "execution_count": 26, 694 | "id": "e97198fb", 695 | "metadata": {}, 696 | "outputs": [ 697 | { 698 | "data": { 699 | "text/plain": [ 700 | "102.29490390585865" 701 | ] 702 | }, 703 | "execution_count": 26, 704 | "metadata": {}, 705 | "output_type": "execute_result" 706 | } 707 | ], 708 | "source": [ 709 | "import math\n", 710 | "from sklearn.metrics import mean_squared_error\n", 711 | "math.sqrt(mean_squared_error(y_train,train_predict))" 712 | ] 713 | }, 714 | { 715 | "cell_type": "code", 716 | "execution_count": 27, 717 | "id": "2b9eba0e", 718 | "metadata": {}, 719 | "outputs": [ 720 | { 721 | "data": { 722 | "text/plain": [ 723 | "145.5714271610192" 724 | ] 725 | }, 726 | "execution_count": 27, 727 | "metadata": {}, 728 | "output_type": "execute_result" 729 | } 730 | ], 731 | "source": [ 732 | "math.sqrt(mean_squared_error(ytest,test_predict))" 733 | ] 734 | }, 735 | { 736 | "cell_type": "code", 737 | "execution_count": 28, 738 | "id": "d17c5a5d", 739 | "metadata": {}, 740 | "outputs": [ 741 | { 742 | "data": { 743 | "image/png": "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\n", 744 | "text/plain": [ 745 | "
" 746 | ] 747 | }, 748 | "metadata": { 749 | "needs_background": "light" 750 | }, 751 | "output_type": "display_data" 752 | } 753 | ], 754 | "source": [ 755 | "#shifting train predictions for plotting\n", 756 | "look_back=100\n", 757 | "trainPredictPlot = numpy.empty_like(df2)\n", 758 | "trainPredictPlot[:,:]= np.nan\n", 759 | "trainPredictPlot[look_back:len(train_predict)+look_back,:] = train_predict\n", 760 | "#shifting test predictions for plotting\n", 761 | "testPredictPlot = numpy.empty_like(df2)\n", 762 | "testPredictPlot[:, :]= np.nan\n", 763 | "testPredictPlot[len(train_predict)+(look_back*2)+1:len(df2)-1, :] = test_predict\n", 764 | "plt.plot(scaler.inverse_transform(df2))\n", 765 | "plt.plot(trainPredictPlot)\n", 766 | "plt.plot(testPredictPlot)\n", 767 | "plt.show()\n" 768 | ] 769 | }, 770 | { 771 | "cell_type": "code", 772 | "execution_count": 29, 773 | "id": "d2e6a43b", 774 | "metadata": {}, 775 | "outputs": [ 776 | { 777 | "data": { 778 | "text/plain": [ 779 | "441" 780 | ] 781 | }, 782 | "execution_count": 29, 783 | "metadata": {}, 784 | "output_type": "execute_result" 785 | } 786 | ], 787 | "source": [ 788 | "len(test_data)" 789 | ] 790 | }, 791 | { 792 | "cell_type": "code", 793 | "execution_count": 30, 794 | "id": "5ada2a8c", 795 | "metadata": {}, 796 | "outputs": [], 797 | "source": [ 798 | "x_input = test_data[341: ].reshape(1,-1)" 799 | ] 800 | }, 801 | { 802 | "cell_type": "code", 803 | "execution_count": 31, 804 | "id": "d1315140", 805 | "metadata": {}, 806 | "outputs": [ 807 | { 808 | "data": { 809 | "text/plain": [ 810 | "(1, 100)" 811 | ] 812 | }, 813 | "execution_count": 31, 814 | "metadata": {}, 815 | "output_type": "execute_result" 816 | } 817 | ], 818 | "source": [ 819 | "x_input.shape" 820 | ] 821 | }, 822 | { 823 | "cell_type": "code", 824 | "execution_count": 50, 825 | "id": "d8bcd34d", 826 | "metadata": {}, 827 | "outputs": [], 828 | "source": [ 829 | "temp_input=list(x_input)\n", 830 | "temp_input=temp_input[0].tolist()" 831 | ] 832 | }, 833 | { 834 | "cell_type": "code", 835 | "execution_count": 51, 836 | "id": "99b6d99f", 837 | "metadata": {}, 838 | "outputs": [ 839 | { 840 | "name": "stdout", 841 | "output_type": "stream", 842 | "text": [ 843 | "[0.83227277]\n", 844 | "101\n", 845 | "1 day input [0.83323898 0.83372493 0.81218125 0.79047559 0.7783269 0.76747407\n", 846 | " 0.78845081 0.79727886 0.78958468 0.79638795 0.79387722 0.79930364\n", 847 | " 0.79120451 0.80667384 0.80594492 0.81031845 0.8108044 0.81606883\n", 848 | " 0.81161431 0.81963245 0.84303892 0.84781741 0.84206703 0.81145233\n", 849 | " 0.81363909 0.81299116 0.82052335 0.81493495 0.82303408 0.86871315\n", 850 | " 0.89843695 0.91722692 0.8998138 0.90969474 0.9452499 0.95942337\n", 851 | " 0.96395889 0.97554064 0.97262495 0.96282501 0.95715562 0.93585492\n", 852 | " 0.91755089 0.93391113 0.92621695 0.9248401 0.95043334 0.96517375\n", 853 | " 0.96525475 0.95812751 0.9498664 0.92079054 0.93998547 0.93350617\n", 854 | " 0.92338226 0.9220864 0.91698395 0.91949468 0.91989964 0.94662675\n", 855 | " 0.9387706 0.9433871 0.94298215 0.95715562 0.97699848 0.96177212\n", 856 | " 0.96023329 0.96557871 0.96557871 0.92961859 0.92986156 0.93374914\n", 857 | " 0.91876576 0.94330611 0.94306314 0.94954244 0.96549772 0.96023329\n", 858 | " 0.9600713 0.95974734 0.96776548 0.98242489 0.97513568 0.99870414\n", 859 | " 1. 0.9935207 0.98169597 0.98201994 0.9591804 0.93399212\n", 860 | " 0.93723177 0.90847987 0.90046173 0.90418733 0.90702202 0.84806038\n", 861 | " 0.81558288 0.86855117 0.84028522 0.83227277]\n", 862 | "1 day output [[0.826955]]\n", 863 | "2 day input [0.83372493 0.81218125 0.79047559 0.7783269 0.76747407 0.78845081\n", 864 | " 0.79727886 0.78958468 0.79638795 0.79387722 0.79930364 0.79120451\n", 865 | " 0.80667384 0.80594492 0.81031845 0.8108044 0.81606883 0.81161431\n", 866 | " 0.81963245 0.84303892 0.84781741 0.84206703 0.81145233 0.81363909\n", 867 | " 0.81299116 0.82052335 0.81493495 0.82303408 0.86871315 0.89843695\n", 868 | " 0.91722692 0.8998138 0.90969474 0.9452499 0.95942337 0.96395889\n", 869 | " 0.97554064 0.97262495 0.96282501 0.95715562 0.93585492 0.91755089\n", 870 | " 0.93391113 0.92621695 0.9248401 0.95043334 0.96517375 0.96525475\n", 871 | " 0.95812751 0.9498664 0.92079054 0.93998547 0.93350617 0.92338226\n", 872 | " 0.9220864 0.91698395 0.91949468 0.91989964 0.94662675 0.9387706\n", 873 | " 0.9433871 0.94298215 0.95715562 0.97699848 0.96177212 0.96023329\n", 874 | " 0.96557871 0.96557871 0.92961859 0.92986156 0.93374914 0.91876576\n", 875 | " 0.94330611 0.94306314 0.94954244 0.96549772 0.96023329 0.9600713\n", 876 | " 0.95974734 0.96776548 0.98242489 0.97513568 0.99870414 1.\n", 877 | " 0.9935207 0.98169597 0.98201994 0.9591804 0.93399212 0.93723177\n", 878 | " 0.90847987 0.90046173 0.90418733 0.90702202 0.84806038 0.81558288\n", 879 | " 0.86855117 0.84028522 0.83227277 0.82695502]\n", 880 | "2 day output [[0.8232421]]\n", 881 | "3 day input [0.81218125 0.79047559 0.7783269 0.76747407 0.78845081 0.79727886\n", 882 | " 0.78958468 0.79638795 0.79387722 0.79930364 0.79120451 0.80667384\n", 883 | " 0.80594492 0.81031845 0.8108044 0.81606883 0.81161431 0.81963245\n", 884 | " 0.84303892 0.84781741 0.84206703 0.81145233 0.81363909 0.81299116\n", 885 | " 0.82052335 0.81493495 0.82303408 0.86871315 0.89843695 0.91722692\n", 886 | " 0.8998138 0.90969474 0.9452499 0.95942337 0.96395889 0.97554064\n", 887 | " 0.97262495 0.96282501 0.95715562 0.93585492 0.91755089 0.93391113\n", 888 | " 0.92621695 0.9248401 0.95043334 0.96517375 0.96525475 0.95812751\n", 889 | " 0.9498664 0.92079054 0.93998547 0.93350617 0.92338226 0.9220864\n", 890 | " 0.91698395 0.91949468 0.91989964 0.94662675 0.9387706 0.9433871\n", 891 | " 0.94298215 0.95715562 0.97699848 0.96177212 0.96023329 0.96557871\n", 892 | " 0.96557871 0.92961859 0.92986156 0.93374914 0.91876576 0.94330611\n", 893 | " 0.94306314 0.94954244 0.96549772 0.96023329 0.9600713 0.95974734\n", 894 | " 0.96776548 0.98242489 0.97513568 0.99870414 1. 0.9935207\n", 895 | " 0.98169597 0.98201994 0.9591804 0.93399212 0.93723177 0.90847987\n", 896 | " 0.90046173 0.90418733 0.90702202 0.84806038 0.81558288 0.86855117\n", 897 | " 0.84028522 0.83227277 0.82695502 0.82324213]\n", 898 | "3 day output [[0.8207005]]\n", 899 | "4 day input [0.79047559 0.7783269 0.76747407 0.78845081 0.79727886 0.78958468\n", 900 | " 0.79638795 0.79387722 0.79930364 0.79120451 0.80667384 0.80594492\n", 901 | " 0.81031845 0.8108044 0.81606883 0.81161431 0.81963245 0.84303892\n", 902 | " 0.84781741 0.84206703 0.81145233 0.81363909 0.81299116 0.82052335\n", 903 | " 0.81493495 0.82303408 0.86871315 0.89843695 0.91722692 0.8998138\n", 904 | " 0.90969474 0.9452499 0.95942337 0.96395889 0.97554064 0.97262495\n", 905 | " 0.96282501 0.95715562 0.93585492 0.91755089 0.93391113 0.92621695\n", 906 | " 0.9248401 0.95043334 0.96517375 0.96525475 0.95812751 0.9498664\n", 907 | " 0.92079054 0.93998547 0.93350617 0.92338226 0.9220864 0.91698395\n", 908 | " 0.91949468 0.91989964 0.94662675 0.9387706 0.9433871 0.94298215\n", 909 | " 0.95715562 0.97699848 0.96177212 0.96023329 0.96557871 0.96557871\n", 910 | " 0.92961859 0.92986156 0.93374914 0.91876576 0.94330611 0.94306314\n", 911 | " 0.94954244 0.96549772 0.96023329 0.9600713 0.95974734 0.96776548\n", 912 | " 0.98242489 0.97513568 0.99870414 1. 0.9935207 0.98169597\n", 913 | " 0.98201994 0.9591804 0.93399212 0.93723177 0.90847987 0.90046173\n", 914 | " 0.90418733 0.90702202 0.84806038 0.81558288 0.86855117 0.84028522\n", 915 | " 0.83227277 0.82695502 0.82324213 0.82070053]\n", 916 | "4 day output [[0.8190786]]\n", 917 | "5 day input [0.7783269 0.76747407 0.78845081 0.79727886 0.78958468 0.79638795\n", 918 | " 0.79387722 0.79930364 0.79120451 0.80667384 0.80594492 0.81031845\n", 919 | " 0.8108044 0.81606883 0.81161431 0.81963245 0.84303892 0.84781741\n", 920 | " 0.84206703 0.81145233 0.81363909 0.81299116 0.82052335 0.81493495\n", 921 | " 0.82303408 0.86871315 0.89843695 0.91722692 0.8998138 0.90969474\n", 922 | " 0.9452499 0.95942337 0.96395889 0.97554064 0.97262495 0.96282501\n", 923 | " 0.95715562 0.93585492 0.91755089 0.93391113 0.92621695 0.9248401\n", 924 | " 0.95043334 0.96517375 0.96525475 0.95812751 0.9498664 0.92079054\n", 925 | " 0.93998547 0.93350617 0.92338226 0.9220864 0.91698395 0.91949468\n", 926 | " 0.91989964 0.94662675 0.9387706 0.9433871 0.94298215 0.95715562\n", 927 | " 0.97699848 0.96177212 0.96023329 0.96557871 0.96557871 0.92961859\n", 928 | " 0.92986156 0.93374914 0.91876576 0.94330611 0.94306314 0.94954244\n", 929 | " 0.96549772 0.96023329 0.9600713 0.95974734 0.96776548 0.98242489\n", 930 | " 0.97513568 0.99870414 1. 0.9935207 0.98169597 0.98201994\n", 931 | " 0.9591804 0.93399212 0.93723177 0.90847987 0.90046173 0.90418733\n", 932 | " 0.90702202 0.84806038 0.81558288 0.86855117 0.84028522 0.83227277\n", 933 | " 0.82695502 0.82324213 0.82070053 0.81907862]\n", 934 | "5 day output [[0.818208]]\n", 935 | "6 day input [0.76747407 0.78845081 0.79727886 0.78958468 0.79638795 0.79387722\n", 936 | " 0.79930364 0.79120451 0.80667384 0.80594492 0.81031845 0.8108044\n", 937 | " 0.81606883 0.81161431 0.81963245 0.84303892 0.84781741 0.84206703\n", 938 | " 0.81145233 0.81363909 0.81299116 0.82052335 0.81493495 0.82303408\n", 939 | " 0.86871315 0.89843695 0.91722692 0.8998138 0.90969474 0.9452499\n", 940 | " 0.95942337 0.96395889 0.97554064 0.97262495 0.96282501 0.95715562\n", 941 | " 0.93585492 0.91755089 0.93391113 0.92621695 0.9248401 0.95043334\n", 942 | " 0.96517375 0.96525475 0.95812751 0.9498664 0.92079054 0.93998547\n", 943 | " 0.93350617 0.92338226 0.9220864 0.91698395 0.91949468 0.91989964\n", 944 | " 0.94662675 0.9387706 0.9433871 0.94298215 0.95715562 0.97699848\n", 945 | " 0.96177212 0.96023329 0.96557871 0.96557871 0.92961859 0.92986156\n", 946 | " 0.93374914 0.91876576 0.94330611 0.94306314 0.94954244 0.96549772\n", 947 | " 0.96023329 0.9600713 0.95974734 0.96776548 0.98242489 0.97513568\n", 948 | " 0.99870414 1. 0.9935207 0.98169597 0.98201994 0.9591804\n", 949 | " 0.93399212 0.93723177 0.90847987 0.90046173 0.90418733 0.90702202\n", 950 | " 0.84806038 0.81558288 0.86855117 0.84028522 0.83227277 0.82695502\n", 951 | " 0.82324213 0.82070053 0.81907862 0.81820798]\n", 952 | "6 day output [[0.8179517]]\n", 953 | "7 day input [0.78845081 0.79727886 0.78958468 0.79638795 0.79387722 0.79930364\n", 954 | " 0.79120451 0.80667384 0.80594492 0.81031845 0.8108044 0.81606883\n", 955 | " 0.81161431 0.81963245 0.84303892 0.84781741 0.84206703 0.81145233\n", 956 | " 0.81363909 0.81299116 0.82052335 0.81493495 0.82303408 0.86871315\n", 957 | " 0.89843695 0.91722692 0.8998138 0.90969474 0.9452499 0.95942337\n", 958 | " 0.96395889 0.97554064 0.97262495 0.96282501 0.95715562 0.93585492\n", 959 | " 0.91755089 0.93391113 0.92621695 0.9248401 0.95043334 0.96517375\n", 960 | " 0.96525475 0.95812751 0.9498664 0.92079054 0.93998547 0.93350617\n", 961 | " 0.92338226 0.9220864 0.91698395 0.91949468 0.91989964 0.94662675\n", 962 | " 0.9387706 0.9433871 0.94298215 0.95715562 0.97699848 0.96177212\n", 963 | " 0.96023329 0.96557871 0.96557871 0.92961859 0.92986156 0.93374914\n", 964 | " 0.91876576 0.94330611 0.94306314 0.94954244 0.96549772 0.96023329\n", 965 | " 0.9600713 0.95974734 0.96776548 0.98242489 0.97513568 0.99870414\n", 966 | " 1. 0.9935207 0.98169597 0.98201994 0.9591804 0.93399212\n", 967 | " 0.93723177 0.90847987 0.90046173 0.90418733 0.90702202 0.84806038\n", 968 | " 0.81558288 0.86855117 0.84028522 0.83227277 0.82695502 0.82324213\n", 969 | " 0.82070053 0.81907862 0.81820798 0.81795168]\n", 970 | "7 day output [[0.8181833]]\n", 971 | "8 day input [0.79727886 0.78958468 0.79638795 0.79387722 0.79930364 0.79120451\n", 972 | " 0.80667384 0.80594492 0.81031845 0.8108044 0.81606883 0.81161431\n", 973 | " 0.81963245 0.84303892 0.84781741 0.84206703 0.81145233 0.81363909\n", 974 | " 0.81299116 0.82052335 0.81493495 0.82303408 0.86871315 0.89843695\n", 975 | " 0.91722692 0.8998138 0.90969474 0.9452499 0.95942337 0.96395889\n", 976 | " 0.97554064 0.97262495 0.96282501 0.95715562 0.93585492 0.91755089\n", 977 | " 0.93391113 0.92621695 0.9248401 0.95043334 0.96517375 0.96525475\n", 978 | " 0.95812751 0.9498664 0.92079054 0.93998547 0.93350617 0.92338226\n", 979 | " 0.9220864 0.91698395 0.91949468 0.91989964 0.94662675 0.9387706\n", 980 | " 0.9433871 0.94298215 0.95715562 0.97699848 0.96177212 0.96023329\n", 981 | " 0.96557871 0.96557871 0.92961859 0.92986156 0.93374914 0.91876576\n", 982 | " 0.94330611 0.94306314 0.94954244 0.96549772 0.96023329 0.9600713\n", 983 | " 0.95974734 0.96776548 0.98242489 0.97513568 0.99870414 1.\n", 984 | " 0.9935207 0.98169597 0.98201994 0.9591804 0.93399212 0.93723177\n", 985 | " 0.90847987 0.90046173 0.90418733 0.90702202 0.84806038 0.81558288\n", 986 | " 0.86855117 0.84028522 0.83227277 0.82695502 0.82324213 0.82070053\n", 987 | " 0.81907862 0.81820798 0.81795168 0.8181833 ]\n", 988 | "8 day output [[0.81878185]]\n", 989 | "9 day input [0.78958468 0.79638795 0.79387722 0.79930364 0.79120451 0.80667384\n", 990 | " 0.80594492 0.81031845 0.8108044 0.81606883 0.81161431 0.81963245\n", 991 | " 0.84303892 0.84781741 0.84206703 0.81145233 0.81363909 0.81299116\n", 992 | " 0.82052335 0.81493495 0.82303408 0.86871315 0.89843695 0.91722692\n", 993 | " 0.8998138 0.90969474 0.9452499 0.95942337 0.96395889 0.97554064\n", 994 | " 0.97262495 0.96282501 0.95715562 0.93585492 0.91755089 0.93391113\n", 995 | " 0.92621695 0.9248401 0.95043334 0.96517375 0.96525475 0.95812751\n", 996 | " 0.9498664 0.92079054 0.93998547 0.93350617 0.92338226 0.9220864\n", 997 | " 0.91698395 0.91949468 0.91989964 0.94662675 0.9387706 0.9433871\n", 998 | " 0.94298215 0.95715562 0.97699848 0.96177212 0.96023329 0.96557871\n", 999 | " 0.96557871 0.92961859 0.92986156 0.93374914 0.91876576 0.94330611\n", 1000 | " 0.94306314 0.94954244 0.96549772 0.96023329 0.9600713 0.95974734\n", 1001 | " 0.96776548 0.98242489 0.97513568 0.99870414 1. 0.9935207\n", 1002 | " 0.98169597 0.98201994 0.9591804 0.93399212 0.93723177 0.90847987\n", 1003 | " 0.90046173 0.90418733 0.90702202 0.84806038 0.81558288 0.86855117\n", 1004 | " 0.84028522 0.83227277 0.82695502 0.82324213 0.82070053 0.81907862\n", 1005 | " 0.81820798 0.81795168 0.8181833 0.81878185]\n", 1006 | "9 day output [[0.8196336]]\n", 1007 | "10 day input [0.79638795 0.79387722 0.79930364 0.79120451 0.80667384 0.80594492\n", 1008 | " 0.81031845 0.8108044 0.81606883 0.81161431 0.81963245 0.84303892\n", 1009 | " 0.84781741 0.84206703 0.81145233 0.81363909 0.81299116 0.82052335\n", 1010 | " 0.81493495 0.82303408 0.86871315 0.89843695 0.91722692 0.8998138\n", 1011 | " 0.90969474 0.9452499 0.95942337 0.96395889 0.97554064 0.97262495\n", 1012 | " 0.96282501 0.95715562 0.93585492 0.91755089 0.93391113 0.92621695\n", 1013 | " 0.9248401 0.95043334 0.96517375 0.96525475 0.95812751 0.9498664\n", 1014 | " 0.92079054 0.93998547 0.93350617 0.92338226 0.9220864 0.91698395\n", 1015 | " 0.91949468 0.91989964 0.94662675 0.9387706 0.9433871 0.94298215\n", 1016 | " 0.95715562 0.97699848 0.96177212 0.96023329 0.96557871 0.96557871\n", 1017 | " 0.92961859 0.92986156 0.93374914 0.91876576 0.94330611 0.94306314\n", 1018 | " 0.94954244 0.96549772 0.96023329 0.9600713 0.95974734 0.96776548\n", 1019 | " 0.98242489 0.97513568 0.99870414 1. 0.9935207 0.98169597\n", 1020 | " 0.98201994 0.9591804 0.93399212 0.93723177 0.90847987 0.90046173\n", 1021 | " 0.90418733 0.90702202 0.84806038 0.81558288 0.86855117 0.84028522\n", 1022 | " 0.83227277 0.82695502 0.82324213 0.82070053 0.81907862 0.81820798\n", 1023 | " 0.81795168 0.8181833 0.81878185 0.8196336 ]\n", 1024 | "10 day output [[0.82063514]]\n", 1025 | "11 day input [0.79387722 0.79930364 0.79120451 0.80667384 0.80594492 0.81031845\n", 1026 | " 0.8108044 0.81606883 0.81161431 0.81963245 0.84303892 0.84781741\n", 1027 | " 0.84206703 0.81145233 0.81363909 0.81299116 0.82052335 0.81493495\n", 1028 | " 0.82303408 0.86871315 0.89843695 0.91722692 0.8998138 0.90969474\n", 1029 | " 0.9452499 0.95942337 0.96395889 0.97554064 0.97262495 0.96282501\n", 1030 | " 0.95715562 0.93585492 0.91755089 0.93391113 0.92621695 0.9248401\n", 1031 | " 0.95043334 0.96517375 0.96525475 0.95812751 0.9498664 0.92079054\n", 1032 | " 0.93998547 0.93350617 0.92338226 0.9220864 0.91698395 0.91949468\n", 1033 | " 0.91989964 0.94662675 0.9387706 0.9433871 0.94298215 0.95715562\n", 1034 | " 0.97699848 0.96177212 0.96023329 0.96557871 0.96557871 0.92961859\n", 1035 | " 0.92986156 0.93374914 0.91876576 0.94330611 0.94306314 0.94954244\n", 1036 | " 0.96549772 0.96023329 0.9600713 0.95974734 0.96776548 0.98242489\n", 1037 | " 0.97513568 0.99870414 1. 0.9935207 0.98169597 0.98201994\n", 1038 | " 0.9591804 0.93399212 0.93723177 0.90847987 0.90046173 0.90418733\n", 1039 | " 0.90702202 0.84806038 0.81558288 0.86855117 0.84028522 0.83227277\n", 1040 | " 0.82695502 0.82324213 0.82070053 0.81907862 0.81820798 0.81795168\n", 1041 | " 0.8181833 0.81878185 0.8196336 0.82063514]\n", 1042 | "11 day output [[0.8216959]]\n", 1043 | "12 day input [0.79930364 0.79120451 0.80667384 0.80594492 0.81031845 0.8108044\n", 1044 | " 0.81606883 0.81161431 0.81963245 0.84303892 0.84781741 0.84206703\n", 1045 | " 0.81145233 0.81363909 0.81299116 0.82052335 0.81493495 0.82303408\n", 1046 | " 0.86871315 0.89843695 0.91722692 0.8998138 0.90969474 0.9452499\n", 1047 | " 0.95942337 0.96395889 0.97554064 0.97262495 0.96282501 0.95715562\n", 1048 | " 0.93585492 0.91755089 0.93391113 0.92621695 0.9248401 0.95043334\n", 1049 | " 0.96517375 0.96525475 0.95812751 0.9498664 0.92079054 0.93998547\n", 1050 | " 0.93350617 0.92338226 0.9220864 0.91698395 0.91949468 0.91989964\n", 1051 | " 0.94662675 0.9387706 0.9433871 0.94298215 0.95715562 0.97699848\n", 1052 | " 0.96177212 0.96023329 0.96557871 0.96557871 0.92961859 0.92986156\n", 1053 | " 0.93374914 0.91876576 0.94330611 0.94306314 0.94954244 0.96549772\n", 1054 | " 0.96023329 0.9600713 0.95974734 0.96776548 0.98242489 0.97513568\n", 1055 | " 0.99870414 1. 0.9935207 0.98169597 0.98201994 0.9591804\n", 1056 | " 0.93399212 0.93723177 0.90847987 0.90046173 0.90418733 0.90702202\n", 1057 | " 0.84806038 0.81558288 0.86855117 0.84028522 0.83227277 0.82695502\n", 1058 | " 0.82324213 0.82070053 0.81907862 0.81820798 0.81795168 0.8181833\n", 1059 | " 0.81878185 0.8196336 0.82063514 0.82169592]\n", 1060 | "12 day output [[0.8227393]]\n", 1061 | "13 day input [0.79120451 0.80667384 0.80594492 0.81031845 0.8108044 0.81606883\n", 1062 | " 0.81161431 0.81963245 0.84303892 0.84781741 0.84206703 0.81145233\n", 1063 | " 0.81363909 0.81299116 0.82052335 0.81493495 0.82303408 0.86871315\n", 1064 | " 0.89843695 0.91722692 0.8998138 0.90969474 0.9452499 0.95942337\n", 1065 | " 0.96395889 0.97554064 0.97262495 0.96282501 0.95715562 0.93585492\n", 1066 | " 0.91755089 0.93391113 0.92621695 0.9248401 0.95043334 0.96517375\n", 1067 | " 0.96525475 0.95812751 0.9498664 0.92079054 0.93998547 0.93350617\n", 1068 | " 0.92338226 0.9220864 0.91698395 0.91949468 0.91989964 0.94662675\n", 1069 | " 0.9387706 0.9433871 0.94298215 0.95715562 0.97699848 0.96177212\n", 1070 | " 0.96023329 0.96557871 0.96557871 0.92961859 0.92986156 0.93374914\n", 1071 | " 0.91876576 0.94330611 0.94306314 0.94954244 0.96549772 0.96023329\n", 1072 | " 0.9600713 0.95974734 0.96776548 0.98242489 0.97513568 0.99870414\n", 1073 | " 1. 0.9935207 0.98169597 0.98201994 0.9591804 0.93399212\n", 1074 | " 0.93723177 0.90847987 0.90046173 0.90418733 0.90702202 0.84806038\n", 1075 | " 0.81558288 0.86855117 0.84028522 0.83227277 0.82695502 0.82324213\n", 1076 | " 0.82070053 0.81907862 0.81820798 0.81795168 0.8181833 0.81878185\n", 1077 | " 0.8196336 0.82063514 0.82169592 0.8227393 ]\n", 1078 | "13 day output [[0.82370317]]\n", 1079 | "14 day input [0.80667384 0.80594492 0.81031845 0.8108044 0.81606883 0.81161431\n", 1080 | " 0.81963245 0.84303892 0.84781741 0.84206703 0.81145233 0.81363909\n", 1081 | " 0.81299116 0.82052335 0.81493495 0.82303408 0.86871315 0.89843695\n", 1082 | " 0.91722692 0.8998138 0.90969474 0.9452499 0.95942337 0.96395889\n", 1083 | " 0.97554064 0.97262495 0.96282501 0.95715562 0.93585492 0.91755089\n", 1084 | " 0.93391113 0.92621695 0.9248401 0.95043334 0.96517375 0.96525475\n", 1085 | " 0.95812751 0.9498664 0.92079054 0.93998547 0.93350617 0.92338226\n", 1086 | " 0.9220864 0.91698395 0.91949468 0.91989964 0.94662675 0.9387706\n", 1087 | " 0.9433871 0.94298215 0.95715562 0.97699848 0.96177212 0.96023329\n", 1088 | " 0.96557871 0.96557871 0.92961859 0.92986156 0.93374914 0.91876576\n", 1089 | " 0.94330611 0.94306314 0.94954244 0.96549772 0.96023329 0.9600713\n", 1090 | " 0.95974734 0.96776548 0.98242489 0.97513568 0.99870414 1.\n", 1091 | " 0.9935207 0.98169597 0.98201994 0.9591804 0.93399212 0.93723177\n", 1092 | " 0.90847987 0.90046173 0.90418733 0.90702202 0.84806038 0.81558288\n", 1093 | " 0.86855117 0.84028522 0.83227277 0.82695502 0.82324213 0.82070053\n", 1094 | " 0.81907862 0.81820798 0.81795168 0.8181833 0.81878185 0.8196336\n", 1095 | " 0.82063514 0.82169592 0.8227393 0.82370317]\n", 1096 | "14 day output [[0.8245392]]\n", 1097 | "15 day input [0.80594492 0.81031845 0.8108044 0.81606883 0.81161431 0.81963245\n", 1098 | " 0.84303892 0.84781741 0.84206703 0.81145233 0.81363909 0.81299116\n", 1099 | " 0.82052335 0.81493495 0.82303408 0.86871315 0.89843695 0.91722692\n", 1100 | " 0.8998138 0.90969474 0.9452499 0.95942337 0.96395889 0.97554064\n", 1101 | " 0.97262495 0.96282501 0.95715562 0.93585492 0.91755089 0.93391113\n", 1102 | " 0.92621695 0.9248401 0.95043334 0.96517375 0.96525475 0.95812751\n", 1103 | " 0.9498664 0.92079054 0.93998547 0.93350617 0.92338226 0.9220864\n", 1104 | " 0.91698395 0.91949468 0.91989964 0.94662675 0.9387706 0.9433871\n", 1105 | " 0.94298215 0.95715562 0.97699848 0.96177212 0.96023329 0.96557871\n", 1106 | " 0.96557871 0.92961859 0.92986156 0.93374914 0.91876576 0.94330611\n", 1107 | " 0.94306314 0.94954244 0.96549772 0.96023329 0.9600713 0.95974734\n", 1108 | " 0.96776548 0.98242489 0.97513568 0.99870414 1. 0.9935207\n", 1109 | " 0.98169597 0.98201994 0.9591804 0.93399212 0.93723177 0.90847987\n", 1110 | " 0.90046173 0.90418733 0.90702202 0.84806038 0.81558288 0.86855117\n", 1111 | " 0.84028522 0.83227277 0.82695502 0.82324213 0.82070053 0.81907862\n", 1112 | " 0.81820798 0.81795168 0.8181833 0.81878185 0.8196336 0.82063514\n", 1113 | " 0.82169592 0.8227393 0.82370317 0.82453918]\n", 1114 | "15 day output [[0.8252124]]\n", 1115 | "16 day input [0.81031845 0.8108044 0.81606883 0.81161431 0.81963245 0.84303892\n", 1116 | " 0.84781741 0.84206703 0.81145233 0.81363909 0.81299116 0.82052335\n", 1117 | " 0.81493495 0.82303408 0.86871315 0.89843695 0.91722692 0.8998138\n", 1118 | " 0.90969474 0.9452499 0.95942337 0.96395889 0.97554064 0.97262495\n", 1119 | " 0.96282501 0.95715562 0.93585492 0.91755089 0.93391113 0.92621695\n", 1120 | " 0.9248401 0.95043334 0.96517375 0.96525475 0.95812751 0.9498664\n", 1121 | " 0.92079054 0.93998547 0.93350617 0.92338226 0.9220864 0.91698395\n", 1122 | " 0.91949468 0.91989964 0.94662675 0.9387706 0.9433871 0.94298215\n", 1123 | " 0.95715562 0.97699848 0.96177212 0.96023329 0.96557871 0.96557871\n", 1124 | " 0.92961859 0.92986156 0.93374914 0.91876576 0.94330611 0.94306314\n", 1125 | " 0.94954244 0.96549772 0.96023329 0.9600713 0.95974734 0.96776548\n", 1126 | " 0.98242489 0.97513568 0.99870414 1. 0.9935207 0.98169597\n", 1127 | " 0.98201994 0.9591804 0.93399212 0.93723177 0.90847987 0.90046173\n", 1128 | " 0.90418733 0.90702202 0.84806038 0.81558288 0.86855117 0.84028522\n", 1129 | " 0.83227277 0.82695502 0.82324213 0.82070053 0.81907862 0.81820798\n", 1130 | " 0.81795168 0.8181833 0.81878185 0.8196336 0.82063514 0.82169592\n", 1131 | " 0.8227393 0.82370317 0.82453918 0.82521242]\n", 1132 | "16 day output [[0.8256999]]\n", 1133 | "17 day input [0.8108044 0.81606883 0.81161431 0.81963245 0.84303892 0.84781741\n", 1134 | " 0.84206703 0.81145233 0.81363909 0.81299116 0.82052335 0.81493495\n", 1135 | " 0.82303408 0.86871315 0.89843695 0.91722692 0.8998138 0.90969474\n", 1136 | " 0.9452499 0.95942337 0.96395889 0.97554064 0.97262495 0.96282501\n", 1137 | " 0.95715562 0.93585492 0.91755089 0.93391113 0.92621695 0.9248401\n", 1138 | " 0.95043334 0.96517375 0.96525475 0.95812751 0.9498664 0.92079054\n", 1139 | " 0.93998547 0.93350617 0.92338226 0.9220864 0.91698395 0.91949468\n", 1140 | " 0.91989964 0.94662675 0.9387706 0.9433871 0.94298215 0.95715562\n", 1141 | " 0.97699848 0.96177212 0.96023329 0.96557871 0.96557871 0.92961859\n", 1142 | " 0.92986156 0.93374914 0.91876576 0.94330611 0.94306314 0.94954244\n", 1143 | " 0.96549772 0.96023329 0.9600713 0.95974734 0.96776548 0.98242489\n", 1144 | " 0.97513568 0.99870414 1. 0.9935207 0.98169597 0.98201994\n", 1145 | " 0.9591804 0.93399212 0.93723177 0.90847987 0.90046173 0.90418733\n", 1146 | " 0.90702202 0.84806038 0.81558288 0.86855117 0.84028522 0.83227277\n", 1147 | " 0.82695502 0.82324213 0.82070053 0.81907862 0.81820798 0.81795168\n", 1148 | " 0.8181833 0.81878185 0.8196336 0.82063514 0.82169592 0.8227393\n", 1149 | " 0.82370317 0.82453918 0.82521242 0.82569993]\n", 1150 | "17 day output [[0.8259902]]\n", 1151 | "18 day input [0.81606883 0.81161431 0.81963245 0.84303892 0.84781741 0.84206703\n", 1152 | " 0.81145233 0.81363909 0.81299116 0.82052335 0.81493495 0.82303408\n", 1153 | " 0.86871315 0.89843695 0.91722692 0.8998138 0.90969474 0.9452499\n", 1154 | " 0.95942337 0.96395889 0.97554064 0.97262495 0.96282501 0.95715562\n", 1155 | " 0.93585492 0.91755089 0.93391113 0.92621695 0.9248401 0.95043334\n", 1156 | " 0.96517375 0.96525475 0.95812751 0.9498664 0.92079054 0.93998547\n", 1157 | " 0.93350617 0.92338226 0.9220864 0.91698395 0.91949468 0.91989964\n", 1158 | " 0.94662675 0.9387706 0.9433871 0.94298215 0.95715562 0.97699848\n", 1159 | " 0.96177212 0.96023329 0.96557871 0.96557871 0.92961859 0.92986156\n", 1160 | " 0.93374914 0.91876576 0.94330611 0.94306314 0.94954244 0.96549772\n", 1161 | " 0.96023329 0.9600713 0.95974734 0.96776548 0.98242489 0.97513568\n", 1162 | " 0.99870414 1. 0.9935207 0.98169597 0.98201994 0.9591804\n", 1163 | " 0.93399212 0.93723177 0.90847987 0.90046173 0.90418733 0.90702202\n", 1164 | " 0.84806038 0.81558288 0.86855117 0.84028522 0.83227277 0.82695502\n", 1165 | " 0.82324213 0.82070053 0.81907862 0.81820798 0.81795168 0.8181833\n", 1166 | " 0.81878185 0.8196336 0.82063514 0.82169592 0.8227393 0.82370317\n", 1167 | " 0.82453918 0.82521242 0.82569993 0.8259902 ]\n", 1168 | "18 day output [[0.8260796]]\n", 1169 | "19 day input [0.81161431 0.81963245 0.84303892 0.84781741 0.84206703 0.81145233\n", 1170 | " 0.81363909 0.81299116 0.82052335 0.81493495 0.82303408 0.86871315\n", 1171 | " 0.89843695 0.91722692 0.8998138 0.90969474 0.9452499 0.95942337\n", 1172 | " 0.96395889 0.97554064 0.97262495 0.96282501 0.95715562 0.93585492\n", 1173 | " 0.91755089 0.93391113 0.92621695 0.9248401 0.95043334 0.96517375\n", 1174 | " 0.96525475 0.95812751 0.9498664 0.92079054 0.93998547 0.93350617\n", 1175 | " 0.92338226 0.9220864 0.91698395 0.91949468 0.91989964 0.94662675\n", 1176 | " 0.9387706 0.9433871 0.94298215 0.95715562 0.97699848 0.96177212\n", 1177 | " 0.96023329 0.96557871 0.96557871 0.92961859 0.92986156 0.93374914\n", 1178 | " 0.91876576 0.94330611 0.94306314 0.94954244 0.96549772 0.96023329\n", 1179 | " 0.9600713 0.95974734 0.96776548 0.98242489 0.97513568 0.99870414\n", 1180 | " 1. 0.9935207 0.98169597 0.98201994 0.9591804 0.93399212\n", 1181 | " 0.93723177 0.90847987 0.90046173 0.90418733 0.90702202 0.84806038\n", 1182 | " 0.81558288 0.86855117 0.84028522 0.83227277 0.82695502 0.82324213\n", 1183 | " 0.82070053 0.81907862 0.81820798 0.81795168 0.8181833 0.81878185\n", 1184 | " 0.8196336 0.82063514 0.82169592 0.8227393 0.82370317 0.82453918\n", 1185 | " 0.82521242 0.82569993 0.8259902 0.82607961]\n", 1186 | "19 day output [[0.82597315]]\n", 1187 | "20 day input [0.81963245 0.84303892 0.84781741 0.84206703 0.81145233 0.81363909\n", 1188 | " 0.81299116 0.82052335 0.81493495 0.82303408 0.86871315 0.89843695\n", 1189 | " 0.91722692 0.8998138 0.90969474 0.9452499 0.95942337 0.96395889\n", 1190 | " 0.97554064 0.97262495 0.96282501 0.95715562 0.93585492 0.91755089\n", 1191 | " 0.93391113 0.92621695 0.9248401 0.95043334 0.96517375 0.96525475\n", 1192 | " 0.95812751 0.9498664 0.92079054 0.93998547 0.93350617 0.92338226\n", 1193 | " 0.9220864 0.91698395 0.91949468 0.91989964 0.94662675 0.9387706\n", 1194 | " 0.9433871 0.94298215 0.95715562 0.97699848 0.96177212 0.96023329\n", 1195 | " 0.96557871 0.96557871 0.92961859 0.92986156 0.93374914 0.91876576\n", 1196 | " 0.94330611 0.94306314 0.94954244 0.96549772 0.96023329 0.9600713\n", 1197 | " 0.95974734 0.96776548 0.98242489 0.97513568 0.99870414 1.\n", 1198 | " 0.9935207 0.98169597 0.98201994 0.9591804 0.93399212 0.93723177\n", 1199 | " 0.90847987 0.90046173 0.90418733 0.90702202 0.84806038 0.81558288\n", 1200 | " 0.86855117 0.84028522 0.83227277 0.82695502 0.82324213 0.82070053\n", 1201 | " 0.81907862 0.81820798 0.81795168 0.8181833 0.81878185 0.8196336\n", 1202 | " 0.82063514 0.82169592 0.8227393 0.82370317 0.82453918 0.82521242\n", 1203 | " 0.82569993 0.8259902 0.82607961 0.82597315]\n", 1204 | "20 day output [[0.8256819]]\n", 1205 | "21 day input [0.84303892 0.84781741 0.84206703 0.81145233 0.81363909 0.81299116\n", 1206 | " 0.82052335 0.81493495 0.82303408 0.86871315 0.89843695 0.91722692\n", 1207 | " 0.8998138 0.90969474 0.9452499 0.95942337 0.96395889 0.97554064\n", 1208 | " 0.97262495 0.96282501 0.95715562 0.93585492 0.91755089 0.93391113\n", 1209 | " 0.92621695 0.9248401 0.95043334 0.96517375 0.96525475 0.95812751\n", 1210 | " 0.9498664 0.92079054 0.93998547 0.93350617 0.92338226 0.9220864\n", 1211 | " 0.91698395 0.91949468 0.91989964 0.94662675 0.9387706 0.9433871\n", 1212 | " 0.94298215 0.95715562 0.97699848 0.96177212 0.96023329 0.96557871\n", 1213 | " 0.96557871 0.92961859 0.92986156 0.93374914 0.91876576 0.94330611\n", 1214 | " 0.94306314 0.94954244 0.96549772 0.96023329 0.9600713 0.95974734\n", 1215 | " 0.96776548 0.98242489 0.97513568 0.99870414 1. 0.9935207\n", 1216 | " 0.98169597 0.98201994 0.9591804 0.93399212 0.93723177 0.90847987\n", 1217 | " 0.90046173 0.90418733 0.90702202 0.84806038 0.81558288 0.86855117\n", 1218 | " 0.84028522 0.83227277 0.82695502 0.82324213 0.82070053 0.81907862\n", 1219 | " 0.81820798 0.81795168 0.8181833 0.81878185 0.8196336 0.82063514\n", 1220 | " 0.82169592 0.8227393 0.82370317 0.82453918 0.82521242 0.82569993\n", 1221 | " 0.8259902 0.82607961 0.82597315 0.82568192]\n", 1222 | "21 day output [[0.8252218]]\n", 1223 | "22 day input [0.84781741 0.84206703 0.81145233 0.81363909 0.81299116 0.82052335\n", 1224 | " 0.81493495 0.82303408 0.86871315 0.89843695 0.91722692 0.8998138\n", 1225 | " 0.90969474 0.9452499 0.95942337 0.96395889 0.97554064 0.97262495\n", 1226 | " 0.96282501 0.95715562 0.93585492 0.91755089 0.93391113 0.92621695\n", 1227 | " 0.9248401 0.95043334 0.96517375 0.96525475 0.95812751 0.9498664\n", 1228 | " 0.92079054 0.93998547 0.93350617 0.92338226 0.9220864 0.91698395\n", 1229 | " 0.91949468 0.91989964 0.94662675 0.9387706 0.9433871 0.94298215\n", 1230 | " 0.95715562 0.97699848 0.96177212 0.96023329 0.96557871 0.96557871\n", 1231 | " 0.92961859 0.92986156 0.93374914 0.91876576 0.94330611 0.94306314\n", 1232 | " 0.94954244 0.96549772 0.96023329 0.9600713 0.95974734 0.96776548\n", 1233 | " 0.98242489 0.97513568 0.99870414 1. 0.9935207 0.98169597\n", 1234 | " 0.98201994 0.9591804 0.93399212 0.93723177 0.90847987 0.90046173\n", 1235 | " 0.90418733 0.90702202 0.84806038 0.81558288 0.86855117 0.84028522\n", 1236 | " 0.83227277 0.82695502 0.82324213 0.82070053 0.81907862 0.81820798\n", 1237 | " 0.81795168 0.8181833 0.81878185 0.8196336 0.82063514 0.82169592\n", 1238 | " 0.8227393 0.82370317 0.82453918 0.82521242 0.82569993 0.8259902\n", 1239 | " 0.82607961 0.82597315 0.82568192 0.82522178]\n", 1240 | "22 day output [[0.8246119]]\n", 1241 | "23 day input [0.84206703 0.81145233 0.81363909 0.81299116 0.82052335 0.81493495\n", 1242 | " 0.82303408 0.86871315 0.89843695 0.91722692 0.8998138 0.90969474\n", 1243 | " 0.9452499 0.95942337 0.96395889 0.97554064 0.97262495 0.96282501\n", 1244 | " 0.95715562 0.93585492 0.91755089 0.93391113 0.92621695 0.9248401\n", 1245 | " 0.95043334 0.96517375 0.96525475 0.95812751 0.9498664 0.92079054\n", 1246 | " 0.93998547 0.93350617 0.92338226 0.9220864 0.91698395 0.91949468\n", 1247 | " 0.91989964 0.94662675 0.9387706 0.9433871 0.94298215 0.95715562\n", 1248 | " 0.97699848 0.96177212 0.96023329 0.96557871 0.96557871 0.92961859\n", 1249 | " 0.92986156 0.93374914 0.91876576 0.94330611 0.94306314 0.94954244\n", 1250 | " 0.96549772 0.96023329 0.9600713 0.95974734 0.96776548 0.98242489\n", 1251 | " 0.97513568 0.99870414 1. 0.9935207 0.98169597 0.98201994\n", 1252 | " 0.9591804 0.93399212 0.93723177 0.90847987 0.90046173 0.90418733\n", 1253 | " 0.90702202 0.84806038 0.81558288 0.86855117 0.84028522 0.83227277\n", 1254 | " 0.82695502 0.82324213 0.82070053 0.81907862 0.81820798 0.81795168\n", 1255 | " 0.8181833 0.81878185 0.8196336 0.82063514 0.82169592 0.8227393\n", 1256 | " 0.82370317 0.82453918 0.82521242 0.82569993 0.8259902 0.82607961\n", 1257 | " 0.82597315 0.82568192 0.82522178 0.8246119 ]\n", 1258 | "23 day output [[0.8238733]]\n", 1259 | "24 day input [0.81145233 0.81363909 0.81299116 0.82052335 0.81493495 0.82303408\n", 1260 | " 0.86871315 0.89843695 0.91722692 0.8998138 0.90969474 0.9452499\n", 1261 | " 0.95942337 0.96395889 0.97554064 0.97262495 0.96282501 0.95715562\n", 1262 | " 0.93585492 0.91755089 0.93391113 0.92621695 0.9248401 0.95043334\n", 1263 | " 0.96517375 0.96525475 0.95812751 0.9498664 0.92079054 0.93998547\n", 1264 | " 0.93350617 0.92338226 0.9220864 0.91698395 0.91949468 0.91989964\n", 1265 | " 0.94662675 0.9387706 0.9433871 0.94298215 0.95715562 0.97699848\n", 1266 | " 0.96177212 0.96023329 0.96557871 0.96557871 0.92961859 0.92986156\n", 1267 | " 0.93374914 0.91876576 0.94330611 0.94306314 0.94954244 0.96549772\n", 1268 | " 0.96023329 0.9600713 0.95974734 0.96776548 0.98242489 0.97513568\n", 1269 | " 0.99870414 1. 0.9935207 0.98169597 0.98201994 0.9591804\n", 1270 | " 0.93399212 0.93723177 0.90847987 0.90046173 0.90418733 0.90702202\n", 1271 | " 0.84806038 0.81558288 0.86855117 0.84028522 0.83227277 0.82695502\n", 1272 | " 0.82324213 0.82070053 0.81907862 0.81820798 0.81795168 0.8181833\n", 1273 | " 0.81878185 0.8196336 0.82063514 0.82169592 0.8227393 0.82370317\n", 1274 | " 0.82453918 0.82521242 0.82569993 0.8259902 0.82607961 0.82597315\n", 1275 | " 0.82568192 0.82522178 0.8246119 0.82387328]\n", 1276 | "24 day output [[0.8230283]]\n", 1277 | "25 day input [0.81363909 0.81299116 0.82052335 0.81493495 0.82303408 0.86871315\n", 1278 | " 0.89843695 0.91722692 0.8998138 0.90969474 0.9452499 0.95942337\n", 1279 | " 0.96395889 0.97554064 0.97262495 0.96282501 0.95715562 0.93585492\n", 1280 | " 0.91755089 0.93391113 0.92621695 0.9248401 0.95043334 0.96517375\n", 1281 | " 0.96525475 0.95812751 0.9498664 0.92079054 0.93998547 0.93350617\n", 1282 | " 0.92338226 0.9220864 0.91698395 0.91949468 0.91989964 0.94662675\n", 1283 | " 0.9387706 0.9433871 0.94298215 0.95715562 0.97699848 0.96177212\n", 1284 | " 0.96023329 0.96557871 0.96557871 0.92961859 0.92986156 0.93374914\n", 1285 | " 0.91876576 0.94330611 0.94306314 0.94954244 0.96549772 0.96023329\n", 1286 | " 0.9600713 0.95974734 0.96776548 0.98242489 0.97513568 0.99870414\n", 1287 | " 1. 0.9935207 0.98169597 0.98201994 0.9591804 0.93399212\n", 1288 | " 0.93723177 0.90847987 0.90046173 0.90418733 0.90702202 0.84806038\n", 1289 | " 0.81558288 0.86855117 0.84028522 0.83227277 0.82695502 0.82324213\n", 1290 | " 0.82070053 0.81907862 0.81820798 0.81795168 0.8181833 0.81878185\n", 1291 | " 0.8196336 0.82063514 0.82169592 0.8227393 0.82370317 0.82453918\n", 1292 | " 0.82521242 0.82569993 0.8259902 0.82607961 0.82597315 0.82568192\n", 1293 | " 0.82522178 0.8246119 0.82387328 0.82302833]\n", 1294 | "25 day output [[0.8221]]\n", 1295 | "26 day input [0.81299116 0.82052335 0.81493495 0.82303408 0.86871315 0.89843695\n", 1296 | " 0.91722692 0.8998138 0.90969474 0.9452499 0.95942337 0.96395889\n", 1297 | " 0.97554064 0.97262495 0.96282501 0.95715562 0.93585492 0.91755089\n", 1298 | " 0.93391113 0.92621695 0.9248401 0.95043334 0.96517375 0.96525475\n", 1299 | " 0.95812751 0.9498664 0.92079054 0.93998547 0.93350617 0.92338226\n", 1300 | " 0.9220864 0.91698395 0.91949468 0.91989964 0.94662675 0.9387706\n", 1301 | " 0.9433871 0.94298215 0.95715562 0.97699848 0.96177212 0.96023329\n", 1302 | " 0.96557871 0.96557871 0.92961859 0.92986156 0.93374914 0.91876576\n", 1303 | " 0.94330611 0.94306314 0.94954244 0.96549772 0.96023329 0.9600713\n", 1304 | " 0.95974734 0.96776548 0.98242489 0.97513568 0.99870414 1.\n", 1305 | " 0.9935207 0.98169597 0.98201994 0.9591804 0.93399212 0.93723177\n", 1306 | " 0.90847987 0.90046173 0.90418733 0.90702202 0.84806038 0.81558288\n", 1307 | " 0.86855117 0.84028522 0.83227277 0.82695502 0.82324213 0.82070053\n", 1308 | " 0.81907862 0.81820798 0.81795168 0.8181833 0.81878185 0.8196336\n", 1309 | " 0.82063514 0.82169592 0.8227393 0.82370317 0.82453918 0.82521242\n", 1310 | " 0.82569993 0.8259902 0.82607961 0.82597315 0.82568192 0.82522178\n", 1311 | " 0.8246119 0.82387328 0.82302833 0.82209998]\n", 1312 | "26 day output [[0.8211101]]\n", 1313 | "27 day input [0.82052335 0.81493495 0.82303408 0.86871315 0.89843695 0.91722692\n", 1314 | " 0.8998138 0.90969474 0.9452499 0.95942337 0.96395889 0.97554064\n", 1315 | " 0.97262495 0.96282501 0.95715562 0.93585492 0.91755089 0.93391113\n", 1316 | " 0.92621695 0.9248401 0.95043334 0.96517375 0.96525475 0.95812751\n", 1317 | " 0.9498664 0.92079054 0.93998547 0.93350617 0.92338226 0.9220864\n", 1318 | " 0.91698395 0.91949468 0.91989964 0.94662675 0.9387706 0.9433871\n", 1319 | " 0.94298215 0.95715562 0.97699848 0.96177212 0.96023329 0.96557871\n", 1320 | " 0.96557871 0.92961859 0.92986156 0.93374914 0.91876576 0.94330611\n", 1321 | " 0.94306314 0.94954244 0.96549772 0.96023329 0.9600713 0.95974734\n", 1322 | " 0.96776548 0.98242489 0.97513568 0.99870414 1. 0.9935207\n", 1323 | " 0.98169597 0.98201994 0.9591804 0.93399212 0.93723177 0.90847987\n", 1324 | " 0.90046173 0.90418733 0.90702202 0.84806038 0.81558288 0.86855117\n", 1325 | " 0.84028522 0.83227277 0.82695502 0.82324213 0.82070053 0.81907862\n", 1326 | " 0.81820798 0.81795168 0.8181833 0.81878185 0.8196336 0.82063514\n", 1327 | " 0.82169592 0.8227393 0.82370317 0.82453918 0.82521242 0.82569993\n", 1328 | " 0.8259902 0.82607961 0.82597315 0.82568192 0.82522178 0.8246119\n", 1329 | " 0.82387328 0.82302833 0.82209998 0.82111013]\n", 1330 | "27 day output [[0.8200791]]\n", 1331 | "28 day input [0.81493495 0.82303408 0.86871315 0.89843695 0.91722692 0.8998138\n", 1332 | " 0.90969474 0.9452499 0.95942337 0.96395889 0.97554064 0.97262495\n", 1333 | " 0.96282501 0.95715562 0.93585492 0.91755089 0.93391113 0.92621695\n", 1334 | " 0.9248401 0.95043334 0.96517375 0.96525475 0.95812751 0.9498664\n", 1335 | " 0.92079054 0.93998547 0.93350617 0.92338226 0.9220864 0.91698395\n", 1336 | " 0.91949468 0.91989964 0.94662675 0.9387706 0.9433871 0.94298215\n", 1337 | " 0.95715562 0.97699848 0.96177212 0.96023329 0.96557871 0.96557871\n", 1338 | " 0.92961859 0.92986156 0.93374914 0.91876576 0.94330611 0.94306314\n", 1339 | " 0.94954244 0.96549772 0.96023329 0.9600713 0.95974734 0.96776548\n", 1340 | " 0.98242489 0.97513568 0.99870414 1. 0.9935207 0.98169597\n", 1341 | " 0.98201994 0.9591804 0.93399212 0.93723177 0.90847987 0.90046173\n", 1342 | " 0.90418733 0.90702202 0.84806038 0.81558288 0.86855117 0.84028522\n", 1343 | " 0.83227277 0.82695502 0.82324213 0.82070053 0.81907862 0.81820798\n", 1344 | " 0.81795168 0.8181833 0.81878185 0.8196336 0.82063514 0.82169592\n", 1345 | " 0.8227393 0.82370317 0.82453918 0.82521242 0.82569993 0.8259902\n", 1346 | " 0.82607961 0.82597315 0.82568192 0.82522178 0.8246119 0.82387328\n", 1347 | " 0.82302833 0.82209998 0.82111013 0.82007909]\n", 1348 | "28 day output [[0.81902635]]\n", 1349 | "29 day input [0.82303408 0.86871315 0.89843695 0.91722692 0.8998138 0.90969474\n", 1350 | " 0.9452499 0.95942337 0.96395889 0.97554064 0.97262495 0.96282501\n", 1351 | " 0.95715562 0.93585492 0.91755089 0.93391113 0.92621695 0.9248401\n", 1352 | " 0.95043334 0.96517375 0.96525475 0.95812751 0.9498664 0.92079054\n", 1353 | " 0.93998547 0.93350617 0.92338226 0.9220864 0.91698395 0.91949468\n", 1354 | " 0.91989964 0.94662675 0.9387706 0.9433871 0.94298215 0.95715562\n", 1355 | " 0.97699848 0.96177212 0.96023329 0.96557871 0.96557871 0.92961859\n", 1356 | " 0.92986156 0.93374914 0.91876576 0.94330611 0.94306314 0.94954244\n", 1357 | " 0.96549772 0.96023329 0.9600713 0.95974734 0.96776548 0.98242489\n", 1358 | " 0.97513568 0.99870414 1. 0.9935207 0.98169597 0.98201994\n", 1359 | " 0.9591804 0.93399212 0.93723177 0.90847987 0.90046173 0.90418733\n", 1360 | " 0.90702202 0.84806038 0.81558288 0.86855117 0.84028522 0.83227277\n", 1361 | " 0.82695502 0.82324213 0.82070053 0.81907862 0.81820798 0.81795168\n", 1362 | " 0.8181833 0.81878185 0.8196336 0.82063514 0.82169592 0.8227393\n", 1363 | " 0.82370317 0.82453918 0.82521242 0.82569993 0.8259902 0.82607961\n", 1364 | " 0.82597315 0.82568192 0.82522178 0.8246119 0.82387328 0.82302833\n", 1365 | " 0.82209998 0.82111013 0.82007909 0.81902635]\n", 1366 | "29 day output [[0.81796867]]\n", 1367 | "[[0.8322727680206299], [0.8269550204277039], [0.8232421278953552], [0.8207005262374878], [0.8190786242485046], [0.8182079792022705], [0.8179516792297363], [0.8181833028793335], [0.818781852722168], [0.8196336030960083], [0.8206351399421692], [0.8216959238052368], [0.82273930311203], [0.8237031698226929], [0.8245391845703125], [0.8252124190330505], [0.8256999254226685], [0.8259902000427246], [0.8260796070098877], [0.8259731531143188], [0.8256819248199463], [0.8252217769622803], [0.8246119022369385], [0.8238732814788818], [0.8230283260345459], [0.8220999836921692], [0.8211101293563843], [0.8200790882110596], [0.8190263509750366], [0.8179686665534973]]\n" 1368 | ] 1369 | } 1370 | ], 1371 | "source": [ 1372 | "from numpy import array\n", 1373 | "\n", 1374 | "lst_output=[]\n", 1375 | "n_steps=100\n", 1376 | "i=0\n", 1377 | "while(i<30):\n", 1378 | " \n", 1379 | " if(len(temp_input)>100):\n", 1380 | " \n", 1381 | " x_input=np.array(temp_input[1:])\n", 1382 | " print(\"{} day input {}\".format(i,x_input))\n", 1383 | " x_input=x_input.reshape(1,-1)\n", 1384 | " x_input = x_input.reshape((1, n_steps, 1))\n", 1385 | " yhat = model.predict(x_input, verbose=0)\n", 1386 | " print(\"{} day output {}\".format(i,yhat))\n", 1387 | " temp_input.extend(yhat[0].tolist())\n", 1388 | " temp_input=temp_input[1:]\n", 1389 | " lst_output.extend(yhat.tolist())\n", 1390 | " i=i+1\n", 1391 | " else:\n", 1392 | " x_input = x_input.reshape((1, n_steps,1))\n", 1393 | " yhat = model.predict(x_input, verbose=0)\n", 1394 | " print(yhat[0])\n", 1395 | " temp_input.extend(yhat[0].tolist())\n", 1396 | " print(len(temp_input))\n", 1397 | " lst_output.extend(yhat.tolist())\n", 1398 | " i=i+1\n", 1399 | " \n", 1400 | "\n", 1401 | "print(lst_output)" 1402 | ] 1403 | }, 1404 | { 1405 | "cell_type": "code", 1406 | "execution_count": 54, 1407 | "id": "32d5b15c", 1408 | "metadata": {}, 1409 | "outputs": [], 1410 | "source": [ 1411 | "new_day = np.arange(1,101)\n", 1412 | "pred_day = np.arange(101,131)\n" 1413 | ] 1414 | }, 1415 | { 1416 | "cell_type": "code", 1417 | "execution_count": 56, 1418 | "id": "c8d3be33", 1419 | "metadata": {}, 1420 | "outputs": [], 1421 | "source": [ 1422 | "import matplotlib.pyplot as plt" 1423 | ] 1424 | }, 1425 | { 1426 | "cell_type": "code", 1427 | "execution_count": 57, 1428 | "id": "6b58a6f2", 1429 | "metadata": {}, 1430 | "outputs": [ 1431 | { 1432 | "data": { 1433 | "text/plain": [ 1434 | "1259" 1435 | ] 1436 | }, 1437 | "execution_count": 57, 1438 | "metadata": {}, 1439 | "output_type": "execute_result" 1440 | } 1441 | ], 1442 | "source": [ 1443 | "len(df2)" 1444 | ] 1445 | }, 1446 | { 1447 | "cell_type": "code", 1448 | "execution_count": 58, 1449 | "id": "96998627", 1450 | "metadata": {}, 1451 | "outputs": [], 1452 | "source": [ 1453 | "df3 = df2.tolist()" 1454 | ] 1455 | }, 1456 | { 1457 | "cell_type": "code", 1458 | "execution_count": 59, 1459 | "id": "41876266", 1460 | "metadata": {}, 1461 | "outputs": [], 1462 | "source": [ 1463 | "df3.extend(lst_output)" 1464 | ] 1465 | }, 1466 | { 1467 | "cell_type": "code", 1468 | "execution_count": 60, 1469 | "id": "c8223f07", 1470 | "metadata": { 1471 | "scrolled": true 1472 | }, 1473 | "outputs": [ 1474 | { 1475 | "data": { 1476 | "text/plain": [ 1477 | "[]" 1478 | ] 1479 | }, 1480 | "execution_count": 60, 1481 | "metadata": {}, 1482 | "output_type": "execute_result" 1483 | }, 1484 | { 1485 | "data": { 1486 | "image/png": "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\n", 1487 | "text/plain": [ 1488 | "
" 1489 | ] 1490 | }, 1491 | "metadata": { 1492 | "needs_background": "light" 1493 | }, 1494 | "output_type": "display_data" 1495 | } 1496 | ], 1497 | "source": [ 1498 | "plt.plot(new_day,scaler.inverse_transform(df2[1159:]))\n", 1499 | "plt.plot(pred_day,scaler.inverse_transform(lst_output))" 1500 | ] 1501 | }, 1502 | { 1503 | "cell_type": "code", 1504 | "execution_count": 61, 1505 | "id": "e8999bbc", 1506 | "metadata": {}, 1507 | "outputs": [ 1508 | { 1509 | "data": { 1510 | "text/plain": [ 1511 | "[]" 1512 | ] 1513 | }, 1514 | "execution_count": 61, 1515 | "metadata": {}, 1516 | "output_type": "execute_result" 1517 | }, 1518 | { 1519 | "data": { 1520 | "image/png": "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\n", 1521 | "text/plain": [ 1522 | "
" 1523 | ] 1524 | }, 1525 | "metadata": { 1526 | "needs_background": "light" 1527 | }, 1528 | "output_type": "display_data" 1529 | } 1530 | ], 1531 | "source": [ 1532 | "df3=df2.tolist()\n", 1533 | "df3.extend(lst_output)\n", 1534 | "plt.plot(df3[1200:])" 1535 | ] 1536 | }, 1537 | { 1538 | "cell_type": "code", 1539 | "execution_count": null, 1540 | "id": "43c02ada", 1541 | "metadata": {}, 1542 | "outputs": [], 1543 | "source": [] 1544 | } 1545 | ], 1546 | "metadata": { 1547 | "kernelspec": { 1548 | "display_name": "Python 3", 1549 | "language": "python", 1550 | "name": "python3" 1551 | }, 1552 | "language_info": { 1553 | "codemirror_mode": { 1554 | "name": "ipython", 1555 | "version": 3 1556 | }, 1557 | "file_extension": ".py", 1558 | "mimetype": "text/x-python", 1559 | "name": "python", 1560 | "nbconvert_exporter": "python", 1561 | "pygments_lexer": "ipython3", 1562 | "version": "3.8.8" 1563 | } 1564 | }, 1565 | "nbformat": 4, 1566 | "nbformat_minor": 5 1567 | } 1568 | --------------------------------------------------------------------------------