models/failure_prediction/jnotebooks/CNN.ipynb

   1 {
   2  "cells": [
   3   {
   4    "cell_type": "markdown",
   5    "metadata": {
   6     "id": "ywp6YMCFQKEQ"
   7    },
   8    "source": [
   9     "Contributors: **Rohit Singh Rathaur, Girish L.** \n",
  10     "\n",
  11     "Copyright [2021](2021) [*Rohit Singh Rathaur, BIT Mesra and Girish L., CIT GUBBI, Karnataka*]\n",
  12     "\n",
  13     "Licensed under the Apache License, Version 2.0 (the \"License\");\n",
  14     "you may not use this file except in compliance with the License.\n",
  15     "You may obtain a copy of the License at\n",
  16     "\n",
  17     "    http://www.apache.org/licenses/LICENSE-2.0\n",
  18     "\n",
  19     "Unless required by applicable law or agreed to in writing, software\n",
  20     "distributed under the License is distributed on an \"AS IS\" BASIS,\n",
  21     "WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
  22     "See the License for the specific language governing permissions and\n",
  23     "limitations under the License."
  24    ]
  25   },
  26   {
  27    "cell_type": "code",
  28    "execution_count": null,
  29    "metadata": {
  30     "colab": {
  31      "base_uri": "https://localhost:8080/"
  32     },
  33     "id": "YQ6lT1e2hrx4",
  34     "outputId": "21d3bdb5-0ac2-44a6-90ec-a3f2677014c4"
  35    },
  36    "outputs": [],
  37    "source": [
  38     "from google.colab import drive\n",
  39     "drive.mount('/content/drive')"
  40    ]
  41   },
  42   {
  43    "cell_type": "code",
  44    "execution_count": null,
  45    "metadata": {
  46     "id": "tLhroy5BnMnC"
  47    },
  48    "outputs": [],
  49    "source": [
  50     "# Importing libraries\n",
  51     "import tensorflow as tf\n",
  52     "import matplotlib.pyplot as plt\n",
  53     "import matplotlib as mpl\n",
  54     "import pandas as pd\n",
  55     "import numpy as np\n",
  56     "import os"
  57    ]
  58   },
  59   {
  60    "cell_type": "code",
  61    "execution_count": null,
  62    "metadata": {
  63     "colab": {
  64      "base_uri": "https://localhost:8080/",
  65      "height": 419
  66     },
  67     "id": "2-UpMVsSnfCI",
  68     "outputId": "b6f5691d-1e76-43a4-de55-3156dbc02b4d"
  69    },
  70    "outputs": [],
  71    "source": [
  72     "df_Ellis  = pd.read_csv(\"/content/drive/MyDrive/Failure/lstm/Ellis_FinalTwoConditionwithOR.csv\")\n",
  73     "df_Ellis"
  74    ]
  75   },
  76   {
  77    "cell_type": "code",
  78    "execution_count": null,
  79    "metadata": {
  80     "colab": {
  81      "base_uri": "https://localhost:8080/",
  82      "height": 293
  83     },
  84     "id": "92xBt43BnjAo",
  85     "outputId": "ed2f1595-c32c-43eb-ae2f-b5fce96e9a92"
  86    },
  87    "outputs": [],
  88    "source": [
  89     "df_Ellis.plot()"
  90    ]
  91   },
  92   {
  93    "cell_type": "code",
  94    "execution_count": null,
  95    "metadata": {
  96     "colab": {
  97      "base_uri": "https://localhost:8080/",
  98      "height": 879
  99     },
 100     "id": "RSo-aa-SIoBR",
 101     "outputId": "63f0c61a-8a5a-41af-cbec-42fe0625b4d1"
 102    },
 103    "outputs": [],
 104    "source": [
 105     "# we show here the hist\n",
 106     "df_Ellis.hist(bins=100,figsize=(20,15))\n",
 107     "#save_fig(\"attribute_histogram_plots\")\n",
 108     "plt.show()"
 109    ]
 110   },
 111   {
 112    "cell_type": "code",
 113    "execution_count": null,
 114    "metadata": {
 115     "colab": {
 116      "base_uri": "https://localhost:8080/",
 117      "height": 634
 118     },
 119     "id": "gggaMJ_2LtFs",
 120     "outputId": "31ad3663-dfe7-4ac5-ddc1-bb5bd6e5bdfd"
 121    },
 122    "outputs": [],
 123    "source": [
 124     "cpu_system_perc = df_Ellis[['ellis-cpu.system_perc']] \n",
 125     "cpu_system_perc.rolling(12).mean().plot(figsize=(20,10), linewidth=5, fontsize=20) \n",
 126     "plt.xlabel('Timestamp', fontsize=30);"
 127    ]
 128   },
 129   {
 130    "cell_type": "code",
 131    "execution_count": null,
 132    "metadata": {
 133     "colab": {
 134      "base_uri": "https://localhost:8080/",
 135      "height": 634
 136     },
 137     "id": "R_ctvXcQL1Xf",
 138     "outputId": "dbc14537-5eb4-4433-f71b-8ad22f551fe8"
 139    },
 140    "outputs": [],
 141    "source": [
 142     "load_avg_1_min = df_Ellis[['ellis-load.avg_1_min']] \n",
 143     "load_avg_1_min.rolling(12).mean().plot(figsize=(20,10), linewidth=5, fontsize=20) \n",
 144     "plt.xlabel('Timestamp', fontsize=30);"
 145    ]
 146   },
 147   {
 148    "cell_type": "code",
 149    "execution_count": null,
 150    "metadata": {
 151     "colab": {
 152      "base_uri": "https://localhost:8080/",
 153      "height": 634
 154     },
 155     "id": "Gkd5ecCmL6Bw",
 156     "outputId": "af90f36e-850f-4ae6-f350-c7a55c2db05b"
 157    },
 158    "outputs": [],
 159    "source": [
 160     "cpu_wait_perc = df_Ellis[['ellis-cpu.wait_perc']] \n",
 161     "cpu_wait_perc.rolling(12).mean().plot(figsize=(20,10), linewidth=5, fontsize=20) \n",
 162     "plt.xlabel('Year', fontsize=30);"
 163    ]
 164   },
 165   {
 166    "cell_type": "code",
 167    "execution_count": null,
 168    "metadata": {
 169     "colab": {
 170      "base_uri": "https://localhost:8080/",
 171      "height": 624
 172     },
 173     "id": "EycZrQU0MBSX",
 174     "outputId": "bcf199b4-b7f9-4a8c-ba2b-aff666038715"
 175    },
 176    "outputs": [],
 177    "source": [
 178     "df_dg = pd.concat([cpu_system_perc.rolling(12).mean(), load_avg_1_min.rolling(12).mean(),cpu_wait_perc.rolling(12).mean()], axis=1) \n",
 179     "df_dg.plot(figsize=(20,10), linewidth=5, fontsize=20) \n",
 180     "plt.xlabel('Year', fontsize=20); "
 181    ]
 182   },
 183   {
 184    "cell_type": "code",
 185    "execution_count": null,
 186    "metadata": {
 187     "id": "YoQA_MIBMknS"
 188    },
 189    "outputs": [],
 190    "source": []
 191   },
 192   {
 193    "cell_type": "code",
 194    "execution_count": null,
 195    "metadata": {
 196     "colab": {
 197      "base_uri": "https://localhost:8080/",
 198      "height": 710
 199     },
 200     "id": "Pi8UMMitMa3Q",
 201     "outputId": "189c418a-6688-4f58-c7f4-1354e235add7"
 202    },
 203    "outputs": [],
 204    "source": [
 205     "# we establish the corrmartrice\n",
 206     "import seaborn as sns\n",
 207     "color = sns.color_palette()\n",
 208     "sns.set_style('darkgrid')\n",
 209     "\n",
 210     "correaltionMatrice = df_Ellis.corr()\n",
 211     "f, ax = plt.subplots(figsize=(20, 10))\n",
 212     "sns.heatmap(correaltionMatrice, cbar=True, vmin=0, vmax=1, square=True, annot=True);\n",
 213     "plt.show()"
 214    ]
 215   },
 216   {
 217    "cell_type": "code",
 218    "execution_count": null,
 219    "metadata": {
 220     "colab": {
 221      "base_uri": "https://localhost:8080/"
 222     },
 223     "id": "rkYwyKtXMvpy",
 224     "outputId": "708e7b7c-10ce-4d4a-ebbb-894567d167c9"
 225    },
 226    "outputs": [],
 227    "source": [
 228     "df_Ellis.corrwith(df_Ellis['ellis-load.avg_1_min'])"
 229    ]
 230   },
 231   {
 232    "cell_type": "code",
 233    "execution_count": null,
 234    "metadata": {
 235     "colab": {
 236      "base_uri": "https://localhost:8080/",
 237      "height": 235
 238     },
 239     "id": "5oQK-ddinvCM",
 240     "outputId": "92bf698d-e2bd-4438-bd84-346da3cfa696"
 241    },
 242    "outputs": [],
 243    "source": [
 244     "## ## using multivariate feature \n",
 245     "\n",
 246     "features_3 = ['ellis-cpu.wait_perc', 'ellis-load.avg_1_min', 'ellis-net.in_bytes_sec', 'Label']\n",
 247     "\n",
 248     "features = df_Ellis[features_3]\n",
 249     "features.index = df_Ellis['Timestamp']\n",
 250     "features.head()"
 251    ]
 252   },
 253   {
 254    "cell_type": "code",
 255    "execution_count": null,
 256    "metadata": {
 257     "colab": {
 258      "base_uri": "https://localhost:8080/",
 259      "height": 386
 260     },
 261     "id": "qbqn755fo81g",
 262     "outputId": "91c28242-4c9a-4ce3-9649-501eafa9247e"
 263    },
 264    "outputs": [],
 265    "source": [
 266     "features.plot(subplots=True)"
 267    ]
 268   },
 269   {
 270    "cell_type": "code",
 271    "execution_count": null,
 272    "metadata": {
 273     "id": "jJQD1x9psWCH"
 274    },
 275    "outputs": [],
 276    "source": [
 277     "features = features.values"
 278    ]
 279   },
 280   {
 281    "cell_type": "code",
 282    "execution_count": null,
 283    "metadata": {
 284     "colab": {
 285      "base_uri": "https://localhost:8080/"
 286     },
 287     "id": "xf8WCiykpUzN",
 288     "outputId": "c34ed8fa-edd0-41d0-e041-29a0853a3370"
 289    },
 290    "outputs": [],
 291    "source": [
 292     "### standardize data\n",
 293     "train_split = 141600\n",
 294     "tf.random.set_seed(13)\n",
 295     "\n",
 296     "### standardize data\n",
 297     "features_mean = features[:train_split].mean()\n",
 298     "features_std = features[:train_split].std()\n",
 299     "features  = (features - features_mean)/ features_std\n",
 300     "\n",
 301     "print(type(features))\n",
 302     "print(features.shape)\n"
 303    ]
 304   },
 305   {
 306    "cell_type": "code",
 307    "execution_count": null,
 308    "metadata": {
 309     "id": "1a0hNDmppnLB"
 310    },
 311    "outputs": [],
 312    "source": [
 313     "### create mutlivariate data\n",
 314     "\n",
 315     "def mutlivariate_data(features , target , start_idx , end_idx , history_size , target_size,\n",
 316     "                      step ,  single_step = False):\n",
 317     "  data = []\n",
 318     "  labels = []\n",
 319     "  start_idx = start_idx + history_size\n",
 320     "  if end_idx is None:\n",
 321     "    end_idx = len(features)- target_size\n",
 322     "  for i in range(start_idx , end_idx ):\n",
 323     "    idxs = range(i-history_size, i, step) ### using step\n",
 324     "    data.append(features[idxs])\n",
 325     "    if single_step:\n",
 326     "      labels.append(target[i+target_size])\n",
 327     "    else:\n",
 328     "      labels.append(target[i:i+target_size])\n",
 329     "\n",
 330     "  return np.array(data) , np.array(labels)"
 331    ]
 332   },
 333   {
 334    "cell_type": "code",
 335    "execution_count": null,
 336    "metadata": {
 337     "colab": {
 338      "base_uri": "https://localhost:8080/"
 339     },
 340     "id": "Z0CivgkitfgE",
 341     "outputId": "fd7abe27-940d-4f71-e581-5deb3ac42262"
 342    },
 343    "outputs": [],
 344    "source": [
 345     "### generate multivariate data\n",
 346     "\n",
 347     "history = 720\n",
 348     "future_target = 72\n",
 349     "STEP = 6\n",
 350     "\n",
 351     "x_train_ss , y_train_ss = mutlivariate_data(features , features[:, 1], 0, train_split, history,\n",
 352     "                                            future_target, STEP , single_step = True)\n",
 353     "\n",
 354     "x_val_ss , y_val_ss = mutlivariate_data(features , features[:,1] , train_split , None , history ,\n",
 355     "                                        future_target, STEP, single_step = True)\n",
 356     "\n",
 357     "print(x_train_ss.shape , y_train_ss.shape)\n",
 358     "print(x_val_ss.shape , y_val_ss.shape)"
 359    ]
 360   },
 361   {
 362    "cell_type": "code",
 363    "execution_count": null,
 364    "metadata": {
 365     "colab": {
 366      "base_uri": "https://localhost:8080/"
 367     },
 368     "id": "VBdr2epGu3aq",
 369     "outputId": "3c3a50d3-6f47-400e-edd0-18a46154f7fc"
 370    },
 371    "outputs": [],
 372    "source": [
 373     "## tensorflow dataset\n",
 374     "batch_size = 256\n",
 375     "buffer_size = 10000\n",
 376     "\n",
 377     "train_ss = tf.data.Dataset.from_tensor_slices((x_train_ss, y_train_ss))\n",
 378     "train_ss = train_ss.cache().shuffle(buffer_size).batch(batch_size).repeat()\n",
 379     "\n",
 380     "val_ss = tf.data.Dataset.from_tensor_slices((x_val_ss, y_val_ss))\n",
 381     "val_ss = val_ss.cache().shuffle(buffer_size).batch(batch_size).repeat()\n",
 382     "\n",
 383     "print(train_ss)\n",
 384     "print(val_ss)"
 385    ]
 386   },
 387   {
 388    "cell_type": "code",
 389    "execution_count": null,
 390    "metadata": {
 391     "id": "9eQpwUyGglu_"
 392    },
 393    "outputs": [],
 394    "source": [
 395     "def root_mean_squared_error(y_true, y_pred):\n",
 396     "        return K.sqrt(K.mean(K.square(y_pred - y_true))) "
 397    ]
 398   },
 399   {
 400    "cell_type": "code",
 401    "execution_count": null,
 402    "metadata": {
 403     "id": "1cKtTAzqyiyL"
 404    },
 405    "outputs": [],
 406    "source": [
 407     "from keras.layers import Activation, Dense, Dropout\n",
 408     "from keras.utils.vis_utils import plot_model\n",
 409     "from keras.layers import Flatten\n",
 410     "from keras.layers.convolutional import Conv1D\n",
 411     "from keras.layers.convolutional import MaxPooling1D\n",
 412     "### Modelling using LSTM\n",
 413     "steps = 50\n",
 414     "\n",
 415     "EPOCHS =20\n",
 416     "\n",
 417     "single_step_model = tf.keras.models.Sequential()\n",
 418     "\n",
 419     "single_step_model.add(Conv1D(filters=64, kernel_size=2, activation='relu', input_shape=(1,48))\n",
 420     "single_step_model.add(MaxPooling1D(pool_size=2))\n",
 421     "single_step_model.add(Flatten())\n",
 422     "single_step_model.add(Dense(50, activation='relu'))\n",
 423     "single_step_model.add(Dense(1))\n",
 424     "single_step_model.compile(optimizer='adam', loss='mae', metrics=[tf.keras.metrics.RootMeanSquaredError(name='rmse')])\n",
 425     "\n",
 426     "\n",
 427     "\n",
 428     "#single_step_model.add(tf.keras.layers.LSTM(32, return_sequences=False, input_shape = x_train_ss.shape[-2:]))\n",
 429     "#single_step_model.add(tf.keras.layers.Dropout(0.3))\n",
 430     "#single_step_model.add(tf.keras.layers.Dense(1))\n",
 431     "#single_step_model.compile(optimizer = tf.keras.optimizers.Adam(), loss = 'mae',metrics=[tf.keras.metrics.RootMeanSquaredError(name='rmse')])\n",
 432     "#single_step_model.compile(loss='mse', optimizer='rmsprop')\n",
 433     "single_step_model_history = single_step_model.fit(train_ss, epochs = EPOCHS , \n",
 434     "                                                  steps_per_epoch =steps, validation_data = val_ss,\n",
 435     "                                                  validation_steps = 50)\n",
 436     "single_step_model.summary()\n",
 437     "plot_model(single_step_model, to_file='/content/drive/MyDrive/Failure/lstm/CNN-LSTM.png', show_shapes=True, show_layer_names=True)\n",
 438     "\n"
 439    ]
 440   },
 441   {
 442    "cell_type": "code",
 443    "execution_count": null,
 444    "metadata": {
 445     "colab": {
 446      "base_uri": "https://localhost:8080/",
 447      "height": 281
 448     },
 449     "id": "Pgev0dgzzBVx",
 450     "outputId": "81b15b3b-0132-428e-d545-d689caa2e2eb"
 451    },
 452    "outputs": [],
 453    "source": [
 454     "## plot train test loss \n",
 455     "\n",
 456     "def plot_loss(history , title):\n",
 457     "  loss = history.history['loss']\n",
 458     "  val_loss = history.history['val_loss']\n",
 459     "\n",
 460     "  epochs = range(len(loss))\n",
 461     "  plt.figure()\n",
 462     "  plt.plot(epochs, loss , 'b' , label = 'Train Loss')\n",
 463     "  plt.plot(epochs, val_loss , 'r' , label = 'Validation Loss')\n",
 464     "  plt.title(title)\n",
 465     "  plt.legend()\n",
 466     "  plt.grid()\n",
 467     "  plt.show()\n",
 468     "\n",
 469     "plot_loss(single_step_model_history , 'Single Step Training and validation loss')"
 470    ]
 471   },
 472   {
 473    "cell_type": "code",
 474    "execution_count": null,
 475    "metadata": {
 476     "colab": {
 477      "base_uri": "https://localhost:8080/",
 478      "height": 281
 479     },
 480     "id": "EnYf6j4okEoC",
 481     "outputId": "89bda316-e762-4aef-b32d-e7649da9ac39"
 482    },
 483    "outputs": [],
 484    "source": [
 485     "## plot train test loss \n",
 486     "\n",
 487     "def plot_loss(history , title):\n",
 488     "  loss = history.history['rmse']\n",
 489     "  val_loss = history.history['val_rmse']\n",
 490     "\n",
 491     "  epochs = range(len(loss))\n",
 492     "  plt.figure()\n",
 493     "  plt.plot(epochs, loss , 'b' , label = 'Train RMSE')\n",
 494     "  plt.plot(epochs, val_loss , 'r' , label = 'Validation RMSE')\n",
 495     "  plt.title(title)\n",
 496     "  plt.legend()\n",
 497     "  plt.grid()\n",
 498     "  plt.show()\n",
 499     "\n",
 500     "plot_loss(single_step_model_history , 'Single Step Training and validation loss')"
 501    ]
 502   },
 503   {
 504    "cell_type": "code",
 505    "execution_count": null,
 506    "metadata": {
 507     "id": "WMegV8mNAwe_"
 508    },
 509    "outputs": [],
 510    "source": [
 511     "### fucntion to create time steps\n",
 512     "def create_time_steps(length):\n",
 513     "  return list(range(-length,0))\n",
 514     "\n",
 515     "### function to plot time series data\n",
 516     "\n",
 517     "def plot_time_series(plot_data, delta , title):\n",
 518     "  labels = [\"History\" , 'True Future' , 'Model Predcited']\n",
 519     "  marker = ['.-' , 'rx' , 'go']\n",
 520     "  time_steps = create_time_steps(plot_data[0].shape[0])\n",
 521     "\n",
 522     "  if delta:\n",
 523     "    future = delta\n",
 524     "  else:\n",
 525     "    future = 0\n",
 526     "  plt.title(title)\n",
 527     "  for i , x in enumerate(plot_data):\n",
 528     "    if i :\n",
 529     "      plt.plot(future , plot_data[i] , marker[i], markersize = 10 , label = labels[i])\n",
 530     "    else:\n",
 531     "      plt.plot(time_steps, plot_data[i].flatten(), marker[i], label = labels[i])\n",
 532     "  plt.legend()\n",
 533     "  plt.xlim([time_steps[0], (future+5) *2])\n",
 534     "\n",
 535     "  plt.xlabel('Time_Step')\n",
 536     "  return plt"
 537    ]
 538   },
 539   {
 540    "cell_type": "code",
 541    "execution_count": null,
 542    "metadata": {
 543     "id": "q99i2c-9XKF3"
 544    },
 545    "outputs": [],
 546    "source": [
 547     "### Moving window average\n",
 548     "\n",
 549     "def MWA(history):\n",
 550     "  return np.mean(history)"
 551    ]
 552   },
 553   {
 554    "cell_type": "code",
 555    "execution_count": null,
 556    "metadata": {
 557     "colab": {
 558      "base_uri": "https://localhost:8080/",
 559      "height": 1000
 560     },
 561     "id": "xFJT1rZDAUVL",
 562     "outputId": "a045ab0c-628b-456c-9ef6-5b92926358c6"
 563    },
 564    "outputs": [],
 565    "source": [
 566     "# plot time series and predicted values\n",
 567     "\n",
 568     "for x, y in val_ss.take(5):\n",
 569     "  plot = plot_time_series([x[0][:, 1].numpy(), y[0].numpy(),\n",
 570     "                    single_step_model.predict(x)[0]], 12,\n",
 571     "                   'Single Step Prediction')\n",
 572     "  plot.show()"
 573    ]
 574   },
 575   {
 576    "cell_type": "markdown",
 577    "metadata": {
 578     "id": "_KXWQVmyCSix"
 579    },
 580    "source": [
 581     "# **MultiStep Forcasting**"
 582    ]
 583   },
 584   {
 585    "cell_type": "code",
 586    "execution_count": null,
 587    "metadata": {
 588     "colab": {
 589      "base_uri": "https://localhost:8080/"
 590     },
 591     "id": "Lu7m2Rr4AbMK",
 592     "outputId": "8e070f0a-fc5e-47a3-e330-ea8c8803c2c8"
 593    },
 594    "outputs": [],
 595    "source": [
 596     "future_target = 72 # 72 future values\n",
 597     "x_train_multi, y_train_multi = mutlivariate_data(features, features[:, 1], 0,\n",
 598     "                                                 train_split, history,\n",
 599     "                                                 future_target, STEP)\n",
 600     "x_val_multi, y_val_multi = mutlivariate_data(features, features[:, 1],\n",
 601     "                                             train_split, None, history,\n",
 602     "                                             future_target, STEP)\n",
 603     "\n",
 604     "print(x_train_multi.shape)\n",
 605     "print(y_train_multi.shape)"
 606    ]
 607   },
 608   {
 609    "cell_type": "code",
 610    "execution_count": null,
 611    "metadata": {
 612     "id": "GLRv5D16CrHj"
 613    },
 614    "outputs": [],
 615    "source": [
 616     "#  TF DATASET\n",
 617     "\n",
 618     "train_data_multi = tf.data.Dataset.from_tensor_slices((x_train_multi, y_train_multi))\n",
 619     "train_data_multi = train_data_multi.cache().shuffle(buffer_size).batch(batch_size).repeat()\n",
 620     "\n",
 621     "val_data_multi = tf.data.Dataset.from_tensor_slices((x_val_multi, y_val_multi))\n",
 622     "val_data_multi = val_data_multi.batch(batch_size).repeat()"
 623    ]
 624   },
 625   {
 626    "cell_type": "code",
 627    "execution_count": null,
 628    "metadata": {
 629     "colab": {
 630      "base_uri": "https://localhost:8080/"
 631     },
 632     "id": "fjXexah9C8yg",
 633     "outputId": "ed05331e-fdf2-460f-a2f5-4bac3be78bc8"
 634    },
 635    "outputs": [],
 636    "source": [
 637     "print(train_data_multi)\n",
 638     "print(val_data_multi)"
 639    ]
 640   },
 641   {
 642    "cell_type": "code",
 643    "execution_count": null,
 644    "metadata": {
 645     "colab": {
 646      "base_uri": "https://localhost:8080/",
 647      "height": 385
 648     },
 649     "id": "7mtLZ6S-DPU-",
 650     "outputId": "02416632-1109-425e-af81-0f17a79e3120"
 651    },
 652    "outputs": [],
 653    "source": [
 654     "#plotting function\n",
 655     "def multi_step_plot(history, true_future, prediction):\n",
 656     "  plt.figure(figsize=(12, 6))\n",
 657     "  num_in = create_time_steps(len(history))\n",
 658     "  num_out = len(true_future)\n",
 659     "  plt.grid()\n",
 660     "  plt.plot(num_in, np.array(history[:, 1]), label='History')\n",
 661     "  plt.plot(np.arange(num_out)/STEP, np.array(true_future), 'bo',\n",
 662     "           label='True Future')\n",
 663     "  if prediction.any():\n",
 664     "    plt.plot(np.arange(num_out)/STEP, np.array(prediction), 'ro',\n",
 665     "             label='Predicted Future')\n",
 666     "  plt.legend(loc='upper left')\n",
 667     "  plt.show()\n",
 668     "  \n",
 669     "\n",
 670     "\n",
 671     "for x, y in train_data_multi.take(1):\n",
 672     "  multi_step_plot(x[0], y[0], np.array([0]))"
 673    ]
 674   },
 675   {
 676    "cell_type": "code",
 677    "execution_count": null,
 678    "metadata": {
 679     "colab": {
 680      "base_uri": "https://localhost:8080/"
 681     },
 682     "id": "snN_Flr5DWQN",
 683     "outputId": "87a55e55-7cfd-4c10-9b15-db992065dd67"
 684    },
 685    "outputs": [],
 686    "source": [
 687     "multi_step_model = tf.keras.models.Sequential()\n",
 688     "\n",
 689     "\n",
 690     "multi_step_model.add(Conv1D(filters=64, kernel_size=2, activation='relu', input_shape=x_train_ss.shape[-2:]))\n",
 691     "multi_step_model.add(MaxPooling1D(pool_size=2))\n",
 692     "multi_step_model.add(Flatten())\n",
 693     "multi_step_model.add(Dense(50, activation='relu'))\n",
 694     "multi_step_model.add(Dense(1))\n",
 695     "multi_step_model.compile(optimizer='adam', loss='mae',metrics=[tf.keras.metrics.RootMeanSquaredError(name='rmse')])\n",
 696     "\n",
 697     "\n",
 698     "#multi_step_model.add(tf.keras.layers.LSTM(32,\n",
 699     " #                                         return_sequences=True,\n",
 700     "  #                                        input_shape=x_train_multi.shape[-2:]))\n",
 701     "#multi_step_model.add(tf.keras.layers.LSTM(16, activation='relu'))\n",
 702     "#aDD dropout layer (0.3)\n",
 703     "#multi_step_model.add(tf.keras.layers.Dense(72)) # for 72 outputs\n",
 704     "\n",
 705     "#multi_step_model.compile(optimizer=tf.keras.optimizers.RMSprop(clipvalue=1.0), loss='mae',metrics=[tf.keras.metrics.RootMeanSquaredError(name='rmse')])\n",
 706     "\n",
 707     "multi_step_history = multi_step_model.fit(train_data_multi, epochs=EPOCHS,\n",
 708     "                                          steps_per_epoch=steps,\n",
 709     "                                          validation_data=val_data_multi,\n",
 710     "                                          validation_steps=50)"
 711    ]
 712   },
 713   {
 714    "cell_type": "code",
 715    "execution_count": null,
 716    "metadata": {
 717     "colab": {
 718      "base_uri": "https://localhost:8080/",
 719      "height": 281
 720     },
 721     "id": "Ay5m27doDsTt",
 722     "outputId": "9b8f5274-03f9-427f-84ce-6dfafc9e7b45"
 723    },
 724    "outputs": [],
 725    "source": [
 726     "plot_loss(multi_step_history, 'Multi-Step Training and validation loss')"
 727    ]
 728   },
 729   {
 730    "cell_type": "code",
 731    "execution_count": null,
 732    "metadata": {
 733     "id": "6ZFP49W4D2wp"
 734    },
 735    "outputs": [],
 736    "source": [
 737     "for x, y in val_data_multi.take(5):\n",
 738     "  multi_step_plot(x[0], y[0], multi_step_model.predict(x)[0])"
 739    ]
 740   },
 741   {
 742    "cell_type": "code",
 743    "execution_count": null,
 744    "metadata": {
 745     "colab": {
 746      "base_uri": "https://localhost:8080/"
 747     },
 748     "id": "DNKMjVoAVqZP",
 749     "outputId": "403d8d4d-ca00-40d2-a179-f13879819f15"
 750    },
 751    "outputs": [],
 752    "source": [
 753     "scores = multi_step_model.evaluate(x_train_multi, y_train_multi, verbose=1, batch_size=200)\n",
 754     "print('MAE: {}'.format(scores[1]))"
 755    ]
 756   },
 757   {
 758    "cell_type": "code",
 759    "execution_count": null,
 760    "metadata": {
 761     "colab": {
 762      "base_uri": "https://localhost:8080/"
 763     },
 764     "id": "oDXXSFLy07gH",
 765     "outputId": "47b9dcf3-cc67-43d3-e88a-8b51ea85a993"
 766    },
 767    "outputs": [],
 768    "source": [
 769     "scores_test = multi_step_model.evaluate(x_val_multi, y_val_multi, verbose=1, batch_size=200)\n",
 770     "print('MAE: {}'.format(scores[1]))\n"
 771    ]
 772   }
 773  ],
 774  "metadata": {
 775   "colab": {
 776    "collapsed_sections": [],
 777    "name": "CNN.ipynb",
 778    "provenance": []
 779   },
 780   "kernelspec": {
 781    "display_name": "Python 3 (ipykernel)",
 782    "language": "python",
 783    "name": "python3"
 784   },
 785   "language_info": {
 786    "codemirror_mode": {
 787     "name": "ipython",
 788     "version": 3
 789    },
 790    "file_extension": ".py",
 791    "mimetype": "text/x-python",
 792    "name": "python",
 793    "nbconvert_exporter": "python",
 794    "pygments_lexer": "ipython3",
 795    "version": "3.9.7"
 796   }
 797  },
 798  "nbformat": 4,
 799  "nbformat_minor": 1
 800 }