{

 "cells": [

  {

   "cell_type": "markdown",

   "metadata": {},

   "source": [

    "# Preprocessing for ECG Classification\n",

    "\n",

    "> Copyright 2019 Dave Fernandes. All Rights Reserved.\n",

    "> \n",

    "> Licensed under the Apache License, Version 2.0 (the \"License\");\n",

    "> you may not use this file except in compliance with the License.\n",

    "> You may obtain a copy of the License at\n",

    ">\n",

    "> http://www.apache.org/licenses/LICENSE-2.0\n",

    ">  \n",

    "> Unless required by applicable law or agreed to in writing, software\n",

    "> distributed under the License is distributed on an \"AS IS\" BASIS,\n",

    "> WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",

    "> See the License for the specific language governing permissions and\n",

    "> limitations under the License."

   ]

  },

  {

   "cell_type": "markdown",

   "metadata": {},

   "source": [

    "Data can be downloaded from: https://www.kaggle.com/shayanfazeli/heartbeat\n",

    "\n",

    "- Randomly sample 100 of each class of time-series for the test set. This is just over 10% of the samples in the smallest class.\n",

    "- Remaining data is balanced for the training set by upsampling under-represented classes."

   ]

  },

  {

   "cell_type": "code",

   "execution_count": null,

   "metadata": {},

   "outputs": [],

   "source": [

    "import numpy as np\n",

    "import pandas as pd\n",

    "import pickle\n",

    "\n",

    "CSV_1 = './Data/mitbih_train.csv'\n",

    "CSV_2 = './Data/mitbih_test.csv'\n",

    "\n",

    "TRAIN_SET = './Data/train_set.pickle'\n",

    "TEST_SET = './Data/test_set.pickle'\n",

    "\n",

    "raw_1 = pd.read_csv(CSV_1, header=None)\n",

    "raw_2 = pd.read_csv(CSV_2, header=None)\n",

    "raw = pd.concat([raw_1, raw_2], axis=0)\n",

    "\n",

    "shuffled = raw.sample(frac=1, axis=0)\n",

    "del raw\n",

    "del raw_1\n",

    "del raw_2\n",

    "\n",

    "values = shuffled.values\n",

    "x = values[:, :-1]\n",

    "y = values[:, -1].astype(int)\n",

    "del values\n",

    "del shuffled"

   ]

  },

  {

   "cell_type": "code",

   "execution_count": null,

   "metadata": {},

   "outputs": [],

   "source": [

    "TEST_CLASS_SIZE = 100\n",

    "\n",

    "class_x = []\n",

    "class_count = []\n",

    "\n",

    "for label in range(5):\n",

    "    x_i = x[y == label]\n",

    "    \n",

    "    # Take the first TEST_CLASS_SIZE elements for the test set\n",

    "    if label == 0:\n",

    "        x_test = x_i[:TEST_CLASS_SIZE, :]\n",

    "        y_test = np.zeros((TEST_CLASS_SIZE)).astype(int)\n",

    "    else:\n",

    "        x_test = np.concatenate((x_test, x_i[:TEST_CLASS_SIZE, :]), axis=0)\n",

    "        y_test = np.concatenate((y_test, np.zeros((TEST_CLASS_SIZE)).astype(int) + label))\n",

    "        \n",

    "    # Use the remainder of the elements for the training set\n",

    "    x_i = x_i[TEST_CLASS_SIZE:, :]\n",

    "    class_x.append(x_i)\n",

    "    class_count.append(len(x_i))\n",

    "\n",

    "# Compute the multiple of class elements needed to balance the classes\n",

    "counts = (np.floor(max(class_count) / np.array(class_count))).astype(int)\n",

    "print('Multiples:', counts)\n",

    "\n",

    "# Append repeated values for under-represented classes\n",

    "for label in range(5):\n",

    "    count = counts[label]\n",

    "    if label == 0:\n",

    "        x_bal = class_x[label]\n",

    "        y_bal = np.zeros((class_count[label])).astype(int)\n",

    "        count -= 1\n",

    "\n",

    "    for j in range(count):\n",

    "        x_bal = np.concatenate((x_bal, class_x[label]), axis=0)\n",

    "        y_bal = np.concatenate((y_bal, np.zeros((class_count[label])).astype(int) + label))\n",

    "\n",

    "print('Training set shapes:', np.shape(x_bal), np.shape(y_bal))\n",

    "print('Test set shapes:', np.shape(x_test), np.shape(y_test))\n",

    "\n",

    "with open(TEST_SET, 'wb') as file:\n",

    "    pickle.dump({'x': x_test, 'y': y_test}, file)\n",

    "\n",

    "with open(TRAIN_SET, 'wb') as file:\n",

    "    pickle.dump({'x': x_bal, 'y': y_bal}, file)"

   ]

  },

  {

   "cell_type": "markdown",

   "metadata": {},

   "source": [

    "## Next\n",

    "Run the `ClassifyECG.ipynb` notebook next..."

   ]

  },

  {

   "cell_type": "code",

   "execution_count": null,

   "metadata": {},

   "outputs": [],

   "source": []

  }

 ],

 "metadata": {

  "kernelspec": {

   "display_name": "Python 3",

   "language": "python",

   "name": "python3"

  },

  "language_info": {

   "codemirror_mode": {

    "name": "ipython",

    "version": 3

   },

   "file_extension": ".py",

   "mimetype": "text/x-python",

   "name": "python",

   "nbconvert_exporter": "python",

   "pygments_lexer": "ipython3",

   "version": "3.6.7"

  }

 },

 "nbformat": 4,

 "nbformat_minor": 2

}