{

 "cells": [

  {

   "cell_type": "code",

   "execution_count": 1,

   "metadata": {},

   "outputs": [],

   "source": [

    "import os\n",

    "import serial\n",

    "from time import time, sleep"

   ]

  },

  {

   "cell_type": "code",

   "execution_count": null,

   "metadata": {},

   "outputs": [],

   "source": [

    "ser = serial.Serial('/dev/ttyUSB0',9600)\n",

    "print(ser.name) \n",

    "\n",

    "# Read from serial moniter\n",

    "line = ser.read_until('e')\n",

    "\n",

    "# Delete ecg_signal.txt file if it's already present.\n",

    "cwd = os.getcwd()\n",

    "check = cwd + \"/ecg_signal.txt\"\n",

    "\n",

    "files = sorted(glob.glob(cwd + '/*.csv'), key=numericalSort)\n",

    "if check in files:\n",

    "    os.remove(check)\n",

    "\n",

    "# Write the data to a file\n",

    "f = open('ecg_signal.txt', 'a')\n",

    "f.write(str(line)[10:])\n",

    "f.close()"

   ]

  },

  {

   "cell_type": "code",

   "execution_count": null,

   "metadata": {},

   "outputs": [],

   "source": [

    "# Convert .txt file into .mat file for prediction\n",

    "a = np.loadtxt('ecg_signal.txt', dtype = 'object')\n",

    "a1 = a[100:9100]\n",

    "a1 = np.asarray(a1, dtype = 'float64')\n",

    "a1 = a1.reshape(1,-1)\n",

    "scipy.io.savemat('ecg_signal.mat', {'val': a1})"

   ]

  },

  {

   "cell_type": "code",

   "execution_count": null,

   "metadata": {

    "scrolled": true

   },

   "outputs": [],

   "source": [

    "!python ecg/ecg/predict.py val.json 0.434-0.864-012-0.309-0.892.hdf5"

   ]

  }

 ],

 "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": "3.6.5"

  }

 },

 "nbformat": 4,

 "nbformat_minor": 2

}