--- a
+++ b/DataExtraction.ipynb
@@ -0,0 +1,142 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import wfdb\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import os"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Retrieve ECG values and annotations using WFDB"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def read_ecg_data(file):\n",
+    "    record = wfdb.rdrecord(os.path.join('picsdb/1.0.0/',file))\n",
+    "    annotation = wfdb.rdann(os.path.join('picsdb/1.0.0/',file), 'atr')\n",
+    "    return(pd.DataFrame(record.p_signal,columns = ['ecg']),pd.DataFrame(annotation.sample,columns = ['time']))    "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Generate CSV storing the retrieved data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def generate_csv(infant_file):    \n",
+    "    ecg, timestamp = read_ecg_data(infant_file)\n",
+    "    ecg.loc[timestamp[\"time\"], 'brady'] = 1\n",
+    "    ecg['brady'] = ecg['brady'].fillna(0)\n",
+    "    ecg.to_csv((infant_file+\".csv\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 63,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "infants = [\"infant2_ecg\",\"infant3_ecg\",\"infant4_ecg\",\"infant6_ecg\",\"infant7_ecg\",\"infant8_ecg\",\"infant9_ecg\",\"infant10_ecg\"]\n",
+    "\n",
+    "#Generating csv for all the infants\n",
+    "for i in infants:\n",
+    "    generate_csv(i)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Retrieve ECG values, bradycardia labels and qrsc peak annotations"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def read_ecg_hr_data(file):\n",
+    "    record = wfdb.rdrecord(os.path.join('picsdb/1.0.0/',file))\n",
+    "    brady_annotation = wfdb.rdann(os.path.join('picsdb/1.0.0/',file), 'atr')\n",
+    "    rpeak_annotation = wfdb.rdann(os.path.join('picsdb/1.0.0/',file), 'qrsc')\n",
+    "    return(pd.DataFrame(record.p_signal,columns = ['ecg']),pd.DataFrame(brady_annotation.sample,columns = ['time']), pd.DataFrame(rpeak_annotation.sample,columns = ['time']))    "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Generate the CSV file of the retrieved data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def generate_csv_2(infant_file):    \n",
+    "    ecg, timestamp, rpeak = read_ecg_hr_data(infant_file)\n",
+    "    ecg.loc[timestamp[\"time\"], 'brady'] = 1\n",
+    "    ecg['brady'] = ecg['brady'].fillna(0)\n",
+    "    ecg.loc[rpeak[\"time\"], 'rpeak'] = 1\n",
+    "    ecg['rpeak'] = ecg['rpeak'].fillna(0)\n",
+    "    ecg.to_csv((infant_file+\"_hr.csv\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "infants2 = [\"infant2_ecg\",\"infant3_ecg\",\"infant4_ecg\",\"infant5_ecg\",\"infant6_ecg\",\"infant7_ecg\",\"infant8_ecg\",\"infant9_ecg\",\"infant10_ecg\"]\n",
+    "for i in infants2:\n",
+    "    generate_csv_2(i)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python [conda env:physio]",
+   "language": "python",
+   "name": "conda-env-physio-py"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}