quality checks and demographic plots

notebooks/data_quality.ipynb

@@ -0,0 +1,102 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Reading SB\n",
+      "Length of SB: 16559\n",
+      "Reading AFIB\n",
+      "Length of AFIB: 9839\n",
+      "Reading GSVT\n",
+      "Length of GSVT: 948\n",
+      "Reading SR\n",
+      "Length of SR: 9720\n"
+     ]
+    }
+   ],
+   "source": [
+    "import pickle\n",
+    "from matplotlib import pyplot as plt\n",
+    "import wfdb\n",
+    "# read pickle files and check len and print first record and first record keys\n",
+    "\n",
+    "path = \"C:/Studium/dsa/data\"\n",
+    "#path = \"C:/Users/Nils/Documents/HS-Mannheim/0000_MASTER/DSA/EKG_Prog/data\"\n",
+    "\n",
+    "categories_dict = {\n",
+    "'SB':    [426177001],\n",
+    "'AFIB':  [164889003, 164890007],\n",
+    "'GSVT':  [426761007, 713422000, 233896004, 233897008, 713422000],\n",
+    "'SR':    [426783006, 427393009]\n",
+    "}\n",
+    "\n",
+    "\n",
+    "data = {}\n",
+    "for cat_name in categories_dict.keys():\n",
+    "    print(f\"Reading {cat_name}\")\n",
+    "    with open(f'{path}/{cat_name}.pkl', 'rb') as f:\n",
+    "        records = pickle.load(f)\n",
+    "        data[cat_name] = records\n",
+    "        print(f\"Length of {cat_name}: {len(records)}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Check for missing data in timeseries"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Missing timeseries in 0 records\n"
+     ]
+    }
+   ],
+   "source": [
+    "missing_timeseries = []\n",
+    "for cat_name, records in data.items():\n",
+    "    for record in records:\n",
+    "        if len(record.p_signal) != 5000:\n",
+    "            missing_timeseries.append(record)\n",
+    "            print(f\"Missing timeseries in {record.record_name}\")\n",
+    "        #if record.comments[2]== '':\n",
+    "print(f\"Missing timeseries in {len(missing_timeseries)} records\")"
+   ]
+  }
+ ],
+ "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": "3.10.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}