DSA_SS24/notebooks/demographic_plots.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "import pickle\n",
    "import wfdb"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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": [
    "\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)}\")\n",
    "\n",
    "data_demographic = {'age':[], 'diag':[], 'gender':[]}\n",
    "for cat_name, records in data.items():\n",
    "    for record in records:\n",
    "        age = record.comments[0].split(' ')[1]\n",
    "        sex = record.comments[1].split(' ')[1]\n",
    "        if age == 'NaN' or sex == 'NaN':\n",
    "            continue\n",
    "        # cut Age: from alter string \n",
    "        data_demographic['age'].append(int(age))\n",
    "        data_demographic['diag'].append(cat_name)\n",
    "        data_demographic['gender'].append(sex)\n",
    "\n",
    "df_dgc = pd.DataFrame(data_demographic)\n",
    "\n",
    "# Change from group to category\n",
    "age_categories = [0, 10, 20, 30, 40, 50, 60, 70, 80, 90]\n",
    "df_dgc['age_group'] = pd.cut(df_dgc['age'], bins=age_categories)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Correlation matrix\n",
    "corr_matrix_age_diag= pd.crosstab(df_dgc['age_group'], df_dgc['diag'])\n",
    "\n",
    "# Plot the correlation matrix\n",
    "sns.heatmap(corr_matrix_age_diag, annot=True, cmap='coolwarm', fmt='d')\n",
    "plt.title('Korrelationsmatrix von Altersgruppen und Diagnosen')\n",
    "plt.xlabel('Diagnose')\n",
    "plt.ylabel('Altersgruppe')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# cut out sex 'unknown' (because only one occurence)\n",
    "df_dgc_bineary = df_dgc[df_dgc['gender'] != 'Unknown']\n",
    "# Correlation matrix\n",
    "corr_matrix_sex_diag = pd.crosstab(df_dgc_bineary['gender'], df_dgc_bineary['diag'])\n",
    "\n",
    "# Plot the correlation matrix\n",
    "sns.heatmap(corr_matrix_sex_diag, annot=True, cmap='coolwarm', fmt='d')\n",
    "plt.title('Korrelationsmatrix von Geschlecht und Diagnosen')\n",
    "plt.xlabel('Diagnose')\n",
    "plt.ylabel('Geschlecht')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<Figure size 640x480 with 4 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 4 subplots for each diagnosis a histrgramm for the age\n",
    "fig, axs = plt.subplots(2, 2)\n",
    "fig.suptitle('Histogramm der Altersverteilung')\n",
    "for i, cat_name in enumerate(categories_dict.keys()):\n",
    "    ax = axs[i // 2, i % 2]\n",
    "    df_dgc[df_dgc['diag'] == cat_name]['age'].hist(ax=ax)\n",
    "    ax.set_title(cat_name)\n",
    "    ax.set_xlabel('Alter')\n",
    "    ax.set_ylabel('Anzahl')\n",
    "    # add some space between the subplots\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# a barplot for each category with the age grpuoped besides each other\n",
    "fig, ax = plt.subplots()\n",
    "sns.countplot(data=df_dgc_bineary, x='diag', hue='gender', ax=ax)\n",
    "plt.title('Anzahl der Diagnosen nach Geschlecht')\n",
    "plt.xlabel('Diagnose')\n",
    "plt.ylabel('Anzahl')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# barplot how many diagnosis are in each age group\n",
    "fig, ax = plt.subplots()\n",
    "sns.countplot(data=df_dgc, x='age_group', hue='diag', ax=ax)\n",
    "plt.title('Anzahl der Diagnosen nach Altersgruppen')\n",
    "plt.xlabel('Altersgruppe')\n",
    "plt.ylabel('Anzahl')\n",
    "plt.show()"
   ]
  }
 ],
 "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
}