ML-Kurs-SS2023/notebooks/01_intro_ex_2_sol.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Exercise 2: Example for pandas using the heart.csv data set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# read the csv Data \n",
    "df = pd.read_csv('heart.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Index(['age', 'sex', 'cp', 'trestbps', 'chol', 'fbs', 'restecg', 'thalach',\n",
      "       'exang', 'oldpeak', 'slope', 'ca', 'thal', 'target'],\n",
      "      dtype='object')\n",
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 303 entries, 0 to 302\n",
      "Data columns (total 14 columns):\n",
      " #   Column    Non-Null Count  Dtype  \n",
      "---  ------    --------------  -----  \n",
      " 0   age       303 non-null    int64  \n",
      " 1   sex       303 non-null    int64  \n",
      " 2   cp        303 non-null    int64  \n",
      " 3   trestbps  303 non-null    int64  \n",
      " 4   chol      303 non-null    int64  \n",
      " 5   fbs       303 non-null    int64  \n",
      " 6   restecg   303 non-null    int64  \n",
      " 7   thalach   303 non-null    int64  \n",
      " 8   exang     303 non-null    int64  \n",
      " 9   oldpeak   303 non-null    float64\n",
      " 10  slope     303 non-null    int64  \n",
      " 11  ca        303 non-null    int64  \n",
      " 12  thal      303 non-null    int64  \n",
      " 13  target    303 non-null    int64  \n",
      "dtypes: float64(1), int64(13)\n",
      "memory usage: 33.3 KB\n",
      "None\n",
      "age           int64\n",
      "sex           int64\n",
      "cp            int64\n",
      "trestbps      int64\n",
      "chol          int64\n",
      "fbs           int64\n",
      "restecg       int64\n",
      "thalach       int64\n",
      "exang         int64\n",
      "oldpeak     float64\n",
      "slope         int64\n",
      "ca            int64\n",
      "thal          int64\n",
      "target        int64\n",
      "dtype: object\n"
     ]
    }
   ],
   "source": [
    "# What is the number of columns and rows\n",
    "print(df.columns)\n",
    "print (df.info())\n",
    "print(df.dtypes)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   age  sex  cp  trestbps  chol  fbs  restecg  thalach  exang  oldpeak  slope  \\\n",
      "0   63    1   3       145   233    1        0      150      0      2.3      0   \n",
      "1   37    1   2       130   250    0        1      187      0      3.5      0   \n",
      "2   41    0   1       130   204    0        0      172      0      1.4      2   \n",
      "\n",
      "   ca  thal  target  \n",
      "0   0     1       1  \n",
      "1   0     2       1  \n",
      "2   0     2       1  \n"
     ]
    }
   ],
   "source": [
    "# get first 3 lines\n",
    "print(df.head(3))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              age         sex          cp    trestbps        chol         fbs  \\\n",
      "count  303.000000  303.000000  303.000000  303.000000  303.000000  303.000000   \n",
      "mean    54.366337    0.683168    0.966997  131.623762  246.264026    0.148515   \n",
      "std      9.082101    0.466011    1.032052   17.538143   51.830751    0.356198   \n",
      "min     29.000000    0.000000    0.000000   94.000000  126.000000    0.000000   \n",
      "25%     47.500000    0.000000    0.000000  120.000000  211.000000    0.000000   \n",
      "50%     55.000000    1.000000    1.000000  130.000000  240.000000    0.000000   \n",
      "75%     61.000000    1.000000    2.000000  140.000000  274.500000    0.000000   \n",
      "max     77.000000    1.000000    3.000000  200.000000  564.000000    1.000000   \n",
      "\n",
      "          restecg     thalach       exang     oldpeak       slope          ca  \\\n",
      "count  303.000000  303.000000  303.000000  303.000000  303.000000  303.000000   \n",
      "mean     0.528053  149.646865    0.326733    1.039604    1.399340    0.729373   \n",
      "std      0.525860   22.905161    0.469794    1.161075    0.616226    1.022606   \n",
      "min      0.000000   71.000000    0.000000    0.000000    0.000000    0.000000   \n",
      "25%      0.000000  133.500000    0.000000    0.000000    1.000000    0.000000   \n",
      "50%      1.000000  153.000000    0.000000    0.800000    1.000000    0.000000   \n",
      "75%      1.000000  166.000000    1.000000    1.600000    2.000000    1.000000   \n",
      "max      2.000000  202.000000    1.000000    6.200000    2.000000    4.000000   \n",
      "\n",
      "             thal      target  \n",
      "count  303.000000  303.000000  \n",
      "mean     2.313531    0.544554  \n",
      "std      0.612277    0.498835  \n",
      "min      0.000000    0.000000  \n",
      "25%      2.000000    0.000000  \n",
      "50%      2.000000    1.000000  \n",
      "75%      3.000000    1.000000  \n",
      "max      3.000000    1.000000  \n"
     ]
    }
   ],
   "source": [
    "#display statistics summary\n",
    "print(df.describe())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "               age       sex        cp  trestbps      chol       fbs  \\\n",
      "age       1.000000 -0.098447 -0.068653  0.279351  0.213678  0.121308   \n",
      "sex      -0.098447  1.000000 -0.049353 -0.056769 -0.197912  0.045032   \n",
      "cp       -0.068653 -0.049353  1.000000  0.047608 -0.076904  0.094444   \n",
      "trestbps  0.279351 -0.056769  0.047608  1.000000  0.123174  0.177531   \n",
      "chol      0.213678 -0.197912 -0.076904  0.123174  1.000000  0.013294   \n",
      "fbs       0.121308  0.045032  0.094444  0.177531  0.013294  1.000000   \n",
      "restecg  -0.116211 -0.058196  0.044421 -0.114103 -0.151040 -0.084189   \n",
      "thalach  -0.398522 -0.044020  0.295762 -0.046698 -0.009940 -0.008567   \n",
      "exang     0.096801  0.141664 -0.394280  0.067616  0.067023  0.025665   \n",
      "oldpeak   0.210013  0.096093 -0.149230  0.193216  0.053952  0.005747   \n",
      "slope    -0.168814 -0.030711  0.119717 -0.121475 -0.004038 -0.059894   \n",
      "ca        0.276326  0.118261 -0.181053  0.101389  0.070511  0.137979   \n",
      "thal      0.068001  0.210041 -0.161736  0.062210  0.098803 -0.032019   \n",
      "target   -0.225439 -0.280937  0.433798 -0.144931 -0.085239 -0.028046   \n",
      "\n",
      "           restecg   thalach     exang   oldpeak     slope        ca  \\\n",
      "age      -0.116211 -0.398522  0.096801  0.210013 -0.168814  0.276326   \n",
      "sex      -0.058196 -0.044020  0.141664  0.096093 -0.030711  0.118261   \n",
      "cp        0.044421  0.295762 -0.394280 -0.149230  0.119717 -0.181053   \n",
      "trestbps -0.114103 -0.046698  0.067616  0.193216 -0.121475  0.101389   \n",
      "chol     -0.151040 -0.009940  0.067023  0.053952 -0.004038  0.070511   \n",
      "fbs      -0.084189 -0.008567  0.025665  0.005747 -0.059894  0.137979   \n",
      "restecg   1.000000  0.044123 -0.070733 -0.058770  0.093045 -0.072042   \n",
      "thalach   0.044123  1.000000 -0.378812 -0.344187  0.386784 -0.213177   \n",
      "exang    -0.070733 -0.378812  1.000000  0.288223 -0.257748  0.115739   \n",
      "oldpeak  -0.058770 -0.344187  0.288223  1.000000 -0.577537  0.222682   \n",
      "slope     0.093045  0.386784 -0.257748 -0.577537  1.000000 -0.080155   \n",
      "ca       -0.072042 -0.213177  0.115739  0.222682 -0.080155  1.000000   \n",
      "thal     -0.011981 -0.096439  0.206754  0.210244 -0.104764  0.151832   \n",
      "target    0.137230  0.421741 -0.436757 -0.430696  0.345877 -0.391724   \n",
      "\n",
      "              thal    target  \n",
      "age       0.068001 -0.225439  \n",
      "sex       0.210041 -0.280937  \n",
      "cp       -0.161736  0.433798  \n",
      "trestbps  0.062210 -0.144931  \n",
      "chol      0.098803 -0.085239  \n",
      "fbs      -0.032019 -0.028046  \n",
      "restecg  -0.011981  0.137230  \n",
      "thalach  -0.096439  0.421741  \n",
      "exang     0.206754 -0.436757  \n",
      "oldpeak   0.210244 -0.430696  \n",
      "slope    -0.104764  0.345877  \n",
      "ca        0.151832 -0.391724  \n",
      "thal      1.000000 -0.344029  \n",
      "target   -0.344029  1.000000  \n"
     ]
    }
   ],
   "source": [
    "#display correlation\n",
    "print (df.corr())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              age       sex        cp    trestbps        chol       fbs  \\\n",
      "target                                                                    \n",
      "0       56.601449  0.826087  0.478261  134.398551  251.086957  0.159420   \n",
      "1       52.496970  0.563636  1.375758  129.303030  242.230303  0.139394   \n",
      "\n",
      "         restecg     thalach     exang   oldpeak     slope        ca      thal  \n",
      "target                                                                          \n",
      "0       0.449275  139.101449  0.550725  1.585507  1.166667  1.166667  2.543478  \n",
      "1       0.593939  158.466667  0.139394  0.583030  1.593939  0.363636  2.121212  \n"
     ]
    }
   ],
   "source": [
    "# Print mean values for each column with and without disease\n",
    "print(df.groupby('target').mean())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "     age  sex  cp  trestbps  chol  fbs  restecg  thalach  exang  oldpeak  \\\n",
      "167   62    0   0       140   268    0        0      160      0      3.6   \n",
      "181   65    0   0       150   225    0        0      114      0      1.0   \n",
      "182   61    0   0       130   330    0        0      169      0      0.0   \n",
      "190   51    0   0       130   305    0        1      142      1      1.2   \n",
      "204   62    0   0       160   164    0        0      145      0      6.2   \n",
      "\n",
      "     slope  ca  thal  target  \n",
      "167      0   2     2       0  \n",
      "181      1   3     3       0  \n",
      "182      2   0     2       0  \n",
      "190      1   0     3       0  \n",
      "204      0   3     3       0  \n"
     ]
    }
   ],
   "source": [
    "# get table with selection on more than 1 column\n",
    "df1 = df[(df[\"sex\"] == 0) & (df[\"target\"] == 0) ]\n",
    "print (df1.head(5))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    " Plots"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0      63\n",
      "1      37\n",
      "3      56\n",
      "5      57\n",
      "7      44\n",
      "       ..\n",
      "295    63\n",
      "297    59\n",
      "299    45\n",
      "300    68\n",
      "301    57\n",
      "Name: age, Length: 207, dtype: int64\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<matplotlib.legend.Legend at 0x7fae906dafa0>"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAjMAAAHFCAYAAAAHcXhbAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjYuMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/P9b71AAAACXBIWXMAAA9hAAAPYQGoP6dpAABA0ElEQVR4nO3deXyNZ/7/8fchyZHIgpANlahYY6nqqKUNVRQ1VFtKq9YpZVpLtaqoaNU6UmYMtbTBV1HVUq2x1ZIuhoZSmnRUbUETaa0RFUuu3x9+OY8eSUgicXLzej4eeUzv677u+/6c6yTOe677OufYjDFGAAAAFlXM1QUAAADcCsIMAACwNMIMAACwNMIMAACwNMIMAACwNMIMAACwNMIMAACwNMIMAACwNMIMAACwNMIMUAC2bNkim82mLVu2ONp69uyp0NDQPJ3n119/VVRUlHbv3p2n47K7ls1m09///vc8nedmZs6cqfnz52dpP3z4sGw2W7b7kHvz58+XzWbT4cOHHW3NmjVTs2bNXFJPTs/3rbp8+bJmz56tBx54QGXKlJGXl5cqVaqkDh06aMWKFQV+Pdz5CDNAIRk9enSe/2H+9ddfNXbs2DyHmfxcKz9yenELDg7Wf//7X7Vr167Qa7jbzJw5UzNnznTZtQsjzHTv3l0vvfSSmjdvrkWLFunzzz/XqFGj5ObmpnXr1hX49XDnc3N1AcCd6t577y30a1y4cEFeXl635Vo3Yrfb9eCDD7q0BiswxujixYvy9PTM9TE1a9YsxIpuv0OHDumjjz7Sm2++qbFjxzraW7Roob/97W/KyMhwYXWwKmZmUKT98ssv6tWrl8LDw+Xl5aXy5curffv22rt3b5a+8fHxatWqlby8vFSuXDkNHDhQq1evznL7R5K+/PJLtWjRQr6+vvLy8lKTJk20cePGXNX0v//9T4899pi8vLxUtmxZ9e/fX6mpqVn6ZXfr5+OPP1bDhg3l5+cnLy8vVa5cWb1795Z07VbVAw88IEnq1auXbDabbDaboqKiHOfz9vbW3r171apVK/n4+KhFixY5XivT7NmzVbVqVdntdtWsWVNLly512h8VFSWbzZbluOtveYSGhio+Pl6xsbGO2jKvmdNtpm+++UYtWrSQj4+PvLy81LhxY61evTrb62zevFkvvviiypYtK39/f3Xq1Em//vprto/pz3bs2KFnnnlGoaGh8vT0VGhoqLp27aojR45k6Xv8+HG98MILqlixojw8PBQSEqKnnnpKJ06ccPQ5c+aMXnnlFVWuXFl2u10BAQFq27at/ve//zn6nDp1SgMGDFD58uXl4eGhypUra+TIkUpPT3e6Xuatvvfee081atSQ3W7XggULJEnbtm1TkyZNVKJECYWEhGjEiBG6fPlylpqvv82UOdb/+Mc/FB0drbCwMHl7e6tRo0batm1bluPnzp3r9PwvXrw4V7dAb/R8S1JiYqKee+45BQQEyG63q0aNGpo6depNw8jJkyclXZvNy06xYs4vS+fOndOwYcMUFhYmDw8PlS9fXoMHD1ZaWpqjT//+/VWiRAnt3LnT0ZaRkaEWLVooMDBQSUlJN6wJ1sfMDIq0X3/9Vf7+/po4caLKlSunU6dOacGCBWrYsKF27dqlatWqSZKSkpIUGRmpkiVLatasWQoICNCSJUuyXTOyaNEiPf/88+rQoYMWLFggd3d3zZ49W61bt9a6descASE7J06cUGRkpNzd3TVz5kwFBgbqww8/zNXalP/+97/q0qWLunTpoqioKJUoUUJHjhzRpk2bJEn169dXTEyMevXqpVGjRjlu2VSoUMFxjkuXLumvf/2r+vXrp9dff11Xrly54TVXrVqlzZs366233lLJkiU1c+ZMde3aVW5ubnrqqaduWvOfrVixQk899ZT8/Pwctz3sdnuO/WNjY9WyZUvVqVNH77//vux2u2bOnKn27dtryZIl6tKli1P/vn37ql27dlq8eLGOHj2qV199Vc8995xjfHJy+PBhVatWTc8884zKlCmjpKQkzZo1Sw888IASEhJUtmxZSdeCzAMPPKDLly/rjTfeUJ06dXTy5EmtW7dOp0+fVmBgoFJTU9W0aVMdPnxYw4cPV8OGDXX+/Hl99dVXSkpKUvXq1XXx4kU1b95cBw4c0NixY1WnTh19/fXXmjBhgnbv3p0lrK1cuVJff/213nzzTQUFBSkgIEAJCQlq0aKFQkNDNX/+fHl5eWnmzJlavHhxrp+Pf//736pevbqmTZsm6dqtxrZt2+rQoUPy8/OTJM2ZM0f9+vXTk08+qXfffVdnz57V2LFjs4Su7Nzo+f7tt9/UuHFjXbp0SW+//bZCQ0P1xRdfaNiwYTpw4MANb4vVqFFDpUqV0tixY1WsWDG1atUqx2B14cIFRUZG6tixY47nLD4+Xm+++ab27t2rL7/8UjabTdOmTdP27dvVuXNn7dy503H+LVu2aO3atTkGJ9xBDGAhV65cMZcuXTLh4eFmyJAhjvZXX33V2Gw2Ex8f79S/devWRpLZvHmzMcaYtLQ0U6ZMGdO+fXunflevXjV169Y1f/nLX254/eHDhxubzWZ2797t1N6yZUun6xhjTI8ePUylSpUc2//4xz+MJHPmzJkczx8XF2ckmZiYmCz7evToYSSZDz74INt9f76WMcZIMp6eniY5OdnRduXKFVO9enVTpUoVR9uYMWNMdv8UxMTEGEnm0KFDjrZatWqZyMjILH0PHTqUpe4HH3zQBAQEmNTUVKfrR0REmAoVKpiMjAyn6wwYMMDpnJMnTzaSTFJSUpbr3ciVK1fM+fPnTcmSJc306dMd7b179zbu7u4mISEhx2PfeustI8ls2LAhxz7vvfeekWSWLVvm1D5p0iQjyaxfv97RJsn4+fmZU6dOOfXt0qVLjs/N9WMeGRnpNOaZY127dm1z5coVR/t3331nJJklS5YYY679TgcFBZmGDRs6XfvIkSPG3d09y+9LdnJ6vl9//XUjyWzfvt2p/cUXXzQ2m83s27fvhuddvXq1KVu2rJFkJBl/f3/z9NNPm1WrVjn1mzBhgilWrJiJi4tzal++fLmRZP7zn/842vbv3298fX1Nx44dzZdffmmKFStmRo0addPHiDsDt5lQpF25ckXjx49XzZo15eHhITc3N3l4eGj//v366aefHP1iY2MVERGRZX1B165dnba3bt2qU6dOqUePHrpy5YrjJyMjQ4899pji4uKcpq+vt3nzZtWqVUt169Z1au/WrdtNH0vmLaTOnTtr2bJlOn78+E2Pyc6TTz6Z676Z0+yZihcvri5duuiXX37RsWPH8nX93EhLS9P27dv11FNPydvb2+n63bt317Fjx7Rv3z6nY/761786bdepU0eSsr1d9Gfnz5/X8OHDVaVKFbm5ucnNzU3e3t5KS0tz+h1Zs2aNmjdvrho1auR4rjVr1qhq1ap69NFHc+yzadMmlSxZMsvMVs+ePSUpy+3KRx55RKVLl3Zq27x5c47PTW61a9dOxYsXd2xfP1779u1TcnKyOnfu7HTcPffcoyZNmuT6OtnZtGmTatasqb/85S9O7T179pQx5qazaW3btlViYqJWrFihYcOGqVatWlq5cqX++te/Os1yfvHFF4qIiFC9evWc/l5bt26d5fZxlSpVNHfuXK1cuVKPP/64HnroIcctWtz5CDMo0oYOHarRo0erY8eO+vzzz7V9+3bFxcWpbt26+uOPPxz9Tp486fTCkOn6tsy1EU899ZTc3d2dfiZNmiRjjE6dOpVjPSdPnlRQUFCW9uzarvfwww9r5cqVunLlip5//nlVqFBBERERWrJkyU2PzeTl5SVfX99c979RrZlrFwrD6dOnZYzJdno/JCQk2+v7+/s7bWfe0vjz85ydbt26acaMGerbt6/WrVun7777TnFxcSpXrpzTsb/99pvTLbvs5KZP5u/A9euMAgIC5ObmluVxZTcGt/J7lOlm45VZR27+LvLq5MmTeXpus+Pp6amOHTtqypQpio2N1S+//KKaNWvq3//+t+Lj4yVd+3vds2dPlr9VHx8fGWP0+++/O52zXbt
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# age dirtibution group into male and female (1 = male; 0 = female)\n",
    "# male\n",
    "plt.title('age distribution according to Sex') \n",
    "df[df[\"sex\"] == 1]['age'].plot.hist()\n",
    "print(df[df[\"sex\"] > 0]['age'])\n",
    "# female\n",
    "df[df[\"sex\"] == 0]['age'].plot.hist()\n",
    "plt.xlabel('age [years]')\n",
    "plt.legend([\"male\", \"female\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 0, 'max heart rate')"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure()\n",
    "# Plot maximum heart rate\n",
    "# Heart disease (0 = no, 1 = yes)\n",
    "plt.title('maximum heart rate according to heart disease') \n",
    "df[df[\"target\"] == 1]['thalach'].plot.hist()\n",
    "# no disease\n",
    "df[df[\"target\"] == 0]['thalach'].plot.hist()\n",
    "plt.legend([\"disease\", \"no disease\"])\n",
    "plt.xlabel('max heart rate')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.legend.Legend at 0x7fae884d8e80>"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Plot sex and target in one histogramm via crosstab\n",
    "pd.crosstab(df.sex,df.target).plot(kind=\"bar\",color=['red','blue' ])\n",
    "plt.title('Heart Disease distribution according to Sex')\n",
    "plt.xlabel('Sex (0 = Female, 1 = Male)')\n",
    "plt.legend([\"no disease\", \"disease\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Frequency of Disease or Not')"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABNYAAAIhCAYAAACCMjckAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjYuMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/P9b71AAAACXBIWXMAAA9hAAAPYQGoP6dpAABg0klEQVR4nO3deZxO9f//8edl9p2xzJhmMBhbtiwJFcKUsZWiorIvIYSkfBOS3UT5WJIsRZbsFZnssu8lHyKMbbLvzDBzfn/0m+vjamaY67jGdeFxv92u2815n/c553Wd65ozzbP3OW+LYRiGAAAAAAAAANglm7MLAAAAAAAAAB5EBGsAAAAAAACACQRrAAAAAAAAgAkEawAAAAAAAIAJBGsAAAAAAACACQRrAAAAAAAAgAkEawAAAAAAAIAJBGsAAAAAAACACQRrAAAAAAAAgAkEawCA+2rKlCmyWCzaunVruuvr1aunAgUK3N+ibvPTTz+pX79+me7fokULWSwW68vPz08FChRQgwYNNHnyZCUmJqbZpnr16qpevbrjinZR/fr1szk3vr6+Cg8P1/PPP68vvvhCly9fTrNNixYt7P78T5w4oX79+mnnzp12bZfesSwWizp37mzXfu5m7NixmjJlSpr2w4cPy2KxpLvufurevbssFovq1avn1DruRep37XYFChRQixYtnFLH3V73+vP/999/q3fv3ipVqpT8/f3l7e2tqKgode3aVX/++ae1X4sWLeTv73+P78o+165dU79+/bRq1apM9U/9OUh9ZcuWTTlz5lRMTIw2bNhg9/HT+y6Y9e/re0av+/09AwC4FndnFwAAgCv56aef9J///MeucM3Hx0crVqyQJF2/fl1Hjx7VkiVL1LZtW40cOVJLly5VeHi4tf/YsWMdXbZLW7p0qYKCgpSUlKQTJ05o+fLl6tWrl4YPH67FixerTJky1r4fffSRunbtatf+T5w4of79+6tAgQIqW7Zsprczcywzxo4dq1y5cqX54ztv3rzasGGDChUqlOU1ZOTmzZv69ttvJf3zOR0/flyPPfaY0+pxpPnz5yswMPC+HrNNmzZ64YUXrMsnT55Uo0aN9M4776hp06bW9nupa/PmzapXr54Mw1Dnzp1VuXJleXp6at++ffr222/15JNP6vz58/f0Pu7FtWvX1L9/f0myK0BMPUfJycnas2eP+vfvrxo1amjDhg164oknMr2ff38G9+Kjjz5Shw4drMvbt29Xp06dNGjQINWoUcPanjt3boccDwDwYCJYAwBA//wx6Ovra2rbbNmy6amnnrJpe+utt9SyZUvVq1dPr7zyijZu3GhdV6JEiXuq9UFTvnx55cqVy7r82muvqXPnzqpWrZoaNGig/fv3y8vLS5LuS8iU+lk7M9CSJC8vrzTfm/tt4cKFOn36tOrWrasff/xRU6dO1YcffujUmtKTnJysW7duWb8nmWFPGOMo4eHhNiH64cOHJUn58uVzyGd96dIlNWzYUN7e3lq/fr3NsapXr6727dvr+++/v+fjOMPt56hq1aoqXLiwatasqbFjx2rixImZ3s+/P4N7UahQIZvrxI0bNyRJUVFRTv/ZBQC4Dm4FBQC4PMMwNHbsWJUtW1Y+Pj7KkSOHXnnlFf311182/eLi4tSwYUOFh4fL29tbhQsXVvv27XXmzBmbfqm3Cm3fvl2vvPKKcuTIoUKFCqlFixb6z3/+I0k2t/mk/nFsr+joaLVt21abNm3SmjVrrO3p3Qo6btw4lSlTRv7+/goICFCxYsXSBBwJCQlq3769wsPD5enpqcjISPXv31+3bt2y6de/f39VqlRJwcHBCgwMVLly5TRp0iQZhmHTb8WKFapevbpy5swpHx8f5cuXTy+//LKuXbtm7ZOUlKSBAweqWLFi8vLyUu7cudWyZUudPn3a1DlJVaZMGfXp00fx8fGaNWuWtT292zPnzJmjSpUqKSgoSL6+vipYsKBatWolSVq1apUqVqwoSWrZsqX1M0sdcZh6K9xvv/2m6OhoBQQEqGbNmhkeK9WECRNUpEgReXl5qUSJEpo5c6bN+oxuN0u91Tn1O1OgQAHt2bNHq1evttaWesyMbgVdt26datasqYCAAPn6+qpKlSr68ccf0z3OypUr9fbbbytXrlzKmTOnGjVqpBMnTqT7ntIzadIkeXp6avLkyYqIiNDkyZPTfE8k6b///a9ef/11hYSEyMvLS/ny5dNbb71lc6vz8ePH1a5dO0VERMjT01NhYWF65ZVX9Pfff1v7xMfH64033lCePHnk5eWl4sWLa+TIkUpJSbH2ST0vw4YN08CBAxUZGSkvLy+tXLlSkvTjjz+qbNmy8vLyUmRkpEaMGJHue/v3raCrVq2SxWLRd999pz59+igsLEyBgYGqVauW9u3bZ7OtYRgaNGiQ8ufPL29vb1WoUEFxcXEOu4170aJFqly5snx9fRUQEKDatWtn6rbHiRMnKiEhQcOGDcswPHrllVfStB04cEAxMTHy9/dXRESEevTokeY29cz+rN/punH48GHr6K3+/fvf062SqcHVkSNHJEmzZs1SdHS08ubNKx8fHxUvXly9e/fW1atXbbbL6LbgevXqaenSpSpXrpx8fHxUrFgxff3113bXdbu1a9dav1P/Nm3aNFksFm3ZskXS/65Fe/bsUc2aNeXn56fcuXOrc+fONtdcKfO/8wAAroFgDQDgFKkjUP79Su+P+vbt26tbt26qVauWFixYoLFjx2rPnj2qUqWKzR/tBw8eVOXKlTVu3DgtW7ZMffv21aZNm/T000/r5s2bafbbqFEjFS5cWHPmzNH48eP10UcfWf8o3bBhg/WVN29e0++zQYMGkmQTrP3bzJkz1bFjR1WrVk3z58/XggUL9O6779r8wZiQkKAnn3xSP//8s/r27aslS5aodevWGjx4sNq2bWuzv8OHD6t9+/aaPXu25s2bZ70V7ZNPPrHpU7duXXl6eurrr7/W0qVLNWTIEPn5+SkpKUmSlJKSooYNG2rIkCFq2rSpfvzxRw0ZMsQaMFy/ft30ecnsudmwYYNeffVVFSxYUDNnztSPP/6ovn37WsPEcuXKafLkyZKk//u//7N+Zm3atLHuIykpSQ0aNNBzzz2nhQsXWm9Ty8iiRYv0+eefa8CAAfr++++VP39+vf7666ZGAs2fP18FCxbUE088Ya1t/vz5GfZfvXq1nnvuOV28eFGTJk3Sd999p4CAANWvX98mgEzVpk0beXh4aMaMGRo2bJhWrVqlN954I1O1HTt2TMuWLVPDhg2VO3duNW/eXAcOHEjzeezatUsVK1bUxo0bNWDAAC1ZskSDBw9WYmKi9bty/PhxVaxYUfPnz1f37t21ZMkSjRo1SkFBQdbbEk+fPq0qVapo2bJl+uSTT7Ro0SLVqlVLPXv2TPe5dp9//rlWrFihESNGaMmSJSpWrJiWL1+uhg0bKiAgQDNnztTw4cM1e/Zs63cgMz788EMdOXJEX331lb788kv9+eefql+/vpKTk619+vTpoz59+uiFF17QwoUL1aFDB7Vp00b79+/P9HEyMmPGDDVs2FCBgYH67rvvNGnSJJ0/f17Vq1fXunXr7rjtsmXL5Obmpvr162f6eDdv3lSDBg1Us2ZNLVy4UK1atdJnn32moUOHWvtk9mf9bteNvHnzaunSpZKk1q1bW7/zH330kd3n6cCBA5L+d5vln3/+qZiYGE2aNElLly5Vt27dNHv27Eyfi127dqlHjx569913tXDhQpUuXVqtW7e+4/Xnbp555hk98cQT1v8hc7sxY8aoYsWK1uBf+ueziImJUc2aNbVgwQJ17txZEyZM0KuvvmqzbWZ/5wEAXIQBAMB9NHnyZEPSHV/58+e39t+wYYMhyRg5cqTNfo4ePWr4+PgYvXr1Svc4KSkpxs2bN40jR44YkoyFCxda13388ceGJKNv375ptuvUqZNhz6/H5s2bG35+fhmu37t3ryHJePvtt61t1apVM6pVq2Zd7ty5s5E9e/Y7Hqd9+/aGv7+/ceTIEZv2ESNGGJKMPXv2pLtdcnKycfPmTWPAgAF
      "text/plain": [
       "<Figure size 1500x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Plot target and cp in one histogramm via crosstab\n",
    "pd.crosstab(df.cp,df.target).plot(kind=\"bar\",figsize=(15,6),color=['#11A5AA','#AA1190' ])\n",
    "plt.title('Heart Disease Distribution According To Chest Pain Type')\n",
    "plt.xlabel('Chest Pain Type')\n",
    "plt.xticks(rotation = 0)\n",
    "plt.ylabel('Frequency of Disease or Not')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.legend.Legend at 0x7fae87ff5c10>"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# plot correlations for target\n",
    "plt.figure()\n",
    "plt.scatter(x=df.age[df.target==1], y=df.thalach[(df.target==1)], c=\"red\")\n",
    "plt.scatter(x=df.age[df.target==0], y=df.thalach[(df.target==0)])\n",
    "plt.title('Age-max Heart Rate Plot')\n",
    "plt.xlabel('age[years]')\n",
    "plt.ylabel('max. heart rate')\n",
    "plt.legend([\"Disease\", \"No Disease\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.legend.Legend at 0x7fae885004f0>"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure()\n",
    "plt.scatter(x=df.age[df.target==1], y=df.chol[(df.target==1)], c=\"red\")\n",
    "plt.scatter(x=df.age[df.target==0], y=df.chol[(df.target==0)])\n",
    "plt.title('Age-Cholesterol Plot')\n",
    "plt.xlabel('age[years]')\n",
    "plt.ylabel('Cholesterol')\n",
    "plt.legend([\"Disease\", \"No Disease\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.8.16"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}