DSA_SoSe_24/Cleaning.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "c95fbd16-09ed-497b-892a-473496150996",
   "metadata": {},
   "source": [
    "<h1>Cleaning</h1>\n",
    "<p>Import dataset using the ucirepo package</p>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "3eb339fa-ef85-4544-9ad0-bc22d4de9f1a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>age</th>\n",
       "      <th>sex</th>\n",
       "      <th>cp</th>\n",
       "      <th>trestbps</th>\n",
       "      <th>chol</th>\n",
       "      <th>fbs</th>\n",
       "      <th>restecg</th>\n",
       "      <th>thalach</th>\n",
       "      <th>exang</th>\n",
       "      <th>oldpeak</th>\n",
       "      <th>slope</th>\n",
       "      <th>ca</th>\n",
       "      <th>thal</th>\n",
       "      <th>goal</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>63</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>145</td>\n",
       "      <td>233</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>150</td>\n",
       "      <td>0</td>\n",
       "      <td>2.3</td>\n",
       "      <td>3</td>\n",
       "      <td>0.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>67</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>160</td>\n",
       "      <td>286</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>108</td>\n",
       "      <td>1</td>\n",
       "      <td>1.5</td>\n",
       "      <td>2</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>67</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>120</td>\n",
       "      <td>229</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>129</td>\n",
       "      <td>1</td>\n",
       "      <td>2.6</td>\n",
       "      <td>2</td>\n",
       "      <td>2.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>37</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>130</td>\n",
       "      <td>250</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>187</td>\n",
       "      <td>0</td>\n",
       "      <td>3.5</td>\n",
       "      <td>3</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>41</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>130</td>\n",
       "      <td>204</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>172</td>\n",
       "      <td>0</td>\n",
       "      <td>1.4</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   age  sex  cp  trestbps  chol  fbs  restecg  thalach  exang  oldpeak  slope  \\\n",
       "0   63    1   1       145   233    1        2      150      0      2.3      3   \n",
       "1   67    1   4       160   286    0        2      108      1      1.5      2   \n",
       "2   67    1   4       120   229    0        2      129      1      2.6      2   \n",
       "3   37    1   3       130   250    0        0      187      0      3.5      3   \n",
       "4   41    0   2       130   204    0        2      172      0      1.4      1   \n",
       "\n",
       "    ca  thal  goal  \n",
       "0  0.0   6.0     0  \n",
       "1  3.0   3.0     2  \n",
       "2  2.0   7.0     1  \n",
       "3  0.0   3.0     0  \n",
       "4  0.0   3.0     0  "
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from ucimlrepo import fetch_ucirepo\n",
    "import pandas as pd\n",
    "\n",
    "# fetch dataset \n",
    "heart_disease = fetch_ucirepo(id=45) \n",
    "  \n",
    "# data (as pandas dataframes) \n",
    "X = heart_disease.data.features \n",
    "y = heart_disease.data.targets \n",
    "\n",
    "df = pd.concat([X, y], axis=1)\n",
    "df = df.rename(columns={'num':'goal'})\n",
    "\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8c5ab8b9-e46a-4968-b0c8-fe393f093f73",
   "metadata": {},
   "source": [
    "<p>Get overview of all missing values. As there are only a few, those rows can be dropped.</p>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "6f7e6a3a-63cb-40e2-8746-937c24b184ef",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "age         0\n",
       "sex         0\n",
       "cp          0\n",
       "trestbps    0\n",
       "chol        0\n",
       "fbs         0\n",
       "restecg     0\n",
       "thalach     0\n",
       "exang       0\n",
       "oldpeak     0\n",
       "slope       0\n",
       "ca          4\n",
       "thal        2\n",
       "goal        0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "d1639e92-d401-49fb-a1f1-67250ffa2c81",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.dropna(inplace=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "192da26d-0fb1-4b06-a046-a41b66576ed0",
   "metadata": {},
   "source": [
    "<h1>Preprocessing</h1>\n",
    "<p>Split</p>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "24675f41-d48f-4e27-a3d8-e303556ee7d1",
   "metadata": {},
   "outputs": [],
   "source": [
    "df['goal'] = df['goal'].replace({0: 0, 1: 1, 2: 1, 3: 1, 4: 1})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "d7bf2c46-7885-4dfe-a4e7-8b8439cf0434",
   "metadata": {},
   "outputs": [],
   "source": [
    "# save 'cleaned' dataset as csv file for further processing\n",
    "import os\n",
    "os.makedirs('data', exist_ok=True)\n",
    "df.to_csv('./data/dataset_cleaned.csv', index=False)"
   ]
  }
 ],
 "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": "3.11.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}