2024-05-08 08:48:17 +02:00
{
"cells": [
{
"cell_type": "code",
2024-06-07 11:20:34 +02:00
"execution_count": 1,
2024-05-08 08:48:17 +02:00
"id": "37d611da-6f56-46d8-905a-62026750150c",
"metadata": {
"tags": []
},
"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",
2024-06-07 15:16:29 +02:00
" <td>male</td>\n",
2024-05-08 08:48:17 +02:00
" <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",
2024-06-07 15:16:29 +02:00
" <td>1</td>\n",
2024-05-08 08:48:17 +02:00
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>67</td>\n",
2024-06-07 15:16:29 +02:00
" <td>male</td>\n",
2024-05-08 08:48:17 +02:00
" <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",
2024-06-07 15:16:29 +02:00
" <td>0</td>\n",
2024-05-08 08:48:17 +02:00
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>67</td>\n",
2024-06-07 15:16:29 +02:00
" <td>male</td>\n",
2024-05-08 08:48:17 +02:00
" <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",
2024-06-07 15:16:29 +02:00
" <td>0</td>\n",
2024-05-08 08:48:17 +02:00
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>37</td>\n",
2024-06-07 15:16:29 +02:00
" <td>male</td>\n",
2024-05-08 08:48:17 +02:00
" <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",
2024-06-07 15:16:29 +02:00
" <td>1</td>\n",
2024-05-08 08:48:17 +02:00
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>41</td>\n",
2024-06-07 15:16:29 +02:00
" <td>female</td>\n",
2024-05-08 08:48:17 +02:00
" <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",
2024-06-07 15:16:29 +02:00
" <td>1</td>\n",
2024-05-08 08:48:17 +02:00
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
2024-06-07 15:16:29 +02:00
" age sex cp trestbps chol fbs restecg thalach exang oldpeak \\\n",
"0 63 male 1 145 233 1 2 150 0 2.3 \n",
"1 67 male 4 160 286 0 2 108 1 1.5 \n",
"2 67 male 4 120 229 0 2 129 1 2.6 \n",
"3 37 male 3 130 250 0 0 187 0 3.5 \n",
"4 41 female 2 130 204 0 2 172 0 1.4 \n",
2024-05-08 08:48:17 +02:00
"\n",
2024-06-07 15:16:29 +02:00
" slope ca thal goal \n",
"0 3 0.0 6.0 1 \n",
"1 2 3.0 3.0 0 \n",
"2 2 2.0 7.0 0 \n",
"3 3 0.0 3.0 1 \n",
"4 1 0.0 3.0 1 "
2024-05-08 08:48:17 +02:00
]
},
2024-06-07 11:20:34 +02:00
"execution_count": 1,
2024-05-08 08:48:17 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
2024-06-07 11:20:34 +02:00
"import pandas as pd\n",
"import numpy as np\n",
"\n",
"df = pd.read_csv('./data/dataset_cleaned.csv')\n",
2024-06-07 15:16:29 +02:00
"df['sex'].replace({0: 'female', 1: 'male'}, inplace=True)\n",
2024-06-07 11:20:34 +02:00
"\n",
"# extract all columns except 'goal' --> X\n",
"X = df.loc[:, df.columns != 'goal']\n",
"# extract only the column 'goal' --> y\n",
"y = df.loc[:, 'goal']\n",
"\n",
2024-05-08 08:48:17 +02:00
"df.head()"
]
},
2024-06-05 11:20:55 +02:00
{
"cell_type": "code",
2024-06-07 11:20:34 +02:00
"execution_count": 2,
2024-05-08 08:48:17 +02:00
"id": "6b3e5424-4a7e-4e53-82b9-d78e38939834",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
2024-06-07 15:16:29 +02:00
"image/png": "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
2024-05-08 08:48:17 +02:00
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
2024-06-07 15:16:29 +02:00
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"201\n"
]
2024-05-08 08:48:17 +02:00
}
],
"source": [
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"\n",
2024-06-07 15:16:29 +02:00
"counts_male = sum(X['sex'] == 'male')\n",
"counts_female = sum(X['sex'] == 'female')\n",
2024-06-07 11:20:34 +02:00
"\n",
2024-06-07 15:16:29 +02:00
"counts_male_sick = sum(np.all([X['sex'] == 'male',\n",
2024-06-07 11:20:34 +02:00
" y > 0], axis=0))\n",
2024-06-07 15:16:29 +02:00
"counts_female_sick = sum(np.all([X['sex'] == 'female',\n",
2024-06-07 11:20:34 +02:00
" y > 0], axis=0))\n",
2024-05-08 08:48:17 +02:00
"\n",
2024-06-07 15:16:29 +02:00
"plt.bar([1, 0], [counts_male, counts_female])\n",
"plt.bar([1, 0], [counts_male_sick, counts_female_sick])\n",
"plt.xticks([1, 0],['male', 'female'])\n",
"plt.ylabel('n')\n",
2024-05-08 08:48:17 +02:00
"plt.title('Age distribution')\n",
2024-06-07 11:20:34 +02:00
"plt.legend(['healthy', 'sick'])\n",
2024-06-07 15:16:29 +02:00
"plt.show()\n",
"print(counts_male)"
2024-05-08 08:48:17 +02:00
]
},
{
"cell_type": "code",
2024-06-07 11:20:34 +02:00
"execution_count": 3,
2024-05-08 08:48:17 +02:00
"id": "48fd2655-1dcc-41f6-9938-ef6ea937d52e",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
2024-06-07 11:20:34 +02:00
"image/png": "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
2024-05-08 08:48:17 +02:00
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"plt.hist(X['age'])\n",
"plt.xlabel('Age')\n",
"plt.ylabel('counts')\n",
"plt.title('Age distribution')\n",
"plt.show()"
]
},
{
"cell_type": "code",
2024-06-07 11:20:34 +02:00
"execution_count": 4,
2024-05-08 08:48:17 +02:00
"id": "b9174a9d-6c8a-4915-9580-48f23cbdd038",
"metadata": {
"tags": []
},
"outputs": [
2024-06-07 15:16:29 +02:00
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/nicole/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
" if pd.api.types.is_categorical_dtype(vector):\n",
"/Users/nicole/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
" if pd.api.types.is_categorical_dtype(vector):\n",
"/Users/nicole/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
" if pd.api.types.is_categorical_dtype(vector):\n"
]
},
2024-05-08 08:48:17 +02:00
{
"data": {
2024-06-07 15:16:29 +02:00
"image/png": "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
2024-05-08 08:48:17 +02:00
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"ax = sns.violinplot(X, x='sex', y='age')\n",
"ax.set_xticklabels(['male', 'female'])\n",
"plt.title('Age distribution')\n",
"plt.show()"
]
},
{
"cell_type": "code",
2024-06-07 11:20:34 +02:00
"execution_count": 5,
2024-05-08 08:48:17 +02:00
"id": "522ff499-cd7f-4417-ae7d-d637402505b8",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
2024-06-07 11:20:34 +02:00
"image/png": "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
2024-05-08 08:48:17 +02:00
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"ax = plt.hist(X['chol'])\n",
"plt.xlabel('Cholesterin')\n",
"plt.ylabel('counts')\n",
"plt.title('Cholesterin distribution')\n",
"plt.show()"
]
},
{
"cell_type": "code",
2024-06-07 11:20:34 +02:00
"execution_count": 6,
2024-05-08 08:48:17 +02:00
"id": "f220fadf-33ec-4bf6-a225-a2c874f02088",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
2024-06-07 11:20:34 +02:00
"image/png": "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
2024-05-08 08:48:17 +02:00
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"plt.hist(X['trestbps'])\n",
"plt.xlabel('Blood pressure (rest)')\n",
"plt.ylabel('counts')\n",
"plt.title('Blood pressure distribution')\n",
"plt.show()"
]
},
{
"cell_type": "code",
2024-06-07 11:20:34 +02:00
"execution_count": 7,
2024-06-07 15:16:29 +02:00
"id": "abe0020f-8588-48bf-af58-f67b326cdd25",
"metadata": {},
2024-05-08 08:48:17 +02:00
"outputs": [
2024-06-07 15:16:29 +02:00
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/nicole/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
" if pd.api.types.is_categorical_dtype(vector):\n",
"/Users/nicole/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
" if pd.api.types.is_categorical_dtype(vector):\n",
"/Users/nicole/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
" if pd.api.types.is_categorical_dtype(vector):\n"
]
},
2024-05-08 08:48:17 +02:00
{
"data": {
2024-06-07 15:16:29 +02:00
"image/png": "iVBORw0KGgoAAAANSUhEUgAAArcAAAIhCAYAAABUopIpAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy81sbWrAAAACXBIWXMAAA9hAAAPYQGoP6dpAABHOklEQVR4nO3de1hUdeLH8c+RuwgooBBy0Ta7uKCWmkUm3hJxldJKki5adtm8JF4yyzJrS0oLNd1urhtlkrWZVl4yLa0MU7ywarpWhgIpmqYgKiBwfn/0OL+dRW1GgcHD+/U88zzO95w5fA7W6dOZ73zHME3TFAAAAGABDVwdAAAAAKgulFsAAABYBuUWAAAAlkG5BQAAgGVQbgEAAGAZlFsAAABYBuUWAAAAlkG5BQAAgGVQbgEAAGAZlFsAdV56eroMw7B7NG3aVF27dtWSJUuq7G8YhiZPnlzrOffs2SPDMJSenl7rP9uqBgwYoJtvvtnVMQBcRCi3AC4ab731ltatW6fMzEy9+eabcnNzU79+/fTpp5+6OhpqwPHjx/XZZ5/p1ltvdXUUABcRd1cHAABHRUdHq0OHDrbnvXv3VpMmTfTee++pX79+LkxWu06cOKGGDRu6OobDTNNUSUmJfHx8nHrdsmXLVF5eXq/+bgFcOO7cArhoeXt7y9PTUx4eHn+47/bt23XzzTerSZMm8vb2Vrt27fT2229X2S83N1d33XWXmjVrJi8vL1111VV6+eWXVVlZabffvn37NHDgQPn5+SkgIEBJSUkqKChwKPfpaRYrV67Uvffeq8DAQPn6+qpfv376+eef7fbt2rWroqOj9fXXXys2NlYNGzbUfffdJ0kqKirSuHHj1LJlS3l6eqp58+ZKSUnR8ePH7Y7xr3/9S506dVJAQIAaNmyoSy+91HYMSaqsrNRzzz2nK664Qj4+PmrcuLHatGmjmTNn2vYZMmSIWrRoUeVcJk+eLMMw7MYMw9CIESP0+uuv66qrrpKXl5ftd/3jjz8qOTnZ7vf797///Yy/p4ULF6p79+5q0qSJJOnnn3/WHXfcobCwMHl5eSkkJEQ9evRQdna23evef/99XX/99fL19VWjRo0UHx+vLVu22LavXbtWHh4eGjdu3Bn/XubOnXvGPAAuDty5BXDRqKioUHl5uUzT1IEDBzRt2jQdP35cycnJ53zdrl27FBsbq2bNmumVV15RUFCQ3n33XQ0ZMkQHDhzQ+PHjJUm//vqrYmNjVVZWpr/97W9q0aKFlixZonHjxmn37t169dVXJUknT55Uz549tW/fPqWmpuryyy/X0qVLlZSU5NT5DB06VDfddJMyMjKUl5enJ598Ul27dtXWrVvVuHFj23779+/XXXfdpfHjx2vKlClq0KCBTpw4obi4OOXn5+uJJ55QmzZt9P3332vSpEnatm2bVq1aJcMwtG7dOiUlJSkpKUmTJ0+Wt7e39u7dqy+//NJ2/KlTp2ry5Ml68skn1aVLF506dUr/+c9/dPToUafO578tXrxY33zzjSZNmqTQ0FA1a9ZMO3bsUGxsrCIjI/Xyyy8rNDRUK1as0COPPKJDhw7p6aeftr2+pKRES5cuVVpamm2sT58+qqio0NSpUxUZGalDhw4pMzPTLueUKVP05JNP6t5779WTTz6psrIyTZs2TTfeeKM2bNig1q1bq3Pnznruuec0YcIEdenSRYmJifr+++81fPhw3XXXXRo6dOh5nzeAOsAEgDrurbfeMiVVeXh5eZmvvvpqlf0lmU8//bTt+R133GF6eXmZubm5dvslJCSYDRs2NI8ePWqapmlOmDDBlGSuX7/ebr+HH37YNAzD3LVrl2mapvnaa6+ZksyPP/7Ybr8HHnjAlGS+9dZbDp1P//797ca//fZbU5L53HPP2cbi4uJMSeYXX3xht29qaqrZoEEDMysry278ww8/NCWZy5YtM03TNF966SVTku0cz6Rv375mu3btzpl58ODBZlRUVJXxp59+2vzf/5RIMgMCAszffvvNbjw+Pt4MDw83CwsL7cZHjBhhent72+2/ePFi083NzTx48KBpmqZ56NAhU5I5Y8aMs2bMzc013d3dzZEjR9qNHzt2zAwNDTUHDhxoG6usrDT79OljNm7c2Ny+fbvZunVr88orrzSLi4vP+XsAUPcxLQHAReOdd95RVlaWsrKytHz5cg0ePFjDhw/X7Nmzz/m6L7/8Uj169FBERITd+JAhQ3TixAmtW7fOtl/r1q117bXXVtnPNE3b3c7Vq1fLz89PiYmJdvv90R3k/3XnnXfaPY+NjVVUVJRWr15tN96kSRN1797dbmzJkiWKjo5Wu3btVF5ebnvEx8fLMAytWbNGktSxY0dJ0sCBA/XBBx/ol19+qZLj2muv1b///W8NGzZMK1asUFFRkVPncSb/PZ1A+v1O7BdffKH+/furYcOGdpn79OmjkpISfffdd7b9Fy5cqBtvvFFNmzaVJAUGBupPf/qTpk2bprS0NG3ZsqXKVJEVK1aovLxc99xzj93xvb29FRcXZ/udSL9PnXjnnXfk5+enDh06KCcnRx988IF8fX0v+NwBuBblFsBF46qrrlKHDh3UoUMH9e7dW2+88YZ69eql8ePHn/Mt9MOHD+uSSy6pMh4WFmbb7ux+ISEhVfYLDQ116nzOtH9oaKjt55x2pkwHDhzQ1q1b5eHhYffw8/OTaZo6dOiQJKlLly5avHixrfSFh4crOjpa7733nu1Yjz/+uF566SV99913SkhIUFBQkHr06KGNGzc6dT7nynz48GGVl5dr1qxZVTL36dNHkmyZT506pU8//dRulQTDMPTFF18oPj5eU6dO1TXXXKOmTZvqkUce0bFjx2y/E+n3Qv+/P+P999+3Hf+0oKAgJSYmqqSkRL1791ZMTMx5ny+AuoM5twAuam3atNGKFSv0ww8/VLnjelpQUJD2799fZXzfvn2SpODgYKf327BhQ5X9HP1A2bn2Lygo0GWXXWY39r8f2DqdxcfHR//85z/PeOzTWSXp5ptv1s0336zS0lJ99913Sk1NVXJyslq0aKHrr79e7u7uGjNmjMaMGaOjR49q1apVeuKJJxQfH6+8vDw1bNhQ3t7eKi0trfJz/rcwni1zkyZN5ObmprvvvlvDhw8/42tatmwpSVq1apUKCwvVv39/u+1RUVG2D3v98MMP+uCDDzR58mSVlZXp9ddft53zhx9+qKioqDP+jP+2cuVKvfbaa7r22mu1aNEiLVy4kGXHAAug3AK4qJ3+pPzpt6/PpEePHlq0aJH27dtnuwsr/T7NoWHDhrruuuts+6Wmpmrz5s265ppr7PYzDEPdunWTJHXr1k0ffPCBPvnkE7upCRkZGU5lnz9/vl2ZyszM1N69e3X//ff/4Wv79u2rKVOmKCgoyFYK/4iXl5fi4uLUuHFjrVixQlu2bNH1119vt0/jxo1122236ZdfflFKSor27Nmj1q1bq0WLFjp48KAOHDhgu2tdVlamFStWOPSzGzZsqG7dumnLli1q06aNPD09z7rvwoULdd1116l58+Zn3efyyy/Xk08+qYULF2rz5s2SpPj4eLm7u2v37t1/WFJPf0gvLi5OK1eu1IABAzR06FBdc801Dv8+AdRNlFsAF43t27ervLxc0u9vc3/00UdauXKl+vfvf85C8vTTT2vJkiXq1q2bJk2apMDAQM2fP19Lly7V1KlTFRAQIEkaPXq03nnnHf3lL3/Rs88+q6ioKC1dulSvvvqqHn74YV1++eWSpHvuuUfTp0/XPffco+eff16tWrXSsmXLHC56p23cuFH333+/br/9duXl5WnixIlq3ry5hg0b9oevTUlJ0cKFC9WlSxeNHj1abdq0UWVlpXJzc/X5559r7Nix6tSpkyZNmqT8/Hz16NFD4eHhOnr0qGbOnCkPDw/FxcVJkvr162dbQ7hp06bau3evZsyYoaioKLVq1UqSlJSUpEmTJumOO+7Qo48+qpKSEr3yyiuqqKhw+Hxnzpypzp0768Ybb9TDDz+sFi1a6NixY/rpp5/06aef6ssvv1RFRYU+/vhjTZgwwe6
2024-05-08 08:48:17 +02:00
"text/plain": [
2024-06-07 15:16:29 +02:00
"<Figure size 800x600 with 1 Axes>"
2024-05-08 08:48:17 +02:00
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
2024-06-07 15:16:29 +02:00
"plt.figure(figsize=(8, 6))\n",
"sns.boxplot(x='sex', y='trestbps', data=df)\n",
"plt.title('Blood pressure/sex')\n",
"plt.xlabel('sex')\n",
2024-05-08 08:48:17 +02:00
"plt.ylabel('Blood pressure (rest)')\n",
"plt.show()"
]
},
{
"cell_type": "code",
2024-06-07 11:20:34 +02:00
"execution_count": 8,
2024-05-08 08:48:17 +02:00
"id": "5c174a9d-59b7-4efe-a0eb-a132388c1d2a",
"metadata": {
"tags": []
},
"outputs": [
2024-06-07 15:16:29 +02:00
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/nicole/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
" if pd.api.types.is_categorical_dtype(vector):\n",
"/Users/nicole/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
" if pd.api.types.is_categorical_dtype(vector):\n",
"/Users/nicole/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
" if pd.api.types.is_categorical_dtype(vector):\n",
"/Users/nicole/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
" if pd.api.types.is_categorical_dtype(vector):\n",
"/Users/nicole/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
" if pd.api.types.is_categorical_dtype(vector):\n"
]
},
2024-05-08 08:48:17 +02:00
{
"data": {
2024-06-07 15:16:29 +02:00
"image/png": "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
2024-05-08 08:48:17 +02:00
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"from sklearn.linear_model import LinearRegression\n",
"\n",
"model = LinearRegression()\n",
"x = np.array(X['age'])\n",
"x = x[:, np.newaxis]\n",
"reg = model.fit(x, X['chol'])\n",
"pred = reg.predict(x)\n",
"\n",
"sns.scatterplot(X, x='age', y='chol', hue='sex')\n",
"plt.plot(x, pred, color='black')\n",
"plt.xlabel('Age')\n",
"plt.ylabel('Chol')\n",
2024-06-07 11:20:34 +02:00
"plt.title('Chol / Age split by sex')\n",
"plt.show()"
2024-05-08 08:48:17 +02:00
]
},
{
"cell_type": "code",
2024-06-07 11:20:34 +02:00
"execution_count": 9,
2024-05-08 08:48:17 +02:00
"id": "b3d627cf-3ec9-4cd9-bee6-5baeb9d1a22d",
"metadata": {
"tags": []
},
"outputs": [
2024-06-07 15:16:29 +02:00
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/nicole/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
" if pd.api.types.is_categorical_dtype(vector):\n",
"/Users/nicole/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
" if pd.api.types.is_categorical_dtype(vector):\n",
"/Users/nicole/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
" if pd.api.types.is_categorical_dtype(vector):\n",
"/Users/nicole/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
" if pd.api.types.is_categorical_dtype(vector):\n",
"/Users/nicole/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
" if pd.api.types.is_categorical_dtype(vector):\n"
]
},
2024-05-08 08:48:17 +02:00
{
"data": {
2024-06-07 15:16:29 +02:00
"image/png": "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
2024-05-08 08:48:17 +02:00
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"model = LinearRegression()\n",
"x = np.array(X['chol'])\n",
"x = x[:, np.newaxis]\n",
"reg = model.fit(x, X['trestbps'])\n",
"pred = reg.predict(x)\n",
"\n",
"sns.scatterplot(X, x='chol', y='trestbps', hue='sex')\n",
"plt.plot(x, pred, color='black')\n",
"plt.xlabel('Chol')\n",
"plt.ylabel('Blood pressure (rest)')\n",
2024-06-07 11:20:34 +02:00
"plt.title('Blood pressure / Age split by sex')\n",
"plt.show()"
2024-05-08 08:48:17 +02:00
]
},
{
"cell_type": "code",
2024-06-07 15:16:29 +02:00
"execution_count": 47,
2024-05-08 08:48:17 +02:00
"id": "3a6dc91a-f3e9-4d7e-9e4b-58c59d24463c",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
2024-06-07 15:16:29 +02:00
"image/png": "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
2024-05-08 08:48:17 +02:00
"text/plain": [
"<Figure size 640x480 with 2 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
2024-06-07 15:16:29 +02:00
"corr = df.loc[:,df.columns!='sex'].corr()\n",
2024-05-08 08:48:17 +02:00
"\n",
2024-06-07 11:20:34 +02:00
"sns.heatmap(corr)\n",
"plt.show()"
2024-05-08 08:48:17 +02:00
]
2024-06-07 15:16:29 +02:00
},
{
"cell_type": "markdown",
"id": "038d8abb-e88f-472d-95c4-bc0c51695196",
"metadata": {},
"source": [
"### Cholesterinwerte im Vergleich Frauen/Männer"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "48e6d986-b7f9-45e6-8bf2-32e687eb132d",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/nicole/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
" if pd.api.types.is_categorical_dtype(vector):\n",
"/Users/nicole/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
" if pd.api.types.is_categorical_dtype(vector):\n",
"/Users/nicole/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
" if pd.api.types.is_categorical_dtype(vector):\n"
]
},
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 800x600 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"df['sex'] = df['sex'].replace({0: 'female', 1: 'male'})\n",
"plt.figure(figsize=(8, 6))\n",
"sns.boxplot(x='sex', y='chol', data=df)\n",
"plt.title('Cholesterinwerte nach Geschlecht')\n",
"plt.xlabel('Geschlecht')\n",
"plt.ylabel('Cholesterin in mg/dl')\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "3e85fdf6-3a77-41b0-bbc7-a407fbb1374f",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" Geschlecht Untere_Grenze Obere_Grenze\n",
"0 Männer 234.288517 246.199046\n",
"1 Frauen 249.044612 275.413721\n"
]
}
],
"source": [
"# Konfidenzintervall (95%) für Cholesterin Level jeweils für Männer und Frauen\n",
"from scipy import stats\n",
"\n",
"# Filtern nach Geschlecht und Berechnen des Konfidenzintervalls\n",
"conf_level = 0.95\n",
"chol_men = df.loc[df['sex'] == 'male', 'chol']\n",
"chol_women = df.loc[df['sex'] == 'female', 'chol']\n",
"conf_int_men = stats.t.interval(conf_level, len(chol_men) - 1, loc=chol_men.mean(), scale=stats.sem(chol_men))\n",
"conf_int_women = stats.t.interval(conf_level, len(chol_women) - 1, loc=chol_women.mean(), scale=stats.sem(chol_women))\n",
"\n",
"result_table_men_vs_women = pd.DataFrame({\n",
" 'Geschlecht': ['Männer', 'Frauen'],\n",
" 'Untere_Grenze': [conf_int_men[0], conf_int_women[0]],\n",
" 'Obere_Grenze': [conf_int_men[1], conf_int_women[1]]\n",
"})\n",
"\n",
"print(result_table_men_vs_women)"
]
},
{
"cell_type": "markdown",
"id": "4d6ef765-3785-4263-a72f-6e3ab5822d61",
"metadata": {},
"source": [
"### Cholesterin im Vergleich zur Erkrankung"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "fb8d7c02-936a-49c1-adfe-43943f7111d0",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/nicole/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
" if pd.api.types.is_categorical_dtype(vector):\n",
"/Users/nicole/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
" if pd.api.types.is_categorical_dtype(vector):\n",
"/Users/nicole/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
" if pd.api.types.is_categorical_dtype(vector):\n"
]
},
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 1000x600 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# Boxplot gruppiert nach Diagnose\n",
"plt.figure(figsize=(10, 6))\n",
"sns.boxplot(x='goal', y='chol', data=df)\n",
"plt.title('Cholesterin im Vergleich zur Erkrankung')\n",
"plt.xlabel('Diagnose')\n",
"plt.ylabel('Cholesterin in mg/dl')\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "f5d1a57a-8d24-4a23-a035-3e6d7fd7eb89",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"t-Statistik: -1.3834015443480652\n",
"p-Wert: 0.9162061164262881\n",
"Der p-Wert ist größer als oder gleich 0.05, daher wird die Nullhypothese nicht abgelehnt.\n",
"Es gibt keine signifikanten Hinweise darauf, dass der Cholesterinwert bei kranken Personen höher ist als bei gesunden Personen.\n"
]
}
],
"source": [
"# t-Test\n",
"# Nullhypothese (HO) = Cholesterinwert bei Kranken ist gleich oder kleiner wie bei Gesunden\n",
"# Alternativhypothese (H1) Cholesterinwert bei Kranken ist höher als bei Gesunden\n",
"\n",
"from scipy.stats import ttest_ind\n",
"\n",
"# Daten für gesunde und kranke Personen\n",
"chol_healthy = df.loc[df['goal'] == 0, 'chol']\n",
"chol_sick = df.loc[df['goal'] == 1, 'chol']\n",
"\n",
"# Durchführung des t-Tests\n",
"t_statistic, p_value = ttest_ind(chol_sick, chol_healthy, alternative='greater')\n",
"\n",
"# Ausgabe der Ergebnisse\n",
"print(\"t-Statistik:\", t_statistic)\n",
"print(\"p-Wert:\", p_value)\n",
"\n",
"# Überprüfung der Nullhypothese\n",
"if p_value < 0.05:\n",
" print(\"Der p-Wert ist kleiner als 0.05, daher wird die Nullhypothese abgelehnt.\")\n",
" print(\"Es gibt signifikante Hinweise darauf, dass der Cholesterinwert bei kranken Personen höher ist als bei gesunden Personen.\")\n",
"else:\n",
" print(\"Der p-Wert ist größer als oder gleich 0.05, daher wird die Nullhypothese nicht abgelehnt.\")\n",
" print(\"Es gibt keine signifikanten Hinweise darauf, dass der Cholesterinwert bei kranken Personen höher ist als bei gesunden Personen.\")"
]
},
{
"cell_type": "markdown",
"id": "362223d0-efaf-426c-8bb7-81108c065ccf",
"metadata": {},
"source": [
"### Systolischer Ruheblutdruck"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "1574b038-0941-4473-a968-adca7f5ec26e",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/nicole/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
" if pd.api.types.is_categorical_dtype(vector):\n",
"/Users/nicole/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
" if pd.api.types.is_categorical_dtype(vector):\n",
"/Users/nicole/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
" if pd.api.types.is_categorical_dtype(vector):\n"
]
},
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 800x600 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"plt.figure(figsize=(8, 6))\n",
"sns.boxplot(x='sex', y='trestbps', data=df)\n",
"plt.title('Überblick über Blutdruck')\n",
"plt.xlabel('Geschlecht')\n",
"plt.ylabel('Systolischer Ruheblutdruck (in mmHg bei Aufnahme ins Krankenhaus)')\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "0a359020-86f6-4d8c-9144-d2977674e51d",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" Diagnose Untere_Grenze Obere_Grenze\n",
"0 Gesund 131.442350 137.827723\n",
"1 Krank 126.618412 131.731588\n"
]
}
],
"source": [
"# Filtern nach goal und Berechnen des Konfidenzintervalls\n",
"conf_level = 0.95\n",
"blutdruck_gesund = df.loc[df['goal'] == 0, 'trestbps']\n",
"blutdruck_krank = df.loc[df['goal'] == 1, 'trestbps']\n",
"conf_int_gesund = stats.t.interval(conf_level, len(blutdruck_gesund) - 1, loc=blutdruck_gesund.mean(), scale=stats.sem(blutdruck_gesund))\n",
"conf_int_krank = stats.t.interval(conf_level, len(blutdruck_krank) - 1, loc=blutdruck_krank.mean(), scale=stats.sem(blutdruck_krank))\n",
"\n",
"# Erstellen der Tabelle\n",
"result_table_blutdruck = pd.DataFrame({\n",
" 'Diagnose': ['Gesund', 'Krank'],\n",
" 'Untere_Grenze': [conf_int_gesund[0], conf_int_krank[0]],\n",
" 'Obere_Grenze': [conf_int_gesund[1], conf_int_krank[1]]\n",
"})\n",
"\n",
"# Anzeige der Tabelle\n",
"print(result_table_blutdruck)"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "003e4148-8318-41f4-8e38-af74c5ad54fa",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"t-Statistik: -2.6678917570482685\n",
"p-Wert: 0.9959726018205624\n",
"Der p-Wert ist größer als oder gleich 0.05, daher wird die Nullhypothese nicht abgelehnt.\n",
"Es gibt keine signifikanten Hinweise darauf, dass der Blutdruck bei kranken Personen höher ist als bei gesunden Personen.\n"
]
}
],
"source": [
"# t-Test\n",
"# H0 Kranke haben einen niedrigeren oder gleichen Blutdruck wie Gesunde\n",
"# H1 Kranke haben einen höheren BLutdruck als Gesunde\n",
"\n",
"# Daten für gesunde und kranke Personen\n",
"blutdruck_healthy = df.loc[df['goal'] == 0, 'trestbps']\n",
"blutdruck_sick = df.loc[df['goal'] == 1, 'trestbps']\n",
"\n",
"# Durchführung des t-Tests\n",
"t_statistic, p_value = ttest_ind(blutdruck_sick, blutdruck_healthy, alternative='greater')\n",
"\n",
"print(\"t-Statistik:\", t_statistic)\n",
"print(\"p-Wert:\", p_value)\n",
"\n",
"# Überprüfung Nullhypothese\n",
"if p_value < 0.05:\n",
" print(\"Der p-Wert ist kleiner als 0.05, daher wird die Nullhypothese abgelehnt.\")\n",
" print(\"Es gibt signifikante Hinweise darauf, dass der Blutdruck bei kranken Personen höher ist als bei gesunden Personen.\")\n",
"else:\n",
" print(\"Der p-Wert ist größer als oder gleich 0.05, daher wird die Nullhypothese nicht abgelehnt.\")\n",
" print(\"Es gibt keine signifikanten Hinweise darauf, dass der Blutdruck bei kranken Personen höher ist als bei gesunden Personen.\")"
]
2024-05-08 08:48:17 +02:00
}
],
"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",
2024-06-07 15:16:29 +02:00
"version": "3.11.5"
2024-05-08 08:48:17 +02:00
}
},
"nbformat": 4,
"nbformat_minor": 5
}
