From f5a8d8d7ace59d1eea23d057e29c4d9e80c001ee Mon Sep 17 00:00:00 2001
From: I569996 <maximilian.otto@sap.com>
Date: Tue, 1 Jul 2025 09:35:33 +0200
Subject: [PATCH] Added some Graphics for the presentation

---
 visualize.ipynb | 61 +++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 49 insertions(+), 12 deletions(-)

diff --git a/visualize.ipynb b/visualize.ipynb
index 31a5e42..cf6e1d5 100644
--- a/visualize.ipynb
+++ b/visualize.ipynb
@@ -9,7 +9,6 @@
    "source": [
     "import numpy as np\n",
     "import pandas as pd\n",
-    "from matplotlib.pyplot import subplots\n",
     "import seaborn as sns\n",
     "import matplotlib.pyplot as plt"
    ]
@@ -67,16 +66,6 @@
     "plt.show()"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "662bb642",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# "
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "277ef692",
@@ -148,6 +137,54 @@
     "        plt.legend()\n",
     "        plt.show()\n"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "061cec86",
+   "metadata": {},
+   "source": [
+    "# Visualisierungen für Präsentation (Data Understanding & Data Prep)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f42b29c1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Hemoglobin - Smoking\n",
+    "\n",
+    "plt.figure(figsize=(8, 4))\n",
+    "for status in df_train['smoking'].unique():\n",
+    "    subset = df_train[df_train['smoking'] == status]\n",
+    "    plt.hist(subset['hemoglobin'], bins=100, alpha=0.5, label=f'Smoking: {status}')\n",
+    "plt.title('Hemoglobin Distribution by Smoking Status')\n",
+    "plt.xlabel('Hemoglobin')\n",
+    "plt.ylabel('Count')\n",
+    "plt.legend()\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "adcef998",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Height - Smoking\n",
+    "\n",
+    "plt.figure(figsize=(8, 4))\n",
+    "for status in df_train['smoking'].unique():\n",
+    "    subset = df_train[df_train['smoking'] == status]\n",
+    "    plt.hist(subset['height(cm)'], bins=11, alpha=0.5, label=f'Smoking: {status}')\n",
+    "plt.title('Height(cm) Distribution by Smoking Status')\n",
+    "plt.xlabel('Height(cm)')\n",
+    "plt.ylabel('Count')\n",
+    "plt.legend()\n",
+    "plt.show()"
+   ]
   }
  ],
  "metadata": {
@@ -166,7 +203,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.13.3"
+   "version": "3.13.4"
   }
  },
  "nbformat": 4,