diff --git a/data-preparation.ipynb b/data-preparation.ipynb
new file mode 100644
index 0000000..70c6ced
--- /dev/null
+++ b/data-preparation.ipynb
@@ -0,0 +1,92 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "eda9759b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "original = pd.read_csv(\"data/smoker_train.csv\")\n",
+    "\n",
+    "# Number of Rows\n",
+    "# Original:         38984\n",
+    "# Ohne Duplikate:   33467\n",
+    "# Ohne Nullwerte:   33467\n",
+    "# Real. Blutdruck:  33467 \n",
+    "# Cholesterin:      33344\n",
+    "# BMI:              33340\n",
+    "# Anderes:          33302"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "94a8e555",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def clean_up(df):\n",
+    "    # Duplikate Löschen\n",
+    "    x = df.drop_duplicates()\n",
+    "    \n",
+    "    # Delete rows with null values\n",
+    "    x = x.dropna()\n",
+    "    \n",
+    "    # Delete rows with impossible blood pressure values\n",
+    "    x = x[x[\"systolic\"] > x[\"relaxation\"]]\n",
+    "    \n",
+    "    # Cholesterin\n",
+    "    x = x[abs(x[\"Cholesterol\"] - x[\"HDL\"] - x[\"LDL\"] - x[\"triglyceride\"] / 5) < 30]\n",
+    "    \n",
+    "    # BMI > 16\n",
+    "    x = x[(x[\"weight(kg)\"] / ((x[\"height(cm)\"] / 100) ** 2)) >= 15]\n",
+    "    \n",
+    "    # Anderes -> 10-facher Normbereich\n",
+    "    x = x[x[\"AST\"] < 500] # 8 Werte\n",
+    "    x = x[x[\"ALT\"] < 500] # 4 Werte\n",
+    "    x = x[x[\"Gtp\"] < 660] # 26 Werte\n",
+    "    x = x[x[\"hemoglobin\"] < 180] # 0 Werte\n",
+    "    x = x[x[\"serum creatinine\"] < 12] # 0 Werte\n",
+    "    x = x[x[\"fasting blood sugar\"] < 1000] # 0 Werte\n",
+    "    \n",
+    "    return x \n",
+    "\n",
+    "print(len(clean_up(original)))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "19704c5b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y = original[\"fasting blood sugar\"].sort_values()\n",
+    "y.tail(30)"
+   ]
+  }
+ ],
+ "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": "3.13.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}