From 561ba54f0bc721db3e96232bcce0f6b24afb62a3 Mon Sep 17 00:00:00 2001
From: I569996 <maximilian.otto@sap.com>
Date: Thu, 26 Jun 2025 09:41:45 +0200
Subject: [PATCH 1/2] added clean_up function

---
 data-preparation.ipynb | 141 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 141 insertions(+)
 create mode 100644 data-preparation.ipynb

diff --git a/data-preparation.ipynb b/data-preparation.ipynb
new file mode 100644
index 0000000..01f54a8
--- /dev/null
+++ b/data-preparation.ipynb
@@ -0,0 +1,141 @@
+{
+ "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": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "33302\n"
+     ]
+    }
+   ],
+   "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": 4,
+   "id": "19704c5b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "18248    302\n",
+       "22530    303\n",
+       "23521    303\n",
+       "25010    305\n",
+       "11078    307\n",
+       "11190    308\n",
+       "15180    309\n",
+       "34033    310\n",
+       "13660    313\n",
+       "19433    313\n",
+       "15530    314\n",
+       "31343    315\n",
+       "8358     315\n",
+       "37194    318\n",
+       "34982    329\n",
+       "7532     330\n",
+       "35606    341\n",
+       "37408    342\n",
+       "32310    342\n",
+       "29230    349\n",
+       "15263    365\n",
+       "5479     369\n",
+       "24060    369\n",
+       "27782    369\n",
+       "25007    375\n",
+       "28494    375\n",
+       "31056    386\n",
+       "4977     391\n",
+       "31123    398\n",
+       "38530    423\n",
+       "Name: fasting blood sugar, dtype: int64"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "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
+}

From ddae472effcad1552ac64dca8f5e57a45e79bfab Mon Sep 17 00:00:00 2001
From: I569996 <maximilian.otto@sap.com>
Date: Thu, 26 Jun 2025 09:43:42 +0200
Subject: [PATCH 2/2] jona rumberg

---
 data-preparation.ipynb | 55 +++---------------------------------------
 1 file changed, 3 insertions(+), 52 deletions(-)

diff --git a/data-preparation.ipynb b/data-preparation.ipynb
index 01f54a8..70c6ced 100644
--- a/data-preparation.ipynb
+++ b/data-preparation.ipynb
@@ -25,15 +25,7 @@
    "execution_count": null,
    "id": "94a8e555",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "33302\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "def clean_up(df):\n",
     "    # Duplikate Löschen\n",
@@ -66,51 +58,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "id": "19704c5b",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "18248    302\n",
-       "22530    303\n",
-       "23521    303\n",
-       "25010    305\n",
-       "11078    307\n",
-       "11190    308\n",
-       "15180    309\n",
-       "34033    310\n",
-       "13660    313\n",
-       "19433    313\n",
-       "15530    314\n",
-       "31343    315\n",
-       "8358     315\n",
-       "37194    318\n",
-       "34982    329\n",
-       "7532     330\n",
-       "35606    341\n",
-       "37408    342\n",
-       "32310    342\n",
-       "29230    349\n",
-       "15263    365\n",
-       "5479     369\n",
-       "24060    369\n",
-       "27782    369\n",
-       "25007    375\n",
-       "28494    375\n",
-       "31056    386\n",
-       "4977     391\n",
-       "31123    398\n",
-       "38530    423\n",
-       "Name: fasting blood sugar, dtype: int64"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "y = original[\"fasting blood sugar\"].sort_values()\n",
     "y.tail(30)"