Unterlagen
This commit is contained in:
git-sandro
parent
89a8543159
commit
be3b063764
1295
notebooks/lego/Bring_data_to_tidy.ipynb
Normal file
1295
notebooks/lego/Bring_data_to_tidy.ipynb
Normal file
File diff suppressed because it is too large
Load Diff
567
notebooks/lego/Datenqualitaet_Loesung_Lego.ipynb
Normal file
567
notebooks/lego/Datenqualitaet_Loesung_Lego.ipynb
Normal file
@ -0,0 +1,567 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "7cff0901",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Datenqualität — Musterlösung (Lego)\n",
|
||||
"\n",
|
||||
"**Modul M04 — Data Strategy, Quality & Tidy Data · `lego_daten_tidy.csv`** \n",
|
||||
"Prof. Dr. Yves Staudt\n",
|
||||
"\n",
|
||||
"Wir beurteilen die **objektive** (messbare) und **subjektive** (zweckabhängige)\n",
|
||||
"Datenqualität und prüfen, ob der Datensatz **tidy** ist."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "ef13c590",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Pakete & Daten"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "ca37b23b",
|
||||
"metadata": {
|
||||
"execution": {
|
||||
"iopub.execute_input": "2026-06-03T21:52:04.296931Z",
|
||||
"iopub.status.busy": "2026-06-03T21:52:04.296673Z",
|
||||
"iopub.status.idle": "2026-06-03T21:52:04.789460Z",
|
||||
"shell.execute_reply": "2026-06-03T21:52:04.789262Z"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"(890, 47)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"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>name</th>\n",
|
||||
" <th>price</th>\n",
|
||||
" <th>link_picture</th>\n",
|
||||
" <th>Produkttyp</th>\n",
|
||||
" <th>Vorgeschlagenes Geschlecht</th>\n",
|
||||
" <th>Empfohlenes Alter in Jahren (mind.)</th>\n",
|
||||
" <th>Empfohlenes Alter in Jahren (max.)</th>\n",
|
||||
" <th>Anzahl Teile</th>\n",
|
||||
" <th>Sound-Effekte</th>\n",
|
||||
" <th>Produktfarbe</th>\n",
|
||||
" <th>...</th>\n",
|
||||
" <th>Anzahl Produkte pro Versandkarton</th>\n",
|
||||
" <th>Hauptkarton GTIN (EAN/UPC)</th>\n",
|
||||
" <th>Lagenanzahl pro Palette</th>\n",
|
||||
" <th>Produkte pro Palettenlage</th>\n",
|
||||
" <th>Fernbedienung erforderlich</th>\n",
|
||||
" <th>Warnung vor Erstickungsgefahr</th>\n",
|
||||
" <th>Fernbedienung enthalten</th>\n",
|
||||
" <th>Akkus/Batterien enthalten</th>\n",
|
||||
" <th>null</th>\n",
|
||||
" <th>LegoCategory</th>\n",
|
||||
" </tr>\n",
|
||||
" </thead>\n",
|
||||
" <tbody>\n",
|
||||
" <tr>\n",
|
||||
" <th>0</th>\n",
|
||||
" <td>LEGO Harry Potter Schloss Hogwarts™ mit Schlos...</td>\n",
|
||||
" <td>179.00</td>\n",
|
||||
" <td>https://www.fcw.ch/api/ProcessRequest/191538/B...</td>\n",
|
||||
" <td>Bausatz</td>\n",
|
||||
" <td>Junge/Mädchen</td>\n",
|
||||
" <td>18.0</td>\n",
|
||||
" <td>99.0</td>\n",
|
||||
" <td>2660.0</td>\n",
|
||||
" <td></td>\n",
|
||||
" <td>Mehrfarbig</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>LEGO Harry Potter Schloss Hogwarts™ mit Schlos...</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>1</th>\n",
|
||||
" <td>LEGO Disney - Kamera – Hommage an Walt Disney ...</td>\n",
|
||||
" <td>119.00</td>\n",
|
||||
" <td>https://www.fcw.ch/api/ProcessRequest/191541/B...</td>\n",
|
||||
" <td>Bausatz</td>\n",
|
||||
" <td>Junge/Mädchen</td>\n",
|
||||
" <td>18.0</td>\n",
|
||||
" <td>99.0</td>\n",
|
||||
" <td>811.0</td>\n",
|
||||
" <td></td>\n",
|
||||
" <td>Mehrfarbig</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>LEGO Disney</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>2</th>\n",
|
||||
" <td>LEGO Technic - Audi RS Q e-tron (42160)</td>\n",
|
||||
" <td>159.00</td>\n",
|
||||
" <td>https://www.fcw.ch/api/ProcessRequest/190646/B...</td>\n",
|
||||
" <td>Bausatz</td>\n",
|
||||
" <td>Junge/Mädchen</td>\n",
|
||||
" <td>10.0</td>\n",
|
||||
" <td>99.0</td>\n",
|
||||
" <td>914.0</td>\n",
|
||||
" <td></td>\n",
|
||||
" <td>Mehrfarbig</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>LEGO Technic</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>3</th>\n",
|
||||
" <td>LEGO Technic - Lamborghini Huracán Tecnica (42...</td>\n",
|
||||
" <td>59.95</td>\n",
|
||||
" <td>https://www.fcw.ch/api/ProcessRequest/190611/B...</td>\n",
|
||||
" <td>Bausatz</td>\n",
|
||||
" <td>Junge/Mädchen</td>\n",
|
||||
" <td>9.0</td>\n",
|
||||
" <td>99.0</td>\n",
|
||||
" <td>806.0</td>\n",
|
||||
" <td></td>\n",
|
||||
" <td>Mehrfarbig</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>LEGO Technic</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>4</th>\n",
|
||||
" <td>LEGO City - Personen-Schnellzug (60337)</td>\n",
|
||||
" <td>169.00</td>\n",
|
||||
" <td>https://www.fcw.ch/api/ProcessRequest/138905/B...</td>\n",
|
||||
" <td>Bausatz</td>\n",
|
||||
" <td>Junge/Mädchen</td>\n",
|
||||
" <td>7.0</td>\n",
|
||||
" <td>99.0</td>\n",
|
||||
" <td>764.0</td>\n",
|
||||
" <td></td>\n",
|
||||
" <td>Mehrfarbig</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>LEGO City</td>\n",
|
||||
" </tr>\n",
|
||||
" </tbody>\n",
|
||||
"</table>\n",
|
||||
"<p>5 rows × 47 columns</p>\n",
|
||||
"</div>"
|
||||
],
|
||||
"text/plain": [
|
||||
" name price \\\n",
|
||||
"0 LEGO Harry Potter Schloss Hogwarts™ mit Schlos... 179.00 \n",
|
||||
"1 LEGO Disney - Kamera – Hommage an Walt Disney ... 119.00 \n",
|
||||
"2 LEGO Technic - Audi RS Q e-tron (42160) 159.00 \n",
|
||||
"3 LEGO Technic - Lamborghini Huracán Tecnica (42... 59.95 \n",
|
||||
"4 LEGO City - Personen-Schnellzug (60337) 169.00 \n",
|
||||
"\n",
|
||||
" link_picture Produkttyp \\\n",
|
||||
"0 https://www.fcw.ch/api/ProcessRequest/191538/B... Bausatz \n",
|
||||
"1 https://www.fcw.ch/api/ProcessRequest/191541/B... Bausatz \n",
|
||||
"2 https://www.fcw.ch/api/ProcessRequest/190646/B... Bausatz \n",
|
||||
"3 https://www.fcw.ch/api/ProcessRequest/190611/B... Bausatz \n",
|
||||
"4 https://www.fcw.ch/api/ProcessRequest/138905/B... Bausatz \n",
|
||||
"\n",
|
||||
" Vorgeschlagenes Geschlecht Empfohlenes Alter in Jahren (mind.) \\\n",
|
||||
"0 Junge/Mädchen 18.0 \n",
|
||||
"1 Junge/Mädchen 18.0 \n",
|
||||
"2 Junge/Mädchen 10.0 \n",
|
||||
"3 Junge/Mädchen 9.0 \n",
|
||||
"4 Junge/Mädchen 7.0 \n",
|
||||
"\n",
|
||||
" Empfohlenes Alter in Jahren (max.) Anzahl Teile Sound-Effekte \\\n",
|
||||
"0 99.0 2660.0 \n",
|
||||
"1 99.0 811.0 \n",
|
||||
"2 99.0 914.0 \n",
|
||||
"3 99.0 806.0 \n",
|
||||
"4 99.0 764.0 \n",
|
||||
"\n",
|
||||
" Produktfarbe ... Anzahl Produkte pro Versandkarton \\\n",
|
||||
"0 Mehrfarbig ... NaN \n",
|
||||
"1 Mehrfarbig ... NaN \n",
|
||||
"2 Mehrfarbig ... NaN \n",
|
||||
"3 Mehrfarbig ... NaN \n",
|
||||
"4 Mehrfarbig ... NaN \n",
|
||||
"\n",
|
||||
" Hauptkarton GTIN (EAN/UPC) Lagenanzahl pro Palette \\\n",
|
||||
"0 NaN NaN \n",
|
||||
"1 NaN NaN \n",
|
||||
"2 NaN NaN \n",
|
||||
"3 NaN NaN \n",
|
||||
"4 NaN NaN \n",
|
||||
"\n",
|
||||
" Produkte pro Palettenlage Fernbedienung erforderlich \\\n",
|
||||
"0 NaN NaN \n",
|
||||
"1 NaN NaN \n",
|
||||
"2 NaN NaN \n",
|
||||
"3 NaN NaN \n",
|
||||
"4 NaN NaN \n",
|
||||
"\n",
|
||||
" Warnung vor Erstickungsgefahr Fernbedienung enthalten \\\n",
|
||||
"0 NaN NaN \n",
|
||||
"1 NaN NaN \n",
|
||||
"2 NaN NaN \n",
|
||||
"3 NaN NaN \n",
|
||||
"4 NaN NaN \n",
|
||||
"\n",
|
||||
" Akkus/Batterien enthalten null \\\n",
|
||||
"0 NaN NaN \n",
|
||||
"1 NaN NaN \n",
|
||||
"2 NaN NaN \n",
|
||||
"3 NaN NaN \n",
|
||||
"4 NaN NaN \n",
|
||||
"\n",
|
||||
" LegoCategory \n",
|
||||
"0 LEGO Harry Potter Schloss Hogwarts™ mit Schlos... \n",
|
||||
"1 LEGO Disney \n",
|
||||
"2 LEGO Technic \n",
|
||||
"3 LEGO Technic \n",
|
||||
"4 LEGO City \n",
|
||||
"\n",
|
||||
"[5 rows x 47 columns]"
|
||||
]
|
||||
},
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import pandas as pd\n",
|
||||
"import numpy as np\n",
|
||||
"df = pd.read_csv(\"../../../Data/lego/lego_daten_tidy.csv\")\n",
|
||||
"print(df.shape)\n",
|
||||
"df.head()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "58a491c1",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 1 Objektive Datenqualität\n",
|
||||
"\n",
|
||||
"Messbar und nutzerunabhängig: **Vollständigkeit**, **Konsistenz**, **Genauigkeit**."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "bdd7106b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Vollständigkeit (fehlende Werte)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "dbd27974",
|
||||
"metadata": {
|
||||
"execution": {
|
||||
"iopub.execute_input": "2026-06-03T21:52:04.790694Z",
|
||||
"iopub.status.busy": "2026-06-03T21:52:04.790633Z",
|
||||
"iopub.status.idle": "2026-06-03T21:52:04.793783Z",
|
||||
"shell.execute_reply": "2026-06-03T21:52:04.793592Z"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Gesamtanteil fehlender Werte: 49.1 %\n",
|
||||
"\n",
|
||||
"Spalten mit den meisten Lücken:\n",
|
||||
"Freigabedatum (TT/MM/JJ) 87.5\n",
|
||||
"Warnung vor Erstickungsgefahr 87.3\n",
|
||||
"Fernbedienung erforderlich 87.1\n",
|
||||
"Fernbedienung enthalten 87.1\n",
|
||||
"Anzahl der Versandkartons pro Vorlagenkarton 86.1\n",
|
||||
"Anzahl der Pakete 85.5\n",
|
||||
"EU TSD Sprache 85.2\n",
|
||||
"null 84.6\n",
|
||||
"Nettogewicht Hauptkarton 84.0\n",
|
||||
"Figur enthalten 83.5\n",
|
||||
"dtype: float64\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"na = (df.isna().mean()*100).round(1)\n",
|
||||
"print('Gesamtanteil fehlender Werte: %.1f %%' % (df.isna().mean().mean()*100))\n",
|
||||
"print('\\nSpalten mit den meisten Lücken:')\n",
|
||||
"print(na.sort_values(ascending=False).head(10))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "a750b3c3",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"**Evaluation.** Viele Spalten haben hohe Fehlquoten (Versand-/Verpackungsangaben oft >80\\,%). Für eine Preisanalyse sind v.\\,a. `price`, `Anzahl Teile`, `Empfohlenes Alter` relevant — diese sind deutlich vollständiger."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "290f7886",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Konsistenz (Duplikate, konstante Spalten, Typen)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "049719ac",
|
||||
"metadata": {
|
||||
"execution": {
|
||||
"iopub.execute_input": "2026-06-03T21:52:04.794890Z",
|
||||
"iopub.status.busy": "2026-06-03T21:52:04.794813Z",
|
||||
"iopub.status.idle": "2026-06-03T21:52:04.800139Z",
|
||||
"shell.execute_reply": "2026-06-03T21:52:04.799954Z"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Doppelte Zeilen: 0\n",
|
||||
"Konstante Spalten (kein Informationsgehalt): 12\n",
|
||||
" ['Sound-Effekte', 'Material', 'Batterien erforderlich', 'Menge pro Packung', 'Montage erforderlich', 'Anzahl der Pakete', 'Figur enthalten', 'Fernbedienung erforderlich']\n",
|
||||
"Datentypen:\n",
|
||||
"object 36\n",
|
||||
"float64 11\n",
|
||||
"Name: count, dtype: int64\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"dups = df.duplicated().sum()\n",
|
||||
"const = [c for c in df.columns if df[c].nunique(dropna=True) <= 1]\n",
|
||||
"print('Doppelte Zeilen:', int(dups))\n",
|
||||
"print('Konstante Spalten (kein Informationsgehalt):', len(const))\n",
|
||||
"print(' ', const[:8])\n",
|
||||
"print('Datentypen:'); print(df.dtypes.value_counts())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "658c1011",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"**Evaluation.** Es gibt **12 konstante** Spalten (inkl. einer Spalte `null`) — redundant/inkonsistent erhoben. Mehrere eigentlich numerische Grössen sind als Text (`object`) gespeichert — ein Konsistenzproblem für spätere Berechnungen."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5aa5a284",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Genauigkeit (Plausibilität)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "735e79b3",
|
||||
"metadata": {
|
||||
"execution": {
|
||||
"iopub.execute_input": "2026-06-03T21:52:04.801270Z",
|
||||
"iopub.status.busy": "2026-06-03T21:52:04.801194Z",
|
||||
"iopub.status.idle": "2026-06-03T21:52:04.803055Z",
|
||||
"shell.execute_reply": "2026-06-03T21:52:04.802889Z"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"price: min=3.00 max=949.00 median=54.95\n",
|
||||
"negative oder Null-Preise: 0\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print('price: min=%.2f max=%.2f median=%.2f' % (df['price'].min(), df['price'].max(), df['price'].median()))\n",
|
||||
"print('negative oder Null-Preise:', int((df['price'] <= 0).sum()))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "8f1109f3",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"**Evaluation.** Genauigkeit lässt sich ohne Referenz nur über Plausibilität prüfen: die Preise liegen im sinnvollen Bereich (keine negativen Werte), einzelne sehr hohe Werte (bis ~949) sind plausible Ausreisser (grosse Sets)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "dd6a6a4c",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 2 Subjektive Datenqualität\n",
|
||||
"\n",
|
||||
"Hängt vom **Verwendungszweck** ab (Eignung, Relevanz, Vertrauenswürdigkeit).\n",
|
||||
"\n",
|
||||
"**Bewertung für den Zweck *Preisvorhersage von Lego-Sets*:**\n",
|
||||
"- *Relevant* sind `price` (Ziel), `Anzahl Teile`, `Empfohlenes Alter`, `Produktfarbe`,\n",
|
||||
" `Ursprungsland` — diese sind brauchbar.\n",
|
||||
"- *Wenig brauchbar* sind die vielen lückenhaften Logistik-/Verpackungsspalten und die\n",
|
||||
" konstanten Spalten — sie stiften für diesen Zweck keinen Mehrwert.\n",
|
||||
"- *Vertrauenswürdigkeit:* mittel — die Kerngrössen wirken solide, aber die vielen\n",
|
||||
" Lücken und Text-statt-Zahl-Felder erfordern Aufbereitung (→ M08/M11).\n",
|
||||
"\n",
|
||||
"Für einen *anderen* Zweck (z.\\,B. Logistikplanung) wären genau die jetzt verworfenen\n",
|
||||
"Verpackungsspalten zentral — Datenqualität ist also **zweckrelativ**."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "cb2d47fb",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 3 Tidy Data\n",
|
||||
"\n",
|
||||
"**Tidy** (Wickham): (1) jede *Variable* eine Spalte, (2) jede *Beobachtung* eine Zeile,\n",
|
||||
"(3) jede *Beobachtungseinheit* eine Tabelle."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "e29cedbb",
|
||||
"metadata": {
|
||||
"execution": {
|
||||
"iopub.execute_input": "2026-06-03T21:52:04.804148Z",
|
||||
"iopub.status.busy": "2026-06-03T21:52:04.804093Z",
|
||||
"iopub.status.idle": "2026-06-03T21:52:04.805688Z",
|
||||
"shell.execute_reply": "2026-06-03T21:52:04.805511Z"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Zeilen = Beobachtungen (Lego-Sets): 890\n",
|
||||
"Eindeutige Produktnamen: 890\n",
|
||||
"Spalten = Variablen: 47\n",
|
||||
"Leere/Pseudo-Spalte vorhanden: True\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print('Zeilen = Beobachtungen (Lego-Sets):', len(df))\n",
|
||||
"print('Eindeutige Produktnamen:', df['name'].nunique())\n",
|
||||
"print('Spalten = Variablen:', df.shape[1])\n",
|
||||
"print('Leere/Pseudo-Spalte vorhanden:', 'null' in df.columns)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "792c7f1b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"**Evaluation.** Der Datensatz ist **weitgehend tidy**: eine Zeile pro Lego-Set, eine Spalte pro Eigenschaft, eine Beobachtungseinheit (Produkte). **Verstösse:** die Spalte `null` ist keine echte Variable, einige numerische Grössen stehen als Text, und konstante Spalten tragen keine Variableninformation. Nach Bereinigung (konstante/`null` entfernen, Typen korrigieren) ist er sauber tidy."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "25ca3d6b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Fazit\n",
|
||||
"\n",
|
||||
"Objektiv: hohe Vollständigkeit nur bei den Kernvariablen, einige Konsistenzmängel (konstante Spalten, Text-statt-Zahl). Subjektiv: für die Preisvorhersage gut nutzbar, für Logistik weniger. Struktur: weitgehend tidy mit kleinen, behebbaren Verstössen."
|
||||
]
|
||||
}
|
||||
],
|
||||
"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": "3.12.7"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
Binary file not shown.
BIN
unterlagen/M05_Data_Formats_Modalities.pdf
Normal file
BIN
unterlagen/M05_Data_Formats_Modalities.pdf
Normal file
Binary file not shown.
BIN
unterlagen/M06_Argue_with_Data.pdf
Normal file
BIN
unterlagen/M06_Argue_with_Data.pdf
Normal file
Binary file not shown.
BIN
unterlagen/ML_Kurs_Aufgabenblatt_Missing_Data.pdf
Normal file
BIN
unterlagen/ML_Kurs_Aufgabenblatt_Missing_Data.pdf
Normal file
Binary file not shown.
BIN
unterlagen/leitfaden.pdf
Normal file
BIN
unterlagen/leitfaden.pdf
Normal file
Binary file not shown.
Loading…
x
Reference in New Issue
Block a user