diff --git a/Semester_2/Einheit_06/Uebung_5_LSG.ipynb b/Semester_2/Einheit_06/Uebung_5_LSG.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..c2dd61d9fe4e55873a0a6b114db534ec52c14765
--- /dev/null
+++ b/Semester_2/Einheit_06/Uebung_5_LSG.ipynb
@@ -0,0 +1,1931 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "id": "03c85993",
+ "metadata": {},
+ "source": [
+ "# <font color='blue'>**Ãœbung 5 - Datenanalyse - Pandas**</font>\n",
+ "(Diese Übung gehört zur Vorlesungseinheit 6)\n",
+ "\n",
+ "## <font color='blue'>**Problemstellung: Analyse von PKW-Verbrauchsdaten**</font>\n",
+ "### <font color='blue'>**Problembeschreibung**</font>\n",
+ "\n",
+ "Eine umfangreiche frei verfügbare Datenbank über Verbrauchsdaten von gut 46.000 PKW-Modelle wird von der US-Regierung unter https://www.fueleconomy.gov/feg/ws/index.shtml zur Verfügung gestellt (Eine bereits etwas aufbereitete Form liegt beweits als \"vehicles.csv\" im Verzeichnis dieser Übung). Diese soll mithilfe des Pakets pandas weiter aufbereitet und untersucht werden. Der Verbrauch ist wie in den USA üblich in **miles per gallon** angegeben. Dies soll zu **l/100km** umgewandelt werden. Außerdem sollen Datenlücken sinnvoll gefüllt werden. Der **Hubraum** (displ) ist bereits in Liter angegeben. Wenn in dieser Übung ohne weitere Angabe von **Verbrauch** gesprochen wird, ist der **kombinierte Verbrauch** (Stadt- und Land) gemeint. **Fueltype** in der bereitgestellten Datenbasis bezieht sich auf den **Primärkraftstoff** (Hybridfahrzeuge erscheinen als Verbenner). Bei Elektrofahrzeugen ist der Verbrauch in **miles per gallon gasoline equivalents** angegeben (Hintergrund für Interessierte https://www.caranddriver.com/research/a31863350/mpge/).\n",
+ "\n",
+ "Nach einer grundsätzlichen Vertrautmachung mit der Datenbasis sollen folgende **Fragestellungen** beantwortet werden:\n",
+ "1) Zusammenhang zwischen Hubraum und Verbrauch, sowie Jahr und Verbrauch bei allen PKW (z.B. Korrelation, Scatter-plot, Liniendiagramm mit Median-Verbrauch über die Zeit)\n",
+ "2) Zusammenhang der Verbrauchsdaten vom verwendeten Kraftstoff (Boxplot mit Quartilen)\n",
+ "3) Vergleich der Verbrauchsdaten der deutschen Marken Audi, BMW, Mercedes-Benz, Porsche und Volkswagen (Boxplot mit Quartilen)\n",
+ "4) Vergleich der Verbrauchsdaten der 5 häufigsten Fahrzeugklassen (Boxplot mit Quartilen, Klassen automatisiert ermitteln)\n",
+ "5) Ermitteln der 15 verbrauchsarmsten Fahrzeuge eines gewählten Herstellers (oder Klasse) unter Ausschluss bestimmter Kraftstoffarten (z.B. ausgenommen Elektrofahrzeuge)\n",
+ "\n",
+ "### <font color='blue'>**Modellbildung und Algorithmierung**</font>\n",
+ "\n",
+ "Das Paket Pandas übernimmt die Methoden zur Datenspeicherung und Auswertung, die wir zum Beantworten der Fragestellungen verwenden und zum Teil kombinieren müssen. Dies wird im Bereich Umsetzung für jede der Fragen separat erklärt. Dies passt zu der eher interaktiven Anwendung bei der Datenauswertung eines neuen Datensatzes. Hat man regelmäßig Datensätze nach gleichem Format, können die pandas-Methoden natürlich auch in Algorithmen verwendet werden (z.B. monatliche Statistiken über Verkaufszahlen).\n",
+ "\n",
+ "### <font color='blue'>**Umsetzung**</font>\n",
+ "\n",
+ "Zunächst importieren wir das Paket pandas und lesen die CSV-Datei in einen Dataframe ein (Da wir später hauptsächlich in einer Kopie arbeiten, nennen wir diesen z.B. `df_orig`). Von diesem lassen wir uns zunächst die ersten Einträge anzeigen, um den Aufbau der Datenbank zu erkennen."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "id": "2d37eba9",
+ "metadata": {},
+ "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>make</th>\n",
+ " <th>model</th>\n",
+ " <th>year</th>\n",
+ " <th>VClass</th>\n",
+ " <th>cylinders</th>\n",
+ " <th>displ</th>\n",
+ " <th>fuelType</th>\n",
+ " <th>city</th>\n",
+ " <th>highway</th>\n",
+ " <th>combined</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>id</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>Alfa Romeo</td>\n",
+ " <td>Spider Veloce 2000</td>\n",
+ " <td>1985</td>\n",
+ " <td>Two Seaters</td>\n",
+ " <td>4.0</td>\n",
+ " <td>2.0</td>\n",
+ " <td>Regular Gasoline</td>\n",
+ " <td>19</td>\n",
+ " <td>25</td>\n",
+ " <td>21</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>Ferrari</td>\n",
+ " <td>Testarossa</td>\n",
+ " <td>1985</td>\n",
+ " <td>Two Seaters</td>\n",
+ " <td>12.0</td>\n",
+ " <td>4.9</td>\n",
+ " <td>Regular Gasoline</td>\n",
+ " <td>9</td>\n",
+ " <td>14</td>\n",
+ " <td>11</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>Dodge</td>\n",
+ " <td>Charger</td>\n",
+ " <td>1985</td>\n",
+ " <td>Subcompact Cars</td>\n",
+ " <td>4.0</td>\n",
+ " <td>2.2</td>\n",
+ " <td>Regular Gasoline</td>\n",
+ " <td>23</td>\n",
+ " <td>33</td>\n",
+ " <td>27</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>Dodge</td>\n",
+ " <td>B150/B250 Wagon 2WD</td>\n",
+ " <td>1985</td>\n",
+ " <td>Vans</td>\n",
+ " <td>8.0</td>\n",
+ " <td>5.2</td>\n",
+ " <td>Regular Gasoline</td>\n",
+ " <td>10</td>\n",
+ " <td>12</td>\n",
+ " <td>11</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>Subaru</td>\n",
+ " <td>Legacy AWD Turbo</td>\n",
+ " <td>1993</td>\n",
+ " <td>Compact Cars</td>\n",
+ " <td>4.0</td>\n",
+ " <td>2.2</td>\n",
+ " <td>Premium Gasoline</td>\n",
+ " <td>17</td>\n",
+ " <td>23</td>\n",
+ " <td>19</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " make model year VClass cylinders displ \\\n",
+ "id \n",
+ "0 Alfa Romeo Spider Veloce 2000 1985 Two Seaters 4.0 2.0 \n",
+ "1 Ferrari Testarossa 1985 Two Seaters 12.0 4.9 \n",
+ "2 Dodge Charger 1985 Subcompact Cars 4.0 2.2 \n",
+ "3 Dodge B150/B250 Wagon 2WD 1985 Vans 8.0 5.2 \n",
+ "4 Subaru Legacy AWD Turbo 1993 Compact Cars 4.0 2.2 \n",
+ "\n",
+ " fuelType city highway combined \n",
+ "id \n",
+ "0 Regular Gasoline 19 25 21 \n",
+ "1 Regular Gasoline 9 14 11 \n",
+ "2 Regular Gasoline 23 33 27 \n",
+ "3 Regular Gasoline 10 12 11 \n",
+ "4 Premium Gasoline 17 23 19 "
+ ]
+ },
+ "execution_count": 1,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "import pandas as pd\n",
+ "df_orig = pd.read_csv(\"vehicles.csv\", index_col=0)\n",
+ "df_orig.head()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "eda1a1b9",
+ "metadata": {},
+ "source": [
+ "Für jedes Fahrzeugmodell stehen die Einträge **id** (fortlaufende Nummer), **make** (Hersteller), **model** (Modell), **year** (Jahr), **VClass** (Fahrzeugtyp/Fahrzeugklasse), **cylinders** (Zylinderanzahl), **displ** (Hubraum in l), **fuelType** (primärer Kraftstoff), **city**, **highway** und **combined** (Verbrauch in mpg für Stadt, Land und kombiniert) zur Verfügung.\n",
+ "\n",
+ "#### <font color='blue'>**Aufbereitung**</font>\n",
+ "\n",
+ "Als erstes sollen die Daten aufbereitet werden. Wir definieren dazu eine Funktion, die den Verbrauch in mpg zu l/100km, gerundet auf eine Nachkommastelle, umrechnet. Dazu benötigen wir die Umrechnungsfaktoren:\n",
+ "\n",
+ "| Imperial | Metrisch |\n",
+ "| :--- | :--- |\n",
+ "| 1 mile | 1.61 km |\n",
+ "| 1 gallon | 3.79 l | "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "id": "801061e9",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def mpg_to_lp100km(mpg):\n",
+ " return round(379./(mpg*1.61), 1) "
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "bf5e39b2",
+ "metadata": {},
+ "source": [
+ "Diese Funktion können wir nun mit `apply`auf die Einträge der Verbauchsspalten anwenden. Dazu kopieren wir zunächst den eingelesenen Dataframe, um die Originaldaten nicht zu beeinflussen. Die ermittelten Spalten werden in der Kopie gespeichert und ersetzen den ursprünglichen Wert. Wir prüfen den Datensatz, um zu erkennen, ob es funktioniert hat."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "id": "b905c9a2",
+ "metadata": {
+ "scrolled": true
+ },
+ "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>make</th>\n",
+ " <th>model</th>\n",
+ " <th>year</th>\n",
+ " <th>VClass</th>\n",
+ " <th>cylinders</th>\n",
+ " <th>displ</th>\n",
+ " <th>fuelType</th>\n",
+ " <th>city</th>\n",
+ " <th>highway</th>\n",
+ " <th>combined</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>id</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>Alfa Romeo</td>\n",
+ " <td>Spider Veloce 2000</td>\n",
+ " <td>1985</td>\n",
+ " <td>Two Seaters</td>\n",
+ " <td>4.0</td>\n",
+ " <td>2.0</td>\n",
+ " <td>Regular Gasoline</td>\n",
+ " <td>12.4</td>\n",
+ " <td>9.4</td>\n",
+ " <td>11.2</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>Ferrari</td>\n",
+ " <td>Testarossa</td>\n",
+ " <td>1985</td>\n",
+ " <td>Two Seaters</td>\n",
+ " <td>12.0</td>\n",
+ " <td>4.9</td>\n",
+ " <td>Regular Gasoline</td>\n",
+ " <td>26.2</td>\n",
+ " <td>16.8</td>\n",
+ " <td>21.4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>Dodge</td>\n",
+ " <td>Charger</td>\n",
+ " <td>1985</td>\n",
+ " <td>Subcompact Cars</td>\n",
+ " <td>4.0</td>\n",
+ " <td>2.2</td>\n",
+ " <td>Regular Gasoline</td>\n",
+ " <td>10.2</td>\n",
+ " <td>7.1</td>\n",
+ " <td>8.7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>Dodge</td>\n",
+ " <td>B150/B250 Wagon 2WD</td>\n",
+ " <td>1985</td>\n",
+ " <td>Vans</td>\n",
+ " <td>8.0</td>\n",
+ " <td>5.2</td>\n",
+ " <td>Regular Gasoline</td>\n",
+ " <td>23.5</td>\n",
+ " <td>19.6</td>\n",
+ " <td>21.4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>Subaru</td>\n",
+ " <td>Legacy AWD Turbo</td>\n",
+ " <td>1993</td>\n",
+ " <td>Compact Cars</td>\n",
+ " <td>4.0</td>\n",
+ " <td>2.2</td>\n",
+ " <td>Premium Gasoline</td>\n",
+ " <td>13.8</td>\n",
+ " <td>10.2</td>\n",
+ " <td>12.4</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " make model year VClass cylinders displ \\\n",
+ "id \n",
+ "0 Alfa Romeo Spider Veloce 2000 1985 Two Seaters 4.0 2.0 \n",
+ "1 Ferrari Testarossa 1985 Two Seaters 12.0 4.9 \n",
+ "2 Dodge Charger 1985 Subcompact Cars 4.0 2.2 \n",
+ "3 Dodge B150/B250 Wagon 2WD 1985 Vans 8.0 5.2 \n",
+ "4 Subaru Legacy AWD Turbo 1993 Compact Cars 4.0 2.2 \n",
+ "\n",
+ " fuelType city highway combined \n",
+ "id \n",
+ "0 Regular Gasoline 12.4 9.4 11.2 \n",
+ "1 Regular Gasoline 26.2 16.8 21.4 \n",
+ "2 Regular Gasoline 10.2 7.1 8.7 \n",
+ "3 Regular Gasoline 23.5 19.6 21.4 \n",
+ "4 Premium Gasoline 13.8 10.2 12.4 "
+ ]
+ },
+ "execution_count": 3,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df = df_orig.copy()\n",
+ "df['city'] = df_orig['city'].apply(mpg_to_lp100km)\n",
+ "df['highway'] = df_orig['highway'].apply(mpg_to_lp100km)\n",
+ "df['combined'] = df_orig['combined'].apply(mpg_to_lp100km)\n",
+ "df.head()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "e87738ba",
+ "metadata": {},
+ "source": [
+ "Als nächstes sollen Datenlücken behandelt werden. Zum Finden der Lücken hilft die `info`-Funktion"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "id": "90cc4bae",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "<class 'pandas.core.frame.DataFrame'>\n",
+ "Int64Index: 46186 entries, 0 to 46185\n",
+ "Data columns (total 10 columns):\n",
+ " # Column Non-Null Count Dtype \n",
+ "--- ------ -------------- ----- \n",
+ " 0 make 46186 non-null object \n",
+ " 1 model 46186 non-null object \n",
+ " 2 year 46186 non-null int64 \n",
+ " 3 VClass 46186 non-null object \n",
+ " 4 cylinders 45680 non-null float64\n",
+ " 5 displ 45682 non-null float64\n",
+ " 6 fuelType 46186 non-null object \n",
+ " 7 city 46186 non-null float64\n",
+ " 8 highway 46186 non-null float64\n",
+ " 9 combined 46186 non-null float64\n",
+ "dtypes: float64(5), int64(1), object(4)\n",
+ "memory usage: 3.9+ MB\n"
+ ]
+ }
+ ],
+ "source": [
+ "df.info()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "c8413d12",
+ "metadata": {},
+ "source": [
+ "Man sieht, dass es **46186 Einträge** gibt, für **Zylinderanzahl** und **Hubraum** aber nur **45680** bzw. **45682**. Auch wenn bereits die Vermutung naheliegt, dass diese Einträge zu Elektrofahrzeugen gehören, auf die diese Motordaten nicht zutreffen, untersuchen wir dies, indem wir uns die betreffenden Einträge anzeigen lassen. Dazu nutzen wir die selektive Auswahl und wählen mithilfe von `isnull()` nur die Einträge aus dem Dataframe aus, bei denen der Wert für die Zylinder nicht vorhanden ist. Da wir diesen noch weiter verwenden, speichern wir ihn ab."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "id": "3b66e4aa",
+ "metadata": {},
+ "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>make</th>\n",
+ " <th>model</th>\n",
+ " <th>year</th>\n",
+ " <th>VClass</th>\n",
+ " <th>cylinders</th>\n",
+ " <th>displ</th>\n",
+ " <th>fuelType</th>\n",
+ " <th>city</th>\n",
+ " <th>highway</th>\n",
+ " <th>combined</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>id</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>7138</th>\n",
+ " <td>Nissan</td>\n",
+ " <td>Altra EV</td>\n",
+ " <td>2000</td>\n",
+ " <td>Midsize Station Wagons</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>Electricity</td>\n",
+ " <td>2.9</td>\n",
+ " <td>2.6</td>\n",
+ " <td>2.8</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7139</th>\n",
+ " <td>Toyota</td>\n",
+ " <td>RAV4 EV</td>\n",
+ " <td>2000</td>\n",
+ " <td>Sport Utility Vehicle - 2WD</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>Electricity</td>\n",
+ " <td>2.9</td>\n",
+ " <td>3.7</td>\n",
+ " <td>3.3</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8143</th>\n",
+ " <td>Toyota</td>\n",
+ " <td>RAV4 EV</td>\n",
+ " <td>2001</td>\n",
+ " <td>Sport Utility Vehicle - 2WD</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>Electricity</td>\n",
+ " <td>2.9</td>\n",
+ " <td>3.7</td>\n",
+ " <td>3.3</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8144</th>\n",
+ " <td>Ford</td>\n",
+ " <td>Th!nk</td>\n",
+ " <td>2001</td>\n",
+ " <td>Two Seaters</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>Electricity</td>\n",
+ " <td>3.2</td>\n",
+ " <td>4.1</td>\n",
+ " <td>3.6</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8146</th>\n",
+ " <td>Ford</td>\n",
+ " <td>Explorer USPS Electric</td>\n",
+ " <td>2001</td>\n",
+ " <td>Sport Utility Vehicle - 2WD</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>Electricity</td>\n",
+ " <td>5.2</td>\n",
+ " <td>7.1</td>\n",
+ " <td>6.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>...</th>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>40253</th>\n",
+ " <td>Hyundai</td>\n",
+ " <td>Ioniq 6 Long range AWD (18 inch Wheels)</td>\n",
+ " <td>2023</td>\n",
+ " <td>Midsize Cars</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>Electricity</td>\n",
+ " <td>1.8</td>\n",
+ " <td>2.1</td>\n",
+ " <td>1.9</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>40254</th>\n",
+ " <td>Hyundai</td>\n",
+ " <td>Ioniq 6 Long range AWD (20 inch Wheels)</td>\n",
+ " <td>2023</td>\n",
+ " <td>Midsize Cars</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>Electricity</td>\n",
+ " <td>2.1</td>\n",
+ " <td>2.5</td>\n",
+ " <td>2.3</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>40255</th>\n",
+ " <td>Hyundai</td>\n",
+ " <td>Ioniq 6 Long range RWD (18 inch Wheels)</td>\n",
+ " <td>2023</td>\n",
+ " <td>Midsize Cars</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>Electricity</td>\n",
+ " <td>1.5</td>\n",
+ " <td>1.9</td>\n",
+ " <td>1.7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>40256</th>\n",
+ " <td>Hyundai</td>\n",
+ " <td>Ioniq 6 Long range RWD (20 inch Wheels)</td>\n",
+ " <td>2023</td>\n",
+ " <td>Midsize Cars</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>Electricity</td>\n",
+ " <td>1.8</td>\n",
+ " <td>2.2</td>\n",
+ " <td>2.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>40257</th>\n",
+ " <td>Hyundai</td>\n",
+ " <td>Ioniq 6 Standard Range RWD</td>\n",
+ " <td>2023</td>\n",
+ " <td>Midsize Cars</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>Electricity</td>\n",
+ " <td>1.6</td>\n",
+ " <td>2.0</td>\n",
+ " <td>1.7</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>506 rows × 10 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " make model year \\\n",
+ "id \n",
+ "7138 Nissan Altra EV 2000 \n",
+ "7139 Toyota RAV4 EV 2000 \n",
+ "8143 Toyota RAV4 EV 2001 \n",
+ "8144 Ford Th!nk 2001 \n",
+ "8146 Ford Explorer USPS Electric 2001 \n",
+ "... ... ... ... \n",
+ "40253 Hyundai Ioniq 6 Long range AWD (18 inch Wheels) 2023 \n",
+ "40254 Hyundai Ioniq 6 Long range AWD (20 inch Wheels) 2023 \n",
+ "40255 Hyundai Ioniq 6 Long range RWD (18 inch Wheels) 2023 \n",
+ "40256 Hyundai Ioniq 6 Long range RWD (20 inch Wheels) 2023 \n",
+ "40257 Hyundai Ioniq 6 Standard Range RWD 2023 \n",
+ "\n",
+ " VClass cylinders displ fuelType city \\\n",
+ "id \n",
+ "7138 Midsize Station Wagons NaN NaN Electricity 2.9 \n",
+ "7139 Sport Utility Vehicle - 2WD NaN NaN Electricity 2.9 \n",
+ "8143 Sport Utility Vehicle - 2WD NaN NaN Electricity 2.9 \n",
+ "8144 Two Seaters NaN NaN Electricity 3.2 \n",
+ "8146 Sport Utility Vehicle - 2WD NaN NaN Electricity 5.2 \n",
+ "... ... ... ... ... ... \n",
+ "40253 Midsize Cars NaN NaN Electricity 1.8 \n",
+ "40254 Midsize Cars NaN NaN Electricity 2.1 \n",
+ "40255 Midsize Cars NaN NaN Electricity 1.5 \n",
+ "40256 Midsize Cars NaN NaN Electricity 1.8 \n",
+ "40257 Midsize Cars NaN NaN Electricity 1.6 \n",
+ "\n",
+ " highway combined \n",
+ "id \n",
+ "7138 2.6 2.8 \n",
+ "7139 3.7 3.3 \n",
+ "8143 3.7 3.3 \n",
+ "8144 4.1 3.6 \n",
+ "8146 7.1 6.0 \n",
+ "... ... ... \n",
+ "40253 2.1 1.9 \n",
+ "40254 2.5 2.3 \n",
+ "40255 1.9 1.7 \n",
+ "40256 2.2 2.0 \n",
+ "40257 2.0 1.7 \n",
+ "\n",
+ "[506 rows x 10 columns]"
+ ]
+ },
+ "execution_count": 5,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df_nulls = df[ df[\"cylinders\"].isnull() ]\n",
+ "df_nulls"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "5d830244",
+ "metadata": {},
+ "source": [
+ "Es sieht so aus, als wären dies alles Elektrofahrzeuge. Um sicher zu sein, lassen wir mithilfe von `describe()` Informationen über die vorhandenen fuelTypes anzeigen."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "id": "474ac122",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "count 506\n",
+ "unique 2\n",
+ "top Electricity\n",
+ "freq 503\n",
+ "Name: fuelType, dtype: object"
+ ]
+ },
+ "execution_count": 6,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df_nulls[\"fuelType\"].describe()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "b33853f1",
+ "metadata": {},
+ "source": [
+ "Nur 503 der 506 Einträge haben den Fueltype \"Electricity\". Um herauszufinden, was es mit diesen Daten auf sich hat, verwenden wir `unique()` um alle darin vorkommenden Werte zu erhalten."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "id": "6c2684f0",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "array(['Electricity', 'Regular Gasoline'], dtype=object)"
+ ]
+ },
+ "execution_count": 7,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df_nulls[\"fuelType\"].unique()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "8321c2fa",
+ "metadata": {},
+ "source": [
+ "Um die 3 Benzin-Fahrzeuge mit fehlenden Informationen zum Motor anzuzeigen, filtern wir den Dataframe nach dem Fueltype."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "id": "fc1c3f5f",
+ "metadata": {},
+ "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>make</th>\n",
+ " <th>model</th>\n",
+ " <th>year</th>\n",
+ " <th>VClass</th>\n",
+ " <th>cylinders</th>\n",
+ " <th>displ</th>\n",
+ " <th>fuelType</th>\n",
+ " <th>city</th>\n",
+ " <th>highway</th>\n",
+ " <th>combined</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>id</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>21410</th>\n",
+ " <td>Subaru</td>\n",
+ " <td>RX Turbo</td>\n",
+ " <td>1985</td>\n",
+ " <td>Subcompact Cars</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>Regular Gasoline</td>\n",
+ " <td>10.7</td>\n",
+ " <td>8.4</td>\n",
+ " <td>9.8</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>21411</th>\n",
+ " <td>Subaru</td>\n",
+ " <td>RX Turbo</td>\n",
+ " <td>1985</td>\n",
+ " <td>Subcompact Cars</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>Regular Gasoline</td>\n",
+ " <td>11.2</td>\n",
+ " <td>8.7</td>\n",
+ " <td>10.2</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>21500</th>\n",
+ " <td>Mazda</td>\n",
+ " <td>RX-7</td>\n",
+ " <td>1986</td>\n",
+ " <td>Two Seaters</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.3</td>\n",
+ " <td>Regular Gasoline</td>\n",
+ " <td>15.7</td>\n",
+ " <td>10.7</td>\n",
+ " <td>13.1</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " make model year VClass cylinders displ \\\n",
+ "id \n",
+ "21410 Subaru RX Turbo 1985 Subcompact Cars NaN NaN \n",
+ "21411 Subaru RX Turbo 1985 Subcompact Cars NaN NaN \n",
+ "21500 Mazda RX-7 1986 Two Seaters NaN 1.3 \n",
+ "\n",
+ " fuelType city highway combined \n",
+ "id \n",
+ "21410 Regular Gasoline 10.7 8.4 9.8 \n",
+ "21411 Regular Gasoline 11.2 8.7 10.2 \n",
+ "21500 Regular Gasoline 15.7 10.7 13.1 "
+ ]
+ },
+ "execution_count": 8,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df_nulls[ df_nulls[\"fuelType\"] == \"Regular Gasoline\" ]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "300b0882",
+ "metadata": {},
+ "source": [
+ "Hier verzichten wir zunächst darauf, den fehlenden Daten über den Hubraum nachzugehen.\n",
+ "\n",
+ "Es muss nun entschieden werden, wie wir mit den fehlenden Daten umgehen wollen, um möglichst aussagekräftige Daten zu behalten. \n",
+ "\n",
+ "Eine Möglichkeit (die wir in dieser Übung verwenden) ist, allen Elektrofahrzeugen bei Zylinderanzahl und Hubraum den Wert `0.0` einzutragen und die wenigen übrigen Datensätze, in denen diese Informationen fehlen, zu entfernen. \n",
+ "\n",
+ "Wir beginnen mit dem Entfernen aller Einträge, bei denen Zylinder keinen Wert hat, obwohl es keine Elektrofahrzeuge sind. Einträge entfernen können wir mit mit der Dataframe-Methode `drop([liste von indizes], inplace = True)`. Nun benötigen wir eine Liste von Indizes. Wir sehen diese zwar in der Tabelle vom Schritt zuvor, können diese aber auch automatisch ermitteln. Ein Dataframe hat das Attribut `index`, in dem eine Liste aller vorhandenen Indizes gespeichert ist. Wir können also dieses Attribut des im Schritt zuvor gefilterten dataframe verwenden, um der Drop-Methode die Indizes zu übergeben. Wir überprüfen das Ergebnis mit `info()`."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "id": "7f4c738f",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "<class 'pandas.core.frame.DataFrame'>\n",
+ "Int64Index: 46183 entries, 0 to 46185\n",
+ "Data columns (total 10 columns):\n",
+ " # Column Non-Null Count Dtype \n",
+ "--- ------ -------------- ----- \n",
+ " 0 make 46183 non-null object \n",
+ " 1 model 46183 non-null object \n",
+ " 2 year 46183 non-null int64 \n",
+ " 3 VClass 46183 non-null object \n",
+ " 4 cylinders 45680 non-null float64\n",
+ " 5 displ 45681 non-null float64\n",
+ " 6 fuelType 46183 non-null object \n",
+ " 7 city 46183 non-null float64\n",
+ " 8 highway 46183 non-null float64\n",
+ " 9 combined 46183 non-null float64\n",
+ "dtypes: float64(5), int64(1), object(4)\n",
+ "memory usage: 3.9+ MB\n"
+ ]
+ }
+ ],
+ "source": [
+ "delete_df = df_nulls[ df_nulls[\"fuelType\"] == \"Regular Gasoline\" ]\n",
+ "df.drop( delete_df.index, inplace = True )\n",
+ "df.info()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "b3d9faef",
+ "metadata": {},
+ "source": [
+ "Nun sind diese 3 Fahrzeuge aus dem Dataframe entfernt. Wir haben bisher nicht die fehlenden Hubraum-Daten untersucht. Da wir bereits wissen, dass wir bei den Elektrofahrzeugen die Werte auf `0.0` setzen werden, müssen wir lediglich überprüfen, ob es noch Einträge ohne angegebenen Hubraum gibt, die keine Elektrofahrzeuge sind. Dazu filtern wir den Dataframe mit einer kombinierten Bedingung. (Achtung, im Zusammenhang mit dem Filtern von Dataframes werden die Operatoren `&` für `and` und `|` für `or` benutzt, und jede Bedingung muss in Klammern gesetzt werden). "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "id": "c8521251",
+ "metadata": {},
+ "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>make</th>\n",
+ " <th>model</th>\n",
+ " <th>year</th>\n",
+ " <th>VClass</th>\n",
+ " <th>cylinders</th>\n",
+ " <th>displ</th>\n",
+ " <th>fuelType</th>\n",
+ " <th>city</th>\n",
+ " <th>highway</th>\n",
+ " <th>combined</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>id</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "Empty DataFrame\n",
+ "Columns: [make, model, year, VClass, cylinders, displ, fuelType, city, highway, combined]\n",
+ "Index: []"
+ ]
+ },
+ "execution_count": 10,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df[ ( df[\"displ\"].isnull() ) & ( df[\"fuelType\"] != \"Electricity\" ) ]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "fe26b2d4",
+ "metadata": {},
+ "source": [
+ "Dieser Dataframe ist leer. Das bedeutet, alle übrigenen fehlenden Daten gehören zu Elektrofahrzeugen. Wir können somit die Methode `fillna(0.0, inplace = True)` auf den gesamten Dataframe anwenden und wissen, dass dies nur noch Elektrofahrzeuge bearbeit. Wir überprüfen das Ergebnis mit `info()`."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "id": "cd124b9b",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "<class 'pandas.core.frame.DataFrame'>\n",
+ "Int64Index: 46183 entries, 0 to 46185\n",
+ "Data columns (total 10 columns):\n",
+ " # Column Non-Null Count Dtype \n",
+ "--- ------ -------------- ----- \n",
+ " 0 make 46183 non-null object \n",
+ " 1 model 46183 non-null object \n",
+ " 2 year 46183 non-null int64 \n",
+ " 3 VClass 46183 non-null object \n",
+ " 4 cylinders 46183 non-null float64\n",
+ " 5 displ 46183 non-null float64\n",
+ " 6 fuelType 46183 non-null object \n",
+ " 7 city 46183 non-null float64\n",
+ " 8 highway 46183 non-null float64\n",
+ " 9 combined 46183 non-null float64\n",
+ "dtypes: float64(5), int64(1), object(4)\n",
+ "memory usage: 3.9+ MB\n"
+ ]
+ }
+ ],
+ "source": [
+ "df.fillna( 0.0, inplace = True )\n",
+ "df.info()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "c6cb248c",
+ "metadata": {},
+ "source": [
+ "#### <font color='blue'>**Datenanalyse**</font>\n",
+ "\n",
+ "Nun können wir die Daten nach belieben analysieren. Dabei orientieren wir uns an den Fragestellungen aus der Problembeschreibung.\n",
+ "\n",
+ "<font color='blue'>*1) Zusammenhang zwischen Hubraum und Verbrauch, sowie Jahr und Verbrauch bei allen PKW (z.B. Korrelation, Scatter-plot, Liniendiagramm mit Median-Verbrauch über die Zeit)*\n",
+ "\n",
+ "Zunächst erstellen wir eine Korrelationsmatrix."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 23,
+ "id": "3dca5c9e",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/tmp/ipykernel_4268/1134722465.py:1: FutureWarning: The default value of numeric_only in DataFrame.corr is deprecated. In a future version, it will default to False. Select only valid columns or specify the value of numeric_only to silence this warning.\n",
+ " df.corr()\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>year</th>\n",
+ " <th>cylinders</th>\n",
+ " <th>displ</th>\n",
+ " <th>city</th>\n",
+ " <th>highway</th>\n",
+ " <th>combined</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>year</th>\n",
+ " <td>1.000000</td>\n",
+ " <td>0.001967</td>\n",
+ " <td>-0.032015</td>\n",
+ " <td>-0.256472</td>\n",
+ " <td>-0.325967</td>\n",
+ " <td>-0.288675</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>cylinders</th>\n",
+ " <td>0.001967</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>0.910062</td>\n",
+ " <td>0.798197</td>\n",
+ " <td>0.684470</td>\n",
+ " <td>0.767443</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>displ</th>\n",
+ " <td>-0.032015</td>\n",
+ " <td>0.910062</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>0.817058</td>\n",
+ " <td>0.739412</td>\n",
+ " <td>0.800452</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>city</th>\n",
+ " <td>-0.256472</td>\n",
+ " <td>0.798197</td>\n",
+ " <td>0.817058</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>0.932662</td>\n",
+ " <td>0.985919</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>highway</th>\n",
+ " <td>-0.325967</td>\n",
+ " <td>0.684470</td>\n",
+ " <td>0.739412</td>\n",
+ " <td>0.932662</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>0.971547</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>combined</th>\n",
+ " <td>-0.288675</td>\n",
+ " <td>0.767443</td>\n",
+ " <td>0.800452</td>\n",
+ " <td>0.985919</td>\n",
+ " <td>0.971547</td>\n",
+ " <td>1.000000</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " year cylinders displ city highway combined\n",
+ "year 1.000000 0.001967 -0.032015 -0.256472 -0.325967 -0.288675\n",
+ "cylinders 0.001967 1.000000 0.910062 0.798197 0.684470 0.767443\n",
+ "displ -0.032015 0.910062 1.000000 0.817058 0.739412 0.800452\n",
+ "city -0.256472 0.798197 0.817058 1.000000 0.932662 0.985919\n",
+ "highway -0.325967 0.684470 0.739412 0.932662 1.000000 0.971547\n",
+ "combined -0.288675 0.767443 0.800452 0.985919 0.971547 1.000000"
+ ]
+ },
+ "execution_count": 23,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df.corr()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "73b47921",
+ "metadata": {},
+ "source": [
+ "Aus diesen Werten erkennen wir bereits, dass eine recht **starke Korrelation zwischen Hubraum und und Verbrauch** besteht, und dass eine **schwache negative Korrelation zwischen dem Jahr und dem Verbrauch** besteht. Das kann man so interpretieren, dass in späteren Jahren tendenziell verbrauchsärmere Autos entwickelt wurden als in früheren, aber viel Streuung vorhanden ist. Diesen Zusammenhang wollen wir mithilfe von Scatter-Plots noch genauer untersuchen. Zunächst erstellen wir den Scatterplot für Hubraum und Verbrauch, bei dem eine recht starke Korrelation (0.8) ermittelt wurde, als Referenz."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 13,
+ "id": "292e5918",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "<Axes: xlabel='displ', ylabel='combined'>"
+ ]
+ },
+ "execution_count": 13,
+ "metadata": {},
+ "output_type": "execute_result"
+ },
+ {
+ "data": {
+ "image/png": "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\n",
+ "text/plain": [
+ "<Figure size 1000x800 with 1 Axes>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "import matplotlib.pyplot as plt\n",
+ "plt.rcParams.update({'font.size': 10, 'figure.figsize': (10, 8)}) # Diese zwei Zeilen vergrößern die Plots, die pandas generiert\n",
+ "\n",
+ "df.plot( kind='scatter', x='displ', y='combined' )"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "af04ff5d",
+ "metadata": {},
+ "source": [
+ "Man kann gut die Tendenz erkennen, dass größerer Hubraum tendenziell mit größerem Verbrauch einhergeht.\n",
+ "Betrachten wir den Plot für die jährliche Entwicklung, bei der die Korrelation mit dem Betrag 0.29 kleiner ist:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "id": "9c0601a7",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "<Axes: xlabel='year', ylabel='combined'>"
+ ]
+ },
+ "execution_count": 14,
+ "metadata": {},
+ "output_type": "execute_result"
+ },
+ {
+ "data": {
+ "image/png": "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\n",
+ "text/plain": [
+ "<Figure size 1000x800 with 1 Axes>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "df.plot( kind='scatter', x='year', y='combined' )"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "34f255df",
+ "metadata": {},
+ "source": [
+ "Hier sieht man deutlich **größere Streuung**. Dennoch ist auch hier die Tendenz zu erkennen. \n",
+ "\n",
+ "Eine weitere aufschlussreiche Grafik ist ein Plot des Medianverbrauchs. Der Median ist der Wert, der die oberen 50% von den unteren 50% trennt. Für einen solchen Plot hat pandas keine direkte Methode implementiert, wir müssen den Plot also manuell erstellen.\n",
+ "\n",
+ "Durch Nutzung der Methode `groupby()` können wir die Daten nach Jahr gruppieren (standardmäßig werden die Gruppen aufsteigend sortiert). Mit dem Indexoperator können wir daraus den Verbrauchswert auswählen und mit `median()` dann den Median aller Verbrauchswerte in dem entsprechenden Jahr erhalten. Die Verwendung dieser Methoden ergibt:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "id": "6130ecbc",
+ "metadata": {
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "year\n",
+ "1984 12.4\n",
+ "1985 12.4\n",
+ "1986 12.4\n",
+ "1987 12.4\n",
+ "1988 12.4\n",
+ "1989 12.4\n",
+ "1990 13.1\n",
+ "1991 13.1\n",
+ "1992 13.1\n",
+ "1993 13.1\n",
+ "1994 13.1\n",
+ "1995 13.1\n",
+ "1996 12.4\n",
+ "1997 12.4\n",
+ "1998 12.4\n",
+ "1999 12.4\n",
+ "2000 12.4\n",
+ "2001 12.4\n",
+ "2002 12.4\n",
+ "2003 12.4\n",
+ "2004 12.4\n",
+ "2005 12.4\n",
+ "2006 12.4\n",
+ "2007 12.4\n",
+ "2008 12.4\n",
+ "2009 11.8\n",
+ "2010 11.8\n",
+ "2011 11.8\n",
+ "2012 11.2\n",
+ "2013 11.2\n",
+ "2014 10.7\n",
+ "2015 10.7\n",
+ "2016 10.2\n",
+ "2017 10.2\n",
+ "2018 10.2\n",
+ "2019 10.2\n",
+ "2020 10.2\n",
+ "2021 10.2\n",
+ "2022 10.2\n",
+ "2023 10.2\n",
+ "2024 9.4\n",
+ "Name: combined, dtype: float64"
+ ]
+ },
+ "execution_count": 15,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df.groupby(\"year\")[\"combined\"].median()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "10e21ceb",
+ "metadata": {},
+ "source": [
+ "Es handelt sich dabei um einen pandas-Datentyp. Wir können daraus mittels `.keys()` eine Liste der Jahre erhalten, und per Konvertierung zu einer Liste eine Liste der dazugehörigen Werte. Diese können wie gewohnt mit plt geplotted werden."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "id": "2b267cf1",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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\n",
+ "text/plain": [
+ "<Figure size 1000x800 with 1 Axes>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "temp_medians = df.groupby(\"year\")[\"combined\"].median()\n",
+ "years = temp_medians.keys()\n",
+ "combined_yearly_median = list(temp_medians)\n",
+ "\n",
+ "plt.plot(years, combined_yearly_median)\n",
+ "plt.show()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "d4057fb9",
+ "metadata": {},
+ "source": [
+ "In diesem Diagramm wird die sinkende Tendenz des Verbrauchs noch einmal sichtbar. Es bleibt aber zu beachten, dass hier nur Fahrzeugmodelle ausgewertet werden. Es werden keine Aussagen über die Verkaufszahlen und Flottenstärke gemacht.\n",
+ "\n",
+ "<font color='blue'>*2) Zusammenhang der Verbrauchsdaten vom verwendeten Kraftstoff (Boxplot mit Quartilen)*\n",
+ " \n",
+ "Für diesen Plot können wir direkt die Methode `boxplot`von pandas verwenden\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 24,
+ "id": "e576a84c",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "<Axes: title={'center': 'combined'}, xlabel='fuelType'>"
+ ]
+ },
+ "execution_count": 24,
+ "metadata": {},
+ "output_type": "execute_result"
+ },
+ {
+ "data": {
+ "image/png": "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\n",
+ "text/plain": [
+ "<Figure size 1000x800 with 1 Axes>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "df.boxplot(column='combined', by='fuelType')"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "f49c89df",
+ "metadata": {},
+ "source": [
+ "<font color='blue'>*3) Vergleich der Verbrauchsdaten der deutschen Marken Audi, BMW, Mercedes-Benz, Porsche und Volkswagen (Boxplot mit Quartilen)*\n",
+ " \n",
+ "Hier kann wieder der Boxplot verwendet werden, allerdings muss zuvor der Dataframe gefiltert werden. Das Kriterium ist, ob der Hersteller einem der 5 Hersteller entspricht. Man könnte dazu wie bereits bei der Datenaufbereitung eine kombinierte Vergleichsoperation aufbauen, allerdings wird der Code dann schnell lang. Stattdessen gibt es mit `isin()` eine Methode, die für jedes Element überprüft, ob es in der übergebenen Liste enthalten ist. Anstelle also nach allen gesuchten Marken händisch zu überprüfen, erstellen wir eine Liste mit allen gewünschten Marken und verwenden die einfache (nicht kombinierte) Bedingung mit `isin()`."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 27,
+ "id": "76c128ad",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "<Axes: title={'center': 'combined'}, xlabel='make'>"
+ ]
+ },
+ "execution_count": 27,
+ "metadata": {},
+ "output_type": "execute_result"
+ },
+ {
+ "data": {
+ "image/png": "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\n",
+ "text/plain": [
+ "<Figure size 1000x800 with 1 Axes>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "german_makes = [\"Volkswagen\",\"BMW\",\"Mercedes-Benz\",\"Porsche\", \"Audi\"]\n",
+ "\n",
+ "df[ df['make'].isin(german_makes) ].boxplot(column='combined', by='make')"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "3f7d3807",
+ "metadata": {},
+ "source": [
+ "<font color='blue'>*4) Vergleich der Verbrauchsdaten der 5 häufigsten Fahrzeugklassen (Boxplot mit Quartilen, Klassen automatisiert ermitteln)*\n",
+ " \n",
+ "Prinzipiell ist das Vorgehen wie bei den Marken. Wir erstellen lediglich die Liste von Fahrzeugklassen nicht selbst, sondern nutzen pandas, um die 5 häufigsten Fahrzeugklassen zu ermitteln. Dazu können wir die Methode `value_counts` auf VClass anwenden. Das Ergebnis ist ähnlich wie bei `groupby()` eine Zusammenstellung der Kategorie mit der jeweiligen Anzahl, absteigend sortiert. Unsere 5 gesuchten Klassen sind die ersten 5 Keys."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 28,
+ "id": "31415b78",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "counts = df[\"VClass\"].value_counts()\n",
+ "# counts # entkommentieren zum Betrachten des Ergebnisses"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 30,
+ "id": "65ce7e2f",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "<Axes: title={'center': 'combined'}, xlabel='VClass'>"
+ ]
+ },
+ "execution_count": 30,
+ "metadata": {},
+ "output_type": "execute_result"
+ },
+ {
+ "data": {
+ "image/png": "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\n",
+ "text/plain": [
+ "<Figure size 1000x800 with 1 Axes>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "classes = counts.keys()[:5]\n",
+ "\n",
+ "df[ df['VClass'].isin(classes) ].boxplot(column='combined', by='VClass')"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "c69ceeac",
+ "metadata": {},
+ "source": [
+ "<font color='blue'> *5) Ermitteln der 15 verbrauchsarmsten Fahrzeuge eines gewählten Herstellers (oder Klasse) unter Ausschluss bestimmter Kraftstoffarten (z.B. ausgenommen Elektrofahrzeuge)*\n",
+ " \n",
+ "Hier können wir wieder mehrere Funktionen kombinieren. Zunächst filtern wir mithilfe einer kombinierten Bedingung den Dataframe nach \"nicht-Elektrofahrzeugen\" und den gewählten Marken. Auf das Ergebnis wenden wir die Methode `sort_values()`an, wobei wir den Verbrauch als Kriterium angeben. Dies sortiert den Dataframe nach aufsteigendem Verbrauch. Von diesem Ergebnis wiederum lassen wir die ersten 15 Einträge mittel `head()` anzeigen."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 36,
+ "id": "32c6d93f",
+ "metadata": {},
+ "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>make</th>\n",
+ " <th>model</th>\n",
+ " <th>year</th>\n",
+ " <th>VClass</th>\n",
+ " <th>cylinders</th>\n",
+ " <th>displ</th>\n",
+ " <th>fuelType</th>\n",
+ " <th>city</th>\n",
+ " <th>highway</th>\n",
+ " <th>combined</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>id</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>28193</th>\n",
+ " <td>Volkswagen</td>\n",
+ " <td>Jetta Hybrid</td>\n",
+ " <td>2015</td>\n",
+ " <td>Compact Cars</td>\n",
+ " <td>4.0</td>\n",
+ " <td>1.4</td>\n",
+ " <td>Premium Gasoline</td>\n",
+ " <td>5.7</td>\n",
+ " <td>4.9</td>\n",
+ " <td>5.4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>26546</th>\n",
+ " <td>Volkswagen</td>\n",
+ " <td>Jetta Hybrid</td>\n",
+ " <td>2014</td>\n",
+ " <td>Compact Cars</td>\n",
+ " <td>4.0</td>\n",
+ " <td>1.4</td>\n",
+ " <td>Premium Gasoline</td>\n",
+ " <td>5.7</td>\n",
+ " <td>4.9</td>\n",
+ " <td>5.4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>29450</th>\n",
+ " <td>Volkswagen</td>\n",
+ " <td>Jetta Hybrid</td>\n",
+ " <td>2016</td>\n",
+ " <td>Compact Cars</td>\n",
+ " <td>4.0</td>\n",
+ " <td>1.4</td>\n",
+ " <td>Premium Gasoline</td>\n",
+ " <td>5.6</td>\n",
+ " <td>4.9</td>\n",
+ " <td>5.4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25661</th>\n",
+ " <td>Volkswagen</td>\n",
+ " <td>Jetta Hybrid</td>\n",
+ " <td>2013</td>\n",
+ " <td>Compact Cars</td>\n",
+ " <td>4.0</td>\n",
+ " <td>1.4</td>\n",
+ " <td>Premium Gasoline</td>\n",
+ " <td>5.7</td>\n",
+ " <td>4.9</td>\n",
+ " <td>5.4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>9770</th>\n",
+ " <td>Volkswagen</td>\n",
+ " <td>Jetta Wagon</td>\n",
+ " <td>2003</td>\n",
+ " <td>Small Station Wagons</td>\n",
+ " <td>4.0</td>\n",
+ " <td>1.9</td>\n",
+ " <td>Diesel</td>\n",
+ " <td>6.7</td>\n",
+ " <td>5.2</td>\n",
+ " <td>6.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8698</th>\n",
+ " <td>Volkswagen</td>\n",
+ " <td>Jetta Wagon</td>\n",
+ " <td>2002</td>\n",
+ " <td>Small Station Wagons</td>\n",
+ " <td>4.0</td>\n",
+ " <td>1.9</td>\n",
+ " <td>Diesel</td>\n",
+ " <td>6.7</td>\n",
+ " <td>5.2</td>\n",
+ " <td>6.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>29788</th>\n",
+ " <td>Audi</td>\n",
+ " <td>A3 e-tron ultra</td>\n",
+ " <td>2016</td>\n",
+ " <td>Compact Cars</td>\n",
+ " <td>4.0</td>\n",
+ " <td>1.4</td>\n",
+ " <td>Premium Gasoline</td>\n",
+ " <td>6.4</td>\n",
+ " <td>5.7</td>\n",
+ " <td>6.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>27756</th>\n",
+ " <td>BMW</td>\n",
+ " <td>i3 REX</td>\n",
+ " <td>2014</td>\n",
+ " <td>Subcompact Cars</td>\n",
+ " <td>2.0</td>\n",
+ " <td>0.6</td>\n",
+ " <td>Premium Gasoline</td>\n",
+ " <td>5.7</td>\n",
+ " <td>6.4</td>\n",
+ " <td>6.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>29889</th>\n",
+ " <td>BMW</td>\n",
+ " <td>i3 REX</td>\n",
+ " <td>2016</td>\n",
+ " <td>Subcompact Cars</td>\n",
+ " <td>2.0</td>\n",
+ " <td>0.6</td>\n",
+ " <td>Premium Gasoline</td>\n",
+ " <td>5.7</td>\n",
+ " <td>6.4</td>\n",
+ " <td>6.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>28586</th>\n",
+ " <td>BMW</td>\n",
+ " <td>i3 REX</td>\n",
+ " <td>2015</td>\n",
+ " <td>Subcompact Cars</td>\n",
+ " <td>2.0</td>\n",
+ " <td>0.6</td>\n",
+ " <td>Premium Gasoline</td>\n",
+ " <td>5.7</td>\n",
+ " <td>6.4</td>\n",
+ " <td>6.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>9392</th>\n",
+ " <td>Volkswagen</td>\n",
+ " <td>New Beetle</td>\n",
+ " <td>2003</td>\n",
+ " <td>Subcompact Cars</td>\n",
+ " <td>4.0</td>\n",
+ " <td>1.9</td>\n",
+ " <td>Diesel</td>\n",
+ " <td>6.7</td>\n",
+ " <td>5.4</td>\n",
+ " <td>6.2</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7297</th>\n",
+ " <td>Volkswagen</td>\n",
+ " <td>New Beetle</td>\n",
+ " <td>2001</td>\n",
+ " <td>Subcompact Cars</td>\n",
+ " <td>4.0</td>\n",
+ " <td>1.9</td>\n",
+ " <td>Diesel</td>\n",
+ " <td>6.7</td>\n",
+ " <td>5.4</td>\n",
+ " <td>6.2</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5625</th>\n",
+ " <td>Volkswagen</td>\n",
+ " <td>New Jetta</td>\n",
+ " <td>1999</td>\n",
+ " <td>Compact Cars</td>\n",
+ " <td>4.0</td>\n",
+ " <td>1.9</td>\n",
+ " <td>Diesel</td>\n",
+ " <td>6.7</td>\n",
+ " <td>5.4</td>\n",
+ " <td>6.2</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>9573</th>\n",
+ " <td>Volkswagen</td>\n",
+ " <td>Jetta</td>\n",
+ " <td>2003</td>\n",
+ " <td>Compact Cars</td>\n",
+ " <td>4.0</td>\n",
+ " <td>1.9</td>\n",
+ " <td>Diesel</td>\n",
+ " <td>6.7</td>\n",
+ " <td>5.4</td>\n",
+ " <td>6.2</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7455</th>\n",
+ " <td>Volkswagen</td>\n",
+ " <td>Golf</td>\n",
+ " <td>2001</td>\n",
+ " <td>Compact Cars</td>\n",
+ " <td>4.0</td>\n",
+ " <td>1.9</td>\n",
+ " <td>Diesel</td>\n",
+ " <td>6.7</td>\n",
+ " <td>5.4</td>\n",
+ " <td>6.2</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7465</th>\n",
+ " <td>Volkswagen</td>\n",
+ " <td>Jetta</td>\n",
+ " <td>2001</td>\n",
+ " <td>Compact Cars</td>\n",
+ " <td>4.0</td>\n",
+ " <td>1.9</td>\n",
+ " <td>Diesel</td>\n",
+ " <td>6.7</td>\n",
+ " <td>5.4</td>\n",
+ " <td>6.2</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3107</th>\n",
+ " <td>Volkswagen</td>\n",
+ " <td>Jetta</td>\n",
+ " <td>1996</td>\n",
+ " <td>Compact Cars</td>\n",
+ " <td>4.0</td>\n",
+ " <td>1.9</td>\n",
+ " <td>Diesel</td>\n",
+ " <td>6.9</td>\n",
+ " <td>5.4</td>\n",
+ " <td>6.2</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5487</th>\n",
+ " <td>Volkswagen</td>\n",
+ " <td>New Beetle</td>\n",
+ " <td>1999</td>\n",
+ " <td>Subcompact Cars</td>\n",
+ " <td>4.0</td>\n",
+ " <td>1.9</td>\n",
+ " <td>Diesel</td>\n",
+ " <td>6.7</td>\n",
+ " <td>5.4</td>\n",
+ " <td>6.2</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3103</th>\n",
+ " <td>Volkswagen</td>\n",
+ " <td>Golf/GTI</td>\n",
+ " <td>1996</td>\n",
+ " <td>Compact Cars</td>\n",
+ " <td>4.0</td>\n",
+ " <td>1.9</td>\n",
+ " <td>Diesel</td>\n",
+ " <td>6.9</td>\n",
+ " <td>5.4</td>\n",
+ " <td>6.2</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8499</th>\n",
+ " <td>Volkswagen</td>\n",
+ " <td>Jetta</td>\n",
+ " <td>2002</td>\n",
+ " <td>Compact Cars</td>\n",
+ " <td>4.0</td>\n",
+ " <td>1.9</td>\n",
+ " <td>Diesel</td>\n",
+ " <td>6.7</td>\n",
+ " <td>5.4</td>\n",
+ " <td>6.2</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " make model year VClass cylinders \\\n",
+ "id \n",
+ "28193 Volkswagen Jetta Hybrid 2015 Compact Cars 4.0 \n",
+ "26546 Volkswagen Jetta Hybrid 2014 Compact Cars 4.0 \n",
+ "29450 Volkswagen Jetta Hybrid 2016 Compact Cars 4.0 \n",
+ "25661 Volkswagen Jetta Hybrid 2013 Compact Cars 4.0 \n",
+ "9770 Volkswagen Jetta Wagon 2003 Small Station Wagons 4.0 \n",
+ "8698 Volkswagen Jetta Wagon 2002 Small Station Wagons 4.0 \n",
+ "29788 Audi A3 e-tron ultra 2016 Compact Cars 4.0 \n",
+ "27756 BMW i3 REX 2014 Subcompact Cars 2.0 \n",
+ "29889 BMW i3 REX 2016 Subcompact Cars 2.0 \n",
+ "28586 BMW i3 REX 2015 Subcompact Cars 2.0 \n",
+ "9392 Volkswagen New Beetle 2003 Subcompact Cars 4.0 \n",
+ "7297 Volkswagen New Beetle 2001 Subcompact Cars 4.0 \n",
+ "5625 Volkswagen New Jetta 1999 Compact Cars 4.0 \n",
+ "9573 Volkswagen Jetta 2003 Compact Cars 4.0 \n",
+ "7455 Volkswagen Golf 2001 Compact Cars 4.0 \n",
+ "7465 Volkswagen Jetta 2001 Compact Cars 4.0 \n",
+ "3107 Volkswagen Jetta 1996 Compact Cars 4.0 \n",
+ "5487 Volkswagen New Beetle 1999 Subcompact Cars 4.0 \n",
+ "3103 Volkswagen Golf/GTI 1996 Compact Cars 4.0 \n",
+ "8499 Volkswagen Jetta 2002 Compact Cars 4.0 \n",
+ "\n",
+ " displ fuelType city highway combined \n",
+ "id \n",
+ "28193 1.4 Premium Gasoline 5.7 4.9 5.4 \n",
+ "26546 1.4 Premium Gasoline 5.7 4.9 5.4 \n",
+ "29450 1.4 Premium Gasoline 5.6 4.9 5.4 \n",
+ "25661 1.4 Premium Gasoline 5.7 4.9 5.4 \n",
+ "9770 1.9 Diesel 6.7 5.2 6.0 \n",
+ "8698 1.9 Diesel 6.7 5.2 6.0 \n",
+ "29788 1.4 Premium Gasoline 6.4 5.7 6.0 \n",
+ "27756 0.6 Premium Gasoline 5.7 6.4 6.0 \n",
+ "29889 0.6 Premium Gasoline 5.7 6.4 6.0 \n",
+ "28586 0.6 Premium Gasoline 5.7 6.4 6.0 \n",
+ "9392 1.9 Diesel 6.7 5.4 6.2 \n",
+ "7297 1.9 Diesel 6.7 5.4 6.2 \n",
+ "5625 1.9 Diesel 6.7 5.4 6.2 \n",
+ "9573 1.9 Diesel 6.7 5.4 6.2 \n",
+ "7455 1.9 Diesel 6.7 5.4 6.2 \n",
+ "7465 1.9 Diesel 6.7 5.4 6.2 \n",
+ "3107 1.9 Diesel 6.9 5.4 6.2 \n",
+ "5487 1.9 Diesel 6.7 5.4 6.2 \n",
+ "3103 1.9 Diesel 6.9 5.4 6.2 \n",
+ "8499 1.9 Diesel 6.7 5.4 6.2 "
+ ]
+ },
+ "execution_count": 36,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df[ ( df['fuelType'] != \"Electricity\" ) & df[\"make\"].isin(german_makes) ].sort_values(\"combined\").head(20)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "6ab19c5c",
+ "metadata": {},
+ "source": [
+ "Damit sind alle Anregungen aus der Problemstellung abgearbeitet.\n",
+ "\n",
+ "### <font color = \"blue\"> **Anregungen zum selbst Programmieren**\n",
+ "\n",
+ "Es gibt unzählige weitere Möglichkeiten, diese Daten auszuwerten. Überlege dir interessante Fragestellungen und werte sie aus."
+ ]
+ }
+ ],
+ "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",
+ "version": "3.8.10"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/Semester_2/Einheit_07/Uebung_6.ipynb b/Semester_2/Einheit_07/Uebung_6.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..d8424894a04ba93363db3db9b0b6d2020cfadb46
--- /dev/null
+++ b/Semester_2/Einheit_07/Uebung_6.ipynb
@@ -0,0 +1,141 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "id": "52dace14",
+ "metadata": {},
+ "source": [
+ "# <font color='blue'>**Ãœbung 6 - Datenanalyse - Pandas**</font>\n",
+ "(Diese Übung gehört zur Vorlesungseinheit 7)\n",
+ "\n",
+ "## <font color='blue'>**Problemstellung: Erstellen und Modifizieren eines Pandas-Datensatzes**</font>\n",
+ "\n",
+ "In der letzten Übung wurde ein großer Datensatz eingelesen und viel analysiert. Im Gegensatz dazu, wird in dieser kürzeren Übung ein kleiner Datensatz angelegt, modifiziert und weniger Auswertungen gemacht. Diese Übung sollte auf jeden Fall selbst ausprobiert werden, bevor die Lösung betrachtet wird.\n",
+ "\n",
+ "### <font color='blue'>**Problembeschreibung**</font>\n",
+ "\n",
+ "Folgende Ergebisse einer Umfrage einer Umfrage liegen vor. Dieser Datensatz soll manuell als Dataframe angelegt werden. Es gibt 6 Personen (um nicht so viel eintragen zu müssen) und 3 Fragen. Die erste Frage ist nur eine ja/nein Frage, die anderen Fragen haben Punkte zwischen 1 und 5.\n",
+ "\n",
+ "| Person | Frage 1 | Frage 2 | Frage 3 |\n",
+ "|---|---|---|---|\n",
+ "| Person 1 | ja | 3 | 5 |\n",
+ "| Person 2 | ja | 1 | 1 |\n",
+ "| Person 3 | nein | 3 | 4 |\n",
+ "| Person 4 | nein | 2 | 4 |\n",
+ "| Person 5 | ja | 2 | 5 |\n",
+ "| Person 6 | ja | 4 | 2 |\n",
+ "\n",
+ "Erstelle einen Pandas Dataframe mit den vorliegenden Daten. Die Spalte Person soll dabei der Index sein, die Fragenbezeichnung der Spaltenname.\n",
+ "\n",
+ "Erstelle nun mithilfe von Pandas Auswertungen: Durchschnittswerte der Fragen und Diagramme, wie viele Personen die Punktzahl vergeben haben (vgl. Histogramm).\n",
+ "\n",
+ "Erstelle zum Schluss eine neue Spalte/Serie mit der durchschnittlichen Bewertung der beiden Punktefragen (pro Person). Ggf. musst du auf den index achten. Gibt es eine Korrelation zwischen der Antwort auf Frage 2 und der durchschnittlichen Bewertung?\n",
+ "\n",
+ "### <font color='blue'>**Umsetzung**</font>"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "f118b640",
+ "metadata": {},
+ "source": [
+ "Dataframe:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "f04c682a",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "markdown",
+ "id": "cadd1033",
+ "metadata": {},
+ "source": [
+ "Durchschnitte"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "ea4577ab",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "markdown",
+ "id": "b06bb1f0",
+ "metadata": {},
+ "source": [
+ "Plot:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "552008f3",
+ "metadata": {
+ "scrolled": true
+ },
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "markdown",
+ "id": "87a8674e",
+ "metadata": {},
+ "source": [
+ "Durchschnittliche Punktzahl pro Person:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "197bf9e7",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "markdown",
+ "id": "125e0f8f",
+ "metadata": {},
+ "source": [
+ "Korrelation:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "b6c2eaf4",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "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",
+ "version": "3.8.7"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}