ki-dhbw/tasks/Untitled.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "dff037b7-7d71-49c2-8a47-48017c073f81",
   "metadata": {},
   "source": [
    "$R^2$ für ein polynomielles Modell"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "id": "8b1ff6ff-f80e-4cc3-b266-0ad417911d1d",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "# plotting settings\n",
    "pd.plotting.register_matplotlib_converters()\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "import seaborn as sns\n",
    "from tqdm.notebook import tqdm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "id": "f698283d-7346-4618-9b87-60a3de061a98",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['Suburb', 'Address', 'Rooms', 'Type', 'Price', 'Method', 'SellerG',\n",
       "       'Date', 'Distance', 'Postcode', 'Bedroom2', 'Bathroom', 'Car',\n",
       "       'Landsize', 'BuildingArea', 'YearBuilt', 'CouncilArea', 'Lattitude',\n",
       "       'Longtitude', 'Regionname', 'Propertycount'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 75,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "melbourne_file_path = 'data/melb_data.csv'\n",
    "melbourne_data = pd.read_csv(melbourne_file_path)\n",
    "melbourne_data = melbourne_data.dropna(axis=0)  # entfernen von Daten mit fehlenden Werten\n",
    "melbourne_data.columns  # Spaltennamen der Tabelle (potentielle Features)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "id": "dac65c52-f2ce-47b6-ba65-3c6bd915dfe8",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/plex/.pyenv/versions/ki/lib/python3.12/site-packages/pandas/core/nanops.py:1016: RuntimeWarning: invalid value encountered in subtract\n",
      "  sqr = _ensure_numeric((avg - values) ** 2)\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>Rooms</th>\n",
       "      <th>BuildingArea</th>\n",
       "      <th>Lattitude</th>\n",
       "      <th>Price</th>\n",
       "      <th>price_per_area</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>79.0</td>\n",
       "      <td>-37.8079</td>\n",
       "      <td>1035000.0</td>\n",
       "      <td>6634.615385</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>150.0</td>\n",
       "      <td>-37.8093</td>\n",
       "      <td>1465000.0</td>\n",
       "      <td>10932.835821</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>142.0</td>\n",
       "      <td>-37.8072</td>\n",
       "      <td>1600000.0</td>\n",
       "      <td>13333.333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>3</td>\n",
       "      <td>210.0</td>\n",
       "      <td>-37.8024</td>\n",
       "      <td>1876000.0</td>\n",
       "      <td>7657.142857</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>2</td>\n",
       "      <td>107.0</td>\n",
       "      <td>-37.8060</td>\n",
       "      <td>1636000.0</td>\n",
       "      <td>6390.625000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Rooms  BuildingArea  Lattitude      Price  price_per_area\n",
       "1      2          79.0   -37.8079  1035000.0     6634.615385\n",
       "2      3         150.0   -37.8093  1465000.0    10932.835821\n",
       "4      4         142.0   -37.8072  1600000.0    13333.333333\n",
       "6      3         210.0   -37.8024  1876000.0     7657.142857\n",
       "7      2         107.0   -37.8060  1636000.0     6390.625000"
      ]
     },
     "execution_count": 83,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#features = ['BuildingArea', Rooms', 'Bathroom', 'Landsize', 'Lattitude', 'Longtitude', 'YearBuilt', 'Distance']\n",
    "features = ['Rooms', 'BuildingArea', 'Lattitude']\n",
    "data = melbourne_data[features + ['Price']]\n",
    "data = data.assign(price_per_area = melbourne_data['Price'] / melbourne_data[\"Landsize\"])\n",
    "data.describe()\n",
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "id": "afe5a08a-abec-4164-85c4-1d3ac8398a62",
   "metadata": {},
   "outputs": [],
   "source": [
    "def h(x, w):\n",
    "    \"\"\"x und w sind numpy arrays; x kann auch die komplette Feature-Matrix sein\"\"\"\n",
    "    # Diese Form erlaubt es für x eine ganze (Feature-)Matrix zu übergeben. Die Matrix enthält\n",
    "    # zeilenweise je einen Datenpunkt, für den h berechnet werden soll.\n",
    "    # w @ x.T ist dann ein Vektor mit je einem Ergebnis in den Komponenten des Vektors pro Zeile\n",
    "    # der übergebenen (Feature-)Matrix.\n",
    "    return x @ w\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "id": "c2e256a3-3575-45c4-a99c-d41c3c56e1c3",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Definition der Kostenfunktion\n",
    "def J(w, X, y):\n",
    "    \"\"\"\n",
    "    w, X, y müssen numpy arrays sein\n",
    "    X: Feature-Matrix aller Trainingsdaten inkl. Spalte mit 1; Dimension: n x (d+1)\n",
    "    y: Vektor aller Targets zu X\n",
    "    \"\"\"\n",
    "    errors = y - h(x=X, w=w)\n",
    "    mse = 1.0/(2.0*len(y)) * ( errors @ errors )\n",
    "    return mse\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "id": "b41b9c03-0c1d-4a6b-80e8-d7e8775b69c0",
   "metadata": {},
   "outputs": [],
   "source": [
    "def feature_matrix_from_data(data):\n",
    "    # hier erzeugen wir die Matrix mit unseren Input-Daten (Features) inklusive der Spalte mit \"1\"\n",
    "    return np.hstack((np.ones((len(data),1)), data.to_numpy(copy=True)))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "id": "2c631e17-eb36-43d0-97b1-59add1c93dd9",
   "metadata": {},
   "outputs": [],
   "source": [
    "# hier erzeugen wir die Matrix mit unseren Input-Daten (Features) inklusive der Spalte mit \"1\"\n",
    "#X = np.hstack((np.ones((len(data),1)), data[features].to_numpy(copy=True)))\n",
    "X = feature_matrix_from_data(data[features])\n",
    "# und ausserdem den Vektor der Targets\n",
    "y = data.Price.to_numpy(copy=True)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "id": "8301eb74-9aae-446c-ad46-924811b99777",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Die 4 Parameter der linearen Regression:\n",
      "[-6.97461781e+07  2.41559504e+05  2.31456611e+03 -1.84562537e+06]\n",
      "Kostenfunktion J(w_ana): 137899453867.5851\n",
      "CPU times: user 495 μs, sys: 39 μs, total: 534 μs\n",
      "Wall time: 553 μs\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "w_ana = np.linalg.solve(X.T @ X, X.T @ y)\n",
    "print('Die {} Parameter der linearen Regression:\\n{}'.format(len(w_ana), w_ana))\n",
    "J_ana = J(w=w_ana, X=X, y=y)\n",
    "print('Kostenfunktion J(w_ana): {}'.format(J_ana))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "id": "a89c591c-4ebd-4a3d-958b-915738d7361a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1     6634.615385\n",
      "2    10932.835821\n",
      "4    13333.333333\n",
      "6     7657.142857\n",
      "7     6390.625000\n",
      "Name: price_per_area, dtype: float64\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<Axes: xlabel='BuildingArea', ylabel='Price'>"
      ]
     },
     "execution_count": 91,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ax = sns.scatterplot(x=data['BuildingArea'], y=data['Price'])\n",
    "\n",
    "xplot = data['price_per_area']\n",
    "yplot = data['price_per_area'][0:len(xplot)]\n",
    "print(yplot.head())\n",
    "sns.lineplot(x=xplot, y=yplot, ax=ax)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "id": "e4fc1d51-3435-415d-875f-db85dfda39e2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1     6634.615385\n",
       "2    10932.835821\n",
       "4    13333.333333\n",
       "6     7657.142857\n",
       "7     6390.625000\n",
       "Name: price_per_area, dtype: float64"
      ]
     },
     "execution_count": 85,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data['price_per_area'].head()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python (ki)",
   "language": "python",
   "name": "myenv"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}