feature: add example jupyter notebooks

SL/aufgaben/WS1/notebooks/1.1 Feature Engineering - Einfuehrung.ipynb

@@ -0,0 +1,222 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**nicht als Notebook verteilen**"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "# Feature Engineering\n",
+    "\n",
+    "## Feature Engineering - Einführung\n",
+    "\n",
+    "### Abgrenzungen\n",
+    "\n",
+    "### CRISP - und die Gliederung des Kurses\n",
+    "\n",
+    "### Strukturierte Daten\n",
+    "\n",
+    "#### Aufbau und Organisation eines Data Frame"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "     age            job  marital  duration  campaign    y\n",
+      "0   30.0  self-employed   single     245.0         3  yes\n",
+      "1   32.0     technician  married     370.0         1   no\n",
+      "2   27.0    blue collar   single     623.0         1  yes\n",
+      "3    NaN    blue collar   single       9.0         6   no\n",
+      "4   27.0         admin.   single     126.0         2  yes\n",
+      "5   34.0         admin.   single     548.0         2  yes\n",
+      "6   46.0           None  married      86.0         2   no\n",
+      "7    NaN        retired  married     707.0         3  yes\n",
+      "8   46.0         admin.  married      96.0         6   no\n",
+      "9   48.0    blue collar  married     241.0         2   no\n",
+      "10  29.0     technician  married     154.0         3   no\n"
+     ]
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "data = pd.read_csv('../3_data/bank_data.csv', sep=';')\n",
+    "#print(data.iloc[0:11, 0:6])\n",
+    "\n",
+    "## arbitrarily input\n",
+    "data.iloc[3, 0] = None\n",
+    "data.iloc[6, 1] = None\n",
+    "#print(data.iloc[0:11, 0:6])\n",
+    "print(data.iloc[0:11, [0,1,2,10,11,20]])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Begriffe"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Beispieldaten"
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "metadata": {},
+   "source": [
+    "import pandas as pd\n",
+    "demo_data_class = pd.read_csv('../3_data/demo_data_class.csv')\n",
+    "demo_data_regr = pd.read_csv('../3_data/demo_data_regr.csv') "
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "metadata": {},
+   "source": [
+    "import seaborn as sns\n",
+    "iris_data = sns.load_dataset('iris')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "jp-MarkdownHeadingCollapsed": true
+   },
+   "source": [
+    "### Anforderungen an die Daten für Machine Learning"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Eine typische ML Sequenz"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Python Libraries"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Feature Engineering"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Die Python Libraries und CRISP-DM"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Begleitende Literatur"
+   ]
+  }
+ ],
+ "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": "3.13.0"
+  },
+  "toc": {
+   "base_numbering": "1.1",
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "1.1 Feature Engineering - Einführung",
+   "title_sidebar": "Contents",
+   "toc_cell": true,
+   "toc_position": {
+    "height": "calc(100% - 180px)",
+    "left": "10px",
+    "top": "150px",
+    "width": "251px"
+   },
+   "toc_section_display": true,
+   "toc_window_display": true
+  },
+  "toc-autonumbering": true,
+  "toc-showcode": false,
+  "toc-showmarkdowntxt": false,
+  "toc-showtags": false,
+  "varInspector": {
+   "cols": {
+    "lenName": 16,
+    "lenType": 16,
+    "lenVar": 40
+   },
+   "kernels_config": {
+    "python": {
+     "delete_cmd_postfix": "",
+     "delete_cmd_prefix": "del ",
+     "library": "var_list.py",
+     "varRefreshCmd": "print(var_dic_list())"
+    },
+    "r": {
+     "delete_cmd_postfix": ") ",
+     "delete_cmd_prefix": "rm(",
+     "library": "var_list.r",
+     "varRefreshCmd": "cat(var_dic_list()) "
+    }
+   },
+   "position": {
+    "height": "326.85px",
+    "left": "910px",
+    "right": "20px",
+    "top": "120px",
+    "width": "350px"
+   },
+   "types_to_exclude": [
+    "module",
+    "function",
+    "builtin_function_or_method",
+    "instance",
+    "_Feature"
+   ],
+   "window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}