{ "cells": [ { "cell_type": "markdown", "metadata": { "toc": true }, "source": [ "# WS 09 Tune AdaBoostRegressor" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "* es wurde festgestellt, dass z.B. AdaBoostRegressor unter Standard-Parametrisierung ein unbrauchbares Ergebnis liefert\n", "* untersuchen Sie das Potential von Parameter-Tuning für diesen Regressor\n", "* konzentrieren Sie sich auf folgende Parameter\n", " * learning_rate, Parameter von AdaBoostRegressor\n", " * max_depth, interner Parameter des Basis-Estimators, hier DecisionTreeRegressor\n", "* falls Zeit übrig, untersuchen Sie noch andere Regressoren Ihrer Wahl dahingehend" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "## prepare env, read and prepare data\n", "import pandas as pd\n", "import numpy as np\n", "import matplotlib.pyplot as plt\n", "import seaborn as sns; sns.set()\n", "\n", "codepath = '../2_code' ## for import of user defined module\n", "datapath = '../3_data'\n", "#codepath = '.././2_code' ## for import of user defined module\n", "#datapath = '../../3_data'\n", "\n", "from sys import path; path.insert(1, codepath)\n", "from os import chdir; chdir(datapath)\n", "\n", "from bfh_cas_pml import prep_data\n", "X_train, X_test, y_train, y_test = prep_data('melb_data_prep.csv', target='Price', seed=1234)\n", "\n", "from bfh_cas_pml import test_regression_model" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "ExecuteTime": { "end_time": "2020-04-08T10:06:45.098899Z", "start_time": "2020-04-08T10:06:44.257283Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "R2 = -0.3023\n" ] } ], "source": [ "## baseline\n", "from sklearn.ensemble import AdaBoostRegressor\n", "this_model = test_regression_model(\n", " AdaBoostRegressor(random_state=1234), \n", " X_train, y_train, X_test, y_test,\n", " show_plot=False)" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [], "source": [ "## tune learning_rate\n", "## tbd: find parameter range here\n", "\n", "\n" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [], "source": [ "## tune max_depth\n", "from sklearn.tree import DecisionTreeRegressor\n", "## tbd: find parameter range here\n", "\n", "\n" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [], "source": [ "## best combination of single parameters\n", "## tbd\n", "\n", "\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Fazit**:\n", "* tbd" ] } ], "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": "3.11.7" }, "toc": { "base_numbering": "1", "nav_menu": {}, "number_sections": false, "sideBar": true, "skip_h1_title": true, "title_cell": "WS 11 Regression - mit FE - solution", "title_sidebar": "Contents", "toc_cell": true, "toc_position": { "height": "calc(100% - 180px)", "left": "10px", "top": "150px", "width": "195.933px" }, "toc_section_display": true, "toc_window_display": true }, "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": "321.85px", "left": "785px", "right": "20px", "top": "118px", "width": "350px" }, "types_to_exclude": [ "module", "function", "builtin_function_or_method", "instance", "_Feature" ], "window_display": false } }, "nbformat": 4, "nbformat_minor": 4 }