166 lines
3.5 KiB
Plaintext
166 lines
3.5 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"toc": true
|
|
},
|
|
"source": [
|
|
"# WS 14 Random Search CV"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"* untersuchen Sie Kombinationen von Parameterwerten bei RandomForestClassifier\n",
|
|
"* Vorschlag:\n",
|
|
" * n_estimators in [50, 100, 150, 200]\n",
|
|
" * max_features in [3, 5, 7, 9]\n",
|
|
" * criterion in ['gini', 'entropy']\n",
|
|
" * min_samples_leaf in [1, 2, 3, 4]\n",
|
|
"* wenden Sie 5-fach Kreuzvalidierung an\n",
|
|
"* setzen Sie die Anzahl der zu untersuchenden Kombinationen auf 12\n",
|
|
"* arbeiten Sie ohne setzen von random_state, damit anschliessend die Ergebnisse verglichen werden können"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"## import libraries\n",
|
|
"import pandas as pd\n",
|
|
"import numpy as np\n",
|
|
"\n",
|
|
"## load data\n",
|
|
"datapath = '../3_data'\n",
|
|
"from os import chdir; chdir(datapath)\n",
|
|
"bank_df = pd.read_csv('bank_data_prep.csv')\n",
|
|
"\n",
|
|
"## features - target - split\n",
|
|
"X = bank_df.drop('y', axis=1)\n",
|
|
"y = bank_df['y']"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"## import classes from sklearn\n",
|
|
"from sklearn.ensemble import RandomForestClassifier\n",
|
|
"from sklearn.model_selection import RandomizedSearchCV\n",
|
|
"\n",
|
|
"## define parameter grid\n",
|
|
"## tbd\n",
|
|
"#parameter_grid = ...\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"## define RandomizedSearchCV\n",
|
|
"## tbd\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"## run RandomizedSearchCV\n",
|
|
"## tbd\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"## evaluate RandomizedSearchCV\n",
|
|
"## tbd\n",
|
|
"\n",
|
|
"\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"**Fazit:**\n",
|
|
"* tbd\n",
|
|
"\n",
|
|
"\n"
|
|
]
|
|
}
|
|
],
|
|
"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": "",
|
|
"nav_menu": {},
|
|
"number_sections": true,
|
|
"sideBar": true,
|
|
"skip_h1_title": false,
|
|
"title_cell": "WS 17 Validierung - Random Search CV",
|
|
"title_sidebar": "Contents",
|
|
"toc_cell": true,
|
|
"toc_position": {
|
|
"height": "calc(100% - 180px)",
|
|
"left": "10px",
|
|
"top": "150px",
|
|
"width": "195.867px"
|
|
},
|
|
"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": "306.85px",
|
|
"left": "862px",
|
|
"right": "20px",
|
|
"top": "137px",
|
|
"width": "350px"
|
|
},
|
|
"types_to_exclude": [
|
|
"module",
|
|
"function",
|
|
"builtin_function_or_method",
|
|
"instance",
|
|
"_Feature"
|
|
],
|
|
"window_display": false
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 4
|
|
}
|