yujunjun/autogen
1
0
Fork 0
mirror of https://github.com/microsoft/autogen.git synced 2025-07-21 16:04:40 +00:00
Code Issues Packages Projects Releases Wiki Activity
autogen/notebook/flaml_lightgbm.ipynb

883 lines
105 KiB
Plaintext
Raw Normal View History

v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "slide"
}
},
"source": [
"Copyright (c) 2020-2021 Microsoft Corporation. All rights reserved. \n",
"\n",
"Licensed under the MIT License.\n",
"\n",
"# Tune LightGBM with FLAML Library\n",
"\n",
"\n",
"## 1. Introduction\n",
"\n",
"FLAML is a Python library (https://github.com/microsoft/FLAML) designed to automatically produce accurate machine learning models \n",
"with low computational cost. It is fast and cheap. The simple and lightweight design makes it easy \n",
"to use and extend, such as adding new learners. FLAML can \n",
"- serve as an economical AutoML engine,\n",
"- be used as a fast hyperparameter tuning tool, or \n",
"- be embedded in self-tuning software that requires low latency & resource in repetitive\n",
" tuning tasks.\n",
"\n",
"In this notebook, we demonstrate how to use FLAML library to tune hyperparameters of LightGBM with a regression example.\n",
"\n",
"FLAML requires `Python>=3.6`. To run this notebook example, please install flaml with the `notebook` option:\n",
"```bash\n",
"pip install flaml[notebook]\n",
"```"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"!pip install flaml[notebook];"
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "slide"
}
},
"source": [
"## 2. Regression Example\n",
"### Load data and preprocess\n",
"\n",
"Download [houses dataset](https://www.openml.org/d/537) from OpenML. The task is to predict median price of the house in the region based on demographic composition and a state of housing market in the region."
]
},
{
"cell_type": "code",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"execution_count": 1,
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
"metadata": {
"slideshow": {
"slide_type": "subslide"
},
"tags": []
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"text": [
"download dataset from openml\nDataset name: houses\nX_train.shape: (15480, 8), y_train.shape: (15480,);\nX_test.shape: (5160, 8), y_test.shape: (5160,)\n"
]
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
}
],
"source": [
"from flaml.data import load_openml_dataset\n",
Issue58 (#59) * iter per learner * code cleanup
2021-04-08 09:29:55 -07:00
"X_train, X_test, y_train, y_test = load_openml_dataset(dataset_id=537, data_dir='./')"
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "slide"
}
},
"source": [
"### Run FLAML\n",
"In the FLAML automl run configuration, users can specify the task type, time budget, error metric, learner list, whether to subsample, resampling strategy type, and so on. All these arguments have default values which will be used if users do not provide them. "
]
},
{
"cell_type": "code",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"execution_count": 2,
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
"metadata": {
"slideshow": {
"slide_type": "slide"
Lgbm w customized obj (#64) * add customized lgbm learner * add comments * fix format issue * format * OpenMLError * add test * add notebook Co-authored-by: Chi Wang (MSR) <chiw@microsoft.com> Co-authored-by: Chi Wang <wang.chi@microsoft.com>
2021-04-10 21:14:28 -04:00
},
"tags": []
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
},
"outputs": [],
"source": [
"''' import AutoML class from flaml package '''\n",
"from flaml import AutoML\n",
"automl = AutoML()"
]
},
{
"cell_type": "code",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"execution_count": 3,
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
"metadata": {
"slideshow": {
"slide_type": "slide"
}
},
"outputs": [],
"source": [
"settings = {\n",
Issue58 (#59) * iter per learner * code cleanup
2021-04-08 09:29:55 -07:00
" \"time_budget\": 120, # total running time in seconds\n",
" \"metric\": 'r2', # primary metrics for regression can be chosen from: ['mae','mse','r2']\n",
" \"estimator_list\": ['lgbm'], # list of ML learners; we tune lightgbm in this example\n",
" \"task\": 'regression', # task type \n",
" \"log_file_name\": 'houses_experiment.log', # flaml log file\n",
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
"}"
]
},
{
"cell_type": "code",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"execution_count": 4,
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
"metadata": {
"slideshow": {
"slide_type": "slide"
},
"tags": []
},
"outputs": [
{
"output_type": "stream",
"name": "stderr",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"text": [
"[flaml.automl: 05-01 16:54:10] {890} INFO - Evaluation method: cv\n",
"[flaml.automl: 05-01 16:54:10] {606} INFO - Using RepeatedKFold\n",
"[flaml.automl: 05-01 16:54:10] {911} INFO - Minimizing error metric: 1-r2\n",
"[flaml.automl: 05-01 16:54:10] {929} INFO - List of ML learners in AutoML Run: ['lgbm']\n",
"[flaml.automl: 05-01 16:54:10] {993} INFO - iteration 0, current learner lgbm\n",
"[flaml.automl: 05-01 16:54:10] {1141} INFO - at 0.6s,\tbest lgbm's error=0.7383,\tbest lgbm's error=0.7383\n",
"[flaml.automl: 05-01 16:54:10] {993} INFO - iteration 1, current learner lgbm\n",
"[flaml.automl: 05-01 16:54:10] {1141} INFO - at 0.8s,\tbest lgbm's error=0.7383,\tbest lgbm's error=0.7383\n",
"[flaml.automl: 05-01 16:54:10] {993} INFO - iteration 2, current learner lgbm\n",
"[flaml.automl: 05-01 16:54:11] {1141} INFO - at 1.2s,\tbest lgbm's error=0.5538,\tbest lgbm's error=0.5538\n",
"[flaml.automl: 05-01 16:54:11] {993} INFO - iteration 3, current learner lgbm\n",
"[flaml.automl: 05-01 16:54:11] {1141} INFO - at 1.5s,\tbest lgbm's error=0.3888,\tbest lgbm's error=0.3888\n",
"[flaml.automl: 05-01 16:54:11] {993} INFO - iteration 4, current learner lgbm\n",
"[flaml.automl: 05-01 16:54:11] {1141} INFO - at 1.8s,\tbest lgbm's error=0.3888,\tbest lgbm's error=0.3888\n",
"[flaml.automl: 05-01 16:54:11] {993} INFO - iteration 5, current learner lgbm\n",
"[flaml.automl: 05-01 16:54:12] {1141} INFO - at 2.0s,\tbest lgbm's error=0.3888,\tbest lgbm's error=0.3888\n",
"[flaml.automl: 05-01 16:54:12] {993} INFO - iteration 6, current learner lgbm\n",
"[flaml.automl: 05-01 16:54:12] {1141} INFO - at 2.4s,\tbest lgbm's error=0.3017,\tbest lgbm's error=0.3017\n",
"[flaml.automl: 05-01 16:54:12] {993} INFO - iteration 7, current learner lgbm\n",
"[flaml.automl: 05-01 16:54:12] {1141} INFO - at 2.9s,\tbest lgbm's error=0.2633,\tbest lgbm's error=0.2633\n",
"[flaml.automl: 05-01 16:54:12] {993} INFO - iteration 8, current learner lgbm\n",
"[flaml.automl: 05-01 16:54:13] {1141} INFO - at 3.3s,\tbest lgbm's error=0.2633,\tbest lgbm's error=0.2633\n",
"[flaml.automl: 05-01 16:54:13] {993} INFO - iteration 9, current learner lgbm\n",
"[flaml.automl: 05-01 16:54:13] {1141} INFO - at 3.9s,\tbest lgbm's error=0.2314,\tbest lgbm's error=0.2314\n",
"[flaml.automl: 05-01 16:54:13] {993} INFO - iteration 10, current learner lgbm\n",
"[flaml.automl: 05-01 16:54:14] {1141} INFO - at 4.3s,\tbest lgbm's error=0.2314,\tbest lgbm's error=0.2314\n",
"[flaml.automl: 05-01 16:54:14] {993} INFO - iteration 11, current learner lgbm\n",
"[flaml.automl: 05-01 16:54:14] {1141} INFO - at 4.6s,\tbest lgbm's error=0.2314,\tbest lgbm's error=0.2314\n",
"[flaml.automl: 05-01 16:54:14] {993} INFO - iteration 12, current learner lgbm\n",
"[flaml.automl: 05-01 16:54:15] {1141} INFO - at 5.4s,\tbest lgbm's error=0.1954,\tbest lgbm's error=0.1954\n",
"[flaml.automl: 05-01 16:54:15] {993} INFO - iteration 13, current learner lgbm\n",
"[flaml.automl: 05-01 16:54:16] {1141} INFO - at 6.0s,\tbest lgbm's error=0.1954,\tbest lgbm's error=0.1954\n",
"[flaml.automl: 05-01 16:54:16] {993} INFO - iteration 14, current learner lgbm\n",
"[flaml.automl: 05-01 16:54:17] {1141} INFO - at 7.0s,\tbest lgbm's error=0.1933,\tbest lgbm's error=0.1933\n",
"[flaml.automl: 05-01 16:54:17] {993} INFO - iteration 15, current learner lgbm\n",
"[flaml.automl: 05-01 16:54:17] {1141} INFO - at 7.6s,\tbest lgbm's error=0.1933,\tbest lgbm's error=0.1933\n",
"[flaml.automl: 05-01 16:54:17] {993} INFO - iteration 16, current learner lgbm\n",
"[flaml.automl: 05-01 16:54:19] {1141} INFO - at 9.2s,\tbest lgbm's error=0.1799,\tbest lgbm's error=0.1799\n",
"[flaml.automl: 05-01 16:54:19] {993} INFO - iteration 17, current learner lgbm\n",
"[flaml.automl: 05-01 16:54:19] {1141} INFO - at 9.8s,\tbest lgbm's error=0.1799,\tbest lgbm's error=0.1799\n",
"[flaml.automl: 05-01 16:54:19] {993} INFO - iteration 18, current learner lgbm\n",
"[flaml.automl: 05-01 16:54:23] {1141} INFO - at 13.1s,\tbest lgbm's error=0.1799,\tbest lgbm's error=0.1799\n",
"[flaml.automl: 05-01 16:54:23] {993} INFO - iteration 19, current learner lgbm\n",
"[flaml.automl: 05-01 16:54:23] {1141} INFO - at 13.6s,\tbest lgbm's error=0.1799,\tbest lgbm's error=0.1799\n",
"[flaml.automl: 05-01 16:54:23] {993} INFO - iteration 20, current learner lgbm\n",
"[flaml.automl: 05-01 16:54:31] {1141} INFO - at 21.7s,\tbest lgbm's error=0.1799,\tbest lgbm's error=0.1799\n",
"[flaml.automl: 05-01 16:54:31] {993} INFO - iteration 21, current learner lgbm\n",
"[flaml.automl: 05-01 16:54:32] {1141} INFO - at 22.6s,\tbest lgbm's error=0.1799,\tbest lgbm's error=0.1799\n",
"[flaml.automl: 05-01 16:54:32] {993} INFO - iteration 22, current learner lgbm\n",
"[flaml.automl: 05-01 16:54:34] {1141} INFO - at 24.5s,\tbest lgbm's error=0.1722,\tbest lgbm's error=0.1722\n",
"[flaml.automl: 05-01 16:54:34] {993} INFO - iteration 23, current learner lgbm\n",
"[flaml.automl: 05-01 16:54:36] {1141} INFO - at 26.4s,\tbest lgbm's error=0.1714,\tbest lgbm's error=0.1714\n",
"[flaml.automl: 05-01 16:54:36] {993} INFO - iteration 24, current learner lgbm\n",
"[flaml.automl: 05-01 16:54:38] {1141} INFO - at 28.1s,\tbest lgbm's error=0.1714,\tbest lgbm's error=0.1714\n",
"[flaml.automl: 05-01 16:54:38] {993} INFO - iteration 25, current learner lgbm\n",
"[flaml.automl: 05-01 16:54:38] {1141} INFO - at 28.4s,\tbest lgbm's error=0.1714,\tbest lgbm's error=0.1714\n",
"[flaml.automl: 05-01 16:54:38] {993} INFO - iteration 26, current learner lgbm\n",
"[flaml.automl: 05-01 16:54:49] {1141} INFO - at 39.6s,\tbest lgbm's error=0.1582,\tbest lgbm's error=0.1582\n",
"[flaml.automl: 05-01 16:54:49] {993} INFO - iteration 27, current learner lgbm\n",
"[flaml.automl: 05-01 16:54:54] {1141} INFO - at 44.7s,\tbest lgbm's error=0.1582,\tbest lgbm's error=0.1582\n",
"[flaml.automl: 05-01 16:54:54] {993} INFO - iteration 28, current learner lgbm\n",
"[flaml.automl: 05-01 16:55:06] {1141} INFO - at 56.8s,\tbest lgbm's error=0.1582,\tbest lgbm's error=0.1582\n",
"[flaml.automl: 05-01 16:55:06] {993} INFO - iteration 29, current learner lgbm\n",
"[flaml.automl: 05-01 16:55:07] {1141} INFO - at 57.9s,\tbest lgbm's error=0.1582,\tbest lgbm's error=0.1582\n",
"[flaml.automl: 05-01 16:55:07] {993} INFO - iteration 30, current learner lgbm\n",
"[flaml.automl: 05-01 16:56:07] {1141} INFO - at 117.4s,\tbest lgbm's error=0.1582,\tbest lgbm's error=0.1582\n",
"[flaml.automl: 05-01 16:56:07] {1187} INFO - selected model: LGBMRegressor(colsample_bytree=0.7018843176351586,\n",
" learning_rate=0.05528362885527569, max_bin=255,\n",
" min_child_samples=64, n_estimators=266, num_leaves=204,\n",
" objective='regression', reg_alpha=0.005771390107656191,\n",
" reg_lambda=62.31073135366825)\n",
"[flaml.automl: 05-01 16:56:07] {944} INFO - fit succeeded\n"
]
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
}
],
"source": [
"'''The main flaml automl API'''\n",
Issue58 (#59) * iter per learner * code cleanup
2021-04-08 09:29:55 -07:00
"automl.fit(X_train=X_train, y_train=y_train, **settings)"
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "slide"
}
},
"source": [
"### Best model and metric"
]
},
{
"cell_type": "code",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"execution_count": 5,
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
"metadata": {
"slideshow": {
"slide_type": "slide"
},
"tags": []
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"text": [
"Best hyperparmeter config: {'n_estimators': 266.0, 'num_leaves': 204.0, 'min_child_samples': 64.0, 'learning_rate': 0.05528362885527569, 'subsample': 1.0, 'log_max_bin': 8.0, 'colsample_bytree': 0.7018843176351586, 'reg_alpha': 0.005771390107656191, 'reg_lambda': 62.31073135366825}\nBest r2 on validation data: 0.8418\nTraining duration of best run: 11.19 s\n"
]
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
}
],
"source": [
"''' retrieve best config'''\n",
"print('Best hyperparmeter config:', automl.best_config)\n",
"print('Best r2 on validation data: {0:.4g}'.format(1-automl.best_loss))\n",
"print('Training duration of best run: {0:.4g} s'.format(automl.best_config_train_time))"
]
},
{
"cell_type": "code",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"execution_count": 6,
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
"metadata": {
"slideshow": {
"slide_type": "slide"
}
},
"outputs": [
{
"output_type": "execute_result",
"data": {
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"text/plain": [
"LGBMRegressor(colsample_bytree=0.7018843176351586,\n",
" learning_rate=0.05528362885527569, max_bin=255,\n",
" min_child_samples=64, n_estimators=266, num_leaves=204,\n",
" objective='regression', reg_alpha=0.005771390107656191,\n",
" reg_lambda=62.31073135366825)"
]
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
},
"metadata": {},
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"execution_count": 6
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
}
],
"source": [
"automl.model"
]
},
{
"cell_type": "code",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"execution_count": 7,
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
"metadata": {
"slideshow": {
"slide_type": "slide"
}
},
"outputs": [],
"source": [
pickle the AutoML object (#37) * pickle the AutoML object * get best model per estimator * test deberta * stateless API * Add Gitter badge (#41) * prevent divide by zero * test roberta * BlendSearchTuner Co-authored-by: Chi Wang (MSR) <chiw@microsoft.com> Co-authored-by: The Gitter Badger <badger@gitter.im>
2021-03-16 22:13:35 -07:00
"''' pickle and save the automl object '''\n",
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
"import pickle\n",
pickle the AutoML object (#37) * pickle the AutoML object * get best model per estimator * test deberta * stateless API * Add Gitter badge (#41) * prevent divide by zero * test roberta * BlendSearchTuner Co-authored-by: Chi Wang (MSR) <chiw@microsoft.com> Co-authored-by: The Gitter Badger <badger@gitter.im>
2021-03-16 22:13:35 -07:00
"with open('automl.pkl', 'wb') as f:\n",
" pickle.dump(automl, f, pickle.HIGHEST_PROTOCOL)"
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
]
},
{
"cell_type": "code",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"execution_count": 8,
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
"metadata": {
"slideshow": {
"slide_type": "slide"
},
"tags": []
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"text": [
"Predicted labels [149389.7449446 258417.92579444 137823.39715453 ... 211944.92125371\n 246243.4022559 277524.07243136]\nTrue labels [136900. 241300. 200700. ... 160900. 227300. 265600.]\n"
]
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
}
],
"source": [
"''' compute predictions of testing dataset ''' \n",
"y_pred = automl.predict(X_test)\n",
"print('Predicted labels', y_pred)\n",
"print('True labels', y_test)"
]
},
{
"cell_type": "code",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"execution_count": 9,
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
"metadata": {
"slideshow": {
"slide_type": "slide"
},
"tags": []
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"text": [
"r2 = 0.8491961402689281\nmse = 1993401806.32529\nmae = 29616.531139250474\n"
]
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
}
],
"source": [
"''' compute different metric values on testing dataset'''\n",
"from flaml.ml import sklearn_metric_loss_score\n",
"print('r2', '=', 1 - sklearn_metric_loss_score('r2', y_pred, y_test))\n",
"print('mse', '=', sklearn_metric_loss_score('mse', y_pred, y_test))\n",
"print('mae', '=', sklearn_metric_loss_score('mae', y_pred, y_test))"
]
},
{
"cell_type": "code",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"execution_count": 10,
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
"metadata": {
"slideshow": {
"slide_type": "subslide"
},
"tags": []
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"text": [
"{'Current Learner': 'lgbm', 'Current Sample': 15480, 'Current Hyper-parameters': {'n_estimators': 4, 'num_leaves': 4, 'min_child_samples': 20, 'learning_rate': 0.1, 'subsample': 1.0, 'log_max_bin': 8, 'colsample_bytree': 1.0, 'reg_alpha': 0.0009765625, 'reg_lambda': 1.0}, 'Best Learner': 'lgbm', 'Best Hyper-parameters': {'n_estimators': 4, 'num_leaves': 4, 'min_child_samples': 20, 'learning_rate': 0.1, 'subsample': 1.0, 'log_max_bin': 8, 'colsample_bytree': 1.0, 'reg_alpha': 0.0009765625, 'reg_lambda': 1.0}}\n{'Current Learner': 'lgbm', 'Current Sample': 15480, 'Current Hyper-parameters': {'n_estimators': 4.0, 'num_leaves': 4.0, 'min_child_samples': 12.0, 'learning_rate': 0.25912534572860507, 'subsample': 0.9266743941610592, 'log_max_bin': 10.0, 'colsample_bytree': 1.0, 'reg_alpha': 0.0013933617380144255, 'reg_lambda': 0.18096917948292954}, 'Best Learner': 'lgbm', 'Best Hyper-parameters': {'n_estimators': 4.0, 'num_leaves': 4.0, 'min_child_samples': 12.0, 'learning_rate': 0.25912534572860507, 'subsample': 0.9266743941610592, 'log_max_bin': 10.0, 'colsample_bytree': 1.0, 'reg_alpha': 0.0013933617380144255, 'reg_lambda': 0.18096917948292954}}\n{'Current Learner': 'lgbm', 'Current Sample': 15480, 'Current Hyper-parameters': {'n_estimators': 4.0, 'num_leaves': 4.0, 'min_child_samples': 24.0, 'learning_rate': 1.0, 'subsample': 0.8513627344387318, 'log_max_bin': 10.0, 'colsample_bytree': 0.946138073111236, 'reg_alpha': 0.0018311776973217071, 'reg_lambda': 0.27901659190538414}, 'Best Learner': 'lgbm', 'Best Hyper-parameters': {'n_estimators': 4.0, 'num_leaves': 4.0, 'min_child_samples': 24.0, 'learning_rate': 1.0, 'subsample': 0.8513627344387318, 'log_max_bin': 10.0, 'colsample_bytree': 0.946138073111236, 'reg_alpha': 0.0018311776973217071, 'reg_lambda': 0.27901659190538414}}\n{'Current Learner': 'lgbm', 'Current Sample': 15480, 'Current Hyper-parameters': {'n_estimators': 11.0, 'num_leaves': 4.0, 'min_child_samples': 36.0, 'learning_rate': 1.0, 'subsample': 0.8894434216129232, 'log_max_bin': 10.0, 'colsample_bytree': 1.0, 'reg_alpha': 0.0013605736901132325, 'reg_lambda': 0.1222158118565165}, 'Best Learner': 'lgbm', 'Best Hyper-parameters': {'n_estimators': 11.0, 'num_leaves': 4.0, 'min_child_samples': 36.0, 'learning_rate': 1.0, 'subsample': 0.8894434216129232, 'log_max_bin': 10.0, 'colsample_bytree': 1.0, 'reg_alpha': 0.0013605736901132325, 'reg_lambda': 0.1222158118565165}}\n{'Current Learner': 'lgbm', 'Current Sample': 15480, 'Current Hyper-parameters': {'n_estimators': 20.0, 'num_leaves': 4.0, 'min_child_samples': 46.0, 'learning_rate': 1.0, 'subsample': 0.9814787163243813, 'log_max_bin': 9.0, 'colsample_bytree': 0.8499027725496043, 'reg_alpha': 0.0022085340760961856, 'reg_lambda': 0.546062702473889}, 'Best Learner': 'lgbm', 'Best Hyper-parameters': {'n_estimators': 20.0, 'num_leaves': 4.0, 'min_child_samples': 46.0, 'learning_rate': 1.0, 'subsample': 0.9814787163243813, 'log_max_bin': 9.0, 'colsample_bytree': 0.8499027725496043, 'reg_alpha': 0.0022085340760961856, 'reg_lambda': 0.546062702473889}}\n{'Current Learner': 'lgbm', 'Current Sample': 15480, 'Current Hyper-parameters': {'n_estimators': 20.0, 'num_leaves': 11.0, 'min_child_samples': 52.0, 'learning_rate': 1.0, 'subsample': 1.0, 'log_max_bin': 9.0, 'colsample_bytree': 0.7967145599266738, 'reg_alpha': 0.05680749758595097, 'reg_lambda': 2.756357095973371}, 'Best Learner': 'lgbm', 'Best Hyper-parameters': {'n_estimators': 20.0, 'num_leaves': 11.0, 'min_child_samples': 52.0, 'learning_rate': 1.0, 'subsample': 1.0, 'log_max_bin': 9.0, 'colsample_bytree': 0.7967145599266738, 'reg_alpha': 0.05680749758595097, 'reg_lambda': 2.756357095973371}}\n{'Current Learner': 'lgbm', 'Current Sample': 15480, 'Current Hyper-parameters': {'n_estimators': 37.0, 'num_leaves': 15.0, 'min_child_samples': 93.0, 'learning_rate': 0.6413547778096401, 'subsample': 1.0, 'log_max_bin': 9.0, 'colsample_bytree': 0.6980216487058154, 'reg_alpha': 0.020158745350617662, 'reg_lambda': 0.954042157679914}, 'Best Learner': 'lgbm', 'Best Hyper-parameters': {'n_estimators': 37.0, 'num_leaves': 15.0, '
]
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
}
],
"source": [
"from flaml.data import get_output_from_log\n",
"time_history, best_valid_loss_history, valid_loss_history, config_history, train_loss_history = \\\n",
Issue58 (#59) * iter per learner * code cleanup
2021-04-08 09:29:55 -07:00
" get_output_from_log(filename=settings['log_file_name'], time_budget=60)\n",
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
"\n",
"for config in config_history:\n",
" print(config)"
]
},
{
"cell_type": "code",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"execution_count": 11,
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
"metadata": {
"slideshow": {
"slide_type": "slide"
}
},
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": "<Figure size 432x288 with 1 Axes>",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"image/svg+xml": "<?xml version=\"1.0\" encoding=\"utf-8\" standalone=\"no\"?>\n<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\n \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n<!-- Created with matplotlib (https://matplotlib.org/) -->\n<svg height=\"277.314375pt\" version=\"1.1\" viewBox=\"0 0 385.78125 277.314375\" width=\"385.78125pt\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">\n <defs>\n <style type=\"text/css\">\n*{stroke-linecap:butt;stroke-linejoin:round;}\n </style>\n </defs>\n <g id=\"figure_1\">\n <g id=\"patch_1\">\n <path d=\"M 0 277.314375 \nL 385.78125 277.314375 \nL 385.78125 0 \nL 0 0 \nz\n\" style=\"fill:none;\"/>\n </g>\n <g id=\"axes_1\">\n <g id=\"patch_2\">\n <path d=\"M 43.78125 239.758125 \nL 378.58125 239.758125 \nL 378.58125 22.318125 \nL 43.78125 22.318125 \nz\n\" style=\"fill:#ffffff;\"/>\n </g>\n <g id=\"PathCollection_1\">\n <defs>\n <path d=\"M 0 3 \nC 0.795609 3 1.55874 2.683901 2.12132 2.12132 \nC 2.683901 1.55874 3 0.795609 3 0 \nC 3 -0.795609 2.683901 -1.55874 2.12132 -2.12132 \nC 1.55874 -2.683901 0.795609 -3 0 -3 \nC -0.795609 -3 -1.55874 -2.683901 -2.12132 -2.12132 \nC -2.683901 -1.55874 -3 -0.795609 -3 0 \nC -3 0.795609 -2.683901 1.55874 -2.12132 2.12132 \nC -1.55874 2.683901 -0.795609 3 0 3 \nz\n\" id=\"m3ea8699d28\" style=\"stroke:#1f77b4;\"/>\n </defs>\n <g clip-path=\"url(#p8819d9a2d9)\">\n <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"58.999432\" xlink:href=\"#m3ea8699d28\" y=\"229.874489\"/>\n <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"63.683239\" xlink:href=\"#m3ea8699d28\" y=\"167.005198\"/>\n <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"66.499179\" xlink:href=\"#m3ea8699d28\" y=\"110.765006\"/>\n <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"73.307571\" xlink:href=\"#m3ea8699d28\" y=\"81.08125\"/>\n <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"77.471251\" xlink:href=\"#m3ea8699d28\" y=\"68.000028\"/>\n <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"85.287235\" xlink:href=\"#m3ea8699d28\" y=\"57.138732\"/>\n <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"96.868044\" xlink:href=\"#m3ea8699d28\" y=\"44.851546\"/>\n <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"108.977895\" xlink:href=\"#m3ea8699d28\" y=\"44.136373\"/>\n <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"125.887583\" xlink:href=\"#m3ea8699d28\" y=\"39.595335\"/>\n <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"245.600162\" xlink:href=\"#m3ea8699d28\" y=\"36.960666\"/>\n <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"259.990447\" xlink:href=\"#m3ea8699d28\" y=\"36.67593\"/>\n <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"363.363068\" xlink:href=\"#m3ea8699d28\" y=\"32.201761\"/>\n </g>\n </g>\n <g id=\"matplotlib.axis_1\">\n <g id=\"xtick_1\">\n <g id=\"line2d_1\">\n <defs>\n <path d=\"M 0 0 \nL 0 3.5 \n\" id=\"m4144f3126f\" style=\"stroke:#000000;stroke-width:0.8;\"/>\n </defs>\n <g>\n <use style=\"stroke:#000000;stroke-width:0.8;\" x=\"54.522871\" xlink:href=\"#m4144f3126f\" y=\"239.758125\"/>\n </g>\n </g>\n <g id=\"text_1\">\n <!-- 0 -->\n <defs>\n <path d=\"M 31.78125 66.40625 \nQ 24.171875 66.40625 20.328125 58.90625 \nQ 16.5 51.421875 16.5 36.375 \nQ 16.5 21.390625 20.328125 13.890625 \nQ 24.171875 6.390625 31.78125 6.390625 \nQ 39.453125 6.390625 43.28125 13.890625 \nQ 47.125 21.390625 47.125 36.375 \nQ 47.125 51.421875 43.28125 58.90625 \nQ 39.453125 66.40625 31.78125 66.40625 \nz\nM 31.78125 74.21875 \nQ 44.046875 74.21875 50.515625 64.515625 \nQ 56.984375 54.828125 56.984375 36.375 \nQ 56.984375 17.96875 50.515625 8.265625 \nQ 44.046875 -1.421875 31.78125 -1.421875 \nQ 19.53125 -1.421875 13.0625 8.265625 \nQ 6.59375 17.96875 6.59375 36.375 \nQ 6.59375 54.828125 13.0625 64.515625 \nQ 19.53125 74.21875 31.78125 74.21875 \nz\n\" id=\"DejaVuSans-48\"/>\n </defs>\n <g transform=\"translate(51.341621 254.356562)scale(0.1 -0.1)\">\n <use xlink:href=\"#DejaVuSans-48\"/>\n
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEWCAYAAABrDZDcAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjAsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy8GearUAAAeaElEQVR4nO3dfbxVZZ338c/XI8gpxZNBDRxAMInCLLCTjtmUOhloJWRm6LzmLpvCmmyabDDowXFsvLWY7LbXzdSQt2mNz4RERdGDZpNagKI8GYZkwoESU9TsJE+/+4+1Di63+2z2OZy19z57fd+v136dva51rbV+Z8HZv31d11rXUkRgZmbFdUC9AzAzs/pyIjAzKzgnAjOzgnMiMDMrOCcCM7OCcyIwMys4JwKzCiT9jaT19Y7DLE9OBNawJD0s6a31jCEi/iciJuS1f0lTJP1c0tOStkm6Q9LpeR3PrBwnAis0SS11PPaZwC3AN4FRwMuBi4B39mFfkuS/Z+sT/8exAUfSAZJmS3pI0h8l3SzpsMz6WyT9XtKT6bftozLrrpH0VUlLJD0DnJS2PP5F0qp0m5skDUnrnyhpc2b7Huum6y+UtFXSFkkflBSSjizzOwi4Avh8RFwVEU9GxJ6IuCMiPpTWuVjSf2e2GZvu78B0+WeSLpV0J/BnYJakFSXH+YSkxen7gyT9h6RHJP1B0tckte7nP4c1AScCG4g+BkwH3gKMBJ4A5mXW/wAYD7wMuBe4rmT7c4BLgUOAX6RlZwFTgXHAa4H3Vzh+2bqSpgIXAG8FjgROrLCPCcBoYEGFOtX4e2Amye/yNWCCpPGZ9ecA16fvLwdeCUxK42snaYFYwTkR2ED0YeAzEbE5Ip4FLgbO7P6mHBFXR8TTmXWvk3RoZvvvRMSd6Tfwv6RlX4mILRHxOPBdkg/LnvRU9yzgGxGxNiL+nB67Jy9Nf26t9pfuwTXp8XZFxJPAd4CzAdKE8CpgcdoCmQl8IiIej4ingf8NzNjP41sTcCKwgehw4FZJ2yVtBx4AdgMvl9Qi6fK02+gp4OF0m2GZ7TeV2efvM+//DBxc4fg91R1Zsu9yx+n2x/TniAp1qlF6jOtJEwFJa2BRmpSGAy8C7smctx+m5VZwTgQ2EG0CTo2ItsxrSER0knz4TSPpnjkUGJtuo8z2eU25u5Vk0Lfb6Ap115P8Hu+uUOcZkg/vbn9Vpk7p7/JjYLikSSQJobtb6DGgCzgqc84OjYhKCc8KwonAGt0gSUMyrwNJ+sIvlXQ4gKThkqal9Q8BniX5xv0iku6PWrkZOFfSqyW9CPhcTxUjmf/9AuBzks6VNDQdBH+TpPlptfuAN0sak3ZtzdlXABGxk+RKpLnAYSSJgYjYA3wd+LKklwFIapc0pc+/rTUNJwJrdEtIvsl2vy4GrgQWAz+S9DTwS+C4tP43gd8BncC6dF1NRMQPgK8AtwMbMsd+tof6C4D3Ah8AtgB/AP6dpJ+fiPgxcBOwCrgH+F6VoVxP0iK6JSJ2Zco/1R1X2m32E5JBays4+cE0ZvmQ9GpgDXBQyQeyWUNxi8CsH0l6V3q9/kuALwDfdRKwRudEYNa/zgMeBR4iuZLpI/UNx2zf3DVkZlZwbhGYmRXcgfUOoLeGDRsWY8eOrXcYZmYDyj333PNYRJS9gXDAJYKxY8eyYsWKfVc0M7O9JP2up3XuGjIzKzgnAjOzgnMiMDMrOCcCM7OCcyIwMyu4AXfVkJlZ0Sxa2cncpevZsr2LkW2tzJoygemT2/tt/04EZmYNbNHKTuYsXE3Xzt0AdG7vYs7C1QD9lgzcNWRm1sDmLl2/Nwl069q5m7lL1/fbMZwIzMwa2JbtXb0q7wsnAjOzBjayrbVX5X3hMQKzJtLXQcW8ByOt72ZNmfC8MQKA1kEtzJrSfw+XcyIwaxJ9HVSsxWCk9V33v8GFC1axY/ce2nNI1APueQQdHR3hSefMXuiEy2+js0y/8eCWA5g8pq3H7VY+sp0du/f0ejurrXVbn2LiiKHcdN7xfdpe0j0R0VFunVsEBeMugObV0+BhuQ/5atbvazurrYkjhjJtUj5/q04EBeIugOY2sq21bIugva214rfInloS+9rOmocTQYH0dD3yhQtWccOyR+oUlfWXIYMO4ADBnkxvbzWDirUYjLTG5kRQIH3tOrCBYdjBBwGw6fGuXg0qdq93l2FxOREMIPvbv9/XrgNrftMnt/uDv8B8Q1kdLVrZyQmX38a42d/nhMtvY9HKzop15yxcTef2LoLn+vcrbVNq1pQJtA5qeV6ZuwDMLNcWgaSpwJVAC3BVRFxesn4McC3QltaZHRFL8oypUfR24La/+vdHtg1h47ZnCMjlemQzG3hySwSSWoB5wCnAZmC5pMURsS5T7bPAzRHxVUkTgSXA2LxiaiS9/WAv16UDve/fH3bwQQw7+CCmTWrnnOPG9GpbM2tOebYIjgU2RMRGAEk3AtOAbCIIYGj6/lBgS47xNJTeDtwObjmg7Dr375vZ/sozEbQDmzLLm4HjSupcDPxI0seAFwNvLbcjSTOBmQBjxjTHt9jeDtyWdiWB+/fNrH/Ue7D4bOCaiBgFnAZ8S9ILYoqI+RHREREdw4cPr3mQeejtwO30ye1cdsbRtLe1IpKEcdkZR7t/38z2W54tgk5gdGZ5VFqW9Q/AVICIuFvSEGAY8GiOcTWEvkwk5Uv8zCwPeSaC5cB4SeNIEsAM4JySOo8AfwtcI+nVwBBgW44xNZTpk9v3Dgy7n9/M6iW3rqGI2AWcDywFHiC5OmitpEsknZ5W+yTwIUn3AzcA74+BNh2qmdkAl+t9BOk9AUtKyi7KvF8HnJBnDGZmVlm9B4vNzKzOnAjMzArOk871Mz/4xcwGGieCfuQHv5jZQORE0I/6MjFc93NIzczqxWME/agvD37J8zmkZmbVcIugH/nBL2Y2ELlF0I/84BczG4jcIuhHfZk/yMys3pwI+pnnDzKzgcZdQ2ZmBedEYGZWcE4EZmYF5zGCXvIUEmbWbJwIesFTSJhZM3Ii6IVqp5DwtBFmNpB4jKAXqp1CwtNGmNlA4hZBL3gKCTNrRm4R9IKnkDCzZuQWQS94Cgkza0ZOBL3kKSTMrNm4a8jMrOCcCMzMCs6JwMys4JwIzMwKLtdEIGmqpPWSNkiaXWb9lyXdl74elLQ9z3jMzOyFcrtqSFILMA84BdgMLJe0OCLWddeJiE9k6n8MmJxXPH1VbpI5M7NmkmeL4FhgQ0RsjIgdwI3AtAr1zwZuyDGeXuueZK5zexfBc5PMPfanZ+sdmplZv8kzEbQDmzLLm9OyF5B0ODAOuC3HeHqtp0nmNm57pk4RmZn1v0YZLJ4BLIiI3eVWSpopaYWkFdu2batZUD1NMhfgSeXMrGnkmQg6gdGZ5VFpWTkzqNAtFBHzI6IjIjqGDx/ejyFWNrKttWx5e1sr5xw3pmZxmJnlKc9EsBwYL2mcpMEkH/aLSytJehXwEuDuHGPpE08yZ2ZFkFsiiIhdwPnAUuAB4OaIWCvpEkmnZ6rOAG6MiMgrlr6aPrmdy844msEtyWlqb2vlsjOO9iRzZtZU1ICfvxV1dHTEihUranrM9/5X0ljxJHNmNlBJuiciOsqta5TBYjMzqxMnAjOzgnMiMDMrOCcCM7OCcyIwMys4JwIzs4JzIjAzKzgnAjOzgnMiMDMrOCcCM7OCcyIwMys4JwIzs4JzIjAzKzgnAjOzgnMiMDMrOCcCM7OCq5gIJA2V9Ioy5a/NLyQzM6ulHhOBpLOAXwPflrRW0hsyq6/JOzAzM6uNSi2CTwOvj4hJwLnAtyS9K12n3CMzM7OaOLDCupaI2AoQEcsknQR8T9JoYGA96NjMzHpUqUXwdHZ8IE0KJwLTgKNyjsvMzGqkUovgI5R0AUXE05KmAmflGpWZmdVMj4kgIu6X1CLp9og4KVO+E7iuJtHVyKKVncxdup4t27sY2dbKrCkTmD65vd5hmZnVRKUWARGxW9IeSYdGxJO1CqqWFq3sZM7C1XTt3A1A5/Yu5ixcDeBkYGaFUDERpP4ErJb
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
},
"metadata": {
"needs_background": "light"
}
}
],
"source": [
"import matplotlib.pyplot as plt\n",
"import numpy as np\n",
"\n",
"plt.title('Learning Curve')\n",
"plt.xlabel('Wall Clock Time (s)')\n",
"plt.ylabel('Validation r2')\n",
Issue58 (#59) * iter per learner * code cleanup
2021-04-08 09:29:55 -07:00
"plt.scatter(time_history, 1 - np.array(valid_loss_history))\n",
"plt.step(time_history, 1 - np.array(best_valid_loss_history), where='post')\n",
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
"plt.show()"
]
},
{
"source": [
"## 3. Comparison with alternatives\n",
"\n",
"### FLAML's accuracy"
],
"cell_type": "markdown",
"metadata": {}
},
{
"cell_type": "code",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"execution_count": 12,
Lgbm w customized obj (#64) * add customized lgbm learner * add comments * fix format issue * format * OpenMLError * add test * add notebook Co-authored-by: Chi Wang (MSR) <chiw@microsoft.com> Co-authored-by: Chi Wang <wang.chi@microsoft.com>
2021-04-10 21:14:28 -04:00
"metadata": {
"tags": []
},
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
"outputs": [
{
"output_type": "stream",
"name": "stdout",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"text": [
"flaml r2 = 0.8491961402689281\n"
]
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
}
],
"source": [
"print('flaml r2', '=', 1 - sklearn_metric_loss_score('r2', y_pred, y_test))"
]
},
{
"source": [
"### Default LightGBM"
],
"cell_type": "markdown",
"metadata": {}
},
{
"cell_type": "code",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"execution_count": 13,
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
"metadata": {},
"outputs": [],
"source": [
"from lightgbm import LGBMRegressor\n",
"lgbm = LGBMRegressor()"
]
},
{
"cell_type": "code",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"execution_count": 14,
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
"metadata": {},
"outputs": [
{
"output_type": "execute_result",
"data": {
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"text/plain": [
"LGBMRegressor()"
]
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
},
"metadata": {},
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"execution_count": 14
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
}
],
"source": [
"lgbm.fit(X_train, y_train)"
]
},
{
"cell_type": "code",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"execution_count": 15,
Lgbm w customized obj (#64) * add customized lgbm learner * add comments * fix format issue * format * OpenMLError * add test * add notebook Co-authored-by: Chi Wang (MSR) <chiw@microsoft.com> Co-authored-by: Chi Wang <wang.chi@microsoft.com>
2021-04-10 21:14:28 -04:00
"metadata": {
"tags": []
},
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
"outputs": [
{
"output_type": "stream",
"name": "stdout",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"text": [
"default lgbm r2 = 0.8296179648694404\n"
]
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
}
],
"source": [
"y_pred = lgbm.predict(X_test)\n",
"from flaml.ml import sklearn_metric_loss_score\n",
"print('default lgbm r2', '=', 1 - sklearn_metric_loss_score('r2', y_pred, y_test))"
]
},
{
"source": [
"### Optuna LightGBM Tuner"
],
"cell_type": "markdown",
"metadata": {}
},
{
"cell_type": "code",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"execution_count": 16,
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
"metadata": {},
"outputs": [],
"source": [
Issue58 (#59) * iter per learner * code cleanup
2021-04-08 09:29:55 -07:00
"# !pip install optuna==2.5.0;"
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
]
},
{
"cell_type": "code",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"execution_count": 17,
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
"metadata": {},
"outputs": [],
"source": [
"from sklearn.model_selection import train_test_split\n",
"train_x, val_x, train_y, val_y = train_test_split(X_train, y_train, test_size=0.1)\n",
"import optuna.integration.lightgbm as lgb\n",
"dtrain = lgb.Dataset(train_x, label=train_y)\n",
"dval = lgb.Dataset(val_x, label=val_y)\n",
"params = {\n",
" \"objective\": \"regression\",\n",
" \"metric\": \"regression\",\n",
" \"verbosity\": -1,\n",
"}\n"
]
},
{
"cell_type": "code",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"execution_count": 18,
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
"metadata": {
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"tags": [
"outputPrepend"
]
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
},
"outputs": [
{
"output_type": "stream",
"name": "stderr",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"text": [
"n': 0.5}. Best is trial 1 with value: 2012422177.233508.\u001b[0m\n",
"feature_fraction, val_score: 2012422177.233508: 43%|####2 | 3/7 [00:07<00:11, 2.76s/it]\u001b[32m[I 2021-05-01 16:56:19,694]\u001b[0m Trial 2 finished with value: 2070320819.099197 and parameters: {'feature_fraction': 0.6}. Best is trial 1 with value: 2012422177.233508.\u001b[0m\n",
"feature_fraction, val_score: 2012422177.233508: 57%|#####7 | 4/7 [00:10<00:08, 2.75s/it]\u001b[32m[I 2021-05-01 16:56:22,414]\u001b[0m Trial 3 finished with value: 2090738130.975806 and parameters: {'feature_fraction': 0.8999999999999999}. Best is trial 1 with value: 2012422177.233508.\u001b[0m\n",
"feature_fraction, val_score: 2012422177.233508: 71%|#######1 | 5/7 [00:13<00:05, 2.67s/it]\u001b[32m[I 2021-05-01 16:56:24,909]\u001b[0m Trial 4 finished with value: 2041753467.8813415 and parameters: {'feature_fraction': 0.8}. Best is trial 1 with value: 2012422177.233508.\u001b[0m\n",
"feature_fraction, val_score: 2012422177.233508: 86%|########5 | 6/7 [00:15<00:02, 2.68s/it]\u001b[32m[I 2021-05-01 16:56:27,596]\u001b[0m Trial 5 finished with value: 2041753467.8813415 and parameters: {'feature_fraction': 0.7}. Best is trial 1 with value: 2012422177.233508.\u001b[0m\n",
"feature_fraction, val_score: 2012422177.233508: 100%|##########| 7/7 [00:18<00:00, 2.59s/it]\u001b[32m[I 2021-05-01 16:56:29,991]\u001b[0m Trial 6 finished with value: 2268739005.2074604 and parameters: {'feature_fraction': 0.4}. Best is trial 1 with value: 2012422177.233508.\u001b[0m\n",
"feature_fraction, val_score: 2012422177.233508: 100%|##########| 7/7 [00:18<00:00, 2.59s/it]\n",
"num_leaves, val_score: 2012422177.233508: 5%|5 | 1/20 [00:05<01:37, 5.15s/it]\u001b[32m[I 2021-05-01 16:56:35,147]\u001b[0m Trial 7 finished with value: 2101942667.8301136 and parameters: {'num_leaves': 100}. Best is trial 7 with value: 2101942667.8301136.\u001b[0m\n",
"num_leaves, val_score: 2012422177.233508: 10%|# | 2/20 [00:11<01:39, 5.53s/it]\u001b[32m[I 2021-05-01 16:56:41,578]\u001b[0m Trial 8 finished with value: 2116990487.8274357 and parameters: {'num_leaves': 170}. Best is trial 7 with value: 2101942667.8301136.\u001b[0m\n",
"num_leaves, val_score: 2012422177.233508: 15%|#5 | 3/20 [00:14<01:19, 4.65s/it]\u001b[32m[I 2021-05-01 16:56:44,174]\u001b[0m Trial 9 finished with value: 2068285393.500253 and parameters: {'num_leaves': 53}. Best is trial 9 with value: 2068285393.500253.\u001b[0m\n",
"num_leaves, val_score: 2012422177.233508: 20%|## | 4/20 [00:25<01:48, 6.75s/it]\u001b[32m[I 2021-05-01 16:56:55,835]\u001b[0m Trial 10 finished with value: 2155721300.061022 and parameters: {'num_leaves': 247}. Best is trial 9 with value: 2068285393.500253.\u001b[0m\n",
"num_leaves, val_score: 2012422177.233508: 25%|##5 | 5/20 [00:27<01:20, 5.36s/it]\u001b[32m[I 2021-05-01 16:56:57,939]\u001b[0m Trial 11 finished with value: 2110152521.9026961 and parameters: {'num_leaves': 14}. Best is trial 9 with value: 2068285393.500253.\u001b[0m\n",
"num_leaves, val_score: 2012422177.233508: 30%|### | 6/20 [00:43<01:59, 8.55s/it]\u001b[32m[I 2021-05-01 16:57:13,922]\u001b[0m Trial 12 finished with value: 2155721300.061022 and parameters: {'num_leaves': 247}. Best is trial 9 with value: 2068285393.500253.\u001b[0m\n",
"num_leaves, val_score: 2012422177.233508: 35%|###5 | 7/20 [00:53<01:53, 8.74s/it]\u001b[32m[I 2021-05-01 16:57:23,128]\u001b[0m Trial 13 finished with value: 2170705249.4392734 and parameters: {'num_leaves': 180}. Best is trial 9 with value: 2068285393.500253.\u001b[0m\n",
"num_leaves, val_score: 2012422177.233508: 40%|#### | 8/20 [00:53<01:16, 6.37s/it]\u001b[32m[I 2021-05-01 16:57:23,950]\u001b[0m Trial 14 finished with value: 3322965157.380943 and parameters: {'num_leaves': 2}. Best is trial 9 with value: 2068285393.500253.\u001b[0m\n",
"num_leaves, val_score: 2012422177.233508: 45%|####5 | 9/20 [01:00<01:09, 6.34s/it]\u001b[32m[I 2021-05-01 16:57:30,222]\u001b[0m Trial 15 finished with value: 2078188917.1665275 and parameters: {'num_leaves': 112}. Best is trial 9 with value: 2068285393.500253.\u001b[0m\n",
"num_leaves, val_score: 2012422177.233508: 50%|##### | 10/20 [01:09<01:12, 7.26s/it]\u001b[32m[I 2021-05-01 16:57:39,631]\u001b[0m Trial 16 finished with value: 2149952453.251796 and parameters: {'num_leaves': 194}. Best is trial 9 with value: 2068285393.500253.\u001b[0m\n",
"num_leaves, val_score: 2012422177.233508: 55%|#####5 | 11/20 [01:12<00:53, 6.00s/it]\u001b[32m[I 2021-05-01 16:57:42,688]\u001b[0m Trial 17 finished with value: 2039014776.0863047 and parameters: {'num_leaves': 50}. Best is trial 17 with value: 2039014776.0863047.\u001b[0m\n",
"num_leaves, val_score: 2012422177.233508: 60%|###### | 12/20 [01:16<00:43, 5.39s/it]\u001b[32m[I 2021-05-01 16:57:46,660]\u001b[0m Trial 18 finished with value: 2028177421.7466378 and parameters: {'num_leaves': 70}. Best is trial 18 with value: 2028177421.7466378.\u001b[0m\n",
"num_leaves, val_score: 2012422177.233508: 65%|######5 | 13/20 [01:21<00:36, 5.21s/it]\u001b[32m[I 2021-05-01 16:57:51,453]\u001b[0m Trial 19 finished with value: 2083200978.2816963 and parameters: {'num_leaves': 72}. Best is trial 18 with value: 2028177421.7466378.\u001b[0m\n",
"num_leaves, val_score: 2012422177.233508: 70%|####### | 14/20 [01:29<00:37, 6.19s/it]\u001b[32m[I 2021-05-01 16:57:59,920]\u001b[0m Trial 20 finished with value: 2121588087.918161 and parameters: {'num_leaves': 129}. Best is trial 18 with value: 2028177421.7466378.\u001b[0m\n",
"num_leaves, val_score: 1997587162.470951: 75%|#######5 | 15/20 [01:33<00:27, 5.55s/it]\u001b[32m[I 2021-05-01 16:58:03,962]\u001b[0m Trial 21 finished with value: 1997587162.470951 and parameters: {'num_leaves': 43}. Best is trial 21 with value: 1997587162.470951.\u001b[0m\n",
"num_leaves, val_score: 1997587162.470951: 80%|######## | 16/20 [01:36<00:18, 4.74s/it]\u001b[32m[I 2021-05-01 16:58:06,830]\u001b[0m Trial 22 finished with value: 2052604443.4670672 and parameters: {'num_leaves': 28}. Best is trial 21 with value: 1997587162.470951.\u001b[0m\n",
"num_leaves, val_score: 1997587162.470951: 85%|########5 | 17/20 [01:43<00:15, 5.24s/it]\u001b[32m[I 2021-05-01 16:58:13,218]\u001b[0m Trial 23 finished with value: 2043471294.5650334 and parameters: {'num_leaves': 80}. Best is trial 21 with value: 1997587162.470951.\u001b[0m\n",
"num_leaves, val_score: 1997587162.470951: 90%|######### | 18/20 [01:51<00:12, 6.21s/it]\u001b[32m[I 2021-05-01 16:58:21,714]\u001b[0m Trial 24 finished with value: 2134499770.7451386 and parameters: {'num_leaves': 138}. Best is trial 21 with value: 1997587162.470951.\u001b[0m\n",
"num_leaves, val_score: 1997587162.470951: 95%|#########5| 19/20 [01:55<00:05, 5.53s/it]\u001b[32m[I 2021-05-01 16:58:25,660]\u001b[0m Trial 25 finished with value: 2044138761.5237503 and parameters: {'num_leaves': 42}. Best is trial 21 with value: 1997587162.470951.\u001b[0m\n",
"num_leaves, val_score: 1997587162.470951: 100%|##########| 20/20 [02:00<00:00, 5.29s/it]\u001b[32m[I 2021-05-01 16:58:30,376]\u001b[0m Trial 26 finished with value: 2043471294.5650334 and parameters: {'num_leaves': 80}. Best is trial 21 with value: 1997587162.470951.\u001b[0m\n",
"num_leaves, val_score: 1997587162.470951: 100%|##########| 20/20 [02:00<00:00, 6.02s/it]\n",
"bagging, val_score: 1997587162.470951: 10%|# | 1/10 [00:03<00:31, 3.52s/it]\u001b[32m[I 2021-05-01 16:58:33,911]\u001b[0m Trial 27 finished with value: 2013108212.2667012 and parameters: {'bagging_fraction': 0.7107931665183529, 'bagging_freq': 4}. Best is trial 27 with value: 2013108212.2667012.\u001b[0m\n",
"bagging, val_score: 1997587162.470951: 20%|## | 2/10 [00:06<00:27, 3.49s/it]\u001b[32m[I 2021-05-01 16:58:37,305]\u001b[0m Trial 28 finished with value: 2115850610.4036384 and parameters: {'bagging_fraction': 0.7110669495016676, 'bagging_freq': 4}. Best is trial 27 with value: 2013108212.2667012.\u001b[0m\n",
"bagging, val_score: 1997587162.470951: 30%|### | 3/10 [00:10<00:25, 3.66s/it]\u001b[32m[I 2021-05-01 16:58:41,369]\u001b[0m Trial 29 finished with value: 2195082524.11466 and parameters: {'bagging_fraction': 0.4223130416728271, 'bagging_freq': 3}. Best is trial 27 with value: 2013108212.2667012.\u001b[0m\n",
"bagging, val_score: 1997587162.470951: 40%|#### | 4/10 [00:14<00:21, 3.67s/it]\u001b[32m[I 2021-05-01 16:58:45,049]\u001b[0m Trial 30 finished with value: 2040265763.438056 and parameters: {'bagging_fraction': 0.9997992429240515, 'bagging_freq': 7}. Best is trial 27 with value: 2013108212.2667012.\u001b[0m\n",
"bagging, val_score: 1997587162.470951: 50%|##### | 5/10 [00:18<00:18, 3.73s/it]\u001b[32m[I 2021-05-01 16:58:48,928]\u001b[0m Trial 31 finished with value: 2131241507.3480675 and parameters: {'bagging_fraction': 0.6896585879210911, 'bagging_freq': 6}. Best is trial 27 with value: 2013108212.2667012.\u001b[0m\n",
"bagging, val_score: 1997587162.470951: 60%|###### | 6/10 [00:21<00:14, 3.62s/it]\u001b[32m[I 2021-05-01 16:58:52,305]\u001b[0m Trial 32 finished with value: 2103907334.0925496 and parameters: {'bagging_fraction': 0.7164061602702391, 'bagging_freq': 1}. Best is trial 27 with value: 2013108212.2667012.\u001b[0m\n",
"bagging, val_score: 1997587162.470951: 70%|####### | 7/10 [00:26<00:11, 3.77s/it]\u001b[32m[I 2021-05-01 16:58:56,405]\u001b[0m Trial 33 finished with value: 2036444350.9989514 and parameters: {'bagging_fraction': 0.8892052985573371, 'bagging_freq': 4}. Best is trial 27 with value: 2013108212.2667012.\u001b[0m\n",
"bagging, val_score: 1997587162.470951: 80%|######## | 8/10 [00:30<00:07, 3.88s/it]\u001b[32m[I 2021-05-01 16:59:00,560]\u001b[0m Trial 34 finished with value: 2225281871.3367276 and parameters: {'bagging_fraction': 0.49661561085854733, 'bagging_freq': 2}. Best is trial 27 with value: 2013108212.2667012.\u001b[0m\n",
"bagging, val_score: 1997587162.470951: 90%|######### | 9/10 [00:34<00:03, 3.91s/it]\u001b[32m[I 2021-05-01 16:59:04,536]\u001b[0m Trial 35 finished with value: 2143704197.0784042 and parameters: {'bagging_fraction': 0.5655413899704534, 'bagging_freq': 5}. Best is trial 27 with value: 2013108212.2667012.\u001b[0m\n",
"bagging, val_score: 1997587162.470951: 100%|##########| 10/10 [00:37<00:00, 3.84s/it]\u001b[32m[I 2021-05-01 16:59:08,211]\u001b[0m Trial 36 finished with value: 2110700689.1702607 and parameters: {'bagging_fraction': 0.8700737972459625, 'bagging_freq': 6}. Best is trial 27 with value: 2013108212.2667012.\u001b[0m\n",
"bagging, val_score: 1997587162.470951: 100%|##########| 10/10 [00:37<00:00, 3.78s/it]\n",
"feature_fraction_stage2, val_score: 1997587162.470951: 17%|#6 | 1/6 [00:02<00:13, 2.66s/it]\u001b[32m[I 2021-05-01 16:59:10,871]\u001b[0m Trial 37 finished with value: 2089539253.8077588 and parameters: {'feature_fraction': 0.58}. Best is trial 37 with value: 2089539253.8077588.\u001b[0m\n",
"feature_fraction_stage2, val_score: 1997587162.470951: 33%|###3 | 2/6 [00:05<00:10, 2.62s/it]\u001b[32m[I 2021-05-01 16:59:13,403]\u001b[0m Trial 38 finished with value: 1997587162.470951 and parameters: {'feature_fraction': 0.484}. Best is trial 38 with value: 1997587162.470951.\u001b[0m\n",
"feature_fraction_stage2, val_score: 1997587162.470951: 50%|##### | 3/6 [00:07<00:07, 2.64s/it]\u001b[32m[I 2021-05-01 16:59:16,077]\u001b[0m Trial 39 finished with value: 1997587162.470951 and parameters: {'feature_fraction': 0.516}. Best is trial 38 with value: 1997587162.470951.\u001b[0m\n",
"feature_fraction_stage2, val_score: 1997587162.470951: 67%|######6 | 4/6 [00:10<00:05, 2.67s/it]\u001b[32m[I 2021-05-01 16:59:18,827]\u001b[0m Trial 40 finished with value: 2284254046.781229 and parameters: {'feature_fraction': 0.42}. Best is trial 38 with value: 1997587162.470951.\u001b[0m\n",
"feature_fraction_stage2, val_score: 1997587162.470951: 83%|########3 | 5/6 [00:14<00:02, 2.93s/it]\u001b[32m[I 2021-05-01 16:59:22,357]\u001b[0m Trial 41 finished with value: 1997587162.470951 and parameters: {'feature_fraction': 0.5479999999999999}. Best is trial 38 with value: 1997587162.470951.\u001b[0m\n",
"feature_fraction_stage2, val_score: 1997587162.470951: 100%|##########| 6/6 [00:17<00:00, 3.01s/it]\u001b[32m[I 2021-05-01 16:59:25,574]\u001b[0m Trial 42 finished with value: 1997587162.470951 and parameters: {'feature_fraction': 0.45199999999999996}. Best is trial 38 with value: 1997587162.470951.\u001b[0m\n",
"feature_fraction_stage2, val_score: 1997587162.470951: 100%|##########| 6/6 [00:17<00:00, 2.89s/it]\n",
"regularization_factors, val_score: 1997587070.360476: 5%|5 | 1/20 [00:03<01:02, 3.31s/it]\u001b[32m[I 2021-05-01 16:59:28,890]\u001b[0m Trial 43 finished with value: 1997587070.3604763 and parameters: {'lambda_l1': 1.3325881401359536e-06, 'lambda_l2': 2.012676569064997e-05}. Best is trial 43 with value: 1997587070.3604763.\u001b[0m\n",
"regularization_factors, val_score: 1997587070.360476: 10%|# | 2/20 [00:06<00:58, 3.27s/it]\u001b[32m[I 2021-05-01 16:59:32,081]\u001b[0m Trial 44 finished with value: 1997587071.8468173 and parameters: {'lambda_l1': 3.416658142750445e-07, 'lambda_l2': 1.971124403055093e-05}. Best is trial 43 with value: 1997587070.3604763.\u001b[0m\n",
"regularization_factors, val_score: 1997587070.360476: 15%|#5 | 3/20 [00:09<00:55, 3.28s/it]\u001b[32m[I 2021-05-01 16:59:35,368]\u001b[0m Trial 45 finished with value: 1997587102.3779635 and parameters: {'lambda_l1': 3.267399616442553e-07, 'lambda_l2': 1.3087509647016092e-05}. Best is trial 43 with value: 1997587070.3604763.\u001b[0m\n",
"regularization_factors, val_score: 1997587070.360476: 20%|## | 4/20 [00:13<00:52, 3.30s/it]\u001b[32m[I 2021-05-01 16:59:38,720]\u001b[0m Trial 46 finished with value: 1997587075.3923492 and parameters: {'lambda_l1': 2.682703999444416e-07, 'lambda_l2': 1.8913639824313343e-05}. Best is trial 43 with value: 1997587070.3604763.\u001b[0m\n",
"regularization_factors, val_score: 1997587070.360476: 25%|##5 | 5/20 [00:16<00:49, 3.32s/it]\u001b[32m[I 2021-05-01 16:59:42,085]\u001b[0m Trial 47 finished with value: 1997587070.787969 and parameters: {'lambda_l1': 1.4561401674574448e-07, 'lambda_l2': 1.9976154048638757e-05}. Best is trial 43 with value: 1997587070.3604763.\u001b[0m\n",
"regularization_factors, val_score: 1997587070.360476: 30%|### | 6/20 [00:19<00:46, 3.35s/it]\u001b[32m[I 2021-05-01 16:59:45,512]\u001b[0m Trial 48 finished with value: 1997587087.4850538 and parameters: {'lambda_l1': 2.9044467527482266e-07, 'lambda_l2': 1.6280849368362258e-05}. Best is trial 43 with value: 1997587070.3604763.\u001b[0m\n",
"regularization_factors, val_score: 1997587057.813578: 35%|###5 | 7/20 [00:23<00:43, 3.34s/it]\u001b[32m[I 2021-05-01 16:59:48,814]\u001b[0m Trial 49 finished with value: 1997587057.8135784 and parameters: {'lambda_l1': 2.736584478611428e-07, 'lambda_l2': 2.2832344774742773e-05}. Best is trial 49 with value: 1997587057.8135784.\u001b[0m\n",
"regularization_factors, val_score: 1997586977.666038: 40%|#### | 8/20 [00:26<00:39, 3.32s/it]\u001b[32m[I 2021-05-01 16:59:52,105]\u001b[0m Trial 50 finished with value: 1997586977.666038 and parameters: {'lambda_l1': 2.2552818901556212e-07, 'lambda_l2': 4.0459809426159216e-05}. Best is trial 50 with value: 1997586977.666038.\u001b[0m\n",
"regularization_factors, val_score: 1997586977.666038: 45%|####5 | 9/20 [00:29<00:36, 3.29s/it]\u001b[32m[I 2021-05-01 16:59:55,317]\u001b[0m Trial 51 finished with value: 1997587069.0728564 and parameters: {'lambda_l1': 2.269836233537227e-07, 'lambda_l2': 2.0400060529051817e-05}. Best is trial 50 with value: 1997586977.666038.\u001b[0m\n",
"regularization_factors, val_score: 1997586977.666038: 50%|##### | 10/20 [00:33<00:33, 3.32s/it]\u001b[32m[I 2021-05-01 16:59:58,719]\u001b[0m Trial 52 finished with value: 1997587038.1018682 and parameters: {'lambda_l1': 2.1190142795602203e-07, 'lambda_l2': 2.7161997048896454e-05}. Best is trial 50 with value: 1997586977.666038.\u001b[0m\n",
"regularization_factors, val_score: 1997586977.666038: 55%|#####5 | 11/20 [00:36<00:30, 3.43s/it]\u001b[32m[I 2021-05-01 17:00:02,410]\u001b[0m Trial 53 finished with value: 1997586992.6494768 and parameters: {'lambda_l1': 2.1728160447318185e-07, 'lambda_l2': 3.710639213958161e-05}. Best is trial 50 with value: 1997586977.666038.\u001b[0m\n",
"regularization_factors, val_score: 1996449931.514239: 60%|###### | 12/20 [00:40<00:27, 3.40s/it]\u001b[32m[I 2021-05-01 17:00:05,742]\u001b[0m Trial 54 finished with value: 1996449931.514239 and parameters: {'lambda_l1': 2.1748994754196613e-07, 'lambda_l2': 0.0001457763270993375}. Best is trial 54 with value: 1996449931.514239.\u001b[0m\n",
"regularization_factors, val_score: 1996449931.514239: 65%|######5 | 13/20 [00:44<00:26, 3.79s/it]\u001b[32m[I 2021-05-01 17:00:10,421]\u001b[0m Trial 55 finished with value: 2067232492.4956243 and parameters: {'lambda_l1': 1.024147819302013e-08, 'lambda_l2': 0.00295027742437926}. Best is trial 54 with value: 1996449931.514239.\u001b[0m\n",
"regularization_factors, val_score: 1996449532.606333: 70%|####### | 14/20 [00:49<00:23, 3.91s/it]\u001b[32m[I 2021-05-01 17:00:14,622]\u001b[0m Trial 56 finished with value: 1996449532.606333 and parameters: {'lambda_l1': 0.0738445887576454, 'lambda_l2': 0.00022249854014829427}. Best is trial 56 with value: 1996449532.606333.\u001b[0m\n",
"regularization_factors, val_score: 1996449532.606333: 75%|#######5 | 15/20 [00:51<00:17, 3.50s/it]\u001b[32m[I 2021-05-01 17:00:17,173]\u001b[0m Trial 57 finished with value: 2030166678.6715233 and parameters: {'lambda_l1': 0.4206025220395843, 'lambda_l2': 0.0013715337299642163}. Best is trial 56 with value: 1996449532.606333.\u001b[0m\n",
"regularization_factors, val_score: 1996449532.606333: 80%|######## | 16/20 [00:54<00:13, 3.26s/it]\u001b[32m[I 2021-05-01 17:00:19,852]\u001b[0m Trial 58 finished with value: 2035151132.9680371 and parameters: {'lambda_l1': 0.04874741366424845, 'lambda_l2': 7.210205334409902}. Best is trial 56 with value: 1996449532.606333.\u001b[0m\n",
"regularization_factors, val_score: 1996449532.606333: 85%|########5 | 17/20 [00:56<00:08, 2.99s/it]\u001b[32m[I 2021-05-01 17:00:22,219]\u001b[0m Trial 59 finished with value: 2030171133.0539286 and parameters: {'lambda_l1': 3.325828713424872e-05, 'lambda_l2': 0.000613610913339345}. Best is trial 56 with value: 1996449532.606333.\u001b[0m\n",
"regularization_factors, val_score: 1996449532.606333: 90%|######### | 18/20 [00:58<00:05, 2.79s/it]\u001b[32m[I 2021-05-01 17:00:24,556]\u001b[0m Trial 60 finished with value: 1997587159.9270165 and parameters: {'lambda_l1': 1.122670575237426e-08, 'lambda_l2': 4.7679572155360673e-07}. Best is trial 56 with value: 1996449532.606333.\u001b[0m\n",
"regularization_factors, val_score: 1996449532.606333: 95%|#########5| 19/20 [01:01<00:02, 2.64s/it]\u001b[32m[I 2021-05-01 17:00:26,854]\u001b[0m Trial 61 finished with value: 1996449770.564637 and parameters: {'lambda_l1': 6.446613270805078e-06, 'lambda_l2': 0.00017942732358506184}. Best is trial 56 with value: 1996449532.606333.\u001b[0m\n",
"regularization_factors, val_score: 1996449418.529521: 100%|##########| 20/20 [01:03<00:00, 2.55s/it]\u001b[32m[I 2021-05-01 17:00:29,173]\u001b[0m Trial 62 finished with value: 1996449418.5295208 and parameters: {'lambda_l1': 8.868453484243689e-06, 'lambda_l2': 0.000252862182277996}. Best is trial 62 with value: 1996449418.5295208.\u001b[0m\n",
"regularization_factors, val_score: 1996449418.529521: 100%|##########| 20/20 [01:03<00:00, 3.18s/it]\n",
"min_data_in_leaf, val_score: 1996449418.529521: 20%|## | 1/5 [00:02<00:08, 2.15s/it]\u001b[32m[I 2021-05-01 17:00:31,325]\u001b[0m Trial 63 finished with value: 2035984658.8333156 and parameters: {'min_child_samples': 5}. Best is trial 63 with value: 2035984658.8333156.\u001b[0m\n",
"min_data_in_leaf, val_score: 1996449418.529521: 40%|#### | 2/5 [00:04<00:07, 2.34s/it]\u001b[32m[I 2021-05-01 17:00:34,112]\u001b[0m Trial 64 finished with value: 2047790552.496713 and parameters: {'min_child_samples': 50}. Best is trial 63 with value: 2035984658.8333156.\u001b[0m\n",
"min_data_in_leaf, val_score: 1996449418.529521: 60%|###### | 3/5 [00:07<00:04, 2.27s/it]\u001b[32m[I 2021-05-01 17:00:36,236]\u001b[0m Trial 65 finished with value: 2022941263.9641247 and parameters: {'min_child_samples': 10}. Best is trial 65 with value: 2022941263.9641247.\u001b[0m\n",
"min_data_in_leaf, val_score: 1996449418.529521: 80%|######## | 4/5 [00:09<00:02, 2.31s/it]\u001b[32m[I 2021-05-01 17:00:38,623]\u001b[0m Trial 66 finished with value: 2034136324.3695369 and parameters: {'min_child_samples': 25}. Best is trial 65 with value: 2022941263.9641247.\u001b[0m\n",
"min_data_in_leaf, val_score: 1996449418.529521: 100%|##########| 5/5 [00:12<00:00, 2.60s/it]\u001b[32m[I 2021-05-01 17:00:41,911]\u001b[0m Trial 67 finished with value: 2038947709.9319875 and parameters: {'min_child_samples': 100}. Best is trial 65 with value: 2022941263.9641247.\u001b[0m\n",
"min_data_in_leaf, val_score: 1996449418.529521: 100%|##########| 5/5 [00:12<00:00, 2.55s/it]CPU times: user 4min 10s, sys: 14.6 s, total: 4min 25s\n",
"Wall time: 4min 30s\n",
"\n"
]
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
}
],
"source": [
"%%time\n",
"model = lgb.train(params, dtrain, valid_sets=[dtrain, dval], verbose_eval=10000) \n"
]
},
Lgbm w customized obj (#64) * add customized lgbm learner * add comments * fix format issue * format * OpenMLError * add test * add notebook Co-authored-by: Chi Wang (MSR) <chiw@microsoft.com> Co-authored-by: Chi Wang <wang.chi@microsoft.com>
2021-04-10 21:14:28 -04:00
{
"cell_type": "markdown",
"metadata": {},
"source": []
},
{
"cell_type": "code",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"execution_count": 19,
Lgbm w customized obj (#64) * add customized lgbm learner * add comments * fix format issue * format * OpenMLError * add test * add notebook Co-authored-by: Chi Wang (MSR) <chiw@microsoft.com> Co-authored-by: Chi Wang <wang.chi@microsoft.com>
2021-04-10 21:14:28 -04:00
"metadata": {
"tags": []
},
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Optuna LightGBM Tuner r2 = 0.8390948396448961\n"
]
}
],
Lgbm w customized obj (#64) * add customized lgbm learner * add comments * fix format issue * format * OpenMLError * add test * add notebook Co-authored-by: Chi Wang (MSR) <chiw@microsoft.com> Co-authored-by: Chi Wang <wang.chi@microsoft.com>
2021-04-10 21:14:28 -04:00
"source": [
"y_pred = model.predict(X_test)\n",
"from flaml.ml import sklearn_metric_loss_score\n",
"print('Optuna LightGBM Tuner r2', '=', 1 - sklearn_metric_loss_score('r2', y_pred, y_test))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 4. Add a customized LightGBM learner in FLAML\n",
"The native API of LightGBM allows one to specify a custom objective function in the model constructor. You can easily enable it by adding a customized LightGBM learner in FLAML. In the following example, we show how to add such a customized LightGBM learner with a custom objective function."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create a customized LightGBM learner with a custom objective function"
]
},
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
{
"cell_type": "code",
Issue58 (#59) * iter per learner * code cleanup
2021-04-08 09:29:55 -07:00
"execution_count": 20,
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
"metadata": {},
Lgbm w customized obj (#64) * add customized lgbm learner * add comments * fix format issue * format * OpenMLError * add test * add notebook Co-authored-by: Chi Wang (MSR) <chiw@microsoft.com> Co-authored-by: Chi Wang <wang.chi@microsoft.com>
2021-04-10 21:14:28 -04:00
"outputs": [],
"source": [
"\n",
"import numpy as np \n",
"\n",
"''' define your customized objective function '''\n",
"def my_loss_obj(y_true, y_pred):\n",
" c = 0.5\n",
" residual = y_pred - y_true\n",
" grad = c * residual /(np.abs(residual) + c)\n",
" hess = c ** 2 / (np.abs(residual) + c) ** 2\n",
" # rmse grad and hess\n",
" grad_rmse = residual\n",
" hess_rmse = 1.0\n",
" \n",
" # mae grad and hess\n",
" grad_mae = np.array(residual)\n",
" grad_mae[grad_mae > 0] = 1.\n",
" grad_mae[grad_mae <= 0] = -1.\n",
" hess_mae = 1.0\n",
"\n",
" coef = [0.4, 0.3, 0.3]\n",
" return coef[0] * grad + coef[1] * grad_rmse + coef[2] * grad_mae, \\\n",
" coef[0] * hess + coef[1] * hess_rmse + coef[2] * hess_mae\n",
"\n",
"\n",
"from flaml.model import LGBMEstimator\n",
"\n",
"''' create a customized LightGBM learner class with your objective function '''\n",
"class MyLGBM(LGBMEstimator):\n",
" '''LGBMEstimator with my_loss_obj as the objective function\n",
" '''\n",
"\n",
" def __init__(self, **params):\n",
" super().__init__(objective=my_loss_obj, **params)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Add the customized learner in FLAML"
]
},
{
"cell_type": "code",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"execution_count": 21,
Lgbm w customized obj (#64) * add customized lgbm learner * add comments * fix format issue * format * OpenMLError * add test * add notebook Co-authored-by: Chi Wang (MSR) <chiw@microsoft.com> Co-authored-by: Chi Wang <wang.chi@microsoft.com>
2021-04-10 21:14:28 -04:00
"metadata": {
"tags": []
},
"outputs": [
{
"output_type": "stream",
"name": "stderr",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"text": [
"[flaml.automl: 05-01 17:00:42] {890} INFO - Evaluation method: cv\n",
"[flaml.automl: 05-01 17:00:42] {606} INFO - Using RepeatedKFold\n",
"[flaml.automl: 05-01 17:00:42] {911} INFO - Minimizing error metric: 1-r2\n",
"[flaml.automl: 05-01 17:00:42] {929} INFO - List of ML learners in AutoML Run: ['my_lgbm']\n",
"[flaml.automl: 05-01 17:00:42] {993} INFO - iteration 0, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:00:42] {1141} INFO - at 0.3s,\tbest my_lgbm's error=2.9883,\tbest my_lgbm's error=2.9883\n",
"[flaml.automl: 05-01 17:00:42] {993} INFO - iteration 1, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:00:43] {1141} INFO - at 0.4s,\tbest my_lgbm's error=2.9883,\tbest my_lgbm's error=2.9883\n",
"[flaml.automl: 05-01 17:00:43] {993} INFO - iteration 2, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:00:43] {1141} INFO - at 0.7s,\tbest my_lgbm's error=1.7530,\tbest my_lgbm's error=1.7530\n",
"[flaml.automl: 05-01 17:00:43] {993} INFO - iteration 3, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:00:43] {1141} INFO - at 0.9s,\tbest my_lgbm's error=0.4472,\tbest my_lgbm's error=0.4472\n",
"[flaml.automl: 05-01 17:00:43] {993} INFO - iteration 4, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:00:43] {1141} INFO - at 1.1s,\tbest my_lgbm's error=0.4472,\tbest my_lgbm's error=0.4472\n",
"[flaml.automl: 05-01 17:00:43] {993} INFO - iteration 5, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:00:43] {1141} INFO - at 1.3s,\tbest my_lgbm's error=0.4472,\tbest my_lgbm's error=0.4472\n",
"[flaml.automl: 05-01 17:00:43] {993} INFO - iteration 6, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:00:44] {1141} INFO - at 1.6s,\tbest my_lgbm's error=0.3146,\tbest my_lgbm's error=0.3146\n",
"[flaml.automl: 05-01 17:00:44] {993} INFO - iteration 7, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:00:44] {1141} INFO - at 2.0s,\tbest my_lgbm's error=0.2722,\tbest my_lgbm's error=0.2722\n",
"[flaml.automl: 05-01 17:00:44] {993} INFO - iteration 8, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:00:44] {1141} INFO - at 2.3s,\tbest my_lgbm's error=0.2722,\tbest my_lgbm's error=0.2722\n",
"[flaml.automl: 05-01 17:00:44] {993} INFO - iteration 9, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:00:45] {1141} INFO - at 2.7s,\tbest my_lgbm's error=0.2060,\tbest my_lgbm's error=0.2060\n",
"[flaml.automl: 05-01 17:00:45] {993} INFO - iteration 10, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:00:45] {1141} INFO - at 3.0s,\tbest my_lgbm's error=0.2060,\tbest my_lgbm's error=0.2060\n",
"[flaml.automl: 05-01 17:00:45] {993} INFO - iteration 11, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:00:45] {1141} INFO - at 3.2s,\tbest my_lgbm's error=0.2060,\tbest my_lgbm's error=0.2060\n",
"[flaml.automl: 05-01 17:00:45] {993} INFO - iteration 12, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:00:46] {1141} INFO - at 3.9s,\tbest my_lgbm's error=0.1864,\tbest my_lgbm's error=0.1864\n",
"[flaml.automl: 05-01 17:00:46] {993} INFO - iteration 13, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:00:46] {1141} INFO - at 4.4s,\tbest my_lgbm's error=0.1864,\tbest my_lgbm's error=0.1864\n",
"[flaml.automl: 05-01 17:00:46] {993} INFO - iteration 14, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:00:47] {1141} INFO - at 5.2s,\tbest my_lgbm's error=0.1864,\tbest my_lgbm's error=0.1864\n",
"[flaml.automl: 05-01 17:00:47] {993} INFO - iteration 15, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:00:48] {1141} INFO - at 5.6s,\tbest my_lgbm's error=0.1864,\tbest my_lgbm's error=0.1864\n",
"[flaml.automl: 05-01 17:00:48] {993} INFO - iteration 16, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:00:49] {1141} INFO - at 6.4s,\tbest my_lgbm's error=0.1856,\tbest my_lgbm's error=0.1856\n",
"[flaml.automl: 05-01 17:00:49] {993} INFO - iteration 17, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:00:49] {1141} INFO - at 6.8s,\tbest my_lgbm's error=0.1856,\tbest my_lgbm's error=0.1856\n",
"[flaml.automl: 05-01 17:00:49] {993} INFO - iteration 18, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:00:51] {1141} INFO - at 8.7s,\tbest my_lgbm's error=0.1724,\tbest my_lgbm's error=0.1724\n",
"[flaml.automl: 05-01 17:00:51] {993} INFO - iteration 19, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:00:51] {1141} INFO - at 9.3s,\tbest my_lgbm's error=0.1724,\tbest my_lgbm's error=0.1724\n",
"[flaml.automl: 05-01 17:00:51] {993} INFO - iteration 20, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:01:01] {1141} INFO - at 18.5s,\tbest my_lgbm's error=0.1724,\tbest my_lgbm's error=0.1724\n",
"[flaml.automl: 05-01 17:01:01] {993} INFO - iteration 21, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:01:02] {1141} INFO - at 19.5s,\tbest my_lgbm's error=0.1724,\tbest my_lgbm's error=0.1724\n",
"[flaml.automl: 05-01 17:01:02] {993} INFO - iteration 22, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:01:06] {1141} INFO - at 24.2s,\tbest my_lgbm's error=0.1696,\tbest my_lgbm's error=0.1696\n",
"[flaml.automl: 05-01 17:01:06] {993} INFO - iteration 23, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:01:08] {1141} INFO - at 25.8s,\tbest my_lgbm's error=0.1696,\tbest my_lgbm's error=0.1696\n",
"[flaml.automl: 05-01 17:01:08] {993} INFO - iteration 24, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:01:14] {1141} INFO - at 32.0s,\tbest my_lgbm's error=0.1696,\tbest my_lgbm's error=0.1696\n",
"[flaml.automl: 05-01 17:01:14] {993} INFO - iteration 25, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:01:15] {1141} INFO - at 32.9s,\tbest my_lgbm's error=0.1696,\tbest my_lgbm's error=0.1696\n",
"[flaml.automl: 05-01 17:01:15] {993} INFO - iteration 26, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:01:33] {1141} INFO - at 50.7s,\tbest my_lgbm's error=0.1607,\tbest my_lgbm's error=0.1607\n",
"[flaml.automl: 05-01 17:01:33] {993} INFO - iteration 27, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:01:45] {1141} INFO - at 62.6s,\tbest my_lgbm's error=0.1607,\tbest my_lgbm's error=0.1607\n",
"[flaml.automl: 05-01 17:01:45] {993} INFO - iteration 28, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:02:08] {1141} INFO - at 86.1s,\tbest my_lgbm's error=0.1607,\tbest my_lgbm's error=0.1607\n",
"[flaml.automl: 05-01 17:02:08] {993} INFO - iteration 29, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:02:13] {1141} INFO - at 91.0s,\tbest my_lgbm's error=0.1607,\tbest my_lgbm's error=0.1607\n",
"[flaml.automl: 05-01 17:02:13] {993} INFO - iteration 30, current learner my_lgbm\n",
"[flaml.automl: 05-01 17:02:32] {1141} INFO - at 109.7s,\tbest my_lgbm's error=0.1607,\tbest my_lgbm's error=0.1607\n",
"[flaml.automl: 05-01 17:02:32] {1187} INFO - selected model: LGBMRegressor(colsample_bytree=0.6261496118517905,\n",
" learning_rate=0.08869510109538115, max_bin=127,\n",
" min_child_samples=79, n_estimators=493, num_leaves=282,\n",
" objective=<function my_loss_obj at 0x7f1fa05b4ca0>,\n",
" reg_alpha=0.023427326819484437, reg_lambda=3.676068046341948,\n",
" subsample=0.9152991332236934)\n",
"[flaml.automl: 05-01 17:02:32] {944} INFO - fit succeeded\n"
]
Lgbm w customized obj (#64) * add customized lgbm learner * add comments * fix format issue * format * OpenMLError * add test * add notebook Co-authored-by: Chi Wang (MSR) <chiw@microsoft.com> Co-authored-by: Chi Wang <wang.chi@microsoft.com>
2021-04-10 21:14:28 -04:00
}
],
"source": [
"automl = AutoML()\n",
"automl.add_learner(learner_name='my_lgbm', learner_class=MyLGBM)\n",
"settings = {\n",
" \"time_budget\": 120, # total running time in seconds\n",
" \"metric\": 'r2', # primary metrics for regression can be chosen from: ['mae','mse','r2']\n",
" \"estimator_list\": ['my_lgbm',], # list of ML learners; we tune lightgbm in this example\n",
" \"task\": 'regression', # task type \n",
" \"log_file_name\": 'houses_experiment_my_lgbm.log', # flaml log file\n",
"}\n",
"automl.fit(X_train=X_train, y_train=y_train, **settings)"
]
},
{
"cell_type": "code",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"execution_count": 22,
Lgbm w customized obj (#64) * add customized lgbm learner * add comments * fix format issue * format * OpenMLError * add test * add notebook Co-authored-by: Chi Wang (MSR) <chiw@microsoft.com> Co-authored-by: Chi Wang <wang.chi@microsoft.com>
2021-04-10 21:14:28 -04:00
"metadata": {
"tags": []
},
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
"outputs": [
{
"output_type": "stream",
"name": "stdout",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"text": [
"Best hyperparmeter config: {'n_estimators': 493.0, 'num_leaves': 282.0, 'min_child_samples': 79.0, 'learning_rate': 0.08869510109538115, 'subsample': 0.9152991332236934, 'log_max_bin': 7.0, 'colsample_bytree': 0.6261496118517905, 'reg_alpha': 0.023427326819484437, 'reg_lambda': 3.676068046341948}\n",
"Best r2 on validation data: 0.8393\n",
"Training duration of best run: 17.8 s\n",
"Predicted labels [145117.75593607 248133.51648268 134326.11799226 ... 197406.17210771\n",
" 245758.5509811 267784.87515589]\n",
"True labels [136900. 241300. 200700. ... 160900. 227300. 265600.]\n",
"r2 = 0.8467399586261989\n",
"mse = 2025868859.4366\n",
"mae = 29981.366220545584\n"
]
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
}
],
"source": [
Lgbm w customized obj (#64) * add customized lgbm learner * add comments * fix format issue * format * OpenMLError * add test * add notebook Co-authored-by: Chi Wang (MSR) <chiw@microsoft.com> Co-authored-by: Chi Wang <wang.chi@microsoft.com>
2021-04-10 21:14:28 -04:00
"print('Best hyperparmeter config:', automl.best_config)\n",
"print('Best r2 on validation data: {0:.4g}'.format(1-automl.best_loss))\n",
"print('Training duration of best run: {0:.4g} s'.format(automl.best_config_train_time))\n",
"\n",
"y_pred = automl.predict(X_test)\n",
"print('Predicted labels', y_pred)\n",
"print('True labels', y_test)\n",
"\n",
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
"from flaml.ml import sklearn_metric_loss_score\n",
Lgbm w customized obj (#64) * add customized lgbm learner * add comments * fix format issue * format * OpenMLError * add test * add notebook Co-authored-by: Chi Wang (MSR) <chiw@microsoft.com> Co-authored-by: Chi Wang <wang.chi@microsoft.com>
2021-04-10 21:14:28 -04:00
"print('r2', '=', 1 - sklearn_metric_loss_score('r2', y_pred, y_test))\n",
"print('mse', '=', sklearn_metric_loss_score('mse', y_pred, y_test))\n",
"print('mae', '=', sklearn_metric_loss_score('mae', y_pred, y_test))"
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
]
}
],
"metadata": {
"kernelspec": {
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"name": "python3",
"display_name": "Python 3.8.0 64-bit",
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
"metadata": {
"interpreter": {
Issue58 (#59) * iter per learner * code cleanup
2021-04-08 09:29:55 -07:00
"hash": "0cfea3304185a9579d09e0953576b57c8581e46e6ebc6dfeb681bc5a511f7544"
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
}
}
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
Notebook (#87) * notebook update
2021-05-08 02:50:50 +00:00
"version": "3.8.0-final"
v0.2.5 (#30) * test distillbert * import check * complete partial config * None check * init config is not suggested by bo * badge * notebook for lightgbm
2021-02-22 22:10:41 -08:00
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Reference in New Issue Copy Permalink