Grid Search#

Installation

# To install the required package, use the following command:
# !pip install modeva

Authentication

# To get authentication, use the following command: (To get full access please replace the token to your own token)
# from modeva.utils.authenticate import authenticate
# authenticate(auth_code='eaaa4301-b140-484c-8e93-f9f633c8bacb')

Import required modules

from modeva import DataSet
from modeva import TestSuite
from modeva.models import MoLGBMClassifier
from modeva.models import ModelTuneGridSearch

Load Dataset

ds = DataSet()
ds.load(name="SimuCredit")
ds.set_random_split()

Run grid search#

param_grid = {"n_estimators": [50, 100, 200],
              "learning_rate": [(i + 1) * 0.01 for i in range(5)]}
model = MoLGBMClassifier(max_depth=2, verbose=-1)
hpo = ModelTuneGridSearch(dataset=ds, model=model)
result = hpo.run(param_grid=param_grid,
                 metric=("AUC", "ACC", "LogLoss", "Brier"),
                 cv=5)
result.table

	n_estimators	learning_rate	AUC	ACC	LogLoss	Brier	AUC_rank	ACC_rank	LogLoss_rank	Brier_rank	Time
14	200	0.05	0.8350	0.7566	0.4983	0.1650	1	1	1	1	0.8698
11	200	0.04	0.8339	0.7552	0.5010	0.1658	2	2	2	2	0.4239
8	200	0.03	0.8315	0.7540	0.5061	0.1674	3	3	3	3	0.3155
13	100	0.05	0.8296	0.7539	0.5099	0.1686	4	4	4	4	0.5588
10	100	0.04	0.8277	0.7500	0.5155	0.1704	5	5	5	5	0.2796
5	200	0.02	0.8276	0.7492	0.5155	0.1704	6	6	6	6	0.3239
7	100	0.03	0.8237	0.7454	0.5244	0.1735	7	7	7	7	0.1723
12	50	0.05	0.8210	0.7418	0.5309	0.1758	8	8	8	8	0.5945
4	100	0.02	0.8170	0.7406	0.5404	0.1794	9	11	10	10	0.0905
2	200	0.01	0.8169	0.7408	0.5406	0.1795	10	9	11	11	0.2870
9	50	0.04	0.8168	0.7407	0.5401	0.1793	11	10	9	9	0.0905
6	50	0.03	0.8101	0.7378	0.5525	0.1843	12	12	12	12	0.0832
3	50	0.02	0.8035	0.7345	0.5713	0.1920	13	13	13	13	0.0531
1	100	0.01	0.8032	0.7344	0.5715	0.1921	14	14	14	14	0.1106
0	50	0.01	0.7925	0.7177	0.6069	0.2080	15	15	15	15	0.1466

result.plot("parallel", figsize=(8, 6))

result.plot(("n_estimators", "AUC"))

result.plot(("learning_rate", "AUC"))

Retrain model with best hyperparameter#

model_tuned = MoLGBMClassifier(**result.value["params"][0],
                               name="LGBM-Tuned",
                               verbose=-1)
model_tuned.fit(ds.train_x, ds.train_y)
model_tuned

MoLGBMClassifier(boosting_type='gbdt', class_weight=None, colsample_bytree=1.0,
                 importance_type='split', learning_rate=0.01, max_depth=-1,
                 min_child_samples=20, min_child_weight=0.001,
                 min_split_gain=0.0, n_estimators=50, n_jobs=None,
                 num_leaves=31, objective=None, random_state=None,
                 reg_alpha=0.0, reg_lambda=0.0, subsample=1.0,
                 subsample_for_bin=200000, subsample_freq=0, verbose=-1)

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

Diagnose the tuned model#

ts = TestSuite(ds, model_tuned)
result = ts.diagnose_accuracy_table()
result.table

	AUC	ACC	F1	LogLoss	Brier
train	0.8436	0.7593	0.8010	0.5771	0.1939
test	0.8363	0.7598	0.7993	0.5813	0.1959
GAP	-0.0073	0.0004	-0.0017	0.0042	0.0019

Total running time of the script: (0 minutes 28.139 seconds)

Gallery generated by Sphinx-Gallery