mirror of
https://github.com/microsoft/FLAML.git
synced 2026-02-09 02:09:16 +08:00
1285700d7a
* Update gitignore * Bump version to 2.4.0 * Update readme * Pre-download california housing data * Use pre-downloaded california housing data * Pin lightning<=2.5.6 * Fix typo in find and replace * Fix estimators has no attribute __sklearn_tags__ * Pin torch to 2.2.2 in tests * Fix conflict * Update pytorch-forecasting * Update pytorch-forecasting * Update pytorch-forecasting * Use numpy<2 for testing * Update scikit-learn * Run Build and UT every other day * Pin pip<24.1 * Pin pip<24.1 in pipeline * Loosen pip, install pytorch_forecasting only in py311 * Add support to new versions of nlp dependecies * Fix formats * Remove redefinition * Update mlflow versions * Fix mlflow version syntax * Update gitignore * Clean up cache to free space * Remove clean up action cache * Fix blendsearch * Update test workflow * Update setup.py * Fix catboost version * Update workflow * Prepare for python 3.14 * Support no catboost * Fix tests * Fix python_requires * Update test workflow * Fix vw tests * Remove python 3.9 * Fix nlp tests * Fix prophet * Print pip freeze for better debugging * Fix Optuna search does not support parameters of type Float with samplers of type Quantized * Save dependencies for later inspection * Fix coverage.xml not exists * Fix github action permission * Handle python 3.13 * Address openml is not installed * Check dependencies before run tests * Update dependencies * Fix syntax error * Use bash * Update dependencies * Fix git error * Loose mlflow constraints * Add rerun, use mlflow-skinny * Fix git error * Remove ray tests * Update xgboost versions * Fix automl pickle error * Don't test python 3.10 on macos as it's stuck * Rebase before push * Reduce number of branches
66 lines
2.6 KiB
Python
66 lines
2.6 KiB
Python
import lightgbm
|
|
from sklearn.datasets import fetch_california_housing
|
|
from sklearn.metrics import mean_squared_error
|
|
from sklearn.model_selection import train_test_split
|
|
|
|
from flaml import tune
|
|
from flaml.automl.model import LGBMEstimator
|
|
|
|
data = fetch_california_housing(return_X_y=False, as_frame=True, data_home="test")
|
|
df, X, y = data.frame, data.data, data.target
|
|
df_train, _, X_train, X_test, _, y_test = train_test_split(df, X, y, test_size=0.33, random_state=42)
|
|
csv_file_name = "test/housing.csv"
|
|
df_train.to_csv(csv_file_name, index=False)
|
|
# X, y = fetch_california_housing(return_X_y=True, as_frame=True, data_home="test")
|
|
# X_train, X_test, y_train, y_test = train_test_split(
|
|
# X, y, test_size=0.33, random_state=42
|
|
# )
|
|
|
|
|
|
def train_lgbm(config: dict) -> dict:
|
|
# convert config dict to lgbm params
|
|
params = LGBMEstimator(**config).params
|
|
# train the model
|
|
# train_set = lightgbm.Dataset(X_train, y_train)
|
|
# LightGBM only accepts the csv with valid number format, if even these string columns are set to ignore.
|
|
train_set = lightgbm.Dataset(csv_file_name, params={"label_column": "name:MedHouseVal", "header": True})
|
|
model = lightgbm.train(params, train_set)
|
|
# evaluate the model
|
|
pred = model.predict(X_test)
|
|
mse = mean_squared_error(y_test, pred)
|
|
# return eval results as a dictionary
|
|
return {"mse": mse}
|
|
|
|
|
|
def test_tune_lgbm_csv():
|
|
# load a built-in search space from flaml
|
|
flaml_lgbm_search_space = LGBMEstimator.search_space(X_train.shape)
|
|
# specify the search space as a dict from hp name to domain; you can define your own search space same way
|
|
config_search_space = {hp: space["domain"] for hp, space in flaml_lgbm_search_space.items()}
|
|
# give guidance about hp values corresponding to low training cost, i.e., {"n_estimators": 4, "num_leaves": 4}
|
|
low_cost_partial_config = {
|
|
hp: space["low_cost_init_value"]
|
|
for hp, space in flaml_lgbm_search_space.items()
|
|
if "low_cost_init_value" in space
|
|
}
|
|
# initial points to evaluate
|
|
points_to_evaluate = [
|
|
{hp: space["init_value"] for hp, space in flaml_lgbm_search_space.items() if "init_value" in space}
|
|
]
|
|
# run the tuning, minimizing mse, with total time budget 3 seconds
|
|
analysis = tune.run(
|
|
train_lgbm,
|
|
metric="mse",
|
|
mode="min",
|
|
config=config_search_space,
|
|
low_cost_partial_config=low_cost_partial_config,
|
|
points_to_evaluate=points_to_evaluate,
|
|
time_budget_s=3,
|
|
num_samples=-1,
|
|
)
|
|
print(analysis.best_result)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
test_tune_lgbm_csv()
|