mirror of
https://github.com/microsoft/autogen.git
synced 2025-09-11 01:06:08 +00:00
44ddf9e104
* Refactor into automl subpackage Moved some of the packages into an automl subpackage to tidy before the task-based refactor. This is in response to discussions with the group and a comment on the first task-based PR. Only changes here are moving subpackages and modules into the new automl, fixing imports to work with this structure and fixing some dependencies in setup.py. * Fix doc building post automl subpackage refactor * Fix broken links in website post automl subpackage refactor * Fix broken links in website post automl subpackage refactor * Remove vw from test deps as this is breaking the build * Move default back to the top-level I'd moved this to automl as that's where it's used internally, but had missed that this is actually part of the public interface so makes sense to live where it was. * Re-add top level modules with deprecation warnings flaml.data, flaml.ml and flaml.model are re-added to the top level, being re-exported from flaml.automl for backwards compatability. Adding a deprecation warning so that we can have a planned removal later. * Fix model.py line-endings * Pin pytorch-lightning to less than 1.8.0 We're seeing strange lightning related bugs from pytorch-forecasting since the release of lightning 1.8.0. Going to try constraining this to see if we have a fix. * Fix the lightning version pin Was optimistic with setting it in the 1.7.x range, but that isn't compatible with python 3.6 * Remove lightning version pin * Revert dependency version changes * Minor change to retrigger the build * Fix line endings in ml.py and model.py Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> Co-authored-by: EgorKraevTransferwise <egor.kraev@transferwise.com>
75 lines
2.6 KiB
Python
75 lines
2.6 KiB
Python
from flaml import tune
|
|
from flaml.automl.model import LGBMEstimator
|
|
import lightgbm
|
|
from sklearn.model_selection import train_test_split
|
|
from sklearn.datasets import fetch_california_housing
|
|
from sklearn.metrics import mean_squared_error
|
|
|
|
data = fetch_california_housing(return_X_y=False, as_frame=True)
|
|
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)
|
|
# 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()
|