mirror of
https://github.com/microsoft/autogen.git
synced 2025-09-13 10:16:06 +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>
101 lines
2.8 KiB
Python
101 lines
2.8 KiB
Python
import unittest
|
|
|
|
from sklearn.datasets import fetch_openml
|
|
from sklearn.model_selection import train_test_split
|
|
from flaml.automl import AutoML
|
|
from flaml.automl.model import XGBoostSklearnEstimator
|
|
from flaml import tune
|
|
|
|
|
|
dataset = "credit-g"
|
|
|
|
|
|
class XGBoost2D(XGBoostSklearnEstimator):
|
|
@classmethod
|
|
def search_space(cls, data_size, task):
|
|
upper = min(32768, int(data_size[0]))
|
|
return {
|
|
"n_estimators": {
|
|
"domain": tune.lograndint(lower=4, upper=upper),
|
|
"low_cost_init_value": 4,
|
|
},
|
|
"max_leaves": {
|
|
"domain": tune.lograndint(lower=4, upper=upper),
|
|
"low_cost_init_value": 4,
|
|
},
|
|
}
|
|
|
|
|
|
def test_simple(method=None):
|
|
automl = AutoML()
|
|
automl.add_learner(learner_name="XGBoost2D", learner_class=XGBoost2D)
|
|
|
|
automl_settings = {
|
|
"estimator_list": ["XGBoost2D"],
|
|
"task": "classification",
|
|
"log_file_name": f"test/xgboost2d_{dataset}_{method}.log",
|
|
"n_jobs": 1,
|
|
"hpo_method": method,
|
|
"log_type": "all",
|
|
"retrain_full": "budget",
|
|
"keep_search_state": True,
|
|
"time_budget": 1,
|
|
}
|
|
from sklearn.externals._arff import ArffException
|
|
|
|
try:
|
|
X, y = fetch_openml(name=dataset, return_X_y=True)
|
|
except (ArffException, ValueError):
|
|
from sklearn.datasets import load_wine
|
|
|
|
X, y = load_wine(return_X_y=True)
|
|
X_train, X_test, y_train, y_test = train_test_split(
|
|
X, y, test_size=0.33, random_state=42
|
|
)
|
|
automl.fit(X_train=X_train, y_train=y_train, **automl_settings)
|
|
print(automl.estimator_list)
|
|
print(automl.search_space)
|
|
print(automl.points_to_evaluate)
|
|
if not automl.best_config:
|
|
return
|
|
config = automl.best_config.copy()
|
|
config["learner"] = automl.best_estimator
|
|
automl.trainable(config)
|
|
from flaml import tune
|
|
from flaml.automl import size
|
|
from functools import partial
|
|
|
|
analysis = tune.run(
|
|
automl.trainable,
|
|
automl.search_space,
|
|
metric="val_loss",
|
|
mode="min",
|
|
low_cost_partial_config=automl.low_cost_partial_config,
|
|
points_to_evaluate=automl.points_to_evaluate,
|
|
cat_hp_cost=automl.cat_hp_cost,
|
|
resource_attr=automl.resource_attr,
|
|
min_resource=automl.min_resource,
|
|
max_resource=automl.max_resource,
|
|
time_budget_s=automl._state.time_budget,
|
|
config_constraints=[(partial(size, automl._state), "<=", automl._mem_thres)],
|
|
metric_constraints=automl.metric_constraints,
|
|
num_samples=5,
|
|
)
|
|
print(analysis.trials[-1])
|
|
|
|
|
|
def test_optuna():
|
|
test_simple(method="optuna")
|
|
|
|
|
|
def test_random():
|
|
test_simple(method="random")
|
|
|
|
|
|
def test_grid():
|
|
test_simple(method="grid")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|