mirror of
https://github.com/microsoft/autogen.git
synced 2025-09-12 09:45:41 +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>
119 lines
4.5 KiB
Python
119 lines
4.5 KiB
Python
import os
|
|
import unittest
|
|
from tempfile import TemporaryDirectory
|
|
|
|
from sklearn.datasets import fetch_california_housing
|
|
|
|
from flaml import AutoML
|
|
from flaml.automl.training_log import training_log_reader
|
|
|
|
|
|
class TestTrainingLog(unittest.TestCase):
|
|
def test_training_log(
|
|
self, path="test_training_log.log", estimator_list="auto", use_ray=False
|
|
):
|
|
|
|
with TemporaryDirectory() as d:
|
|
filename = os.path.join(d, path)
|
|
|
|
# Run a simple job.
|
|
automl = AutoML()
|
|
automl_settings = {
|
|
"time_budget": 1,
|
|
"metric": "mse",
|
|
"task": "regression",
|
|
"log_file_name": filename,
|
|
"log_training_metric": True,
|
|
"mem_thres": 1024 * 1024,
|
|
"n_jobs": 1,
|
|
"model_history": True,
|
|
"train_time_limit": 0.1,
|
|
"verbose": 3,
|
|
# "ensemble": True,
|
|
"keep_search_state": True,
|
|
"estimator_list": estimator_list,
|
|
}
|
|
X_train, y_train = fetch_california_housing(return_X_y=True)
|
|
automl.fit(X_train=X_train, y_train=y_train, **automl_settings)
|
|
# Check if the training log file is populated.
|
|
self.assertTrue(os.path.exists(filename))
|
|
if automl.best_estimator:
|
|
estimator, config = automl.best_estimator, automl.best_config
|
|
model0 = automl.best_model_for_estimator(estimator)
|
|
print(model0.params["n_estimators"], config)
|
|
|
|
# train on full data with no time limit
|
|
automl._state.time_budget = -1
|
|
model, _ = automl._state._train_with_config(estimator, config)
|
|
|
|
# assuming estimator & config are saved and loaded as follows
|
|
automl = AutoML()
|
|
automl.fit(
|
|
X_train=X_train,
|
|
y_train=y_train,
|
|
max_iter=1,
|
|
task="regression",
|
|
estimator_list=[estimator],
|
|
n_jobs=1,
|
|
starting_points={estimator: config},
|
|
use_ray=use_ray,
|
|
)
|
|
print(automl.best_config)
|
|
# then the fitted model should be equivalent to model
|
|
assert (
|
|
str(model.estimator) == str(automl.model.estimator)
|
|
or estimator == "xgboost"
|
|
and str(model.estimator.get_dump())
|
|
== str(automl.model.estimator.get_dump())
|
|
or estimator == "catboost"
|
|
and str(model.estimator.get_all_params())
|
|
== str(automl.model.estimator.get_all_params())
|
|
)
|
|
automl.fit(
|
|
X_train=X_train,
|
|
y_train=y_train,
|
|
max_iter=1,
|
|
task="regression",
|
|
estimator_list=[estimator],
|
|
n_jobs=1,
|
|
starting_points={estimator: {}},
|
|
)
|
|
print(automl.best_config)
|
|
|
|
with training_log_reader(filename) as reader:
|
|
count = 0
|
|
for record in reader.records():
|
|
print(record)
|
|
count += 1
|
|
self.assertGreater(count, 0)
|
|
|
|
automl_settings["log_file_name"] = ""
|
|
automl.fit(X_train=X_train, y_train=y_train, **automl_settings)
|
|
if automl._selected:
|
|
automl._selected.update(None, 0)
|
|
automl = AutoML()
|
|
automl.fit(X_train=X_train, y_train=y_train, max_iter=0, task="regression")
|
|
|
|
def test_illfilename(self):
|
|
try:
|
|
self.test_training_log("/")
|
|
except IsADirectoryError:
|
|
print("IsADirectoryError happens as expected in linux.")
|
|
except PermissionError:
|
|
print("PermissionError happens as expected in windows.")
|
|
|
|
def test_each_estimator(self):
|
|
try:
|
|
import ray
|
|
|
|
ray.shutdown()
|
|
ray.init()
|
|
use_ray = True
|
|
except ImportError:
|
|
use_ray = False
|
|
self.test_training_log(estimator_list=["xgboost"], use_ray=use_ray)
|
|
self.test_training_log(estimator_list=["catboost"], use_ray=use_ray)
|
|
self.test_training_log(estimator_list=["extra_tree"], use_ray=use_ray)
|
|
self.test_training_log(estimator_list=["rf"], use_ray=use_ray)
|
|
self.test_training_log(estimator_list=["lgbm"], use_ray=use_ray)
|