def test_conversion():
model = to_sk_model("sklearn.linear_model.LinearRegression")
expr = to_sk_model_expr(model)
assert "sklearn.linear_model._base.LinearRegression" == expr
expr = to_sk_model_expr("sklearn.linear_model.LinearRegression")
assert "sklearn.linear_model._base.LinearRegression" == expr
raises(TypeError, lambda: to_sk_model("int"))
def run(self, trial: Trial) -> TrialReport:
params = dict(trial.params)
if trial.trial_id != self._last_id:
self._model_type = to_sk_model(params.pop(SPACE_MODEL_NAME))
self._model_expr = to_sk_model_expr(self._model_type)
self._train_x, self._train_y = self._reset_xy(
trial.dfs[TUNE_DATASET_DF_DEFAULT_NAME]
)
self._test_x, self._test_y = self._reset_xy(
trial.dfs[TUNE_DATASET_VALIDATION_DF_DEFAULT_NAME]
)
self._last_id = trial.trial_id
else:
params.pop(SPACE_MODEL_NAME)
model = self._model_type(**params).fit(self._train_x, self._train_y)
metric = get_scorer(self._scoring)(model, self._test_x, self._test_y)
metadata = dict(model=self._model_expr)
if self._checkpoint_path is not None:
fp = os.path.join(self._checkpoint_path, str(uuid4()) + ".pkl")
with FileSystem().openbin(fp, mode="wb") as f:
pickle.dump(model, f)
metadata["checkpoint_path"] = fp
return TrialReport(
trial,
metric=metric,
metadata=metadata,
sort_metric=self.generate_sort_metric(metric),
)
def run(self, trial: Trial) -> TrialReport:
params = dict(trial.params)
if trial.trial_id != self._last_id:
self._model_type = to_sk_model(params.pop(SPACE_MODEL_NAME))
self._model_expr = to_sk_model_expr(self._model_type)
self._train_x, self._train_y = self._reset_xy(
trial.dfs[TUNE_DATASET_DF_DEFAULT_NAME]
)
self._last_id = trial.trial_id
else:
params.pop(SPACE_MODEL_NAME)
model = self._model_type(**params)
s = cross_val_score(
model, self._train_x, self._train_y, cv=self._cv, scoring=self._scoring
)
metadata = dict(model=self._model_expr, cv_scores=[float(x) for x in s])
if self._checkpoint_path is not None:
model.fit(self._train_x, self._train_y)
fp = os.path.join(self._checkpoint_path, str(uuid4()) + ".pkl")
with FileSystem().openbin(fp, mode="wb") as f:
pickle.dump(model, f)
metadata["checkpoint_path"] = fp
metric = float(np.mean(s))
return TrialReport(
trial,
metric=metric,
metadata=metadata,
sort_metric=self.generate_sort_metric(metric),
)