def test_ranking(self):
# generate random data
x_train = np.random.rand(1000, 10)
y_train = np.random.randint(5, size=1000)
train_qid = np.repeat(np.array([list(range(20))]), 50)
x_valid = np.random.rand(200, 10)
y_valid = np.random.randint(5, size=200)
valid_qid = np.repeat(np.array([list(range(4))]), 50)
x_test = np.random.rand(100, 10)
params = {
"objective": "rank:pairwise",
"learning_rate": 0.1,
"gamma": 1.0,
"min_child_weight": 0.1,
"max_depth": 6,
"n_estimators": 4,
"random_state": 1,
"n_jobs": 2
}
model = RayXGBRanker(**params)
model.fit(
x_train,
y_train,
qid=train_qid,
eval_set=[(x_valid, y_valid)],
eval_qid=[valid_qid])
assert model.evals_result()
pred = model.predict(x_test)
train_data = RayDMatrix(x_train, y_train, qid=train_qid)
valid_data = RayDMatrix(x_valid, y_valid, qid=valid_qid)
test_data = RayDMatrix(x_test)
params_orig = {
"objective": "rank:pairwise",
"eta": 0.1,
"gamma": 1.0,
"min_child_weight": 0.1,
"max_depth": 6,
"random_state": 1
}
xgb_model_orig = train(
params_orig,
train_data,
num_boost_round=4,
evals=[(valid_data, "validation")],
ray_params=RayParams(num_actors=2, max_actor_restarts=0))
pred_orig = predict(
xgb_model_orig,
test_data,
ray_params=RayParams(num_actors=2, max_actor_restarts=0))
np.testing.assert_almost_equal(pred, pred_orig)
def test_best_ntree_limit(self):
self._init_ray()
from sklearn.datasets import load_iris
X, y = load_iris(return_X_y=True)
def train(booster, forest):
rounds = 4
cls = RayXGBClassifier(
n_estimators=rounds, num_parallel_tree=forest,
booster=booster).fit(
X, y, eval_set=[(X, y)], early_stopping_rounds=3)
if forest:
assert cls.best_ntree_limit == rounds * forest
else:
assert cls.best_ntree_limit == 0
# best_ntree_limit is used by default,
# assert that under gblinear it's
# automatically ignored due to being 0.
cls.predict(X)
num_parallel_tree = 4
train("gbtree", num_parallel_tree)
train("dart", num_parallel_tree)
train("gblinear", None)
def fit(
self,
X,
y,
*,
group=None,
qid=None,
sample_weight=None,
base_margin=None,
eval_set=None,
eval_group=None,
eval_qid=None,
eval_metric=None,
early_stopping_rounds=None,
verbose=False,
xgb_model: Optional[Union[Booster, str, XGBModel]] = None,
sample_weight_eval_set=None,
base_margin_eval_set=None,
feature_weights=None,
callbacks=None,
ray_params: Union[None, RayParams, Dict] = None,
_remote: Optional[bool] = None,
ray_dmatrix_params: Optional[Dict] = None,
):
if not (group is None and eval_group is None):
raise ValueError("Use `qid` instead of `group` for RayXGBRanker.")
if qid is None:
raise ValueError("`qid` is required for ranking.")
if eval_set is not None:
if eval_qid is None:
raise ValueError("`eval_qid `is required if"
" `eval_set` is not None")
evals_result = {}
ray_dmatrix_params = ray_dmatrix_params or {}
params = self.get_xgb_params()
train_dmatrix, evals = _check_if_params_are_ray_dmatrix(
X, sample_weight, base_margin, eval_set, sample_weight_eval_set,
base_margin_eval_set, eval_qid)
if train_dmatrix is None:
train_dmatrix, evals = _wrap_evaluation_matrices(
missing=self.missing,
X=X,
y=y,
group=group,
qid=qid,
sample_weight=sample_weight,
base_margin=base_margin,
feature_weights=feature_weights,
eval_set=eval_set,
sample_weight_eval_set=sample_weight_eval_set,
base_margin_eval_set=base_margin_eval_set,
eval_group=eval_group,
eval_qid=eval_qid,
# changed in xgboost-ray:
create_dmatrix=lambda **kwargs: RayDMatrix(**{
**kwargs,
**ray_dmatrix_params
}),
**self._ray_get_wrap_evaluation_matrices_compat_kwargs())
try:
model, feval, params = self._configure_fit(xgb_model, eval_metric,
params)
except TypeError:
# XGBoost >= 1.6.0
(model, feval, params, early_stopping_rounds,
callbacks) = self._configure_fit(xgb_model, eval_metric, params,
early_stopping_rounds, callbacks)
if callable(feval):
raise ValueError(
"Custom evaluation metric is not yet supported for XGBRanker.")
# remove those as they will be set in RayXGBoostActor
params.pop("n_jobs", None)
params.pop("nthread", None)
ray_params = self._ray_set_ray_params_n_jobs(ray_params, self.n_jobs)
additional_results = {}
self._Booster = train(
params,
train_dmatrix,
self.n_estimators,
early_stopping_rounds=early_stopping_rounds,
evals=evals,
evals_result=evals_result,
feval=feval,
verbose_eval=verbose,
xgb_model=model,
callbacks=callbacks,
# changed in xgboost-ray:
additional_results=additional_results,
ray_params=ray_params,
_remote=_remote,
)
self.objective = params["objective"]
self.additional_results_ = additional_results
self._set_evaluation_result(evals_result)
return self
def fit(
self,
X,
y,
*,
sample_weight=None,
base_margin=None,
eval_set=None,
eval_metric=None,
early_stopping_rounds=None,
verbose=True,
xgb_model=None,
sample_weight_eval_set=None,
base_margin_eval_set=None,
feature_weights=None,
callbacks=None,
ray_params: Union[None, RayParams, Dict] = None,
_remote: Optional[bool] = None,
ray_dmatrix_params: Optional[Dict] = None,
):
evals_result = {}
ray_dmatrix_params = ray_dmatrix_params or {}
params = self.get_xgb_params()
train_dmatrix, evals = _check_if_params_are_ray_dmatrix(
X, sample_weight, base_margin, eval_set, sample_weight_eval_set,
base_margin_eval_set)
if train_dmatrix is not None:
if not hasattr(self, "use_label_encoder"):
warnings.warn("If X is a RayDMatrix, no label encoding"
" will be performed. Ensure the labels are"
" encoded.")
elif self.use_label_encoder:
raise ValueError(
"X cannot be a RayDMatrix if `use_label_encoder` "
"is set to True")
if "num_class" not in params:
raise ValueError(
"`num_class` must be set during initalization if X"
" is a RayDMatrix")
self.classes_ = list(range(0, params["num_class"]))
self.n_classes_ = params["num_class"]
if self.n_classes_ <= 2:
params.pop("num_class")
label_transform = lambda x: x # noqa: E731
else:
if len(X.shape) != 2:
# Simply raise an error here since there might be many
# different ways of reshaping
raise ValueError(
"Please reshape the input data X into 2-dimensional "
"matrix.")
label_transform = self._ray_fit_preprocess(y)
if callable(self.objective):
obj = _objective_decorator(self.objective)
# Use default value. Is it really not used ?
params["objective"] = "binary:logistic"
else:
obj = None
if self.n_classes_ > 2:
# Switch to using a multiclass objective in the underlying
# XGB instance
params["objective"] = "multi:softprob"
params["num_class"] = self.n_classes_
try:
model, feval, params = self._configure_fit(xgb_model, eval_metric,
params)
except TypeError:
# XGBoost >= 1.6.0
(model, feval, params, early_stopping_rounds,
callbacks) = self._configure_fit(xgb_model, eval_metric, params,
early_stopping_rounds, callbacks)
if train_dmatrix is None:
train_dmatrix, evals = _wrap_evaluation_matrices(
missing=self.missing,
X=X,
y=y,
group=None,
qid=None,
sample_weight=sample_weight,
base_margin=base_margin,
feature_weights=feature_weights,
eval_set=eval_set,
sample_weight_eval_set=sample_weight_eval_set,
base_margin_eval_set=base_margin_eval_set,
eval_group=None,
eval_qid=None,
# changed in xgboost-ray:
create_dmatrix=lambda **kwargs: RayDMatrix(**{
**kwargs,
**ray_dmatrix_params
}),
**self._ray_get_wrap_evaluation_matrices_compat_kwargs(
label_transform=label_transform))
# remove those as they will be set in RayXGBoostActor
params.pop("n_jobs", None)
params.pop("nthread", None)
ray_params = self._ray_set_ray_params_n_jobs(ray_params, self.n_jobs)
additional_results = {}
self._Booster = train(
params,
train_dmatrix,
self.get_num_boosting_rounds(),
evals=evals,
early_stopping_rounds=early_stopping_rounds,
evals_result=evals_result,
obj=obj,
feval=feval,
verbose_eval=verbose,
xgb_model=model,
callbacks=callbacks,
# changed in xgboost-ray:
additional_results=additional_results,
ray_params=ray_params,
_remote=_remote,
)
if not callable(self.objective):
self.objective = params["objective"]
self.additional_results_ = additional_results
self._set_evaluation_result(evals_result)
return self
def fit(
self,
X,
y,
*,
sample_weight=None,
base_margin=None,
eval_set=None,
eval_metric=None,
early_stopping_rounds=None,
verbose=True,
xgb_model: Optional[Union[Booster, str, "XGBModel"]] = None,
sample_weight_eval_set=None,
base_margin_eval_set=None,
feature_weights=None,
callbacks=None,
ray_params: Union[None, RayParams, Dict] = None,
_remote: Optional[bool] = None,
ray_dmatrix_params: Optional[Dict] = None,
):
evals_result = {}
ray_dmatrix_params = ray_dmatrix_params or {}
train_dmatrix, evals = _check_if_params_are_ray_dmatrix(
X, sample_weight, base_margin, eval_set, sample_weight_eval_set,
base_margin_eval_set)
if train_dmatrix is None:
train_dmatrix, evals = _wrap_evaluation_matrices(
missing=self.missing,
X=X,
y=y,
group=None,
qid=None,
sample_weight=sample_weight,
base_margin=base_margin,
feature_weights=feature_weights,
eval_set=eval_set,
sample_weight_eval_set=sample_weight_eval_set,
base_margin_eval_set=base_margin_eval_set,
eval_group=None,
eval_qid=None,
# changed in xgboost-ray:
create_dmatrix=lambda **kwargs: RayDMatrix(**{
**kwargs,
**ray_dmatrix_params
}),
**self._ray_get_wrap_evaluation_matrices_compat_kwargs())
params = self.get_xgb_params()
if callable(self.objective):
obj = _objective_decorator(self.objective)
params["objective"] = "reg:squarederror"
else:
obj = None
try:
model, feval, params = self._configure_fit(xgb_model, eval_metric,
params)
except TypeError:
# XGBoost >= 1.6.0
(model, feval, params, early_stopping_rounds,
callbacks) = self._configure_fit(xgb_model, eval_metric, params,
early_stopping_rounds, callbacks)
# remove those as they will be set in RayXGBoostActor
params.pop("n_jobs", None)
params.pop("nthread", None)
ray_params = self._ray_set_ray_params_n_jobs(ray_params, self.n_jobs)
additional_results = {}
self._Booster = train(
params,
train_dmatrix,
self.get_num_boosting_rounds(),
evals=evals,
early_stopping_rounds=early_stopping_rounds,
evals_result=evals_result,
obj=obj,
feval=feval,
verbose_eval=verbose,
xgb_model=model,
callbacks=callbacks,
# changed in xgboost-ray:
additional_results=additional_results,
ray_params=ray_params,
_remote=_remote,
)
self.additional_results_ = additional_results
self._set_evaluation_result(evals_result)
return self