def setup_class(cls):
"""
Download and setup the test fixtures
"""
cls.dpath = 'demo/rank/'
(x_train, y_train, qid_train, x_test, y_test, qid_test,
x_valid, y_valid, qid_valid) = tm.get_mq2008(cls.dpath)
# instantiate the matrices
cls.dtrain = xgboost.DMatrix(x_train, y_train)
cls.dvalid = xgboost.DMatrix(x_valid, y_valid)
cls.dtest = xgboost.DMatrix(x_test, y_test)
# set the group counts from the query IDs
cls.dtrain.set_group([len(list(items))
for _key, items in itertools.groupby(qid_train)])
cls.dtest.set_group([len(list(items))
for _key, items in itertools.groupby(qid_test)])
cls.dvalid.set_group([len(list(items))
for _key, items in itertools.groupby(qid_valid)])
# save the query IDs for testing
cls.qid_train = qid_train
cls.qid_test = qid_test
cls.qid_valid = qid_valid
# model training parameters
cls.params = {'objective': 'rank:pairwise',
'booster': 'gbtree',
'eval_metric': ['ndcg']
}
def test_dask_ranking(client: "Client") -> None:
dpath = "demo/rank/"
mq2008 = tm.get_mq2008(dpath)
data = []
for d in mq2008:
if isinstance(d, scipy.sparse.csr_matrix):
d[d == 0] = np.inf
d = d.toarray()
d[d == 0] = np.nan
d[np.isinf(d)] = 0
data.append(da.from_array(d))
else:
data.append(da.from_array(d))
(
x_train,
y_train,
qid_train,
x_test,
y_test,
qid_test,
x_valid,
y_valid,
qid_valid,
) = data
qid_train = qid_train.astype(np.uint32)
qid_valid = qid_valid.astype(np.uint32)
qid_test = qid_test.astype(np.uint32)
rank = xgb.dask.DaskXGBRanker(n_estimators=2500)
rank.fit(
x_train,
y_train,
qid=qid_train,
eval_set=[(x_test, y_test), (x_train, y_train)],
eval_qid=[qid_test, qid_train],
eval_metric=["ndcg"],
verbose=True,
early_stopping_rounds=10,
)
assert rank.n_features_in_ == 46
assert rank.best_score > 0.98