[ci] [python] reduce unnecessary data loading in tests

.gitignore

@@ -318,6 +318,8 @@ htmlcov/
 .coverage.*
 .cache
 nosetests.xml
+prof/
+*.prof
 coverage.xml
 *,cover
 .hypothesis/

tests/python_package_test/test_basic.py

@@ -10,11 +10,30 @@
 from sklearn.datasets import load_breast_cancer, dump_svmlight_file, load_svmlight_file
 from sklearn.model_selection import train_test_split
 
+try:
+    from functools import lru_cache
+except ImportError:
+    warnings.warn("Could not import functools.lru_cache", RuntimeWarning)
+
+    def lru_cache(user_function, maxsize=None):
+        @wraps(user_function)
+        def wrapper(*args, **kwargs):
+            arg_key = tuple(args, [item for item in kwargs.items()])
+            if arg_key not in cache:
+                cache[arg_key] = user_function(*args)
+            return cache[arg_key]
+        return wrapper
+
+
+@lru_cache(maxsize=None)
+def _load_breast_cancer(**kwargs):
+    return load_breast_cancer(**kwargs)
+
 
 class TestBasic(unittest.TestCase):
 
     def test(self):
-        X_train, X_test, y_train, y_test = train_test_split(*load_breast_cancer(return_X_y=True),
+        X_train, X_test, y_train, y_test = train_test_split(*_load_breast_cancer(return_X_y=True),
                                                             test_size=0.1, random_state=2)
         train_data = lgb.Dataset(X_train, label=y_train)
         valid_data = train_data.create_valid(X_test, label=y_test)
@@ -86,7 +105,7 @@ def test(self):
         os.remove(tname)
 
     def test_chunked_dataset(self):
-        X_train, X_test, y_train, y_test = train_test_split(*load_breast_cancer(return_X_y=True), test_size=0.1, random_state=2)
+        X_train, X_test, y_train, y_test = train_test_split(*_load_breast_cancer(return_X_y=True), test_size=0.1, random_state=2)
 
         chunk_size = X_train.shape[0] // 10 + 1
         X_train = [X_train[i * chunk_size:(i + 1) * chunk_size, :] for i in range(X_train.shape[0] // chunk_size + 1)]
@@ -273,7 +292,7 @@ def check_asserts(data):
             self.assertAlmostEqual(data.label[1], data.weight[1])
             self.assertListEqual(data.feature_name, data.get_feature_name())
 
-        X, y = load_breast_cancer(return_X_y=True)
+        X, y = _load_breast_cancer(return_X_y=True)
         sequence = np.ones(y.shape[0])
         sequence[0] = np.nan
         sequence[1] = np.inf