def test_subset_raises_on_float():
"""[Base] SubsetIndex: check raises error on floats for n_part, n_split."""
with np.testing.assert_raises(ValueError):
SubsetIndex(0.5, 2, X=X)
with np.testing.assert_raises(ValueError):
SubsetIndex(2, 0.5, X=X)
def test_subset_partition():
"""[Base] Subset: test partition indexing on tuples."""
parts = list()
for part in SubsetIndex(X=X).partition():
parts.append(part)
assert parts == [(0, 3), (3, 5)]
def test_subset_tuple_shape():
"""[Base] SubsetIndex: test the tuple shape on generation."""
tup = [(tri, tei) for tri, tei in SubsetIndex(2, 2).generate(X)]
assert tup == [(((2, 3), ), [(0, 2), (3, 4)]),
(((0, 2), ), [(2, 3), (4, 5)]),
(((4, 5), ), [(0, 2), (3, 4)]),
(((3, 4), ), [(2, 3), (4, 5)])]
def test_subset_partition_array():
"""[Base] Subset: test partition indexing on arrays."""
parts = list()
for part in SubsetIndex(X=X).partition(as_array=True):
parts.append(part)
np.testing.assert_array_equal(parts[0], np.array([0, 1, 2]))
np.testing.assert_array_equal(parts[1], np.array([3, 4]))
def test_subset_index_is_fitted():
"""[Base] BlendIndex: check fit methods."""
attrs = ['n_samples', 'n_test_samples']
idx = SubsetIndex()
for attr in attrs: assert not hasattr(idx, attr)
idx.fit(X)
for attr in attrs: assert hasattr(idx, attr)
idx = SubsetIndex()
for attr in attrs: assert not hasattr(idx, attr)
for _ in idx.generate(X): pass
for attr in attrs: assert hasattr(idx, attr)
idx = SubsetIndex(X=X)
for attr in attrs: assert hasattr(idx, attr)
def test_subset_array_shape():
"""[Base] ClusteredSubsetIndex: test the array shape on generation."""
t = list()
e = list()
for tri, tei in SubsetIndex(2, 2, X=X).generate(as_array=True):
t.append(tri.tolist())
e.append(tei.tolist())
assert t == [[2], [0, 1], [4], [3]]
assert e == [[0, 1, 3], [2, 4], [0, 1, 3], [2, 4]]
import numpy as np
from mlens.utils.dummy import OLS
from mlens.base import SubsetIndex
from mlens.parallel.subset import _expand_instance_list, _get_col_idx
from mlens.ensemble.base import LayerContainer
x = np.arange(24).reshape((12, 2))
y = x[:, 0] * x[:, 1]
estimators = [('ols-%i' % i, OLS(i)) for i in range(2)]
indexer = SubsetIndex(2, 3, X=x)
def ground_truth():
"""Ground truth for subset test.
"""
e = _expand_instance_list(estimators, indexer)
P = np.zeros((12, 2 * 2))
F = np.zeros((12, 2 * 2))
cols = _get_col_idx(e, 2, 1)
for name, tri, tei, est_list in e:
for est_name, est in est_list:
if tei is None:
est.fit(x[tri[0]:tri[1]], y[tri[0]:tri[1]])
p = est.predict(x)
P[:, cols[(name, est_name)]] = p
def test_subset_raises_empty():
"""[Base] SubsetIndex: check raises error on empty train set."""
with np.testing.assert_raises(ValueError):
SubsetIndex(2, 2, X=np.empty(1))
def test_subset_raises_no_partition():
"""[Base] SubsetIndex: check raises error on 0 partitions."""
with np.testing.assert_raises(ValueError):
SubsetIndex(0, X=X)
def test_subset_raises_on_no_split_part():
"""[Base] SubsetIndex: check raises error n_part * n_split > n_samples."""
with np.testing.assert_raises(ValueError):
SubsetIndex(3, 3, X=X)
def test_subset_raises_on_partitions_and_one_split():
"""[Base] SubsetIndex: check raises error on single split of partitions."""
with np.testing.assert_raises(ValueError):
SubsetIndex(2, 1, X=X)
def test_subset_raises_on_w_raise_():
"""[Base] SubsetIndex: check raises on n_part = 1, n_splits = 1."""
with np.testing.assert_raises(ValueError):
SubsetIndex(1, 1, X=X)
def test_subset_warns_on_wo_raise_():
"""[Base] SubsetIndex: check raises on n_part = 1, n_splits = 1."""
with np.testing.assert_warns(UserWarning):
SubsetIndex(1, 1, raise_on_exception=False, X=X)