def test_compute_sample_weight():
# Test (and demo) compute_sample_weight.
# Test with balanced classes
y = np.asarray([1, 1, 1, 2, 2, 2])
sample_weight = compute_sample_weight("auto", y)
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
# Test with user-defined weights
sample_weight = compute_sample_weight({1: 2, 2: 1}, y)
assert_array_almost_equal(sample_weight, [2., 2., 2., 1., 1., 1.])
# Test with column vector of balanced classes
y = np.asarray([[1], [1], [1], [2], [2], [2]])
sample_weight = compute_sample_weight("auto", y)
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
# Test with unbalanced classes
y = np.asarray([1, 1, 1, 2, 2, 2, 3])
sample_weight = compute_sample_weight("auto", y)
expected = np.asarray([.6, .6, .6, .6, .6, .6, 1.8])
assert_array_almost_equal(sample_weight, expected)
# Test with `None` weights
sample_weight = compute_sample_weight(None, y)
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1., 1.])
# Test with multi-output of balanced classes
y = np.asarray([[1, 0], [1, 0], [1, 0], [2, 1], [2, 1], [2, 1]])
sample_weight = compute_sample_weight("auto", y)
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
# Test with multi-output with user-defined weights
y = np.asarray([[1, 0], [1, 0], [1, 0], [2, 1], [2, 1], [2, 1]])
sample_weight = compute_sample_weight([{1: 2, 2: 1}, {0: 1, 1: 2}], y)
assert_array_almost_equal(sample_weight, [2., 2., 2., 2., 2., 2.])
# Test with multi-output of unbalanced classes
y = np.asarray([[1, 0], [1, 0], [1, 0], [2, 1], [2, 1], [2, 1], [3, -1]])
sample_weight = compute_sample_weight("auto", y)
assert_array_almost_equal(sample_weight, expected ** 2)
def test_compute_sample_weight_with_subsample():
# Test compute_sample_weight with subsamples specified.
# Test with balanced classes and all samples present
y = np.asarray([1, 1, 1, 2, 2, 2])
sample_weight = compute_sample_weight("auto", y, range(6))
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
# Test with column vector of balanced classes and all samples present
y = np.asarray([[1], [1], [1], [2], [2], [2]])
sample_weight = compute_sample_weight("auto", y, range(6))
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
# Test with a subsample
y = np.asarray([1, 1, 1, 2, 2, 2])
sample_weight = compute_sample_weight("auto", y, range(4))
assert_array_almost_equal(sample_weight, [.5, .5, .5, 1.5, 1.5, 1.5])
# Test with a bootstrap subsample
y = np.asarray([1, 1, 1, 2, 2, 2])
sample_weight = compute_sample_weight("auto", y, [0, 1, 1, 2, 2, 3])
expected = np.asarray([1/3., 1/3., 1/3., 5/3., 5/3., 5/3.])
assert_array_almost_equal(sample_weight, expected)
# Test with a bootstrap subsample for multi-output
y = np.asarray([[1, 0], [1, 0], [1, 0], [2, 1], [2, 1], [2, 1]])
sample_weight = compute_sample_weight("auto", y, [0, 1, 1, 2, 2, 3])
assert_array_almost_equal(sample_weight, expected ** 2)
# Test with a missing class
y = np.asarray([1, 1, 1, 2, 2, 2, 3])
sample_weight = compute_sample_weight("auto", y, range(6))
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1., 0.])
# Test with a missing class for multi-output
y = np.asarray([[1, 0], [1, 0], [1, 0], [2, 1], [2, 1], [2, 1], [2, 2]])
sample_weight = compute_sample_weight("auto", y, range(6))
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1., 0.])
