def test_compact_with_random(self):
data = np.random.randint(0, 10, 30, dtype=np.uint16)
indices = np.arange(30, dtype=np.uint32)
vec = SparseVector(data, indices, 30)
vec.compact()
zi = np.where(data == 0)
expected = SparseVector(np.delete(data, zi), np.delete(indices, zi),
30)
result = copy(vec)
self.assertEqual(result, expected)
def read_set(pool, stream):
"""
Resds a testing set from the specified CSV stream using the specified
processing pool to improve I/O performance.
:param pool: The processing pool to use.
:param stream: The CSV stream to read from.
:return: A set filled with some data to test with.
"""
tests = []
processor = partial(CsvIO.process_line, skip_class=True, skip_id=False)
results = pool.map(processor, CsvIO.generate_lines(stream))
for result in results:
tests.append(
Test(
result.id,
SparseVector(data=np.array(result.data,
copy=False,
dtype=np.uint16),
indices=np.array(result.cols,
copy=False,
dtype=np.uint32),
size=61189)))
return TestingSet(tests)
def test_compact_with_zero(self):
vec = SparseVector(np.zeros(10, dtype=np.uint16),
np.arange(10, dtype=np.uint32), 10)
vec.compact()
expected = SparseVector.zero(10)
result = copy(vec)
self.assertEqual(result, expected)
def test_venn_with_random(self):
array_a = np.random.randint(0, 100, 30)
array_b = np.random.randint(0, 100, 30)
a = SparseVector.from_list(array_a)
b = SparseVector.from_list(array_b)
a_i = np.in1d(a.indices, b.indices)
a_d = np.in1d(a.indices, np.setdiff1d(a.indices, a.indices[a_i]))
expected0 = SparseVector(a.data[a_i], a.indices[a_i], a.size)
expected1 = SparseVector(a.data[a_d], a.indices[a_d], a.size)
result0, result1 = a.venn(b)
self.assertEqual(result0, expected0)
self.assertEqual(result1, expected1)
self.assertEqual(result0.data.size + result1.data.size, a.data.size)
self.assertEqual(result0.indices.size + result1.indices.size,
a.indices.size)
