def test_dump_qid(self):
tmpfile = "/tmp/tmp_dump.txt"
try:
# loads from file
Xs, y, q = load_svmlight_file(qid_datafile, query_id=True)
# dumps to file
dump_svmlight_file(Xs,
y,
tmpfile,
query_id=list(q),
zero_based=False)
# loads them as CSR MATRIX with scikit-learn
X2, y2, q2 = sk_load_svmlight_file(tmpfile, query_id=True)
X3 = np.ndarray(shape=X2.shape, dtype=X2.dtype)
X2.toarray(out=X3)
# check assertions
assert_array_almost_equal(Xs, X3)
assert_array_almost_equal(y, y2)
assert_array_equal(q, q2)
finally:
if os.path.exists(tmpfile):
os.remove(tmpfile)
def test_dump(self):
tmpfile = "tmp_dump.txt"
try:
# loads from file
Xs, y = load_svmlight_file(datafile)
# dumps to file
dump_svmlight_file(Xs, y, tmpfile, zero_based=False)
# loads them as CSR MATRIX
X2, y2 = sk_load_svmlight_file(tmpfile)
X3 = np.ndarray(shape=X2.shape, dtype=X2.dtype)
X2.toarray(out=X3)
# check assertions
assert_array_almost_equal(Xs, X3)
assert_array_almost_equal(y, y2)
finally:
if os.path.exists(tmpfile):
os.remove(tmpfile)