test_feature_hasher.py 文件源码

def test_feature_hasher_strings():
    # mix byte and Unicode strings; note that "foo" is a duplicate in row 0
    raw_X = [["foo", "bar", "baz", "foo".encode("ascii")],
             ["bar".encode("ascii"), "baz", "quux"]]

    for lg_n_features in (7, 9, 11, 16, 22):
        n_features = 2 ** lg_n_features

        it = (x for x in raw_X)                 # iterable

        h = FeatureHasher(n_features, non_negative=True, input_type="string")
        X = h.transform(it)

        assert_equal(X.shape[0], len(raw_X))
        assert_equal(X.shape[1], n_features)

        assert_true(np.all(X.data > 0))
        assert_equal(X[0].sum(), 4)
        assert_equal(X[1].sum(), 3)

        assert_equal(X.nnz, 6)