Example #1
0
    def test_cython_right_outer_join(self):
        left = a_([0, 1, 2, 1, 2, 0, 0, 1, 2, 3, 3], dtype=np.int64)
        right = a_([1, 1, 0, 4, 2, 2, 1], dtype=np.int64)
        max_group = 5

        rs, ls  = lib.left_outer_join(right, left, max_group)

        exp_ls = left.argsort(kind='mergesort')
        exp_rs = right.argsort(kind='mergesort')

        #            0        1        1        1
        exp_li = a_([0, 1, 2, 3, 4, 5, 3, 4, 5, 3, 4, 5,
        #            2        2        4
                     6, 7, 8, 6, 7, 8, -1])
        exp_ri = a_([0, 0, 0, 1, 1, 1, 2, 2, 2, 3, 3, 3,
                     4, 4, 4, 5, 5, 5, 6])

        exp_ls = exp_ls.take(exp_li)
        exp_ls[exp_li == -1] = -1

        exp_rs = exp_rs.take(exp_ri)
        exp_rs[exp_ri == -1] = -1

        self.assert_(np.array_equal(ls, exp_ls))
        self.assert_(np.array_equal(rs, exp_rs))
Example #2
0
    def test_cython_right_outer_join(self):
        left = a_([0, 1, 2, 1, 2, 0, 0, 1, 2, 3, 3], dtype='i4')
        right = a_([1, 1, 0, 4, 2, 2, 1], dtype='i4')
        max_group = 5

        rs, ls  = lib.left_outer_join(right, left, max_group)

        exp_ls = left.argsort(kind='mergesort')
        exp_rs = right.argsort(kind='mergesort')

        #            0        1        1        1
        exp_li = a_([0, 1, 2, 3, 4, 5, 3, 4, 5, 3, 4, 5,
        #            2        2        4
                     6, 7, 8, 6, 7, 8, -1])
        exp_ri = a_([0, 0, 0, 1, 1, 1, 2, 2, 2, 3, 3, 3,
                     4, 4, 4, 5, 5, 5, 6])

        exp_ls = exp_ls.take(exp_li)
        exp_ls[exp_li == -1] = -1

        exp_rs = exp_rs.take(exp_ri)
        exp_rs[exp_ri == -1] = -1

        self.assert_(np.array_equal(ls, exp_ls))
        self.assert_(np.array_equal(rs, exp_rs))
Example #3
0
File: merge.py Project: lahi/pandas
def _get_single_indexer(join_key, index, sort=False):
    left_key, right_key, count = _factorize_objects(join_key, index, sort=sort)

    left_indexer, right_indexer = \
        lib.left_outer_join(left_key.astype('i4'), right_key.astype('i4'),
                            count, sort=sort)

    return left_indexer, right_indexer
Example #4
0
def _get_single_indexer(join_key, index, sort=False):
    left_key, right_key, count = _factorize_objects(join_key, index, sort=sort)

    left_indexer, right_indexer = \
        lib.left_outer_join(left_key.astype('i4'), right_key.astype('i4'),
                            count, sort=sort)

    return left_indexer, right_indexer
Example #5
0
def _get_single_indexer(join_key, index, sort=False):
    left_key, right_key, count = _factorize_keys(join_key, index, sort=sort)

    left_indexer, right_indexer = \
        lib.left_outer_join(com._ensure_int64(left_key),
                            com._ensure_int64(right_key),
                            count, sort=sort)

    return left_indexer, right_indexer
Example #6
0
def _get_multiindex_indexer(join_keys, index, sort=False):
    shape = []
    labels = []
    for level, key in zip(index.levels, join_keys):
        llab, rlab, count = _factorize_objects(level, key, sort=False)
        labels.append(rlab)
        shape.append(count)

    left_group_key = get_group_index(labels, shape)
    right_group_key = get_group_index(index.labels, shape)

    left_group_key, right_group_key, max_groups = _factorize_int64(left_group_key, right_group_key, sort=False)

    left_indexer, right_indexer = lib.left_outer_join(
        left_group_key.astype("i4"), right_group_key.astype("i4"), max_groups, sort=False
    )

    return left_indexer, right_indexer
Example #7
0
def test_left_outer_join_bug():
    left = np.array([0, 1, 0, 1, 1, 2, 3, 1, 0, 2, 1, 2, 0, 1, 1, 2, 3, 2, 3,
                     2, 1, 1, 3, 0, 3, 2, 3, 0, 0, 2, 3, 2, 0, 3, 1, 3, 0, 1,
                     3, 0, 0, 1, 0, 3, 1, 0, 1, 0, 1, 1, 0, 2, 2, 2, 2, 2, 0,
                     3, 1, 2, 0, 0, 3, 1, 3, 2, 2, 0, 1, 3, 0, 2, 3, 2, 3, 3,
                     2, 3, 3, 1, 3, 2, 0, 0, 3, 1, 1, 1, 0, 2, 3, 3, 1, 2, 0,
                     3, 1, 2, 0, 2], dtype=np.int64)

    right = np.array([3, 1], dtype=np.int64)
    max_groups = 4

    lidx, ridx = lib.left_outer_join(left, right, max_groups, sort=False)

    exp_lidx = np.arange(len(left))
    exp_ridx = -np.ones(len(left))
    exp_ridx[left == 1] = 1
    exp_ridx[left == 3] = 0

    assert(np.array_equal(lidx, exp_lidx))
    assert(np.array_equal(ridx, exp_ridx))
Example #8
0
File: merge.py Project: lahi/pandas
def _get_multiindex_indexer(join_keys, index, sort=False):
    shape = []
    labels = []
    for level, key in zip(index.levels, join_keys):
        llab, rlab, count = _factorize_objects(level, key, sort=False)
        labels.append(rlab)
        shape.append(count)

    left_group_key = get_group_index(labels, shape)
    right_group_key = get_group_index(index.labels, shape)

    left_group_key, right_group_key, max_groups = \
        _factorize_int64(left_group_key, right_group_key,
                         sort=False)

    left_indexer, right_indexer = \
        lib.left_outer_join(left_group_key.astype('i4'),
                            right_group_key.astype('i4'),
                            max_groups, sort=False)

    return left_indexer, right_indexer
Example #9
0
    def test_cython_left_outer_join(self):
        left = a_([0, 1, 2, 1, 2, 0, 0, 1, 2, 3, 3], dtype=np.int64)
        right = a_([1, 1, 0, 4, 2, 2, 1], dtype=np.int64)
        max_group = 5

        ls, rs = lib.left_outer_join(left, right, max_group)

        exp_ls = left.argsort(kind="mergesort")
        exp_rs = right.argsort(kind="mergesort")

        exp_li = a_([0, 1, 2, 3, 3, 3, 4, 4, 4, 5, 5, 5, 6, 6, 7, 7, 8, 8, 9, 10])
        exp_ri = a_([0, 0, 0, 1, 2, 3, 1, 2, 3, 1, 2, 3, 4, 5, 4, 5, 4, 5, -1, -1])

        exp_ls = exp_ls.take(exp_li)
        exp_ls[exp_li == -1] = -1

        exp_rs = exp_rs.take(exp_ri)
        exp_rs[exp_ri == -1] = -1

        self.assert_(np.array_equal(ls, exp_ls))
        self.assert_(np.array_equal(rs, exp_rs))
Example #10
0
def test_left_outer_join_bug():
    left = np.array([
        0, 1, 0, 1, 1, 2, 3, 1, 0, 2, 1, 2, 0, 1, 1, 2, 3, 2, 3, 2, 1, 1, 3, 0,
        3, 2, 3, 0, 0, 2, 3, 2, 0, 3, 1, 3, 0, 1, 3, 0, 0, 1, 0, 3, 1, 0, 1, 0,
        1, 1, 0, 2, 2, 2, 2, 2, 0, 3, 1, 2, 0, 0, 3, 1, 3, 2, 2, 0, 1, 3, 0, 2,
        3, 2, 3, 3, 2, 3, 3, 1, 3, 2, 0, 0, 3, 1, 1, 1, 0, 2, 3, 3, 1, 2, 0, 3,
        1, 2, 0, 2
    ],
                    dtype=np.int32)

    right = np.array([3, 1], dtype=np.int32)
    max_groups = 4

    lidx, ridx = lib.left_outer_join(left, right, max_groups, sort=False)

    exp_lidx = np.arange(len(left))
    exp_ridx = -np.ones(len(left))
    exp_ridx[left == 1] = 1
    exp_ridx[left == 3] = 0

    assert (np.array_equal(lidx, exp_lidx))
    assert (np.array_equal(ridx, exp_ridx))
Example #11
0
def _right_outer_join(x, y, max_groups):
    right_indexer, left_indexer = lib.left_outer_join(y, x, max_groups)
    return left_indexer, right_indexer
Example #12
0
File: merge.py Project: lahi/pandas
def _right_outer_join(x, y, max_groups):
    right_indexer, left_indexer = lib.left_outer_join(y, x, max_groups)
    return left_indexer, right_indexer