Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
test_convert_partition.py 4.55 KB
Newer Older
kylasa's avatar
[DistDGL][Robustness]Replacing numpy's unique with custom implementation (#5391)  
kylasa committed
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154 
import os
import tempfile

import numpy as np
import pytest

import utils

from convert_partition import _get_unique_invidx


@pytest.mark.parametrize(
    "num_nodes, num_edges, nid_begin, nid_end",
    [
        [4000, 40000, 0, 1000],
        [4000, 40000, 1000, 2000],
        [4000, 40000, 2000, 3000],
        [4000, 40000, 3000, 4000],
        [4000, 100, 0, 1000],
        [4000, 100, 1000, 2000],
        [4000, 100, 2000, 3000],
        [4000, 100, 3000, 4000],
        [1, 1, 0, 1],
    ],
)
def test_get_unique_invidx_with_numpy(num_nodes, num_edges, nid_begin, nid_end):
    # prepare data for the function
    # generate synthetic edges
    if num_edges > 0:
        srcids = np.random.randint(0, num_nodes, (num_edges,))  # exclusive
        dstids = np.random.randint(
            nid_begin, nid_end, (num_edges,)
        )  # exclusive
    else:
        srcids = np.array([])
        dstids = np.array([])

    assert nid_begin <= nid_end

    # generate unique node-ids for any
    # partition. This list should be sorted.
    # This is equivilant to shuffle_nids in a partition
    unique_nids = np.arange(nid_begin, nid_end)  # exclusive

    # test with numpy unique here
    orig_srcids = srcids.copy()
    orig_dstids = dstids.copy()
    input_arr = np.concatenate([srcids, dstids, unique_nids])

    # test
    uniques, idxes, srcids, dstids = _get_unique_invidx(
        srcids, dstids, unique_nids
    )

    assert len(uniques) == len(idxes)
    assert np.all(srcids < len(uniques))
    assert np.all(dstids < len(uniques))
    assert np.all(uniques[srcids].sort() == orig_srcids.sort())
    assert np.all(uniques[dstids] == orig_dstids)

    assert np.all(uniques == input_arr[idxes])

    # numpy
    np_uniques, np_idxes, np_inv_idxes = np.unique(
        np.concatenate([orig_srcids, orig_dstids, unique_nids]),
        return_index=True,
        return_inverse=True,
    )

    # test uniques
    assert np.all(np_uniques == uniques)

    # test idxes array
    assert np.all(input_arr[idxes].sort() == input_arr[np_idxes].sort())

    # test srcids, inv_indices
    assert np.all(
        uniques[srcids].sort()
        == np_uniques[np_inv_idxes[0 : len(srcids)]].sort()
    )

    # test dstids, inv_indices
    assert np.all(
        uniques[dstids].sort() == np_uniques[np_inv_idxes[len(srcids) :]].sort()
    )


@pytest.mark.parametrize(
    "num_nodes, num_edges, nid_begin, nid_end",
    [
        # dense networks, no. of edges more than no. of nodes
        [4000, 40000, 0, 1000],
        [4000, 40000, 1000, 2000],
        [4000, 40000, 2000, 3000],
        [4000, 40000, 3000, 4000],
        # sparse networks, no. of edges smaller than no. of nodes
        [4000, 100, 0, 1000],
        [4000, 100, 1000, 2000],
        [4000, 100, 2000, 3000],
        [4000, 100, 3000, 4000],
        # corner case
        [1, 1, 0, 1],
    ],
)
def test_get_unique_invidx(num_nodes, num_edges, nid_begin, nid_end):
    # prepare data for the function
    # generate synthetic edges
    if num_edges > 0:
        srcids = np.random.randint(0, num_nodes, (num_edges,))
        dstids = np.random.randint(nid_begin, nid_end, (num_edges,))
    else:
        srcids = np.array([])
        dstids = np.array([])

    assert nid_begin <= nid_end

    # generate unique node-ids for any
    # partition. This list should be sorted.
    # This is equivilant to shuffle_nids in a partition
    unique_nids = np.arange(nid_begin, nid_end)

    # invoke the test target
    uniques, idxes, src_ids, dst_ids = _get_unique_invidx(
        srcids, dstids, unique_nids
    )

    # validate the outputs of this function
    # array uniques should be sorted list of integers.
    assert np.all(
        np.diff(uniques) >= 0
    ), f"Output parameter uniques assert failing."

    # idxes are list of integers
    # these are indices in the concatenated list (srcids, dstids, unique_nids)
    max_idx = len(src_ids) + len(dst_ids) + len(unique_nids)
    assert np.all(idxes >= 0), f"Output parameter idxes has negative values."
    assert np.all(
        idxes < max_idx
    ), f"Output parameter idxes has invalid maximum value."

    # srcids and dstids will be inverse indices in the uniques list
    min_src = np.amin(src_ids)
    max_src = np.amax(src_ids)

    min_dst = np.amin(dst_ids)
    max_dst = np.amax(dst_ids)

    assert (
        len(uniques) > max_src
    ), f"Inverse idx, src_ids, has invalid max value."
    assert min_src >= 0, f"Inverse idx, src_ids has negative values."

    assert len(uniques) > max_dst, f"Inverse idx, dst_ids, invalid max value."
    assert max_dst >= 0, f"Inverse idx, dst_ids has negative values."