Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[REVIEW] dask personalization, fix df query #1237

Merged
merged 16 commits into from
Nov 20, 2020
10 changes: 0 additions & 10 deletions datasets/asymmetric_directed__tiny.csv

This file was deleted.

78 changes: 78 additions & 0 deletions datasets/karate-asymmetric.csv
Original file line number Diff line number Diff line change
@@ -0,0 +1,78 @@
1 2 1.0
1 3 1.0
1 4 1.0
1 5 1.0
1 6 1.0
1 7 1.0
1 8 1.0
1 9 1.0
1 11 1.0
1 12 1.0
1 13 1.0
1 14 1.0
1 18 1.0
1 20 1.0
1 22 1.0
1 32 1.0
2 3 1.0
2 4 1.0
2 8 1.0
2 14 1.0
2 18 1.0
2 20 1.0
2 22 1.0
2 31 1.0
3 4 1.0
3 8 1.0
3 9 1.0
3 10 1.0
3 14 1.0
3 28 1.0
3 29 1.0
3 33 1.0
4 8 1.0
4 13 1.0
4 14 1.0
5 7 1.0
5 11 1.0
6 7 1.0
6 11 1.0
6 17 1.0
7 17 1.0
9 31 1.0
9 33 1.0
9 34 1.0
10 34 1.0
14 34 1.0
15 33 1.0
15 34 1.0
16 33 1.0
16 34 1.0
19 33 1.0
19 34 1.0
20 34 1.0
21 33 1.0
21 34 1.0
23 33 1.0
23 34 1.0
24 26 1.0
24 28 1.0
24 30 1.0
24 33 1.0
24 34 1.0
25 26 1.0
25 28 1.0
25 32 1.0
26 32 1.0
27 30 1.0
27 34 1.0
28 34 1.0
29 32 1.0
29 34 1.0
30 33 1.0
30 34 1.0
31 33 1.0
31 34 1.0
32 33 1.0
32 34 1.0
33 34 1.0
156 changes: 78 additions & 78 deletions datasets/karate_undirected.csv
Original file line number Diff line number Diff line change
@@ -1,78 +1,78 @@
1 2 1.0
1 3 1.0
1 4 1.0
1 5 1.0
1 6 1.0
1 7 1.0
1 8 1.0
1 9 1.0
1 11 1.0
1 12 1.0
1 13 1.0
1 14 1.0
1 18 1.0
1 20 1.0
1 22 1.0
1 32 1.0
2 3 1.0
2 4 1.0
2 8 1.0
2 14 1.0
2 18 1.0
2 20 1.0
2 22 1.0
2 31 1.0
3 4 1.0
3 8 1.0
3 9 1.0
3 10 1.0
3 14 1.0
3 28 1.0
3 29 1.0
3 33 1.0
4 8 1.0
4 13 1.0
4 14 1.0
5 7 1.0
5 11 1.0
6 7 1.0
6 11 1.0
6 17 1.0
7 17 1.0
9 31 1.0
9 33 1.0
9 34 1.0
10 34 1.0
14 34 1.0
15 33 1.0
15 34 1.0
16 33 1.0
16 34 1.0
19 33 1.0
19 34 1.0
20 34 1.0
21 33 1.0
21 34 1.0
23 33 1.0
23 34 1.0
24 26 1.0
24 28 1.0
24 30 1.0
24 33 1.0
24 34 1.0
25 26 1.0
25 28 1.0
25 32 1.0
26 32 1.0
27 30 1.0
27 34 1.0
28 34 1.0
29 32 1.0
29 34 1.0
30 33 1.0
30 34 1.0
31 33 1.0
31 34 1.0
32 33 1.0
32 34 1.0
33 34 1.0
1 2
1 3
1 4
1 5
1 6
1 7
1 8
1 9
1 11
1 12
1 13
1 14
1 18
1 20
1 22
1 32
2 3
2 4
2 8
2 14
2 18
2 20
2 22
2 31
3 4
3 8
3 9
3 10
3 14
3 28
3 29
3 33
4 8
4 13
4 14
5 7
5 11
6 7
6 11
6 17
7 17
9 31
9 33
9 34
10 34
14 34
15 33
15 34
16 33
16 34
19 33
19 34
20 34
21 33
21 34
23 33
23 34
24 26
24 28
24 30
24 33
24 34
25 26
25 28
25 32
26 32
27 30
27 34
28 34
29 32
29 34
30 33
30 34
31 33
31 34
32 33
32 34
33 34
17 changes: 0 additions & 17 deletions python/cugraph/tests/test_k_core.py
Original file line number Diff line number Diff line change
@@ -65,23 +65,6 @@ def compare_edges(cg, nxg):
return True


# FIXME: the default set of datasets includes an asymmetric directed graph
# (email-EU-core.csv), which currently produces different results between
# cugraph and Nx and fails that test. Investigate, resolve, and use
# utils.DATASETS instead.
#
# https://github.com/rapidsai/cugraph/issues/1046
#
# @pytest.mark.parametrize("graph_file", utils.DATASETS)
@pytest.mark.parametrize("graph_file", utils.DATASETS_UNDIRECTED)
def test_core_number_DiGraph(graph_file):
gc.collect()

cu_kcore, nx_kcore = calc_k_cores(graph_file)

assert compare_edges(cu_kcore, nx_kcore)


@pytest.mark.parametrize("graph_file", utils.DATASETS_UNDIRECTED)
def test_core_number_Graph(graph_file):
gc.collect()