Github user jingyimei commented on a diff in the pull request: https://github.com/apache/madlib/pull/244#discussion_r177916983 --- Diff: src/ports/postgres/modules/graph/test/pagerank.sql_in --- @@ -95,6 +101,49 @@ SELECT assert(relative_error(SUM(pagerank), 1) < 0.00001, ) FROM pagerank_gr_out WHERE user_id=2; +-- Tests for Personalized Page Rank + +-- Test without grouping + +DROP TABLE IF EXISTS pagerank_ppr_out; +DROP TABLE IF EXISTS pagerank_ppr_out_summary; +SELECT pagerank( + 'vertex', -- Vertex table + 'id', -- Vertix id column + '"EDGE"', -- "EDGE" table + 'src=src, dest=dest', -- "EDGE" args + 'pagerank_ppr_out', -- Output table of PageRank + NULL, -- Default damping factor (0.85) + NULL, -- Default max iters (100) + NULL, -- Default Threshold + NULL, -- Grouping column + '{1,3}'); -- Personlized Nodes + + +-- View the PageRank of all vertices, sorted by their scores. +SELECT assert(relative_error(SUM(pagerank), 1) < 0.00124, + 'PageRank: Scores do not sum up to 1.' + ) FROM pagerank_ppr_out; + + +-- Test with grouping + +DROP TABLE IF EXISTS pagerank_ppr_grp_out; +DROP TABLE IF EXISTS pagerank_ppr_grp_out_summary; +SELECT pagerank( + 'vertex', -- Vertex table + 'id', -- Vertix id column + '"EDGE"', -- "EDGE" table + 'src=src, dest=dest', -- "EDGE" args + 'pagerank_ppr_grp_out', -- Output table of PageRank + NULL, -- Default damping factor (0.85) + NULL, -- Default max iters (100) + NULL, -- Default Threshold + 'user_id', -- Grouping column + '{1,3}'); -- Personlized Nodes + +SELECT assert(count(*) = 14, 'Tuple count for Pagerank out table != 14') FROM pagerank_ppr_grp_out; --- End diff -- can we do similar assertion here by group?
---