def aggregate_into_cliques()

in sourcecode/scoring/post_selection_similarity_old.py [0:0]

• 32 lines of code
• 7 McCabe index (conditional complexity)

def aggregate_into_cliques(graphDf):
  with c.time_block("Aggregate into cliques by post selection similarity"):
    userToCliqueMap = dict()
    cliqueToUserMap = dict()

    nextNewCliqueId = 1  # start cliqueIdxs from 1
    for i, row in graphDf.iterrows():
      sid = row["leftRaterId"]
      tid = row["rightRaterId"]
      if sid in userToCliqueMap:
        if tid in userToCliqueMap:
          # both in map. merge if not same clique
          if userToCliqueMap[sid] != userToCliqueMap[tid]:
            # merge. assign all member's of target clique to source clique.
            # slow way: iterate over all values here.
            # fast way: maintain a reverse map of cliqueToUserMap.
            sourceDestClique = userToCliqueMap[sid]
            oldTargetCliqueToDel = userToCliqueMap[tid]

            for userId in cliqueToUserMap[oldTargetCliqueToDel]:
              cliqueToUserMap[sourceDestClique].append(userId)
              userToCliqueMap[userId] = sourceDestClique
            del cliqueToUserMap[oldTargetCliqueToDel]
            gc.collect()

        else:
          # source in map; target not. add target to source's clique
          sourceClique = userToCliqueMap[sid]
          userToCliqueMap[tid] = sourceClique
          cliqueToUserMap[sourceClique].append(tid)
      elif tid in userToCliqueMap:
        # target in map; source not. add source to target's clique
        targetClique = userToCliqueMap[tid]
        userToCliqueMap[sid] = targetClique
        cliqueToUserMap[targetClique].append(sid)
      else:
        # new clique
        userToCliqueMap[sid] = nextNewCliqueId
        userToCliqueMap[tid] = nextNewCliqueId
        cliqueToUserMap[nextNewCliqueId] = [sid, tid]
        nextNewCliqueId += 1
  return cliqueToUserMap, userToCliqueMap