# Script for Distributed Similarity Clustering as in Paper on Distributed Arrays - Report 381

let sizeT = size(T);
query share("sizeT", TRUE, Workers)

let SS = T dmap["", . feed some[10000 div sizeT]] dsummarize consume

let k = 50;
@&Scripts/SimilarityPartitioning.sec;
let n = PC count;
let MinPts = 10;
let Eps = 100.0;
let wgs84 = create_geoid("WGS1984");
let myPort = ...

query share("PC", TRUE, Workers);
query share("MinPts", TRUE, Workers);
query share("Eps", TRUE, Workers);
query share("wgs84", TRUE, Workers);
query share("n", TRUE, Workers);

query memclear(); query T dcommand['query memclear()'] consume;
query T dcommand['query meminit(3600)'] consume;

query T dlet["PCm", 'PC feed mconsume'] consume;
query T dlet["PCm_Pos_mtree", 'PCm mcreatemtree[Pos, wgs84]'] consume

let V = T 
  dmap["",  . feed 
    loopjoin[fun(t: TUPLE) PCm_Pos_mtree PCm mdistScan[attr(t, Pos)] head[1] 
      projectextend[N; Dist: distance(attr(t, Pos), .Pos, wgs84)]]
    loopjoin[fun(u: TUPLE) PCm_Pos_mtree PCm mdistRange[attr(u, Pos), 
      attr(u, Dist) + (2 * Eps)] projectextend[; N2: .N]] ]
  partition["", .N2, n] 
  collectB["V", myPort]

let X = V 
  dmap["X", $1 feed extend[Pos2: gk(.Pos)] dbscanM[Pos2, CID0, Eps, MinPts]
    extend[CID: (.CID0 * n) + $2] consume
  ]

query T dcommand['query memclear()'] filter[.Ok] count;

let Wm = X dmap["Wm", . feed filter[.N # .N2] mconsume];
let Wm_Pos_mtree = Wm dmap["Wm_Pos_mtree", . mcreatemtree[Pos, wgs84]];

let Neighbors = X Wm_Pos_mtree Wm 
dmap3["Neighbors", $1 feed filter[.N = .N2] 
  loopsel[fun(t: TUPLE) $2 $3 mdistRange[attr(t, Pos), Eps] 
    projectextend[; P: attr(t, Osm_id), PosP: attr(t, Pos), CID0: attr(t, CID0), 
      CIDp: attr(t, CID), IsCoreP: attr(t, IsCore), Np: attr(t, N), Q: .Osm_id, 
      QPos: .Pos]] 
  , myPort]
  
let NeighborsByP = Neighbors partition["", hashvalue(.P, 999997), 0]
  collect2["NeighborsByP", myPort];
let NeighborsByQ = Neighbors partition["", hashvalue(.Q, 999997), 0]
  collect2["NeighborsByQ", myPort];

let Merge =  NeighborsByQ NeighborsByP 
  dmap2["Merge", . feed {n1} .. feed {n2} itHashJoin[Q_n1, P_n2] 
    filter[.P_n1 = .Q_n2]
    filter[.IsCoreP_n1 and .IsCoreP_n2] 
    project[CIDp_n1, CIDp_n2] 
    rduph[]
    consume, myPort
  ]

let Assignments = NeighborsByQ NeighborsByP 
  dmap2["", . feed {n1} .. feed {n2} itHashJoin[Q_n1, P_n2]
    filter[.P_n1 = .Q_n2]
    filter[.IsCoreP_n1 and not(.IsCoreP_n2)] 
    projectextend[; P: .P_n2, N: .Np_n2,  CID: .CIDp_n1]
    krduph[P]
    consume, myPort
  ]
  partition["", .N, 0]
  collect2["Assignments", myPort]

let MergeM = Merge dsummarize rduph[] createmgraph2[CIDp_n1, CIDp_n2, 1.0];
let MaxCN = X dmap["", . feed max[CID] feed transformstream] dsummarize max[Elem];

let Renumber = MergeM mg2connectedcomponents projectextend[; CID: .CIDp_n1, 
  CIDnew: .CompNo + MaxCN] rduph[] consume

query share("Renumber", TRUE, Workers);

query X Assignments 
  dmap2["",  $1 feed addid filter[.N = .N2] $2 feed krduph[P] {a} 
    itHashJoin[Osm_id, P_a] $1 updatedirect2[TID; CID: .CID_a] count, myPort
  ] 
  getValue tie[. + ..]

query X 
  dmap["", $1 feed addid filter[.N = .N2] Renumber feed krduph[CID] {a} 
    itHashJoin[CID, CID_a] $1 updatedirect2[TID; CID: .CIDnew_a] count
  ] 
  getValue tie[. + ..]