added my R scripts

1 files changed, 50 insertions, 0 deletions

diff --git a/R Scripts/-generate-dag-dat-sim.R b/R Scripts/-generate-dag-dat-sim.R
new file mode 100755
index 0000000..a6d115d
--- /dev/null
+++ b/R Scripts/-generate-dag-dat-sim.R
@@ -0,0 +1,50 @@
+library(igraph)
+setwd("/Users/Ben/Documents/Harvard/Fall 2014/CS 284r Social Data Mining/Cascade Project/")
+load('Data/lcc_sim2a.RData')
+
+# d = remove.edge.attribute(person,'weight')
+# lcc = induced.subgraph(d,which(clusters(d)$membership==which.max(clusters(d)$csize)))
+# vic_ids = which(V(lcc)$vic==TRUE)
+# dag = graph.empty(vcount(lcc))
+# dag = set.edge.attribute(dag,'weight',value=0)
+
+lcc = lcc.sim
+vic_ids = vic_ids.sim
+ei = 1
+
+dag_dat = matrix(0,253096,5)
+for (1 in 1:length(vic_ids)){
+  if (i %% 100)==0)  print(which(vic_ids==u))
+
+  u = vic_ids[i]
+  nbhd = unlist(neighborhood(lcc, nodes=u, order=3)) # get nodes within neighborhood
+  nbhd = intersect(vic_ids,nbhd) # only want victim nodes
+  nbhd = setdiff(nbhd,u) # don't want to include u in the neighborhood
+  
+  tu = as.numeric(V(lcc)$vic_date[u])
+  tvs = as.numeric(V(lcc)$vic_date[nbhd])
+  Es = tu<tvs
+  tvs = tvs[Es]
+
+  if (sum(Es)>0){
+    nbhd = nbhd[Es]
+    dists = as.numeric(shortest.paths(lcc,u,nbhd))  
+    
+    for (j in 1:sum(Es)){
+      v = nbhd[j]
+      d = dists[j]
+      tv = tvs[j]
+#       dag_dat[ei,] = c(u,v,d,tu,tv)
+      dag_dat = rbind(dag_dat,c(u,v,d,tu,tv))
+#       f = time(tu,tv)
+#       h = structural(d)
+#       weight[ei] = f*h
+      ei = ei+1
+    }
+  }
+}
+
+dag_dat = dag_dat[rowSums(dag_dat)>0,]
+dag_dat = as.data.frame(dag_dat)
+colnames(dag_dat) = c('from','to','dist','t1','t2')
+# save(dag_dat,file='Data/dag_dat_sim2a.RData')