1 files changed, 27 insertions, 0 deletions
diff --git a/R Scripts/-recover-data.R b/R Scripts/-recover-data.R
new file mode 100755
index 0000000..b34ffc6
--- /dev/null
+++ b/R Scripts/-recover-data.R
@@ -0,0 +1,27 @@
+library(igraph)
+setwd("/Users/Ben/Documents/Harvard/Fall 2014/CS 284r Social Data Mining/Cascade Project/")
+
+el = read.csv('Data/dag.csv')
+lcc = induced.subgraph(d,which(clusters(d)$membership==which.max(clusters(d)$csize)))
+vic_ids = which(V(lcc)$vic==TRUE)
+
+from = vic_ids[el$from]
+to = vic_ids[el$to]
+
+t1 = as.Date(V(lcc)$vic_date[from],format='%m/%d/%y')
+t2 = as.Date(V(lcc)$vic_date[to],format='%m/%d/%y')
+
+uf = unique(from)
+dist = rep(0,length(from))
+for (i in 1:length(uf)){
+  if (i%%1000==0) print(i)
+  f = uf[i]
+  fi = which(from==f)
+  ds = as.numeric(shortest.paths(lcc,v=f,to=to[fi]))
+  dist[fi] = ds
+}
+
+dag_dat = data.frame(from=el$from,to=el$to,dist,t1,t2)
+
+save(dag_dat,file='Data/dag_dat.RData')
+write.csv(dag_dat,'Data/dag_dat.csv')