Worked on synthetic data recovery so we can tell how high the actual

infector is ranked among all potential parents. Cleaned up code for the
predicting victims benchmarking test.

1 files changed, 40 insertions, 0 deletions

diff --git a/R Scripts/find-parents.R b/R Scripts/find-parents.R
new file mode 100644
index 0000000..3ec8809
--- /dev/null
+++ b/R Scripts/find-parents.R
@@ -0,0 +1,40 @@
+# library(igraph)
+# setwd("~/Documents/Cascade Project/")
+# load('Results/hyper-lcc.RData')
+# load('Results/dag_dat_vics.RData')
+# source('criminal_cascades/R Scripts/temporal.R')
+# source('criminal_cascades/R Scripts/structural.R')
+
+##### Initialize parameters based on what ml2 found
+alpha = 0.061
+delta = 0.082
+
+##### Get weights
+edges = dag_dat_test[!is.na(dag_dat_test$t2),]
+
+dt = edges$t2 - edges$t1
+p_t = exp(-alpha*dt) * (exp(alpha)-1)
+p_s = structural(delta, edges$dist)
+p = p_s * p_t
+p_tilde = 1 - p_s + p_s * exp(-alpha*dt)
+weights = p/p_tilde
+edges$weight = weights
+
+##### Find most likely parents
+parents = data.frame(vic=0,Npars=0,par_rank=0)
+vics = setdiff(vic_ids,seeds)
+for (u in vics){
+  u_parents = edges[edges$to==u,]
+  u_parents = u_parents[order(u_parents$weight,decreasing=T),]
+  Nparents = dim(u_parents)[1]
+  infector = V(g)$infector[u]
+  infectorID = which(u_parents$from==infector)
+  parents[which(vics==u),] = c(u, Nparents, infectorID)
+}
+
+##### Get some summary statistics on how well 
+median(parents$par_rank[parents$Npars>9])
+median(parents$par_rank[parents$Npars>99])
+
+
+