initial import of material for public archive into git

We're creating a fresh archive because the history for our old chapter includes
API keys, data files, and other material we can't share.

code/prediction/utils.R

@@ -0,0 +1,13 @@
+
+# Use this to check for underpopulated cells
+gen.counts <- function(df, c.var){
+    tapply(df[,"eid"], c.var, function(x) length(unique(x)))
+}
+
+# use this to remove underpopulated cells
+restrict <- function(df, c.var, c.min){
+    var.counts <- gen.counts(df, c.var)
+    out.df <- df[c.var %in% names(var.counts[var.counts >
+                                                   c.min]),] 
+    return(out.df)
+}