adapt validation to r-util (split), add new r plots

3 files changed, 5 insertions, 210 deletions

diff --git a/lib/merge.rb b/lib/merge.rb
index f30a3c1..bc6e1a7 100644
--- a/lib/merge.rb
+++ b/lib/merge.rb
@@ -31,6 +31,11 @@ module Lib
       return merge_count(object)>1
     end
     
+    def self.merge_count( object )
+      @@merge_count[object] = 1 if @@merge_count[object]==nil
+      return @@merge_count[object] 
+    end
+    
     def self.merge_objects( object1, object2 )
       raise "classes not equal : "+object1.class.to_s+" != "+object2.class.to_s if object1.class != object2.class
       object_class = object1.class
@@ -137,11 +142,6 @@ module Lib
       {:value => value, :variance => variance }
     end 
     
-    def self.merge_count( object )
-      @@merge_count[object] = 1 if @@merge_count[object]==nil
-      return @@merge_count[object] 
-    end
-    
     def self.set_merge_count(object, merge_count)
       @@merge_count[object] = merge_count
     end
diff --git a/lib/r-util.rb b/lib/r-util.rb
deleted file mode 100644
index 0d58389..0000000
--- a/lib/r-util.rb
+++ /dev/null
@@ -1,82 +0,0 @@
-# pending: package dir hack ---------
-# CONFIG[:base_dir] = "/home/<user>/opentox-ruby/www"
-# PACKAGE_DIR = "/home/<user>/opentox-ruby/r-packages"
-package_dir = CONFIG[:base_dir].split("/")
-package_dir[-1] = "r-packages"
-package_dir = package_dir.join("/")
-PACKAGE_DIR = package_dir
-
-
-
-module Lib
-  
-  module RUtil
-    
-    def self.dataset_to_dataframe( dataset )
-      LOGGER.debug "convert dataset to dataframe #{dataset.uri}"
-      all_features = []
-      dataset.features.each do |f|
-        feat_name = "feature_#{f[0].split("/")[-1]}"
-        LOGGER.debug "- adding feature: #{feat_name}"
-        feat = OpenTox::Feature.find(f[0])
-        nominal = feat.metadata[RDF.type].to_a.flatten.include?(OT.NominalFeature)
-        values = []
-        dataset.compounds.each do |c|
-          val = dataset.data_entries[c][f[0]]
-          raise "not yet implemented" if val!=nil && val.size>1
-          v = val==nil ? "" : val[0].to_s
-          v = "NA" if v.size()==0
-          values << v
-        end
-        all_features << feat_name
-        @@r.assign feat_name,values
-        @@r.eval "#{feat_name} <- as.numeric(#{feat_name})" unless nominal
-      end
-      df_name = "df_#{dataset.uri.split("/")[-1].split("?")[0]}"
-      cmd =  "#{df_name} <- data.frame(#{all_features.join(",")})"
-      @@r.eval cmd
-      #@@r.eval "head(#{df_name})"
-      df_name
-    end
-    
-    def self.stratified_split( dataframe, pct=0.3, seed=42 )
-      @@r.eval "set.seed(#{seed})"
-      @@r.eval "split <- stratified_split(#{dataframe}, ratio=#{pct})"
-      split = @@r.pull 'split'
-      split.collect{|s| s.to_i}
-    end
-    
-    def self.package_installed?( package )
-      @@r.eval ".libPaths(\"#{PACKAGE_DIR}\")"
-      p = @@r.pull "installed.packages()[,1]"
-      p.include?(package) 
-    end
-    
-    def self.install_packages( package )
-      unless package_installed? package
-        @@r.eval "install.packages(\"#{package}\", repos=\"http://cran.r-project.org\", dependencies=T, lib=\"#{PACKAGE_DIR}\")"
-      end
-    end
-    
-    def self.library( package )
-      install_packages( package )
-      @@r.eval "library(\"#{package}\")"
-    end
-    
-    def self.init_r
-      @@r = RinRuby.new(true,false) unless defined?(@@r) and @@r
-      library("sampling")
-      library("gam")
-      @@r.eval "source(\"#{PACKAGE_DIR}/stratification.R\")"
-    end
-    
-    def self.quit_r
-      begin
-        @@r.quit
-        @@r = nil
-      rescue
-      end
-    end
-    
-  end
-end
diff --git a/lib/stratification.R b/lib/stratification.R
deleted file mode 100644
index 9aa8d1f..0000000
--- a/lib/stratification.R
+++ /dev/null
@@ -1,123 +0,0 @@
-library("sampling")
-library("gam")
-
-nominal_to_binary <- function( orig_data )
-{
-  data = as.data.frame( orig_data )
-  result = NULL
-  for (i in 1:ncol(data))
-  {
-     #print(i)
-     if (is.numeric( data[,i] ) )
-     {
-        if (is.null(result))
-          result = data.frame(data[,i])
-        else
-          result = data.frame(result, data[,i])
-        colnames(result)[ncol(result)] <- colnames(data)[i]
-     }
-     else
-     {
-        vals = unique(data[,i])
-        for (j in 1:length(vals))
-        {
-           #print(j)
-           bins = c()
-           for (k in 1:nrow(data))
-           {
-              if(data[,i][k] == vals[j])
-                bins = c(bins,1)
-              else
-                bins = c(bins,0)
-           }
-           #print(bins)
-           if (is.null(result))
-             result = data.frame(bins)
-           else
-             result = data.frame(result, bins)
-           colnames(result)[ncol(result)] <- paste(colnames(data)[i],"is",vals[j])
-           if (length(vals)==2) break
-        }
-     }
-  }
-  result
-}
-
-process_data <- function( data )
-{
-  if (!is.numeric(data))
-    data.num = nominal_to_binary(data)
-  else
-    data.num = data
-  if(any(is.na(data.num)))
-  	data.repl = na.gam.replace(data.num)
-  else
-  	data.repl = data.num
-  data.repl
-}
-
-stratified_split <- function( data, ratio=0.3 )
-{
-    data.processed = as.matrix(process_data( data ))
-    pik = rep(ratio,times=nrow(data.processed))
-    data.strat = cbind(pik,data.processed)
-    samplecube(data.strat,pik,order=2,comment=F)
-}
-
-stratified_k_fold_split <- function( data, num_folds=10 )
-{
-  print(paste(num_folds,"-fold-split, data-size",nrow(data)))
-  data.processed = as.matrix(process_data( data ))
-  folds = rep(0, times=nrow(data))
-  for (i in 1:(num_folds-1))
-  {
-    prop = 1/(num_folds-(i-1))
-    print(paste("fold",i,"/",num_folds," prop",prop))
-    pik = rep(prop,times=nrow(data))
-    for (j in 1:nrow(data))
-      if(folds[j]!=0)
-        pik[j]=0
-    data.strat = cbind(pik,data.processed)
-    s<-samplecube(data.strat,pik,order=2,comment=F)
-    print(paste("fold size: ",sum(s)))
-    for (j in 1:nrow(data))
-      if (s[j] == 1)
-        folds[j]=i
-  }
-  for (j in 1:nrow(data))
-    if (folds[j] == 0)
-      folds[j]=num_folds
-  folds
-}
-
-plot_split <- function( data, split )
-{
-  data.processed = process_data( data )
-	data.pca <- prcomp(data.processed, scale=TRUE)
-  data.2d =as.data.frame(data.pca$x)[1:2]
-  plot( NULL,
-        xlim = extendrange(data.2d[,1]), ylim = extendrange(data.2d[,2]), 
-        xlab = "pc 1", ylab = "pc 2")
-  for (j in 0:max(split))
-  {
-    set = c()
-    for (i in 1:nrow(data))
-      if (split[i] == j)
-        set = c(set,i)
-    points(data.2d[set,], pch = 2, col=(j+1))
-  }
-}
-
-#a<-matrix(rnorm(100, mean=50,  sd=4), ncol=5)
-#b<-matrix(rnorm(5000, mean=0, sd=10), ncol=5)
-#data<-rbind(a,b)
-#c<-matrix(rnorm(50, mean=-50, sd=2), ncol=5)
-#data<-rbind(data,c)
-#data=iris
-#split = stratified_k_fold_split(data, num_folds=3)
-#split = stratified_split(data, ratio=0.3)
-#plot_split(data,split)
-
-
-
-