diff histogram.r @ 7:2e2d92b2ae38 draft

Uploaded

--- a/histogram.r	Thu Apr 17 13:22:34 2014 -0400
+++ b/histogram.r	Thu Apr 17 17:35:24 2014 -0400
@@ -4,31 +4,44 @@
     l <- list()
 
     # loop through all columns
+    m <- list()
     for (key in names(columns)) {
         # load column data
         column <- as.numeric(columns[key])
         column_data <- sapply( table[column], as.numeric )
 
+        # collect vectors in list
+        m <- append(m, list(column_data))
+    }
+    
+    # get min/max boundaries
+    max_value <- max(unlist(m))
+    min_value <- min(unlist(m))
+    
+    # fix range and bins
+    bin_seq = seq(min_value, max_value, by=10)
+
+    # add as first column
+    l <- append(l, list(bin_seq[2: length(bin_seq)]))
+    
+    # loop through all columns
+    for (key in seq(m)) {
+        # load column data
+        column_data <- m[[key]]
+        
         # create hist data
-        hist_data <- hist(column_data, plot=FALSE)
+        hist_data <- hist(column_data, breaks=bin_seq, plot=FALSE)
         
         # normalize densities
         count_sum <- sum(hist_data$counts)
         if (count_sum > 0) {
-            hist_data$counts=hist_data$counts/count_sum
+            hist_data$counts = hist_data$counts / count_sum
         }
 
         # collect vectors in list
-        l <- append(l, list(hist_data$breaks[2: length(hist_data$breaks)]))
         l <- append(l, list(hist_data$counts))
     }
     
-    # make sure length is fine
-    n <- max(sapply(l, length))
-    ll <- lapply(l, function(X) {
-        c(as.character(X), rep('2147483647', times = n - length(X)))
-    })
-    l <- do.call(cbind, ll)
 
     # return
     return (l)