diff --git a/tools/prepare_corpus_figures.py b/tools/prepare_corpus_figures.py
index 687dbe3..26cd726 100755
--- a/tools/prepare_corpus_figures.py
+++ b/tools/prepare_corpus_figures.py
@@ -4,6 +4,7 @@
 from os import listdir
 import numpy as np
 import matplotlib.pyplot as plt
+import sys
 
 
 input_dir = 'stats'
@@ -37,9 +38,9 @@ with open(output_dir+'/stats_table.tex', 'w') as stats_table:
     stats_table.write(r'Corpus name & Total sentences & Non-empty & Unique\\'+'\n')
     stats_table.write(r'\hline\hline'+'\n')
     for corpus in corpora:
-        non_empty_percentage = float(100*corpus["total"] - corpus["empty"])/corpus["total"]
+        non_empty_percentage = float(100*(corpus["total"] - corpus["empty"]))/corpus["total"]
         unique_percentage = float(100*corpus["unique"])/corpus["total"]
-        stats_table.write("%s & %d & %d (%.2f%%) & %d (%.2f%%) \\\\\n" % (corpus["name"], corpus["total"], corpus["total"] - corpus["empty"], non_empty_percentage, corpus["unique"], unique_percentage))
+        stats_table.write("%s & %d & %d (%.2f\%%) & %d (%.2f\%%) \\\\\n" % (corpus["name"], corpus["total"], corpus["total"] - corpus["empty"], non_empty_percentage, corpus["unique"], unique_percentage))
         
     stats_table.write(r'\hline'+'\n')
     stats_table.write(r'\end{tabular}'+'\n')
@@ -59,7 +60,7 @@ for corpus in corpora:
         freq_table.write(r'Occurences & Sentence\\'+'\n')
         freq_table.write(r'\hline\hline'+'\n')
         for data in corpus["most_frequent"]:
-            freq_table.write("%d & %s\n" % data)            
+            freq_table.write("%d & %s\\\\\n" % data)            
         freq_table.write(r'\hline'+'\n')
         freq_table.write(r'\end{tabular}'+'\n')
         freq_table.write(r'\caption{Most frequent sentences in the corpus '+corpus["name"]+'}\n')
@@ -69,23 +70,21 @@ for corpus in corpora:
 
 # plot
 
-N = 5
-menMeans   = (20, 35, 30, 35, 27)
-womenMeans = (25, 32, 34, 20, 25)
-menStd     = (2, 3, 4, 1, 2)
-womenStd   = (3, 5, 2, 3, 3)
+N = len(corpora)
+uniques = [float(100*corpus["unique"]) / corpus["total"] for corpus in corpora]
+repeated = [float(100*(corpus["total"] - corpus["unique"] - corpus["empty"])) / corpus["total"] for corpus in corpora]
+empty = [float(100*corpus["empty"]) / corpus["total"] for corpus in corpora]
+
 ind = np.arange(N)    # the x locations for the groups
 width = 0.35       # the width of the bars: can also be len(x) sequence
 
-p1 = plt.bar(ind, menMeans,   width, color='r', yerr=womenStd)
-p2 = plt.bar(ind, womenMeans, width, color='y',
-             bottom=menMeans, yerr=menStd)
+p1 = plt.bar(ind, uniques,   width, color='#009900')
+p2 = plt.bar(ind, repeated, width, color='#99FF66', bottom=uniques)
+p3 = plt.bar(ind, empty, width, color='#999966', bottom=[sum(x) for x in zip(repeated,uniques)])
 
-plt.ylabel('Scores')
-plt.title('Scores by group and gender')
-plt.xticks(ind+width/2., ('G1', 'G2', 'G3', 'G4', 'G5') )
-plt.yticks(np.arange(0,81,10))
-plt.legend( (p1[0], p2[0]), ('Men', 'Women') )
+plt.xticks(ind+width/2., [corpus["name"] for corpus in corpora] )
+plt.yticks(np.arange(0,101,10))
+plt.legend( (p1[0], p2[0], p3[0]), ('unique', 'repeated', 'empty') )
 
 
-plt.savefig('bar_graph.eps', format='eps')
+plt.savefig(output_dir+'/bar_graph.eps', format='eps')