diff --git a/genetics/simulation/discrete.py b/genetics/simulation/discrete.py
index 555a5b9..1cc5a13 100644
--- a/genetics/simulation/discrete.py
+++ b/genetics/simulation/discrete.py
@@ -1,9 +1,10 @@
 from collections.abc import Sequence
 
+
 def pairwise(iterable):
     '''
     Given an iterable, yield the items in it in pairs. For instance:
-    
+
         list(pairwise([1,2,3,4])) == [(1,2), (3,4)]
     '''
     x = iter(iterable)
@@ -11,9 +12,10 @@ def pairwise(iterable):
 
 
 class DiscreteSimulation:
+
     def __init__(self, population_size, mutation_mask, crossover_mask,
-            selection_function, elite_size,
-            initial_generator, fitness_function):
+                 selection_function, elite_size,
+                 initial_generator, fitness_function):
         self.population_size = population_size
         self.mutation_mask = mutation_mask
         self.crossover_mask = crossover_mask
@@ -45,7 +47,7 @@ def initial_population(self):
         Create an initial populaton
         '''
         return [self.initial_generator() for _ in
-                    range(self.population_size)]
+                range(self.population_size)]
 
     def step_generator(self, population):
         '''
@@ -53,8 +55,8 @@ def step_generator(self, population):
         population members
         '''
         # Score and sort population
-        scored_population = sorted(self.find_scores(population), reverse=True,
-            key=lambda member: member[0])
+        scored_population = [m[1] for m in sorted(self.find_scores(population), reverse=True,
+                                                  key=lambda member: member[0])]
 
         # Yield the elite elements
         yield from scored_population[:self.elite_size]
@@ -72,4 +74,3 @@ def step(self, population):
         list.
         '''
         return list(self.step_generator(population))
-
diff --git a/main.py b/main.py
new file mode 100644
index 0000000..44d15d3
--- /dev/null
+++ b/main.py
@@ -0,0 +1,58 @@
+
+import string
+import random
+
+import genetics
+
+letters = string.ascii_uppercase + string.ascii_lowercase + string.punctuation + ' '
+solution = 'Hello World!'
+
+
+class LetterComponent(genetics.DNAComponent):
+
+    def mutate_value(self):
+        return random.choice(letters)
+
+
+class WordDNA(genetics.arrayed_segment(len(solution), LetterComponent)):
+
+    def score(self):
+        score = sum(comp.value == letter for comp, letter in zip(self, solution))
+        return score
+
+    def __str__(self):
+        return ''.join(comp.value for comp in self)
+
+    def __gt__(self, other):
+        return self.score() > other.score()
+
+sim = genetics.DiscreteSimulation(
+    population_size=100,
+    mutation_mask=genetics.mutation_rate(0.05),  # Mutate at a 5% rate
+    crossover_mask=genetics.two_point_crossover,
+    selection_function=genetics.tournament(2),
+    elite_size=2,
+    initial_generator=WordDNA,
+    fitness_function=WordDNA.score)
+
+
+def dna_stats(population):
+    '''Best DNA, best score, average score'''
+    best_dna = max(population)
+    best_score = best_dna.score
+    average_score = sum(member.score() for member in population) / len(population)
+
+    return best_dna, best_score, average_score
+
+
+population = sim.initial_population()
+
+while True:
+    best, best_score, average_score = dna_stats(population)
+
+    print('{} | Average score: {}'.format(str(best), average_score))
+
+    if str(best) == solution:
+        break
+
+    population = sim.step(population)