Updated memory example to work with current library code.

Removed unused code.
Fix typos.

Author: CodeReclaimers

examples/memory/nn_evolve.py

@@ -19,12 +19,15 @@
 from neat.stagnation import DefaultStagnation
 
 # num_tests is the number of random examples each network is tested against.
-num_tests = 16
+num_tests = 8
 # N is the length of the test sequence.
-N = 4
+N = 2
 
+num_evaluations = 0
 
 def eval_fitness(genome_id, genome, config):
+    global num_evaluations
+    num_evaluations += 1
     net = nn.create_recurrent_phenotype(genome, config)
 
     error = 0.0
@@ -78,17 +81,15 @@ def run():
     pop.run(eval_genomes, 1000)
 
     # Log statistics.
-    statistics.save_stats(pop.statistics)
-    statistics.save_species_count(pop.statistics)
-    statistics.save_species_fitness(pop.statistics)
+    pop.statistics.save()
 
-    print('Number of evaluations: {0}'.format(pop.total_evaluations))
+    print('Number of genome evaluations: {0}'.format(num_evaluations))
 
     # Show output of the most fit genome against a random input.
     winner = pop.statistics.best_genome()
     print('\nBest genome:\n{!s}'.format(winner))
     print('\nOutput:')
-    winner_net = nn.create_recurrent_phenotype(winner)
+    winner_net = nn.create_recurrent_phenotype(winner, config)
     for n in range(4):
         print('\nRun {0} output:'.format(n))
         seq = [random.choice((0, 1)) for _ in range(N)]

neat/genome.py

@@ -131,7 +131,7 @@ def mutate(self, config):
         """ Mutates this genome. """
 
         # TODO: Make a configuration item to choose whether or not multiple
-        # mutations can happen simulataneously.
+        # mutations can happen simultaneously.
         if random() < config.node_add_prob:
             self.mutate_add_node(config)
 

neat/nn/__init__.py

@@ -1,7 +1,4 @@
-import copy
-
 from neat.six_util import iterkeys, itervalues, iteritems
-#from neat.config import aggregation_function_defs
 
 # TODO: All this directed graph logic should be in a core module.
 
@@ -96,42 +93,6 @@ def feed_forward_layers(inputs, outputs, connections):
     return layers
 
 
-# def find_evaluation_order(inputs, outputs, connections):
-#     '''
-#     Collect the layers whose members can be evaluated in parallel in a feed-forward network.
-#     :param inputs: list of the input identifiers
-#     :param outputs: list of the output node identifiers
-#     :param connections: list of (input, output) connections in the network.
-#     NOTE: It is assumed that the input identifier set and the node identifier set are disjoint.
-#     By convention, the output node ids are always the same as the output index.
-#
-#     Returns a list of layers, with each layer consisting of a set of identifiers.
-#     '''
-#
-#     layers = [set(outputs)]
-#     S = set(outputs)
-#     while 1:
-#         # Find candidate nodes C for the previous layer.  These nodes
-#         # should connect a node in S to a node not in S.
-#         T = set(a for (a, b) in connections if b in S and a not in S)
-#         #T = set()
-#         #for n in C:
-#         #    if all(a in S for (a, b) in connections if b == n):
-#         #        T.add(n)
-#
-#         if not T:
-#             break
-#
-#         layer_nodes = set(x for x in T if x not in inputs)
-#         if not layer_nodes:
-#             break
-#
-#         layers.append(layer_nodes)
-#         S = S.union(T)
-#
-#     return layers[::-1]
-
-
 class FeedForwardNetwork(object):
     def __init__(self, max_node, inputs, outputs, node_evals):
         self.node_evals = node_evals

neat/reporting.py

@@ -121,7 +121,7 @@ def complete_extinction(self):
 
     def found_solution(self, config, generation, best):
         print('\nBest individual in generation {0} meets fitness threshold - complexity: {1!r}'.format(
-            self.generation, best.size(config)))
+            self.generation, best.size()))
 
     def species_stagnant(self, sid, species):
         print("\nSpecies {0} with {1} members is stagnated: removing it".format(sid, len(species.members)))