Still more refactoring.

Moved genome-related configuration from the Config object to DefaultGenomeConfig.
Config now only handles generic high-level configuration explicitly.  Component-specific configuration is handled by the user-specified types.
Updated memory example so that it runs.
Pass around configuration object as necessary (this needs to be cleaned up later, it's too cumbersome now).

Author: CodeReclaimers

examples/memory/nn_config

@@ -4,51 +4,53 @@
 # tasks in the NEAT algorithm.  If you use a non-default class here, you
 # must register it with your Config instance before loading the config file.
 [Types]
-stagnation_type      = DefaultStagnation
-reproduction_type    = DefaultReproduction
+genome_type       = DefaultGenome
+reproduction_type = DefaultReproduction
+stagnation_type   = DefaultStagnation
 
-[phenotype]
-input_nodes          = 2
-hidden_nodes         = 0
-output_nodes         = 1
-initial_connection   = partial 0.5
-max_weight           = 30
-min_weight           = -30
-feedforward          = 0
-activation_functions = clamped sigmoid tanh my_sinc_function
-aggregation_functions = sum
-weight_stdev         = 1.0
+# The `NEAT` section specifies parameters particular to the NEAT algorithm
+# or the experiment itself.
+[NEAT]
+pop_size              = 150
+max_fitness_threshold = -0.05
+reset_on_extinction   = 0
 
-[genetic]
-pop_size                = 150
-max_fitness_threshold   = -0.05
-prob_add_conn           = 0.5
-prob_add_node           = 0.5
-prob_delete_conn        = 0.25
-prob_delete_node        = 0.25
-prob_mutate_bias        = 0.8
-bias_mutation_power     = 0.5
-prob_mutate_response    = 0.8
-response_mutation_power = 0.5
-prob_mutate_weight      = 0.8
-prob_replace_weight     = 0.1
-weight_mutation_power   = 0.5
-prob_mutate_activation  = 0.002
-prob_mutate_aggregation = 0.0
-prob_toggle_link        = 0.01
-reset_on_extinction     = 1
-
-[genotype compatibility]
+[DefaultGenome]
+num_inputs              = 2
+num_hidden              = 0
+num_outputs             = 1
+initial_connection      = partial 0.5
+feed_forward            = 0
+activation              = clamped sigmoid tanh my_sinc_function
+aggregation             = sum
+conn_add_prob           = 0.5
+conn_delete_prob        = 0.25
+node_add_prob           = 0.5
+node_delete_prob        = 0.25
+bias_mutate_prob        = 0.8
+bias_mutate_power       = 0.5
+response_mutate_prob    = 0.8
+response_mutate_power   = 0.5
+weight_max              = 30
+weight_min              = -30
+weight_mean             = 0.0
+weight_stdev            = 1.0
+weight_mutate_prob      = 0.8
+weight_replace_prob     = 0.1
+weight_mutate_power     = 0.5
+activation_mutate_prob  = 0.002
+aggregation_mutate_prob = 0.0
+link_toggle_prob        = 0.01
 compatibility_threshold = 3.0
 excess_coefficient      = 1.0
 disjoint_coefficient    = 1.0
 weight_coefficient      = 0.5
 
 [DefaultStagnation]
-species_fitness_func = median
-max_stagnation       = 10
+species_fitness = median
+max_stagnation  = 10
 
 [DefaultReproduction]
-elitism              = 2
-survival_threshold   = 0.2
+elitism            = 2
+survival_threshold = 0.2
 

examples/memory/nn_evolve.py

@@ -12,16 +12,17 @@
 import os
 import random
 
-from neat import nn, population, statistics, parallel, activation_functions
+from neat.config import Config
+from neat import nn, population, statistics, parallel
 
 # num_tests is the number of random examples each network is tested against.
 num_tests = 16
 # N is the length of the test sequence.
 N = 4
 
 
-def eval_fitness(genome_id, genome):
-    net = nn.create_recurrent_phenotype(genome)
+def eval_fitness(genome_id, genome, config):
+    net = nn.create_recurrent_phenotype(genome, config)
 
     error = 0.0
     for _ in range(num_tests):
@@ -43,25 +44,30 @@ def eval_fitness(genome_id, genome):
     return -(error / (N * num_tests)) ** 0.5
 
 
-def eval_genomes(genomes):
+def eval_genomes(genomes, config):
     for genome_id, genome in genomes:
-        genome.fitness = eval_fitness(genome_id, genome)
+        genome.fitness = eval_fitness(genome_id, genome, config)
 
 
 # Demonstration of how to add your own custom activation function.
 def sinc(x):
     return 1.0 if x == 0 else math.sin(x) / x
 
-# This sinc function will be available if my_sinc_function is included in the
-# config file activation_functions option under the pheotype section.
-# Note that sinc is not necessarily useful for this example, it was chosen
-# arbitrarily just to demonstrate adding a custom activation function.
-activation_functions.add('my_sinc_function', sinc)
-
 
 def run():
+
+    # Determine path to configuration file.
     local_dir = os.path.dirname(__file__)
-    pop = population.Population(os.path.join(local_dir, 'nn_config'))
+    config_path = os.path.join(local_dir, 'nn_config')
+    config = Config(config_path)
+
+    # This sinc function will be available if my_sinc_function is included in the
+    # config file activation_functions option under the pheotype section.
+    # Note that sinc is not necessarily useful for this example, it was chosen
+    # arbitrarily just to demonstrate adding a custom activation function.
+    config.genome_config.activation_defs.add('my_sinc_function', sinc)
+
+    pop = population.Population(config)
     #pe = parallel.ParallelEvaluator(4, eval_fitness)
     #pop.run(pe.evaluate, 1000)
     pop.run(eval_genomes, 1000)