def update_stats(individuals, end):
"""
Update all stats in the stats dictionary.
:param individuals: A population of individuals.
:param end: Boolean flag for indicating the end of an evolutionary run.
:return: Nothing.
"""
if not end:
# Time Stats
trackers.time_list.append(time() - stats['time_adjust'])
stats['time_taken'] = trackers.time_list[-1] - \
trackers.time_list[-2]
stats['total_time'] = trackers.time_list[-1] - \
trackers.time_list[0]
# Population Stats
stats['total_inds'] = params['POPULATION_SIZE'] * (stats['gen'] + 1)
stats['runtime_error'] = len(trackers.runtime_error_cache)
if params['CACHE']:
stats['unique_inds'] = len(trackers.unique_ind_tracker)
stats['unused_search'] = 100 - stats['unique_inds'] / \
stats['total_inds'] * 100
# Genome Stats
genome_lengths = [len(i.genome) for i in individuals]
stats['max_genome_length'] = np.nanmax(genome_lengths)
stats['ave_genome_length'] = np.nanmean(genome_lengths)
stats['min_genome_length'] = np.nanmin(genome_lengths)
# Used Codon Stats
codons = [i.used_codons for i in individuals]
stats['max_used_codons'] = np.nanmax(codons)
stats['ave_used_codons'] = np.nanmean(codons)
stats['min_used_codons'] = np.nanmin(codons)
# Tree Depth Stats
depths = [i.depth for i in individuals]
stats['max_tree_depth'] = np.nanmax(depths)
stats['ave_tree_depth'] = np.nanmean(depths)
stats['min_tree_depth'] = np.nanmin(depths)
# Tree Node Stats
nodes = [i.nodes for i in individuals]
stats['max_tree_nodes'] = np.nanmax(nodes)
stats['ave_tree_nodes'] = np.nanmean(nodes)
stats['min_tree_nodes'] = np.nanmin(nodes)
# Not using this for current research, don't need to waste time calculating
# Novelty Stats
# n = novelty()
# total_geno = 0
# total_levi = 0
# total_ast = 0
# total_deriv = 0
# total_output = 0
# ind_size = len(individuals)
# for ind in individuals:
# ind.novelty = np.NaN
# total_output += n.evaluate_distance(ind, "output")
# ind.novelty = np.NaN
# total_geno += n.evaluate_distance(ind, "genotype")
# ind.novelty = np.NaN
# total_levi += n.evaluate_distance(ind, "levi")
# ind.novelty = np.NaN
# total_ast += n.evaluate_distance(ind, "ast")
# ind.novelty = np.NaN
# total_deriv += n.evaluate_distance(ind, "derivation")
# ind.novelty = np.NaN
#
# stats["novelty_output"] = total_output / ind_size
# stats["novelty_genotype"] = total_geno / ind_size
# stats["novelty_phenotype"] = total_levi / ind_size
# stats["novelty_ast"] = total_ast / ind_size
# stats["novelty_derivation"] = total_deriv / ind_size
# import datetime
# start = datetime.datetime.now()
if params["NOVELTY"]:
if end:
import random
from representation.individual import Individual
# Total Novelty Stats
n = novelty()
total_output = 0
total_geno = 0
total_levi = 0
total_ast = 0
total_deriv = 0
cache_size = len(trackers.cache)
individual_dics = list(trackers.cache.values())
sample_size = min(max(1000, cache_size // 10), 10000)
sample_size = min(cache_size, sample_size)
ind_sample = random.sample(individual_dics, sample_size)
derivation_novelties = []
output_novelties = []
for ind_dic in ind_sample:
ind = Individual(ind_dic["genome"], None, False)
ind.fitness = ind_dic["fitness"]
ind.phenotype = ind_dic["phenotype"]
ind.AST = ind_dic["AST"]
ind.derivation = ind_dic["derivation"]
ind.test_cases = ind_dic["output_cases"]
ind.novelty = np.NaN
out_distance = n.evaluate_distance(ind, "output")
output_novelties.append(out_distance)
total_output += out_distance
ind.novelty = np.NaN
total_geno += n.evaluate_distance(ind, "genotype")
ind.novelty = np.NaN
total_levi += n.evaluate_distance(ind, "levi")
ind.novelty = np.NaN
total_ast += n.evaluate_distance(ind, "ast")
ind.novelty = np.NaN
der_distance = n.evaluate_distance(ind, "derivation")
derivation_novelties.append(der_distance)
total_deriv += der_distance
ind.novelty = np.NaN
stats["nov_output_total"] = total_output / sample_size
stats["nov_genotype_total"] = total_geno / sample_size
stats["nov_phenotype_total"] = total_levi / sample_size
stats["nov_ast_total"] = total_ast / sample_size
stats["nov_derivation_total"] = total_deriv / sample_size
# Change the last generation stats in the stats list too
final_stats = trackers.stats_list[-1]
final_stats["nov_output_total"] = total_output / sample_size
final_stats["nov_genotype_total"] = total_geno / sample_size
final_stats["nov_phenotype_total"] = total_levi / sample_size
final_stats["nov_ast_total"] = total_ast / sample_size
final_stats["nov_derivation_total"] = total_deriv / sample_size
# print("Novelty calculation time: " + str(datetime.datetime.now() - start))
if not hasattr(params['FITNESS_FUNCTION'], 'multi_objective'):
# Fitness Stats
fitnesses = [i.fitness for i in individuals]
stats['ave_fitness'] = np.nanmean(fitnesses, axis=0)
stats['best_fitness'] = trackers.best_ever.fitness
def load_population(target):
"""
Given a target folder, read all files in the folder and load/parse
solutions found in each file.
:param target: A target folder stored in the "seeds" folder.
:return: A list of all parsed individuals stored in the target folder.
"""
# Set path for seeds folder
path_1 = path.join(getcwd(), "..", "seeds")
if not path.isdir(path_1):
# Seeds folder does not exist.
s = "scripts.seed_PonyGE2.load_population\n" \
"Error: `seeds` folder does not exist in root directory."
raise Exception(s)
path_2 = path.join(path_1, target)
if not path.isdir(path_2):
# Target folder does not exist.
s = "scripts.seed_PonyGE2.load_population\n" \
"Error: target folder " + target + \
" does not exist in seeds directory."
raise Exception(s)
# Get list of all target individuals in the target folder.
target_inds = [i for i in listdir(path_2) if i.endswith(".txt")]
# Initialize empty list for seed individuals.
seed_inds = []
for ind in target_inds:
# Loop over all target individuals.
# Get full file path.
file_name = path.join(path_2, ind)
# Initialise None data for ind info.
genotype, phenotype = None, None
# Open file.
with open(file_name, "r") as f:
# Read file.
raw_content = f.read()
# Read file.
content = raw_content.split("\n")
# Check if genotype is already saved in file.
if "Genotype:" in content:
# Get index location of genotype.
gen_idx = content.index("Genotype:") + 1
# Get the genotype.
try:
genotype = eval(content[gen_idx])
except:
s = "scripts.seed_PonyGE2.load_population\n" \
"Error: Genotype from file " + file_name + \
" not recognized: " + content[gen_idx]
raise Exception(s)
# Check if phenotype (target string) is already saved in file.
if "Phenotype:" in content:
# Get index location of genotype.
phen_idx = content.index("Phenotype:") + 1
# Get the phenotype.
phenotype = content[phen_idx]
# TODO: Current phenotype is read in as single-line only. Split is performed on "\n", meaning phenotypes that span multiple lines will not be parsed correctly. This must be fixed in later editions.
elif "Genotype:" not in content:
# There is no explicit genotype or phenotype in the target
# file, read in entire file as phenotype.
phenotype = raw_content
if genotype:
# Generate individual from genome.
ind = Individual(genotype, None)
if phenotype and ind.phenotype != phenotype:
s = "scripts.seed_PonyGE2.load_population\n" \
"Error: Specified genotype from file " + file_name + \
" doesn't map to same phenotype. Check the specified " \
"grammar to ensure all is correct: " + \
params['GRAMMAR_FILE']
raise Exception(s)
else:
# Set target for GE LR Parser.
params['REVERSE_MAPPING_TARGET'] = phenotype
# Parse target phenotype.
ind = GE_LR_parser.main()
# Add new ind to the list of seed individuals.
seed_inds.append(ind)
return seed_inds
def evaluate_distance(self,
ind: Individual,
novelty_alg: str = "levi",
max_comparisons: int = 100) -> float:
"""Compare current phenotype with phenotypes from other seen phenotypes:
scales very poorly without a max number of comparisons, as the cache is constantly
growing"
:param ind: An individual to be evaluated
:param novelty_alg: algorithm to be used
:param max_comparisons: The upper bound on the number of comparisons to run
:return: The novelty of the individual, larger number represents larger novelty
"""
if not np.isnan(ind.novelty):
return ind.novelty
size_cache = len(cache)
# Bound the number of comparisons
number_comparisons = (size_cache if size_cache < max_comparisons else
max_comparisons)
total_novelty = 0
if size_cache > 0:
choices = sample(cache.keys(), number_comparisons)
for other_phenotype in choices:
# If comparing to itself, don't count it
if other_phenotype == ind.phenotype:
number_comparisons -= 1
continue
# Want hamming distance of genotype
if novelty_alg in ("geno", "genotype"):
other_geno = cache[other_phenotype]["genome"]
smaller_size = min(len(ind.genome), len(other_geno))
this_novelty = 0
for index in range(smaller_size):
if ind.genome[index] != other_geno[index]:
this_novelty += 1
total_novelty += this_novelty / smaller_size
# Compute hamming distance of phenotype
elif novelty_alg == 'hamming':
smaller_size = min(len(ind.phenotype),
len(other_phenotype))
total_novelty += hdistance(ind.phenotype[:smaller_size],
other_phenotype[:smaller_size])
# Compute the normalized levenshtein distance
elif novelty_alg in ("levi", "levenshtein", "pheno",
"phenotype"):
total_novelty += ldistance(
ind.phenotype, other_phenotype) / max(
len(ind.phenotype), len(other_phenotype))
# Compute distance of flat AST trees
elif novelty_alg == "ast":
other_ind = cache[other_phenotype]
total_novelty += self.compare_tree_dicts(
ind.AST, other_ind["AST"])
# Compute distance of flat derivation trees
elif novelty_alg == "derivation":
other_ind = cache[other_phenotype]
total_novelty += self.compare_tree_dicts(
ind.derivation, other_ind["derivation"])
elif novelty_alg == "fitness":
other_ind = cache[other_phenotype]
total_novelty += abs(ind.fitness - other_ind["fitness"])
elif novelty_alg == "output":
other_ind = cache[other_phenotype]
count = 0
for tcase_ind in range(len(ind.test_cases)):
count += ((ind.test_cases[tcase_ind] +
other_ind["output_cases"][tcase_ind]) % 2)
total_novelty += count
else:
raise NotImplementedError(novelty_alg +
" has not been implemented")
ind.novelty = total_novelty / number_comparisons
return ind.novelty
# If cache is empty, doesn't matter what is returned since every individual will reach this point
# and thus will all have the same novelty. Also, cache should never be empty.
return 0