def train(self, pop = 20, gen = 10):
from deap import algorithms
from deap import base
from deap import creator
from deap import tools
from deap.tools import Statistics
# import random
from scipy.stats import rv_discrete
# creator.create("FitnessMulti", base.Fitness, weights=(1.0, -1.0))
# creator.create("Individual", list, fitness=creator.FitnessMulti)
creator.create("FitnessMin", base.Fitness, weights=(-1.0,))
creator.create("Individual", list, fitness=creator.FitnessMin)
toolbox = base.Toolbox()
# Attribute generator
custm = rv_discrete(name='custm', values=(self.a_w.index, self.a_w.values))
toolbox.register("attr_int", custm.rvs)
# Structure initializers
toolbox.register("individual", tools.initRepeat, creator.Individual, toolbox.attr_int, n=len(self.s))
toolbox.register("population", tools.initRepeat, list, toolbox.individual, n=pop)
# Operator registering
toolbox.register("evaluate", self.eval_classifer)
toolbox.register("mate", tools.cxUniform, indpb=0.5)
toolbox.register("mutate", tools.mutUniformInt, low=min(self.a.index), up=max(self.a.index), indpb=0.1)
toolbox.register("select", tools.selNSGA2)
MU, LAMBDA = pop, pop
population = toolbox.population(n=MU)
hof = tools.ParetoFront()
s = Statistics(key=lambda ind: ind.fitness.values)
s.register("mean", np.mean)
s.register("min", min)
# pop, logbook = algorithms.eaMuPlusLambda(pop, toolbox, mu=MU, lambda_=LAMBDA, cxpb=0.7, mutpb=0.3, ngen=gen, stats=s, halloffame=hof)
for i in range(gen):
offspring = algorithms.varAnd(population, toolbox, cxpb=0.95, mutpb=0.1)
fits = toolbox.map(toolbox.evaluate, offspring)
for fit, ind in zip(fits, offspring):
ind.fitness.values = fit
population = tools.selBest(offspring, int(0.05*len(offspring))) + tools.selTournament(offspring, len(offspring)-int(0.05*len(offspring)), tournsize=3)
# population = toolbox.select(offspring, k=len(population))
print s.compile(population)
top10 = tools.selBest(population, k=10)
return top10
def train(self, pop = 20, gen = 10):
from deap import algorithms
from deap import base
from deap import creator
from deap import tools
import random
import numpy as np
from deap.tools import Statistics
# creator.create("FitnessMulti", base.Fitness, weights=(1.0, -1.0))
# creator.create("Individual", list, fitness=creator.FitnessMulti)
creator.create("FitnessMax", base.Fitness, weights=(1.0,))
creator.create("Individual", list, fitness=creator.FitnessMax)
toolbox = base.Toolbox()
# Attribute generator
toolbox.register("attr_bool", random.randint, 0, 1)
# Structure initializers
toolbox.register("individual", tools.initRepeat, creator.Individual, toolbox.attr_bool, n=len(self.X.columns))
toolbox.register("population", tools.initRepeat, list, toolbox.individual, n=pop)
# Operator registering
toolbox.register("evaluate", self.eval_classifer)
toolbox.register("mate", tools.cxUniform, indpb=0.1)
toolbox.register("mutate", tools.mutFlipBit, indpb=0.05)
# toolbox.register("select", tools.selNSGA2)
MU, LAMBDA = pop, pop
population = toolbox.population(n=MU)
# hof = tools.ParetoFront()
s = Statistics(key=lambda ind: ind.fitness.values)
s.register("mean", np.mean)
s.register("max", max)
# pop, logbook = algorithms.eaMuPlusLambda(pop, toolbox, mu=MU, lambda_=LAMBDA, cxpb=0.7, mutpb=0.3, ngen=gen, stats=s, halloffame=hof)
for i in range(gen):
offspring = algorithms.varAnd(population, toolbox, cxpb=0.95, mutpb=0.1)
fits = toolbox.map(toolbox.evaluate, offspring)
for fit, ind in zip(fits, offspring):
ind.fitness.values = fit
population = tools.selBest(offspring, int(0.05*len(offspring))) + tools.selTournament(offspring, len(offspring)-int(0.05*len(offspring)), tournsize=3)
# population = toolbox.select(offspring, k=len(population))
print s.compile(population)
top10 = tools.selBest(population, k=10)
print top10
return top10[0]
class Population(list):
"""
A collection of individuals
"""
INDIVIDUAL_CLASS = Individual
POPULATION_SIZE = 100
CLONE_BEST = 5
MAX_MATE_ATTEMPTS = 10
MATE_MUTATE_CLONE = (80, 18, 2)
def __init__(self, bset):
self.bset = bset
pop = [Population.INDIVIDUAL_CLASS(self.bset) for _ in range(self.POPULATION_SIZE)]
super(Population, self).__init__(pop)
self.stats = Statistics(lambda ind: ind.fitness.values)
self.stats.register("avg", np.mean)
self.stats.register("std", np.std)
self.stats.register("min", np.min)
self.stats.register("max", np.max)
self.logbook = Logbook()
self.logbook.header = ['gen'] + self.stats.fields
self.hof = HallOfFame(1)
self.generation = 0
# do an initial evaluation
for ind in self:
ind.fitness.values = ind.evaluate()
def select(self, k):
"""Probablistic select *k* individuals among the input *individuals*. The
list returned contains references to the input *individuals*.
:param k: The number of individuals to select.
:returns: A list containing k individuals.
The individuals returned are randomly selected from individuals according
to their fitness such that the more fit the individual the more likely
that individual will be chosen. Less fit individuals are less likely, but
still possibly, selected.
"""
# adjusted pop is a list of tuples (adjusted fitness, individual)
adjusted_pop = [(1.0 / (1.0 + i.fitness.values[0]), i) for i in self]
# normalised_pop is a list of tuples (float, individual) where the float indicates
# a 'share' of 1.0 that the individual deserves based on it's fitness relative to
# the other individuals. It is sorted so the best chances are at the front of the list.
denom = sum([fit for fit, ind in adjusted_pop])
normalised_pop = [(fit / denom, ind) for fit, ind in adjusted_pop]
normalised_pop = sorted(normalised_pop, key=lambda i: i[0], reverse=True)
# randomly select with a fitness bias
# FIXME: surely this can be optimized?
selected = []
for x in range(k):
rand = random.random()
accumulator = 0.0
for share, ind in normalised_pop:
accumulator += share
if rand <= accumulator:
selected.append(ind)
break
if len(selected) == 1:
return selected[0]
else:
return selected
def evolve(self):
"""
Evolve this population by one generation
"""
self.logbook.record(gen=self.generation, **self.stats.compile(self))
self.hof.update(self)
print(self.logbook.stream)
# the best x of the population are cloned directly into the next generation
offspring = self[:self.CLONE_BEST]
# rest of the population clone, mate, or mutate at random
for idx in range(len(self) - self.CLONE_BEST):
# decide how to alter this individual
rand = random.randint(0,100)
for _ in range(0, self.MAX_MATE_ATTEMPTS):
try:
if rand < self.MATE_MUTATE_CLONE[0]: # MATE/CROSSOVER
receiver, contributor = self.select(2)
child = receiver.clone()
child.mate(contributor)
break
elif rand < (self.MATE_MUTATE_CLONE[0] + self.MATE_MUTATE_CLONE[1]): # MUTATE
ind = self.select(1)
child = ind.clone()
child.mutate()
break
else:
child = self.select(1).clone()
break
except BirthError:
continue
# generate new blood when reproduction fails so badly
else:
child = Population.INDIVIDUAL_CLASS(self.bset)
offspring.append(child)
self[:] = offspring
self.generation += 1
# evaluate every individual and sort
for ind in self:
if not len(ind.fitness.values):
ind.fitness.values = ind.evaluate()
self.sort(key=lambda i: i.fitness.values[0])
def train(self, pop=20, gen=10):
from deap import algorithms
from deap import base
from deap import creator
from deap import tools
from deap.tools import Statistics
# import random
from scipy.stats import rv_discrete
# creator.create("FitnessMulti", base.Fitness, weights=(1.0, -1.0))
# creator.create("Individual", list, fitness=creator.FitnessMulti)
creator.create("FitnessMin", base.Fitness, weights=(-1.0, ))
creator.create("Individual", list, fitness=creator.FitnessMin)
toolbox = base.Toolbox()
# Attribute generator
custm = rv_discrete(name='custm',
values=(self.a_w.index, self.a_w.values))
toolbox.register("attr_int", custm.rvs)
# Structure initializers
toolbox.register("individual",
tools.initRepeat,
creator.Individual,
toolbox.attr_int,
n=len(self.s))
toolbox.register("population",
tools.initRepeat,
list,
toolbox.individual,
n=pop)
# Operator registering
toolbox.register("evaluate", self.eval_classifer)
toolbox.register("mate", tools.cxUniform, indpb=0.5)
toolbox.register("mutate",
tools.mutUniformInt,
low=min(self.a.index),
up=max(self.a.index),
indpb=0.1)
toolbox.register("select", tools.selNSGA2)
MU, LAMBDA = pop, pop
population = toolbox.population(n=MU)
hof = tools.ParetoFront()
s = Statistics(key=lambda ind: ind.fitness.values)
s.register("mean", np.mean)
s.register("min", min)
# pop, logbook = algorithms.eaMuPlusLambda(pop, toolbox, mu=MU, lambda_=LAMBDA, cxpb=0.7, mutpb=0.3, ngen=gen, stats=s, halloffame=hof)
for i in range(gen):
offspring = algorithms.varAnd(population,
toolbox,
cxpb=0.95,
mutpb=0.1)
fits = toolbox.map(toolbox.evaluate, offspring)
for fit, ind in zip(fits, offspring):
ind.fitness.values = fit
population = tools.selBest(offspring, int(
0.05 * len(offspring))) + tools.selTournament(
offspring,
len(offspring) - int(0.05 * len(offspring)),
tournsize=3)
# population = toolbox.select(offspring, k=len(population))
print s.compile(population)
top10 = tools.selBest(population, k=10)
return top10
