def brute_force(self, **kwargs):
"""
Sample random bayesian network and keep the best
Args
names (list of string): the names of the nodes
data (np array): (nsamples, nfeatures)
"""
# get args
names = kwargs.get("names")
data = kwargs.get("data")
nsamples = kwargs.get("nsamples", 1000)
# initialize
g = BayesNet(names)
g.random_init()
s = g.score(data)
# explore
for i in xrange(nsamples):
sys.stdout.write("\rIter {}".format(i))
sys.stdout.flush()
g_new = BayesNet(names)
g_new.random_init()
s_new = g_new.score(data)
if s_new > s:
print "\nFound new best score at {}".format(s_new)
g = g_new
s = s_new
return g, s
def genetic(self, **kwargs):
"""
Implements genetic reproduction
If local search is set to True, implements mimetic
"""
names = kwargs.get("names")
data = kwargs.get("data")
max_iter = kwargs.get("max_iter", 30)
nb_start = kwargs.get("nb_start", 10)
max_pop = kwargs.get("max_pop", nb_start)
max_parents = kwargs.get("max_parents", None)
mut_rate = kwargs.get("mut_rate", 0.01)
local_search = kwargs.get("local_search", False)
# initialize the population
s_max = None
g_max = None
population = []
for i in xrange(nb_start):
g = BayesNet(names)
g.random_init(max_parents)
if local_search:
g, s, _ = self.best_neighbour(names, data, g, max_parents)
else:
s = g.score(data)
population += [(g, s)]
if s > s_max or s_max is None:
s_max = s
g_max = g
# let evolution do its work
criteria = True
niter = 0
def update_criteria_from(population):
s = None
g = None
for (_g, _s) in population:
if s is None or _s > s:
s = _s
g = _g
if s > s_max:
return g, s, True
else:
return g_max, s_max, True
while criteria and niter < max_iter:
print "Iter {}, Population {}".format(niter, len(population))
population = self.evolve(names, data, population, max_parents,
mut_rate, max_pop, local_search)
g_max, s_max, criteria = update_criteria_from(population)
if self.plotting:
try:
self.plt_mgr.add(name="Genetic Score Max", y=s_max)
self.plt_mgr.update()
except Exception, e:
pass
niter += 1
def evolve(self, names, data, population, max_parents, mut_rate, max_pop,
local_search):
"""
Given a population, creates a new population with random pairing and mixing
If local seach is true, children is the best neigbour of the random merge
"""
new_population = []
s_tot = sum([s for (_, s) in population])
n = len(population)
population = np.random.permutation(population)
for p in xrange(n / 2):
(g1, s1) = population[2 * p]
(g2, s2) = population[2 * p + 1]
nchildren = int(n * (s1 + s2) / s_tot) + 1
for i in xrange(nchildren):
if len(new_population) < max_pop:
g = BayesNet(names)
g.merge(g1, g2, s1 / s_tot, s2 / s_tot, max_parents,
mut_rate)
if local_search:
g, s, _ = self.best_neighbour(names, data, g,
max_parents)
else:
s = g.score(data)
new_population += [(g, s)]
if self.plotting:
try:
self.plt_mgr.add(name="Genetic Score", y=s)
self.plt_mgr.update()
except Exception, e:
pass
def k2(self, **kwargs):
"""
Implements k2 algorithm
"""
names = kwargs.get("names")
data = kwargs.get("data")
max_iter = kwargs.get("max_iter", 30)
nb_start = kwargs.get("nb_start", 3)
max_parents = kwargs.get("max_parents", None)
ordering = np.random.permutation(range(len(names)))
g = BayesNet(names)
s = g.score(data)
for i in ordering:
found_new = True
while found_new:
print "Node {}, score is {}".format(i, s)
g, s, found_new = self.best_parent(g, s, i, data, max_parents)
if self.plotting:
try:
self.plt_mgr.add(name="score k2 {}".format(
self.start_no),
y=s)
self.plt_mgr.update()
except Exception, e:
pass
def hill_climbing(self, **kwargs):
"""
Implements Hill Climbing Algorithm
Args
names (list of string): the name of the nodes
data (np array): (nsamples, nfeatures)
max_iter (int): max number of iteration
g0 (BayesNet): the start point
Returns
g: best graph found
s: score of best graph
"""
# get args
names = kwargs.get("names")
data = kwargs.get("data")
max_iter = kwargs.get("max_iter", 20)
max_parents = kwargs.get("max_parents", None)
# initialize
g0 = BayesNet(names)
g0.random_init(max_parents=max_parents)
g = g0
s = g0.score(data)
found_new = True
niter = 0
# explore
while found_new and niter < max_iter:
print "Iter {}".format(niter)
niter += 1
g, s, found_new = self.best_neighbour(names, data, g, max_parents)
if self.plotting:
try:
self.plt_mgr.add(name="score hill climbing {}".format(
self.start_no),
y=s)
self.plt_mgr.update()
except Exception, e:
pass