def compute_log_inv_acc_p(self, node_id, param, len_both_children_terminal, loglik, grow_nodes, \
cache, settings, data):
# 1/acc for PRUNE is acc for GROW except for corrections to both_children_terminal
# and grow_nodes list
logprior_children = 0.0
left, right = get_children_id(node_id)
if not no_valid_split_exists(data, cache, self.train_ids[left], settings):
logprior_children += np.log(self.compute_pnosplit(left, param))
if not no_valid_split_exists(data, cache, self.train_ids[right], settings):
logprior_children += np.log(self.compute_pnosplit(right, param))
try:
check_if_zero(logprior_children - self.logprior[left] - self.logprior[right])
except AssertionError:
print 'oh oh ... looks like a bug in compute_log_inv_acc_p'
print 'term 1 = %s' % logprior_children
print 'term 2 = %s, 2a = %s, 2b = %s' % (self.logprior[left]+self.logprior[right], \
self.logprior[left], self.logprior[right])
print 'node_id = %s, left = %s, right = %s, logprior = %s' % (node_id, left, right, self.logprior)
raise AssertionError
log_inv_acc_prior = np.log(self.compute_psplit(node_id, param)) \
- np.log(self.compute_pnosplit(node_id, param)) \
-np.log(len_both_children_terminal) + np.log(len(grow_nodes)) \
+ logprior_children
log_inv_acc_loglik = (loglik - self.loglik[node_id])
log_inv_acc = log_inv_acc_loglik + log_inv_acc_prior
if settings.verbose >= 2:
print 'compute_log_inv_acc_p: log_acc_loglik = %s, log_acc_prior = %s' \
% (-log_inv_acc_loglik, -log_inv_acc_prior)
assert(log_inv_acc > -np.inf)
return log_inv_acc
def compute_log_inv_acc_p(self, node_id, param, len_both_children_terminal, loglik, grow_nodes, \
cache, settings, data):
# 1/acc for PRUNE is acc for GROW except for corrections to both_children_terminal
# and grow_nodes list
logprior_children = 0.0
left, right = get_children_id(node_id)
if not no_valid_split_exists(data, cache, self.train_ids[left], settings):
logprior_children += np.log(self.compute_pnosplit(left, param))
if not no_valid_split_exists(data, cache, self.train_ids[right], settings):
logprior_children += np.log(self.compute_pnosplit(right, param))
try:
check_if_zero(logprior_children - self.logprior[left] - self.logprior[right])
except AssertionError:
print 'oh oh ... looks like a bug in compute_log_inv_acc_p'
print 'term 1 = %s' % logprior_children
print 'term 2 = %s, 2a = %s, 2b = %s' % (self.logprior[left]+self.logprior[right], \
self.logprior[left], self.logprior[right])
print 'node_id = %s, left = %s, right = %s, logprior = %s' % (node_id, left, right, self.logprior)
raise AssertionError
log_inv_acc_prior = np.log(self.compute_psplit(node_id, param)) \
- np.log(self.compute_pnosplit(node_id, param)) \
-np.log(len_both_children_terminal) + np.log(len(grow_nodes)) \
+ logprior_children
log_inv_acc_loglik = (loglik - self.loglik[node_id])
log_inv_acc = log_inv_acc_loglik + log_inv_acc_prior
if settings.verbose >= 2:
print 'compute_log_inv_acc_p: log_acc_loglik = %s, log_acc_prior = %s' \
% (-log_inv_acc_loglik, -log_inv_acc_prior)
assert(log_inv_acc > -np.inf)
return log_inv_acc
def compute_log_acc_g(self, node_id, param, len_both_children_terminal, loglik, \
train_ids_left, train_ids_right, cache, settings, data, grow_nodes):
# effect of do_not_split does not matter for node_id since it has children
logprior_children = 0.0
left, right = get_children_id(node_id)
if not no_valid_split_exists(data, cache, train_ids_left, settings):
logprior_children += np.log(self.compute_pnosplit(left, param))
if not no_valid_split_exists(data, cache, train_ids_right, settings):
logprior_children += np.log(self.compute_pnosplit(right, param))
log_acc_prior = np.log(self.compute_psplit(node_id, param)) \
-np.log(self.compute_pnosplit(node_id, param)) \
-np.log(len_both_children_terminal) + np.log(len(grow_nodes)) \
+ logprior_children
log_acc_loglik = (loglik - self.loglik[node_id])
log_acc = log_acc_prior + log_acc_loglik
if settings.verbose >= 2:
print('compute_log_acc_g: log_acc_loglik = %s, log_acc_prior = %s' \
% (log_acc_loglik, log_acc_prior))
if loglik == -np.inf: # just need to ensure that an invalid split is not grown
log_acc = -np.inf
return log_acc
def compute_log_acc_g(self, node_id, param, len_both_children_terminal, loglik, \
train_ids_left, train_ids_right, cache, settings, data, grow_nodes):
# effect of do_not_split does not matter for node_id since it has children
logprior_children = 0.0
left, right = get_children_id(node_id)
if not no_valid_split_exists(data, cache, train_ids_left, settings):
logprior_children += np.log(self.compute_pnosplit(left, param))
if not no_valid_split_exists(data, cache, train_ids_right, settings):
logprior_children += np.log(self.compute_pnosplit(right, param))
log_acc_prior = np.log(self.compute_psplit(node_id, param)) \
-np.log(self.compute_pnosplit(node_id, param)) \
-np.log(len_both_children_terminal) + np.log(len(grow_nodes)) \
+ logprior_children
log_acc_loglik = (loglik - self.loglik[node_id])
log_acc = log_acc_prior + log_acc_loglik
if settings.verbose >= 2:
print 'compute_log_acc_g: log_acc_loglik = %s, log_acc_prior = %s' \
% (log_acc_loglik, log_acc_prior)
if loglik == -np.inf: # just need to ensure that an invalid split is not grown
log_acc = -np.inf
return log_acc