def _sample_row(self):
"""Generate a single sampled row from vine model.
Returns:
numpy.ndarray
"""
unis = np.random.uniform(0, 1, self.n_var)
# randomly select a node to start with
first_ind = np.random.randint(0, self.n_var)
adj = self.trees[0].get_adjacent_matrix()
visited = []
explore = [first_ind]
sampled = np.zeros(self.n_var)
itr = 0
while explore:
current = explore.pop(0)
neighbors = np.where(adj[current, :] == 1)[0].tolist()
if itr == 0:
new_x = self.ppfs[current](unis[current])
else:
for i in range(itr - 1, -1, -1):
current_ind = -1
if i >= self.truncated:
continue
current_tree = self.trees[i].edges
# get index of edge to retrieve
for edge in current_tree:
if i == 0:
if (edge.L == current and edge.R == visited[0]) or\
(edge.R == current and edge.L == visited[0]):
current_ind = edge.index
break
else:
if edge.L == current or edge.R == current:
condition = set(edge.D)
condition.add(edge.L)
condition.add(edge.R)
visit_set = set(visited)
visit_set.add(current)
if condition.issubset(visit_set):
current_ind = edge.index
break
if current_ind != -1:
# the node is not indepedent contional on visited node
copula_type = current_tree[current_ind].name
copula = Bivariate(
copula_type=CopulaTypes(copula_type))
copula.theta = current_tree[current_ind].theta
U = np.array([unis[visited[0]]])
if i == itr - 1:
tmp = copula.percent_point(
np.array([unis[current]]), U)[0]
else:
tmp = copula.percent_point(np.array([tmp]), U)[0]
tmp = min(max(tmp, EPSILON), 0.99)
new_x = self.ppfs[current](np.array([tmp]))
sampled[current] = new_x
for s in neighbors:
if s not in visited:
explore.insert(0, s)
itr += 1
visited.insert(0, current)
return sampled
def sample(self, num_rows=1, seed=None):
"""Generating samples from vine model."""
s1 = np.random.get_state()
s2 = random.getstate()
np.random.seed(seed)
random.setstate(seed)
unis = np.random.uniform(0, 1, self.n_var)
# randomly select a node to start with
first_ind = random.randint(0, self.n_var - 1)
np.random.seed(s1)
random.setstate(s2)
adj = self.trees[0].get_adjacent_matrix()
visited = []
explore = [first_ind]
sampled = np.zeros(self.n_var)
itr = 0
while explore:
current = explore.pop(0)
neighbors = np.where(adj[current, :] == 1)[0].tolist()
if itr == 0:
new_x = self.ppfs[current](unis[current])
else:
for i in range(itr - 1, -1, -1):
current_ind = -1
if i >= self.truncated:
continue
current_tree = self.trees[i].edges
# get index of edge to retrieve
for edge in current_tree:
if i == 0:
if (edge.L == current and edge.R == visited[0]) or\
(edge.R == current and edge.L == visited[0]):
current_ind = edge.index
break
else:
if edge.L == current or edge.R == current:
condition = set(edge.D)
condition.add(edge.L)
condition.add(edge.R)
visit_set = set(visited).add(current)
if condition.issubset(visit_set):
current_ind = edge.index
break
if current_ind != -1:
# the node is not indepedent contional on visited node
copula_type = current_tree[current_ind].name
copula_para = current_tree[current_ind].param
cop = Bivariate(CopulaTypes(copula_type))
derivative = cop.get_h_function()
# start with last level
if i == itr - 1:
tmp = optimize.fminbound(derivative,
EPSILON,
1.0,
args=(unis[visited[0]],
copula_para,
unis[current]))
else:
tmp = optimize.fminbound(derivative,
EPSILON,
1.0,
args=(unis[visited[0]],
copula_para, tmp))
tmp = min(max(tmp, EPSILON), 0.99)
new_x = self.ppfs[current](tmp)
sampled[current] = new_x
for s in neighbors:
if s not in visited:
explore.insert(0, s)
itr += 1
visited.insert(0, current)
return sampled