def predict_proportional(self, input_data, path=None,
missing_found=False):
"""Makes a prediction based on a number of field values considering all
the predictions of the leaves that fall in a subtree.
Each time a splitting field has no value assigned, we consider
both branches of the split to be true, merging their
predictions. The function returns the merged distribution and the
last node reached by a unique path.
"""
if path is None:
path = []
if not self.children:
return (self.g_sum, self.h_sum, self.count, path)
if one_branch(self.children, input_data) or \
self.fields[split(self.children)]["optype"] in \
["text", "items"]:
for child in self.children:
if child.predicate.apply(input_data, self.fields):
new_rule = child.predicate.to_rule(self.fields)
if new_rule not in path and not missing_found:
path.append(new_rule)
return child.predict_proportional(input_data, path,
missing_found)
else:
# missing value found, the unique path stops
missing_found = True
g_sums = 0.0
h_sums = 0.0
population = 0
for child in self.children:
g_sum, h_sum, count, _ = \
child.predict_proportional(input_data, path,
missing_found)
g_sums += g_sum
h_sums += h_sum
population += count
return (g_sums, h_sums, population, path)
def predict_proportional(self, input_data, path=None,
missing_found=False):
"""Makes a prediction based on a number of field values considering all
the predictions of the leaves that fall in a subtree.
Each time a splitting field has no value assigned, we consider
both branches of the split to be true, merging their
predictions. The function returns the merged distribution and the
last node reached by a unique path.
"""
if path is None:
path = []
if not self.children:
return (self.g_sum, self.h_sum, self.count, path)
if one_branch(self.children, input_data) or \
self.fields[split(self.children)]["optype"] in \
["text", "items"]:
for child in self.children:
if child.predicate.apply(input_data, self.fields):
new_rule = child.predicate.to_rule(self.fields)
if new_rule not in path and not missing_found:
path.append(new_rule)
return child.predict_proportional(input_data, path,
missing_found)
else:
# missing value found, the unique path stops
missing_found = True
g_sums = 0.0
h_sums = 0.0
population = 0
for child in self.children:
g_sum, h_sum, count, _ = \
child.predict_proportional(input_data, path,
missing_found)
g_sums += g_sum
h_sums += h_sum
population += count
return (g_sums, h_sums, population, path)