def _score_disc_bin():
n_values = len(attr.values)
if n_values == 2:
return _score_disc()
score, mapping = _tree_scorers.find_binarization_MSE(
col_x, col_y, n_values, self.min_samples_leaf)
# The score is already adjusted for missing attribute values, so
# we don't do it here
if score == 0:
return REJECT_ATTRIBUTE
mapping, branches = MappedDiscreteNode.branches_from_mapping(
data.X[:, attr_no], mapping, len(attr.values))
node = MappedDiscreteNode(attr, attr_no, mapping, None)
return score, node, branches, 2
def _score_disc_bin():
n_values = len(attr.values)
if n_values == 2:
return _score_disc()
score, mapping = _tree_scorers.find_binarization_MSE(
col_x, col_y, n_values, self.min_samples_leaf)
# The score is already adjusted for missing attribute values, so
# we don't do it here
if score == 0:
return REJECT_ATTRIBUTE
mapping, branches = MappedDiscreteNode.branches_from_mapping(
col_x, mapping, len(attr.values))
node = MappedDiscreteNode(attr, attr_no, mapping, None)
return score, node, branches, 2
def _score_disc_bin():
"""Scoring for discrete attributes, with binarization"""
n_values = len(attr.values)
if n_values <= 2:
return _score_disc()
cont = contingency.Discrete(data, attr)
attr_distr = np.sum(cont, axis=0)
# Skip instances with missing value of the attribute
cls_distr = np.sum(cont, axis=1)
if np.sum(attr_distr) == 0: # all values are missing
return REJECT_ATTRIBUTE
best_score, best_mapping = _tree_scorers.find_binarization_entropy(
cont, cls_distr, attr_distr, self.min_samples_leaf)
if best_score <= 0:
return REJECT_ATTRIBUTE
best_score *= 1 - np.sum(cont.unknowns) / len(data)
mapping, branches = MappedDiscreteNode.branches_from_mapping(
col_x, best_mapping, n_values)
node = MappedDiscreteNode(attr, attr_no, mapping, None)
return best_score, node, branches, 2
def _score_disc_bin():
"""Scoring for discrete attributes, with binarization"""
n_values = len(attr.values)
if n_values <= 2:
return _score_disc()
cont = contingency.Discrete(data, attr)
attr_distr = np.sum(cont, axis=0)
# Skip instances with missing value of the attribute
cls_distr = np.sum(cont, axis=1)
if np.sum(attr_distr) == 0: # all values are missing
return REJECT_ATTRIBUTE
best_score, best_mapping = _tree_scorers.find_binarization_entropy(
cont, cls_distr, attr_distr, self.min_samples_leaf)
if best_score <= 0:
return REJECT_ATTRIBUTE
best_score *= 1 - np.sum(cont.unknowns) / len(data)
mapping, branches = MappedDiscreteNode.branches_from_mapping(
data.X[:, attr_no], best_mapping, n_values)
node = MappedDiscreteNode(attr, attr_no, mapping, None)
return best_score, node, branches, 2
