def summarize(self, out=sys.stdout):
"""Prints summary grouping distribution as class header and details
"""
tree = self.tree
def extract_common_path(groups):
"""Extracts the common segment of the prediction path for a group
"""
for group in groups:
details = groups[group]['details']
common_path = []
if len(details) > 0:
mcd_len = min([len(x[0]) for x in details])
for i in range(0, mcd_len):
test_common_path = details[0][0][i]
for subgroup in details:
if subgroup[0][i] != test_common_path:
i = mcd_len
break
if i < mcd_len:
common_path.append(test_common_path)
groups[group]['total'][0] = common_path
if len(details) > 0:
groups[group]['details'] = sorted(details,
key=lambda x: x[1],
reverse=True)
def confidence_error(value, impurity=None):
"""Returns confidence for categoric objective fields
and error for numeric objective fields
"""
if value is None:
return ""
impurity_literal = ""
if impurity is not None and impurity > 0:
impurity_literal = "; impurity: %.2f%%" % (round(impurity, 4))
objective_type = self.fields[tree.objective_id]['optype']
if objective_type == 'numeric':
return u" [Error: %s]" % value
else:
return u" [Confidence: %.2f%%%s]" % ((round(value, 4) * 100),
impurity_literal)
distribution = self.get_data_distribution()
out.write(u"Data distribution:\n")
print_distribution(distribution, out=out)
out.write(u"\n\n")
groups = self.group_prediction()
predictions = self.get_prediction_distribution(groups)
out.write(u"Predicted distribution:\n")
print_distribution(predictions, out=out)
out.write(u"\n\n")
if self.field_importance:
out.write(u"Field importance:\n")
print_importance(self, out=out)
extract_common_path(groups)
for group in [x[0] for x in predictions]:
details = groups[group]['details']
path = [prediction.to_rule(self.fields) for
prediction in groups[group]['total'][0]]
data_per_group = groups[group]['total'][1] * 1.0 / tree.count
pred_per_group = groups[group]['total'][2] * 1.0 / tree.count
out.write(utf8(u"\n\n%s : (data %.2f%% / prediction %.2f%%) %s\n" %
(group,
round(data_per_group, 4) * 100,
round(pred_per_group, 4) * 100,
" and ".join(path))))
if len(details) == 0:
out.write(u" The model will never predict this class\n")
for j in range(0, len(details)):
subgroup = details[j]
pred_per_sgroup = subgroup[1] * 1.0 / groups[group]['total'][2]
path = [prediction.to_rule(self.fields) for
prediction in subgroup[0]]
path_chain = " and ".join(path) if len(path) else "(root node)"
out.write(utf8(u" · %.2f%%: %s%s\n" %
(round(pred_per_sgroup, 4) * 100,
path_chain,
confidence_error(subgroup[2],
impurity=subgroup[3]))))
out.flush()
def print_importance(self, out=sys.stdout):
"""Prints ensemble field importance
"""
print_importance(self, out=out)
def summarize(self, out=sys.stdout):
"""Prints summary grouping distribution as class header and details
"""
tree = self.tree
def extract_common_path(groups):
"""Extracts the common segment of the prediction path for a group
"""
for group in groups:
details = groups[group]['details']
common_path = []
if len(details) > 0:
mcd_len = min([len(x[0]) for x in details])
for i in range(0, mcd_len):
test_common_path = details[0][0][i]
for subgroup in details:
if subgroup[0][i] != test_common_path:
i = mcd_len
break
if i < mcd_len:
common_path.append(test_common_path)
groups[group]['total'][0] = common_path
if len(details) > 0:
groups[group]['details'] = sorted(details,
key=lambda x: x[1],
reverse=True)
def confidence_error(value):
"""Returns confidence for categoric objective fields
and error for numeric objective fields
"""
if value is None:
return ""
objective_type = self.fields[tree.objective_field]['optype']
if objective_type == 'numeric':
return u" [Error: %s]" % value
else:
return u" [Confidence: %.2f%%]" % (round(value, 4) * 100)
distribution = self.get_data_distribution()
out.write(u"Data distribution:\n")
print_distribution(distribution, out=out)
out.write(u"\n\n")
groups = self.group_prediction()
predictions = self.get_prediction_distribution(groups)
out.write(u"Predicted distribution:\n")
print_distribution(predictions, out=out)
out.write(u"\n\n")
if self.field_importance:
out.write(u"Field importance:\n")
print_importance(self, out=out)
extract_common_path(groups)
for group in [x[0] for x in predictions]:
details = groups[group]['details']
path = [
prediction.to_rule(self.fields)
for prediction in groups[group]['total'][0]
]
data_per_group = groups[group]['total'][1] * 1.0 / tree.count
pred_per_group = groups[group]['total'][2] * 1.0 / tree.count
out.write(
utf8(u"\n\n%s : (data %.2f%% / prediction %.2f%%) %s\n" %
(group, round(data_per_group, 4) * 100,
round(pred_per_group, 4) * 100, " and ".join(path))))
if len(details) == 0:
out.write(u" The model will never predict this class\n")
for j in range(0, len(details)):
subgroup = details[j]
pred_per_sgroup = subgroup[1] * 1.0 / groups[group]['total'][2]
path = [
prediction.to_rule(self.fields)
for prediction in subgroup[0]
]
path_chain = " and ".join(path) if len(path) else "(root node)"
out.write(
utf8(u" · %.2f%%: %s%s\n" %
(round(pred_per_sgroup, 4) * 100, path_chain,
confidence_error(subgroup[2]))))
out.flush()
def print_importance(self, out=sys.stdout):
"""Prints ensemble field importance
"""
print_importance(self, out=out)
def summarize(model, out=sys.stdout, format=BRIEF):
"""Prints summary grouping distribution as class header and details
"""
if model.boosting:
raise AttributeError("This method is not available for boosting"
" models.")
tree = model.tree
def extract_common_path(groups):
"""Extracts the common segment of the prediction path for a group
"""
for group in groups:
details = groups[group]['details']
common_path = []
if len(details) > 0:
mcd_len = min([len(x[0]) for x in details])
for i in range(0, mcd_len):
test_common_path = details[0][0][i]
for subgroup in details:
if subgroup[0][i] != test_common_path:
i = mcd_len
break
if i < mcd_len:
common_path.append(test_common_path)
groups[group]['total'][0] = common_path
if len(details) > 0:
groups[group]['details'] = sorted(details,
key=lambda x: x[1],
reverse=True)
def confidence_error(value, impurity=None):
"""Returns confidence for categoric objective fields
and error for numeric objective fields
"""
if value is None:
return ""
impurity_literal = ""
if impurity is not None and impurity > 0:
impurity_literal = "; impurity: %.2f%%" % (round(impurity, 4))
objective_type = model.fields[model.objective_id]['optype']
if objective_type == 'numeric':
return " [Error: %s]" % value
return " [Confidence: %.2f%%%s]" % (round(value, 4) * 100,
impurity_literal)
distribution = get_data_distribution(model)
out.write(utf8("Data distribution:\n"))
print_distribution(distribution, out=out)
out.write(utf8("\n\n"))
groups = group_prediction(model)
predictions = get_prediction_distribution(model, groups)
out.write(utf8("Predicted distribution:\n"))
print_distribution(predictions, out=out)
out.write(utf8("\n\n"))
if model.field_importance:
out.write(utf8("Field importance:\n"))
print_importance(model, out=out)
extract_common_path(groups)
out.write(utf8("\n\nRules summary:"))
node = get_node(tree)
count = node[model.offsets["count"]]
for group in [x[0] for x in predictions]:
details = groups[group]['details']
path = Path(groups[group]['total'][0])
data_per_group = groups[group]['total'][1] * 1.0 / count
pred_per_group = groups[group]['total'][2] * 1.0 / count
out.write(
utf8("\n\n%s : (data %.2f%% / prediction %.2f%%) %s" %
(group, round(data_per_group, 4) * 100,
round(pred_per_group, 4) * 100,
path.to_rules(model.fields, format=format))))
if len(details) == 0:
out.write(
utf8("\n The model will never predict this"
" class\n"))
elif len(details) == 1:
subgroup = details[0]
out.write(
utf8("%s\n" %
confidence_error(subgroup[2], impurity=subgroup[3])))
else:
out.write(utf8("\n"))
for subgroup in details:
pred_per_sgroup = subgroup[1] * 1.0 / \
groups[group]['total'][2]
path = Path(subgroup[0])
path_chain = path.to_rules(model.fields, format=format) if \
path.predicates else "(root node)"
out.write(
utf8(
" · %.2f%%: %s%s\n" %
(round(pred_per_sgroup, 4) * 100, path_chain,
confidence_error(subgroup[2], impurity=subgroup[3]))))
out.flush()
