def __init__(self,
loss='ls',
learning_rate=0.1,
n_estimators=100,
subsample=1.0,
criterion='friedman_mse',
min_samples_split=2,
min_samples_leaf=1,
min_weight_fraction_leaf=0.,
max_depth=3,
min_impurity_decrease=0.,
min_impurity_split=None,
init=None,
random_state=None,
max_features=None,
alpha=0.9,
verbose=0,
max_leaf_nodes=None,
warm_start=False,
presort='auto'):
n_estimators = int(n_estimators)
_GradientBoostingRegressor.__init__(
self, loss, learning_rate, n_estimators, subsample, criterion,
min_samples_split, min_samples_leaf, min_weight_fraction_leaf,
max_depth, min_impurity_decrease, min_impurity_split, init,
random_state, max_features, alpha, verbose, max_leaf_nodes,
warm_start, presort)
BaseWrapperReg.__init__(self)
def __init__(self, pmml):
PMMLBaseRegressor.__init__(self, pmml)
mining_model = self.root.find('MiningModel')
if mining_model is None:
raise Exception('PMML model does not contain MiningModel.')
segmentation = mining_model.find('Segmentation')
if segmentation is None:
raise Exception('PMML model does not contain Segmentation.')
if segmentation.get('multipleModelMethod') not in ['sum']:
raise Exception('PMML model ensemble should use sum.')
# Parse segments
segments = segmentation.findall('Segment')
valid_segments = [
segment for segment in segments if segment.find('True') is not None
and segment.find('TreeModel') is not None
]
n_estimators = len(valid_segments)
self.n_outputs_ = 1
GradientBoostingRegressor.__init__(self, n_estimators=n_estimators)
clf = DecisionTreeRegressor(random_state=123)
try:
clf.n_features_in_ = self.n_features_in_
except AttributeError:
clf.n_features_ = self.n_features_
clf.n_outputs_ = self.n_outputs_
self.template_estimator = clf
self._check_params()
self._init_state()
mean = mining_model.find('Targets').find('Target').get(
'rescaleConstant', 0)
self.init_.constant_ = np.array([mean])
self.init_.n_outputs_ = 1
for x, y in np.ndindex(self.estimators_.shape):
factor = float(
mining_model.find('Targets').find('Target').get(
'rescaleFactor', 1))
self.estimators_[x, y] = get_tree(self,
valid_segments[x],
rescale_factor=factor)
# Required after constructing trees, because categories may be inferred in
# the parsing process
target = self.target_field.get('name')
fields = [
field for name, field in self.fields.items() if name != target
]
for x, y in np.ndindex(self.estimators_.shape):
clf = self.estimators_[x, y]
n_categories = np.asarray([
len(self.field_mapping[field.get('name')][1].categories)
if field.get('optype') == 'categorical' else -1
for field in fields if field.tag == 'DataField'
],
dtype=np.int32,
order='C')
clf.n_categories = n_categories
clf.tree_.set_n_categories(n_categories)
self.categorical = [
x != -1 for x in self.estimators_[0, 0].n_categories
]
