def _get_tree_state(self):
"""
Internal utility that returns an array behind scikit-learn's tree object
from daal_model_ produced by call to fit
"""
check_is_fitted(self, ['daal_model_', '_cached_tree_state_'])
if self._cached_tree_state_ is None:
tree_state_class = d4p.getTreeState(self.daal_model_, int(self.n_classes_))
self._cached_tree_state_ = tree_state_class
return self._cached_tree_state_
def estimators_(self):
if hasattr(self, '_cached_estimators_'):
if self._cached_estimators_:
return self._cached_estimators_
if LooseVersion(sklearn_version) >= LooseVersion("0.22"):
check_is_fitted(self)
else:
check_is_fitted(self, 'daal_model_')
# convert model to estimators
est = DecisionTreeClassifier(
criterion=self.criterion,
max_depth=self.max_depth,
min_samples_split=self.min_samples_split,
min_samples_leaf=self.min_samples_leaf,
min_weight_fraction_leaf=self.min_weight_fraction_leaf,
max_features=self.max_features,
max_leaf_nodes=self.max_leaf_nodes,
min_impurity_decrease=self.min_impurity_decrease,
min_impurity_split=self.min_impurity_split,
random_state=None)
# we need to set est.tree_ field with Trees constructed from Intel(R) DAAL solution
estimators_ = []
for i in range(self.n_estimators):
# print("Tree #{}".format(i))
est_i = clone(est)
est_i.n_features_ = self.n_features_
est_i.n_outputs_ = self.n_outputs_
est_i.classes_ = self.classes_
est_i.n_classes_ = self.n_classes_
# treeState members: 'class_count', 'leaf_count', 'max_depth', 'node_ar', 'node_count', 'value_ar'
tree_i_state_class = daal4py.getTreeState(self.daal_model_, i,
self.n_classes_)
node_ndarray = tree_i_state_class.node_ar
value_ndarray = tree_i_state_class.value_ar
value_shape = (node_ndarray.shape[0], self.n_outputs_,
self.n_classes_)
# assert np.allclose(value_ndarray, value_ndarray.astype(np.intc, casting='unsafe')), "Value array is non-integer"
tree_i_state_dict = {
'max_depth': tree_i_state_class.max_depth,
'node_count': tree_i_state_class.node_count,
'nodes': tree_i_state_class.node_ar,
'values': tree_i_state_class.value_ar
}
#
est_i.tree_ = Tree(self.n_features_,
np.array([self.n_classes_], dtype=np.intp),
self.n_outputs_)
est_i.tree_.__setstate__(tree_i_state_dict)
estimators_.append(est_i)
self._cached_estimators_ = estimators_
return estimators_
def _estimators_(self):
if hasattr(self, '_cached_estimators_'):
if self._cached_estimators_:
return self._cached_estimators_
if sklearn_check_version('0.22'):
check_is_fitted(self)
else:
check_is_fitted(self, 'daal_model_')
# convert model to estimators
params = {
'criterion': self.criterion,
'max_depth': self.max_depth,
'min_samples_split': self.min_samples_split,
'min_samples_leaf': self.min_samples_leaf,
'min_weight_fraction_leaf': self.min_weight_fraction_leaf,
'max_features': self.max_features,
'max_leaf_nodes': self.max_leaf_nodes,
'min_impurity_decrease': self.min_impurity_decrease,
'random_state': None,
}
if not sklearn_check_version('1.0'):
params['min_impurity_split'] = self.min_impurity_split
est = DecisionTreeClassifier(**params)
# we need to set est.tree_ field with Trees constructed from Intel(R)
# oneAPI Data Analytics Library solution
estimators_ = []
random_state_checked = check_random_state(self.random_state)
for i in range(self.n_estimators):
est_i = clone(est)
est_i.set_params(random_state=random_state_checked.randint(
np.iinfo(np.int32).max))
if sklearn_check_version('1.0'):
est_i.n_features_in_ = self.n_features_in_
else:
est_i.n_features_ = self.n_features_in_
est_i.n_outputs_ = self.n_outputs_
tree_i_state_class = daal4py.getTreeState(self.daal_model_, i)
tree_i_state_dict = {
'max_depth': tree_i_state_class.max_depth,
'node_count': tree_i_state_class.node_count,
'nodes': tree_i_state_class.node_ar,
'values': tree_i_state_class.value_ar
}
est_i.tree_ = Tree(self.n_features_in_, np.array([1],
dtype=np.intp),
self.n_outputs_)
est_i.tree_.__setstate__(tree_i_state_dict)
estimators_.append(est_i)
return estimators_
def _estimators_(self):
if hasattr(self, '_cached_estimators_'):
if self._cached_estimators_:
return self._cached_estimators_
if LooseVersion(sklearn_version) >= LooseVersion("0.22"):
check_is_fitted(self)
else:
check_is_fitted(self, 'daal_model_')
# convert model to estimators
est = DecisionTreeRegressor(
criterion=self.criterion,
max_depth=self.max_depth,
min_samples_split=self.min_samples_split,
min_samples_leaf=self.min_samples_leaf,
min_weight_fraction_leaf=self.min_weight_fraction_leaf,
max_features=self.max_features,
max_leaf_nodes=self.max_leaf_nodes,
min_impurity_decrease=self.min_impurity_decrease,
min_impurity_split=self.min_impurity_split,
random_state=None)
# we need to set est.tree_ field with Trees constructed from Intel(R)
# oneAPI Data Analytics Library solution
estimators_ = []
random_state_checked = check_random_state(self.random_state)
for i in range(self.n_estimators):
est_i = clone(est)
est_i.set_params(random_state=random_state_checked.randint(
np.iinfo(np.int32).max))
est_i.n_features_ = self.n_features_
est_i.n_outputs_ = self.n_outputs_
tree_i_state_class = daal4py.getTreeState(self.daal_model_, i)
tree_i_state_dict = {
'max_depth': tree_i_state_class.max_depth,
'node_count': tree_i_state_class.node_count,
'nodes': tree_i_state_class.node_ar,
'values': tree_i_state_class.value_ar
}
est_i.tree_ = Tree(self.n_features_, np.array([1], dtype=np.intp),
self.n_outputs_)
est_i.tree_.__setstate__(tree_i_state_dict)
estimators_.append(est_i)
return estimators_
import daal4py as d4p
from numpy import loadtxt, allclose
from gradient_boosted_regression_batch import main as gbt_regression
def printTree(nodes, values):
def printNodes(node_id, nodes, values, level):
node = nodes[node_id]
value = values[node_id]
if not math.isnan(node["threshold"]):
print(" " * level + "Level " + str(level) + ": Feature = " + str(node["feature"]) + ", Threshold = " + str(node["threshold"]))
else:
print(" " * level + "Level " + str(level) + ", Value = " + str(value).replace(" ", ""))
if node["left_child"] != -1:
printNodes(node["left_child"], nodes, values, level + 1)
if node["right_child"] != -1:
printNodes(node["right_child"], nodes, values, level + 1)
printNodes(0, nodes, values, 0)
if __name__ == "__main__":
# First get our result and model
(train_result, _, _) = gbt_regression()
# Retrieve and print all trees; encoded as in sklearn.ensamble.tree_.Tree
for treeId in range(train_result.model.NumberOfTrees):
treeState = d4p.getTreeState(train_result.model, treeId)
printTree(treeState.node_ar, treeState.value_ar)
print('Traversed {} trees.'.format(train_result.model.NumberOfTrees))
print('All looks good!')
def _estimators_(self):
if hasattr(self, '_cached_estimators_'):
if self._cached_estimators_:
return self._cached_estimators_
if LooseVersion(sklearn_version) >= LooseVersion("0.22"):
check_is_fitted(self)
else:
check_is_fitted(self, 'daal_model_')
classes_ = self.classes_[0]
n_classes_ = self.n_classes_[0]
# convert model to estimators
params = {
'criterion': self.criterion,
'max_depth': self.max_depth,
'min_samples_split': self.min_samples_split,
'min_samples_leaf': self.min_samples_leaf,
'min_weight_fraction_leaf': self.min_weight_fraction_leaf,
'max_features': self.max_features,
'max_leaf_nodes': self.max_leaf_nodes,
'min_impurity_decrease': self.min_impurity_decrease,
'random_state': None,
}
if not sklearn_check_version('1.0'):
params['min_impurity_split'] = self.min_impurity_split
est = DecisionTreeClassifier(**params)
# we need to set est.tree_ field with Trees constructed from Intel(R)
# oneAPI Data Analytics Library solution
estimators_ = []
random_state_checked = check_random_state(self.random_state)
for i in range(self.n_estimators):
# print("Tree #{}".format(i))
est_i = clone(est)
est_i.set_params(random_state=random_state_checked.randint(
np.iinfo(np.int32).max))
if sklearn_check_version('1.0'):
est_i.n_features_in_ = self.n_features_in_
else:
est_i.n_features_ = self.n_features_in_
est_i.n_outputs_ = self.n_outputs_
est_i.classes_ = classes_
est_i.n_classes_ = n_classes_
# treeState members: 'class_count', 'leaf_count', 'max_depth',
# 'node_ar', 'node_count', 'value_ar'
tree_i_state_class = daal4py.getTreeState(self.daal_model_, i,
n_classes_)
# node_ndarray = tree_i_state_class.node_ar
# value_ndarray = tree_i_state_class.value_ar
# value_shape = (node_ndarray.shape[0], self.n_outputs_,
# n_classes_)
# assert np.allclose(
# value_ndarray, value_ndarray.astype(np.intc, casting='unsafe')
# ), "Value array is non-integer"
tree_i_state_dict = {
'max_depth': tree_i_state_class.max_depth,
'node_count': tree_i_state_class.node_count,
'nodes': tree_i_state_class.node_ar,
'values': tree_i_state_class.value_ar
}
est_i.tree_ = Tree(self.n_features_in_,
np.array([n_classes_], dtype=np.intp),
self.n_outputs_)
est_i.tree_.__setstate__(tree_i_state_dict)
estimators_.append(est_i)
self._cached_estimators_ = estimators_
return estimators_
def daal_fit(self, X, y):
self._check_daal_supported_parameters()
_supported_dtypes_ = [np.double, np.single]
X = check_array(X, dtype=_supported_dtypes_)
y = np.atleast_1d(y)
if y.ndim == 2 and y.shape[1] == 1:
warnings.warn(
"A column-vector y was passed when a 1d array was"
" expected. Please change the shape of y to "
"(n_samples,), for example using ravel().",
DataConversionWarning,
stacklevel=2)
y = check_array(y, ensure_2d=False, dtype=X.dtype)
check_consistent_length(X, y)
if y.ndim == 1:
# reshape is necessary to preserve the data contiguity against vs
# [:, np.newaxis] that does not.
y = np.reshape(y, (-1, 1))
self.n_outputs_ = y.shape[1]
self.n_features_ = X.shape[1]
rs_ = check_random_state(self.random_state)
if not self.bootstrap and self.oob_score:
raise ValueError("Out of bag estimation only available"
" if bootstrap=True")
X_fptype = getFPType(X)
seed_ = rs_.randint(0, np.iinfo('i').max)
daal_engine = daal4py.engines_mt2203(seed=seed_, fptype=X_fptype)
_featuresPerNode = _to_absolute_max_features(self.max_features,
X.shape[1],
is_classification=False)
# create algorithm
dfr_algorithm = daal4py.decision_forest_regression_training(
fptype=getFPType(X),
method='defaultDense',
nTrees=int(self.n_estimators),
observationsPerTreeFraction=1,
featuresPerNode=int(_featuresPerNode),
maxTreeDepth=int(0 if self.max_depth is None else self.max_depth),
minObservationsInLeafNode=1,
engine=daal_engine,
impurityThreshold=float(0.0 if self.min_impurity_split is None else
self.min_impurity_split),
varImportance="MDI",
resultsToCompute="",
memorySavingMode=False,
bootstrap=bool(self.bootstrap))
dfr_trainingResult = dfr_algorithm.compute(X, y)
# get resulting model
model = dfr_trainingResult.model
self.daal_model_ = model
# convert model to estimators
est = DecisionTreeRegressor(
criterion=self.criterion,
max_depth=self.max_depth,
min_samples_split=self.min_samples_split,
min_samples_leaf=self.min_samples_leaf,
min_weight_fraction_leaf=self.min_weight_fraction_leaf,
max_features=self.max_features,
max_leaf_nodes=self.max_leaf_nodes,
min_impurity_decrease=self.min_impurity_decrease,
min_impurity_split=self.min_impurity_split,
random_state=None)
# we need to set est.tree_ field with Trees constructed from Intel(R) DAAL solution
estimators_ = []
for i in range(self.n_estimators):
est_i = clone(est)
est_i.n_features_ = self.n_features_
est_i.n_outputs_ = self.n_outputs_
tree_i_state_class = daal4py.getTreeState(model, i)
tree_i_state_dict = {
'max_depth': tree_i_state_class.max_depth,
'node_count': tree_i_state_class.node_count,
'nodes': tree_i_state_class.node_ar,
'values': tree_i_state_class.value_ar
}
est_i.tree_ = Tree(self.n_features_, np.array([1], dtype=np.intp),
self.n_outputs_)
est_i.tree_.__setstate__(tree_i_state_dict)
estimators_.append(est_i)
self.estimators_ = estimators_
# compute oob_score_
if self.oob_score:
self._set_oob_score(X, y)
return self
def daal_fit(self, X, y):
self._check_daal_supported_parameters()
_supported_dtypes_ = [np.single, np.double]
X = check_array(X, dtype=_supported_dtypes_)
y = np.atleast_1d(y)
if y.ndim == 2 and y.shape[1] == 1:
warnings.warn(
"A column-vector y was passed when a 1d array was"
" expected. Please change the shape of y to "
"(n_samples,), for example using ravel().",
DataConversionWarning,
stacklevel=2)
check_consistent_length(X, y)
if y.ndim == 1:
# reshape is necessary to preserve the data contiguity against vs
# [:, np.newaxis] that does not.
y = np.reshape(y, (-1, 1))
self.n_outputs_ = y.shape[1]
if self.n_outputs_ != 1:
_class_name = self.__class__.__name__
raise ValueError(
_class_name +
" does not currently support multi-output data. Consider using OneHotEncoder"
)
y = check_array(y, ensure_2d=False, dtype=None)
y, _ = self._validate_y_class_weight(y)
self.n_classes_ = self.n_classes_[0]
self.classes_ = self.classes_[0]
self.n_features_ = X.shape[1]
rs_ = check_random_state(self.random_state)
seed_ = rs_.randint(0, np.iinfo('i').max)
if self.n_classes_ < 2:
raise ValueError(
"Training data only contain information about one class.")
# create algorithm
X_fptype = getFPType(X)
daal_engine_ = daal4py.engines_mt2203(seed=seed_, fptype=X_fptype)
_featuresPerNode = _to_absolute_max_features(self.max_features,
X.shape[1],
is_classification=False)
dfc_algorithm = daal4py.decision_forest_classification_training(
nClasses=int(self.n_classes_),
fptype=X_fptype,
method='defaultDense',
nTrees=int(self.n_estimators),
observationsPerTreeFraction=1,
featuresPerNode=int(_featuresPerNode),
maxTreeDepth=int(0 if self.max_depth is None else self.max_depth),
minObservationsInLeafNode=1,
engine=daal_engine_,
impurityThreshold=float(0.0 if self.min_impurity_split is None else
self.min_impurity_split),
varImportance="MDI",
resultsToCompute="",
memorySavingMode=False,
bootstrap=bool(self.bootstrap))
# compute
dfc_trainingResult = dfc_algorithm.compute(X, y)
# get resulting model
model = dfc_trainingResult.model
self.daal_model_ = model
# convert model to estimators
est = DecisionTreeClassifier(
criterion=self.criterion,
max_depth=self.max_depth,
min_samples_split=self.min_samples_split,
min_samples_leaf=self.min_samples_leaf,
min_weight_fraction_leaf=self.min_weight_fraction_leaf,
max_features=self.max_features,
max_leaf_nodes=self.max_leaf_nodes,
min_impurity_decrease=self.min_impurity_decrease,
min_impurity_split=self.min_impurity_split,
random_state=None)
# we need to set est.tree_ field with Trees constructed from Intel(R) DAAL solution
estimators_ = []
for i in range(self.n_estimators):
# print("Tree #{}".format(i))
est_i = clone(est)
est_i.n_features_ = self.n_features_
est_i.n_outputs_ = self.n_outputs_
est_i.classes_ = self.classes_
est_i.n_classes_ = self.n_classes_
# treeState members: 'class_count', 'leaf_count', 'max_depth', 'node_ar', 'node_count', 'value_ar'
tree_i_state_class = daal4py.getTreeState(model, i,
self.n_classes_)
node_ndarray = tree_i_state_class.node_ar
value_ndarray = tree_i_state_class.value_ar
value_shape = (node_ndarray.shape[0], self.n_outputs_,
self.n_classes_)
# assert np.allclose(value_ndarray, value_ndarray.astype(np.intc, casting='unsafe')), "Value array is non-integer"
tree_i_state_dict = {
'max_depth': tree_i_state_class.max_depth,
'node_count': tree_i_state_class.node_count,
'nodes': tree_i_state_class.node_ar,
'values': tree_i_state_class.value_ar
}
#
est_i.tree_ = Tree(self.n_features_,
np.array([self.n_classes_], dtype=np.intp),
self.n_outputs_)
est_i.tree_.__setstate__(tree_i_state_dict)
estimators_.append(est_i)
self.estimators_ = estimators_
# compute oob_score_
if self.oob_score:
self._set_oob_score(X, y)
return self
