def transform(self, **Xy):
"""
Parameter
---------
Xy: dictionary
parameters for fit and transform
"""
if conf.KW_SPLIT_TRAIN_TEST in Xy:
Xy_train, Xy_test = train_test_split(Xy)
res = self.estimator.fit(**_sub_dict(Xy_train, self.in_args_fit))
# catch args_transform in ds, transform, store output in a dict
Xy_out_tr = _as_dict(self.estimator.transform(
**_sub_dict(Xy_train, self.in_args_transform)),
keys=self.in_args_transform)
Xy_out_te = _as_dict(self.estimator.transform(**_sub_dict(Xy_test,
self.in_args_transform)),
keys=self.in_args_transform)
Xy_out = train_test_merge(Xy_out_tr, Xy_out_te)
else:
res = self.estimator.fit(**_sub_dict(Xy, self.in_args_fit))
# catch args_transform in ds, transform, store output in a dict
Xy_out = _as_dict(self.estimator.transform(**_sub_dict(Xy,
self.in_args_transform)),
keys=self.in_args_transform)
# update ds with transformed values
Xy.update(Xy_out)
return Xy
def transform(self, **Xy):
"""
Parameter
---------
Xy: dictionary
parameters for transform
"""
if conf.KW_SPLIT_TRAIN_TEST in Xy:
Xy_train, Xy_test = train_test_split(Xy)
# catch args_transform in ds, transform, store output in a dict
Xy_out_tr = self.wrapped_node.transform(
**_sub_dict(Xy_train, self.in_args_transform))
Xy_out_te = self.wrapped_node.transform(
**_sub_dict(Xy_test, self.in_args_transform))
if type(Xy_out_tr) is not dict or type(Xy_out_te) is not dict:
raise ValueError("%s.transform should return a dictionary" %
(self.wrapped_node.__class__.__name__))
Xy_out = train_test_merge(Xy_out_tr, Xy_out_te)
else:
# catch args_transform in ds, transform, store output in a dict
Xy_out = self.wrapped_node.transform(
**_sub_dict(Xy, self.in_args_transform))
if type(Xy_out) is not dict:
raise ValueError("%s.transform should return a dictionary" %
(self.wrapped_node.__class__.__name__))
return Xy_out
def transform(self, **Xy):
"""
Parameter
---------
Xy: dictionary
parameters for transform
"""
if conf.KW_SPLIT_TRAIN_TEST in Xy:
Xy_train, Xy_test = train_test_split(Xy)
# catch args_transform in ds, transform, store output in a dict
Xy_out_tr = self.wrapped_node.transform(**_sub_dict(
Xy_train,
self.in_args_transform))
Xy_out_te = self.wrapped_node.transform(**_sub_dict(
Xy_test,
self.in_args_transform))
if type(Xy_out_tr) is not dict or type(Xy_out_te) is not dict:
raise ValueError("%s.transform should return a dictionary"
% (self.wrapped_node.__class__.__name__))
Xy_out = train_test_merge(Xy_out_tr, Xy_out_te)
else:
# catch args_transform in ds, transform, store output in a dict
Xy_out = self.wrapped_node.transform(**_sub_dict(Xy,
self.in_args_transform))
if type(Xy_out) is not dict:
raise ValueError("%s.transform should return a dictionary"
% (self.wrapped_node.__class__.__name__))
return Xy_out
def __init__(self, *nodes):
super(Methods, self).__init__()
for node in nodes:
node_cp = copy.deepcopy(node)
node_cp = node_cp if isinstance(node_cp, BaseNode) else \
LeafEstimator(node_cp)
self.add_child(node_cp)
curr_nodes = self.children
leaves_key = [l.get_key() for l in self.walk_leaves()]
curr_nodes_key = [c.get_key() for c in curr_nodes]
while len(leaves_key) != len(set(leaves_key)) and curr_nodes:
curr_nodes_state = [c.get_parameters() for c in curr_nodes]
curr_nodes_next = list()
for key in set(curr_nodes_key):
collision_indices = _list_indices(curr_nodes_key, key)
if len(collision_indices) == 1: # no collision for this cls
continue
diff_arg_keys = dict_diff(*[curr_nodes_state[i] for i
in collision_indices]).keys()
for curr_node_idx in collision_indices:
if diff_arg_keys:
curr_nodes[curr_node_idx].signature_args = \
_sub_dict(curr_nodes_state[curr_node_idx],
diff_arg_keys)
curr_nodes_next += curr_nodes[curr_node_idx].children
curr_nodes = curr_nodes_next
curr_nodes_key = [c.get_key() for c in curr_nodes]
leaves_key = [l.get_key() for l in self.walk_leaves()]
leaves_key = [l.get_key() for l in self.walk_leaves()]
if len(leaves_key) != len(set(leaves_key)):
raise ValueError("Some methods are identical, they could not be "
"differentiated according to their arguments")
def __init__(self, *nodes):
super(Methods, self).__init__()
for node in nodes:
node_cp = copy.deepcopy(node)
node_cp = NodeFactory.build(node_cp)
self.add_child(node_cp)
curr_nodes = self.children
leaves_key = [l.get_key() for l in self.walk_leaves()]
curr_nodes_key = [c.get_key() for c in curr_nodes]
while len(leaves_key) != len(set(leaves_key)) and curr_nodes:
curr_nodes_state = [c.get_parameters() for c in curr_nodes]
curr_nodes_next = list()
for key in set(curr_nodes_key):
collision_indices = _list_indices(curr_nodes_key, key)
if len(collision_indices) == 1: # no collision for this cls
continue
diff_arg_keys = dict_diff(
*[curr_nodes_state[i] for i in collision_indices]).keys()
for curr_node_idx in collision_indices:
if diff_arg_keys:
curr_nodes[curr_node_idx].signature_args = \
_sub_dict(curr_nodes_state[curr_node_idx],
diff_arg_keys)
curr_nodes_next += curr_nodes[curr_node_idx].children
curr_nodes = curr_nodes_next
curr_nodes_key = [c.get_key() for c in curr_nodes]
leaves_key = [l.get_key() for l in self.walk_leaves()]
leaves_key = [l.get_key() for l in self.walk_leaves()]
if len(leaves_key) != len(set(leaves_key)):
raise ValueError("Some methods are identical, they could not be "
"differentiated according to their arguments")
def transform(self, **Xy):
"""
Parameter
---------
Xy: dictionary
parameters for fit and transform
"""
if conf.KW_SPLIT_TRAIN_TEST in Xy:
Xy_train, Xy_test = train_test_split(Xy)
Xy_out = dict()
# Train fit
res = self.estimator.fit(**_sub_dict(Xy_train, self.in_args_fit))
# Train predict
Xy_out_tr = _as_dict(self.estimator.predict(**_sub_dict(Xy_train,
self.in_args_predict)),
keys=self.out_args_predict)
Xy_out_tr = _dict_suffix_keys(Xy_out_tr,
suffix=conf.SEP + conf.TRAIN + conf.SEP + conf.PREDICTION)
Xy_out.update(Xy_out_tr)
# Test predict
Xy_out_te = _as_dict(self.estimator.predict(**_sub_dict(Xy_test,
self.in_args_predict)),
keys=self.out_args_predict)
Xy_out_te = _dict_suffix_keys(Xy_out_te,
suffix=conf.SEP + conf.TEST + conf.SEP + conf.PREDICTION)
Xy_out.update(Xy_out_te)
## True test
Xy_test_true = _sub_dict(Xy_test, self.out_args_predict)
Xy_out_true = _dict_suffix_keys(Xy_test_true,
suffix=conf.SEP + conf.TEST + conf.SEP + conf.TRUE)
Xy_out.update(Xy_out_true)
else:
res = self.estimator.fit(**_sub_dict(Xy, self.in_args_fit))
# catch args_transform in ds, transform, store output in a dict
Xy_out = _as_dict(self.estimator.predict(**_sub_dict(Xy,
self.in_args_predict)),
keys=self.out_args_predict)
Xy_out = _dict_suffix_keys(Xy_out,
suffix=conf.SEP + conf.PREDICTION)
## True test
Xy_true = _sub_dict(Xy, self.out_args_predict)
Xy_out_true = _dict_suffix_keys(Xy_true,
suffix=conf.SEP + conf.TRUE)
Xy_out.update(Xy_out_true)
return Xy_out
def transform(self, **Xy):
"""
Parameter
---------
Xy: dictionary
parameters for fit and transform
"""
is_fit_predict = False
is_fit_transform = False
if (hasattr(self.wrapped_node, "transform") and
hasattr(self.wrapped_node, "predict")):
if not self.children:
# leaf node
is_fit_predict = True
else:
# internal node
is_fit_transform = True
elif hasattr(self.wrapped_node, "transform"):
is_fit_transform = True
elif hasattr(self.wrapped_node, "predict"):
is_fit_predict = True
if is_fit_transform:
Xy_train, Xy_test = train_test_split(Xy)
if Xy_train is not Xy_test:
res = self.wrapped_node.fit(**_sub_dict(Xy_train,
self.in_args_fit))
Xy_out_tr = self._wrapped_node_transform(**Xy_train)
Xy_out_te = self._wrapped_node_transform(**Xy_test)
Xy_out = train_test_merge(Xy_out_tr, Xy_out_te)
else:
res = self.wrapped_node.fit(**_sub_dict(Xy, self.in_args_fit))
Xy_out = self._wrapped_node_transform(**Xy)
# update ds with transformed values
Xy.update(Xy_out)
return Xy
elif is_fit_predict:
Xy_train, Xy_test = train_test_split(Xy)
if Xy_train is not Xy_test:
Xy_out = dict()
res = self.wrapped_node.fit(**_sub_dict(Xy_train,
self.in_args_fit))
Xy_out_tr = self._wrapped_node_predict(**Xy_train)
Xy_out_tr = _dict_suffix_keys(
Xy_out_tr,
suffix=conf.SEP + conf.TRAIN + conf.SEP + conf.PREDICTION)
Xy_out.update(Xy_out_tr)
# Test predict
Xy_out_te = self._wrapped_node_predict(**Xy_test)
Xy_out_te = _dict_suffix_keys(
Xy_out_te,
suffix=conf.SEP + conf.TEST + conf.SEP + conf.PREDICTION)
Xy_out.update(Xy_out_te)
## True test
Xy_test_true = _sub_dict(Xy_test, self.out_args_predict)
Xy_out_true = _dict_suffix_keys(
Xy_test_true,
suffix=conf.SEP + conf.TEST + conf.SEP + conf.TRUE)
Xy_out.update(Xy_out_true)
else:
res = self.wrapped_node.fit(**_sub_dict(Xy, self.in_args_fit))
Xy_out = self._wrapped_node_predict(**Xy)
Xy_out = _dict_suffix_keys(
Xy_out,
suffix=conf.SEP + conf.PREDICTION)
## True test
Xy_true = _sub_dict(Xy, self.out_args_predict)
Xy_out_true = _dict_suffix_keys(
Xy_true,
suffix=conf.SEP + conf.TRUE)
Xy_out.update(Xy_out_true)
return Xy_out
else:
raise ValueError("%s should implement either transform or predict"
% self.wrapped_node.__class__.__name__)
def _wrapped_node_predict(self, **Xy):
Xy_out = _as_dict(self.wrapped_node.predict(
**_sub_dict(Xy, self.in_args_predict)),
keys=self.out_args_predict)
return Xy_out
def _wrapped_node_transform(self, **Xy):
Xy_out = _as_dict(self.wrapped_node.transform(
**_sub_dict(Xy, self.in_args_transform)),
keys=self.in_args_transform)
return Xy_out
def transform(self, **Xy):
"""
Parameter
---------
Xy: dictionary
parameters for fit and transform
"""
is_fit_predict = False
is_fit_transform = False
if (hasattr(self.wrapped_node, "transform") and
hasattr(self.wrapped_node, "predict")):
if not self.children:
# leaf node
is_fit_predict = True
else:
# internal node
is_fit_transform = True
elif hasattr(self.wrapped_node, "transform"):
is_fit_transform = True
elif hasattr(self.wrapped_node, "predict"):
is_fit_predict = True
if is_fit_transform:
Xy_train, Xy_test = train_test_split(Xy)
if Xy_train is not Xy_test:
res = self.wrapped_node.fit(**_sub_dict(Xy_train,
self.in_args_fit))
Xy_out_tr = self._wrapped_node_transform(**Xy_train)
Xy_out_te = self._wrapped_node_transform(**Xy_test)
Xy_out = train_test_merge(Xy_out_tr, Xy_out_te)
else:
res = self.wrapped_node.fit(**_sub_dict(Xy, self.in_args_fit))
Xy_out = self._wrapped_node_transform(**Xy)
# update ds with transformed values
Xy.update(Xy_out)
return Xy
elif is_fit_predict:
Xy_train, Xy_test = train_test_split(Xy)
if Xy_train is not Xy_test:
Xy_out = dict()
res = self.wrapped_node.fit(**_sub_dict(Xy_train,
self.in_args_fit))
Xy_out_tr = self._wrapped_node_predict(**Xy_train)
Xy_out_tr = _dict_suffix_keys(
Xy_out_tr,
suffix=conf.SEP + conf.TRAIN + conf.SEP + conf.PREDICTION)
Xy_out.update(Xy_out_tr)
# Test predict
Xy_out_te = self._wrapped_node_predict(**Xy_test)
Xy_out_te = _dict_suffix_keys(
Xy_out_te,
suffix=conf.SEP + conf.TEST + conf.SEP + conf.PREDICTION)
Xy_out.update(Xy_out_te)
## True test
Xy_test_true = _sub_dict(Xy_test, self.out_args_predict)
Xy_out_true = _dict_suffix_keys(
Xy_test_true,
suffix=conf.SEP + conf.TEST + conf.SEP + conf.TRUE)
Xy_out.update(Xy_out_true)
else:
res = self.wrapped_node.fit(**_sub_dict(Xy, self.in_args_fit))
Xy_out = self._wrapped_node_predict(**Xy)
Xy_out = _dict_suffix_keys(
Xy_out,
suffix=conf.SEP + conf.PREDICTION)
## True test
Xy_true = _sub_dict(Xy, self.out_args_predict)
Xy_out_true = _dict_suffix_keys(
Xy_true,
suffix=conf.SEP + conf.TRUE)
Xy_out.update(Xy_out_true)
return Xy_out
else:
raise ValueError("%s should implement either transform or predict"
% self.wrapped_node.__class__.__name__)
def _wrapped_node_predict(self, **Xy):
Xy_out = _as_dict(self.wrapped_node.predict(
**_sub_dict(Xy, self.in_args_predict)),
keys=self.out_args_predict)
return Xy_out
def _wrapped_node_transform(self, **Xy):
Xy_out = _as_dict(self.wrapped_node.transform(
**_sub_dict(Xy, self.in_args_transform)),
keys=self.in_args_transform)
return Xy_out
