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 __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 __init__(self, node, n_perms=100, permute="y", random_state=None,
reducer=PvalPerms(), col_or_row=False, **kwargs):
super(Perms, self).__init__(**kwargs)
self.n_perms = n_perms
self.permute = permute # the name of the bloc to be permuted
self.random_state = random_state
self.reducer = reducer
self.slicer = CRSlicer(signature_name="Perm",
nb=0,
apply_on=permute,
col_or_row=col_or_row)
self.children = VirtualList(size=n_perms,
parent=self)
self.slicer.parent = self
subtree = NodeFactory.build(node)
# subtree = node if isinstance(node, BaseNode) else LeafEstimator(node)
self.slicer.add_child(subtree)
self.col_or_row = col_or_row
def __init__(self, node, n_folds=5, random_state=None,
cv_type="stratified", cv_key="y", reducer=ClassificationReport(),
**kwargs):
super(CV, self).__init__(**kwargs)
self.n_folds = n_folds
self.random_state = random_state
self.cv_type = cv_type
self.cv_key = cv_key
self.reducer = reducer
self.slicer = CRSlicer(signature_name="CV",
nb=0,
apply_on=None,
col_or_row=False)
self.children = VirtualList(size=n_folds,
parent=self)
self.slicer.parent = self
subtree = NodeFactory.build(node)
# subtree = node if isinstance(node, BaseNode) else LeafEstimator(node)
self.slicer.add_child(subtree)
def __init__(self, node, indices_of_groups, col_or_row=True):
super(CRSplitter, self).__init__()
self.indices_of_groups = indices_of_groups
self.slicer = CRSlicer(signature_name=self.__class__.__name__,
nb=0,
apply_on=None,
col_or_row=col_or_row)
self.uni_indices_of_groups = {}
for key_indices_of_groups in indices_of_groups:
self.uni_indices_of_groups[key_indices_of_groups] = \
list(set(indices_of_groups[key_indices_of_groups]))
self.size = 1
for key_indices_of_groups in self.uni_indices_of_groups:
tmp_data = list(self.uni_indices_of_groups[key_indices_of_groups])
self.size = self.size * len(tmp_data)
self.children = VirtualList(size=self.size, parent=self)
self.slicer.parent = self
subtree = NodeFactory.build(node)
# subtree = node if isinstance(node, BaseNode) else LeafEstimator(node)
self.slicer.add_child(subtree)
def __init__(self,
node,
n_perms=100,
permute="y",
random_state=None,
reducer=PvalPerms(),
col_or_row=False,
**kwargs):
super(Perms, self).__init__(**kwargs)
self.n_perms = n_perms
self.permute = permute # the name of the bloc to be permuted
self.random_state = random_state
self.reducer = reducer
self.slicer = CRSlicer(signature_name="Perm",
nb=0,
apply_on=permute,
col_or_row=col_or_row)
self.children = VirtualList(size=n_perms, parent=self)
self.slicer.parent = self
subtree = NodeFactory.build(node)
# subtree = node if isinstance(node, BaseNode) else LeafEstimator(node)
self.slicer.add_child(subtree)
self.col_or_row = col_or_row
def __init__(self,
node,
n_folds=5,
random_state=None,
cv_type="stratified",
cv_key="y",
reducer=ClassificationReport(),
**kwargs):
super(CV, self).__init__(**kwargs)
self.n_folds = n_folds
self.random_state = random_state
self.cv_type = cv_type
self.cv_key = cv_key
self.reducer = reducer
self.slicer = CRSlicer(signature_name="CV",
nb=0,
apply_on=None,
col_or_row=False)
self.children = VirtualList(size=n_folds, parent=self)
self.slicer.parent = self
subtree = NodeFactory.build(node)
# subtree = node if isinstance(node, BaseNode) else LeafEstimator(node)
self.slicer.add_child(subtree)
def __init__(self, node, indices_of_groups, col_or_row=True):
super(CRSplitter, self).__init__()
self.indices_of_groups = indices_of_groups
self.slicer = CRSlicer(signature_name=self.__class__.__name__,
nb=0,
apply_on=None,
col_or_row=col_or_row)
self.uni_indices_of_groups = {}
for key_indices_of_groups in indices_of_groups:
self.uni_indices_of_groups[key_indices_of_groups] = \
list(set(indices_of_groups[key_indices_of_groups]))
self.size = 1
for key_indices_of_groups in self.uni_indices_of_groups:
tmp_data = list(self.uni_indices_of_groups[key_indices_of_groups])
self.size = self.size * len(tmp_data)
self.children = VirtualList(size=self.size, parent=self)
self.slicer.parent = self
subtree = NodeFactory.build(node)
# subtree = node if isinstance(node, BaseNode) else LeafEstimator(node)
self.slicer.add_child(subtree)
def Pipe(*nodes):
"""
Pipelineuential execution of Nodes.
Parameters
----------
task [, task]*
Example
-------
>>> from epac import Pipe
>>> from sklearn import datasets
>>> from sklearn.feature_selection import SelectKBest
>>> from sklearn.lda import LDA
>>> from sklearn.svm import SVC
>>>
>>> X, y = datasets.make_classification(n_samples=12,
... n_features=10,
... n_informative=2,
... random_state=1)
>>> pipe = Pipe(SelectKBest(k=2), LDA())
>>> pipe.transform(X=X, y=y)
{'y': array([1, 0, 0, 1, 0, 0, 1, 0, 1, 1, 0, 1]), 'X': array([[-0.34385368, 0.75623409],
[ 0.19829972, -1.16389861],
[-0.74715829, 0.86977629],
[ 1.13162939, 0.90876519],
[ 0.23009474, -0.68017257],
[ 0.16003707, -1.55458039],
[ 0.40349164, 1.38791468],
[-1.11731035, 0.23476552],
[ 1.19891788, 0.0888684 ],
[-0.75439794, -0.90039992],
[ 0.12015895, 2.05996541],
[-0.20889423, 2.05313908]])}
>>>
>>> pipe2 = Pipe(Pipe(SelectKBest(k=2), LDA()), SVC())
>>> pipe2.transform(X=X, y=y)
{'y': array([1, 0, 0, 1, 0, 0, 1, 0, 1, 1, 0, 1]), 'X': array([[-0.34385368, 0.75623409],
[ 0.19829972, -1.16389861],
[-0.74715829, 0.86977629],
[ 1.13162939, 0.90876519],
[ 0.23009474, -0.68017257],
[ 0.16003707, -1.55458039],
[ 0.40349164, 1.38791468],
[-1.11731035, 0.23476552],
[ 1.19891788, 0.0888684 ],
[-0.75439794, -0.90039992],
[ 0.12015895, 2.05996541],
[-0.20889423, 2.05313908]])}
"""
root = None
prev = None
for i in range(len(nodes)):
node = nodes[i]
curr = NodeFactory.build(node)
if not root:
root = curr
else:
__insert_node_at_leaf(curr, prev)
# prev.add_child(curr)
prev = curr
return root
def Pipe(*nodes):
"""
Pipelineuential execution of Nodes.
Parameters
----------
task [, task]*
Example
-------
>>> from epac import Pipe
>>> from sklearn import datasets
>>> from sklearn.feature_selection import SelectKBest
>>> from sklearn.lda import LDA
>>> from sklearn.svm import SVC
>>>
>>> X, y = datasets.make_classification(n_samples=12,
... n_features=10,
... n_informative=2,
... random_state=1)
>>> pipe = Pipe(SelectKBest(k=2), LDA())
>>> pipe.transform(X=X, y=y)
{'y': array([1, 0, 0, 1, 0, 0, 1, 0, 1, 1, 0, 1]), 'X': array([[-0.34385368, 0.75623409],
[ 0.19829972, -1.16389861],
[-0.74715829, 0.86977629],
[ 1.13162939, 0.90876519],
[ 0.23009474, -0.68017257],
[ 0.16003707, -1.55458039],
[ 0.40349164, 1.38791468],
[-1.11731035, 0.23476552],
[ 1.19891788, 0.0888684 ],
[-0.75439794, -0.90039992],
[ 0.12015895, 2.05996541],
[-0.20889423, 2.05313908]])}
>>>
>>> pipe2 = Pipe(Pipe(SelectKBest(k=2), LDA()), SVC())
>>> pipe2.transform(X=X, y=y)
{'y': array([1, 0, 0, 1, 0, 0, 1, 0, 1, 1, 0, 1]), 'X': array([[-0.34385368, 0.75623409],
[ 0.19829972, -1.16389861],
[-0.74715829, 0.86977629],
[ 1.13162939, 0.90876519],
[ 0.23009474, -0.68017257],
[ 0.16003707, -1.55458039],
[ 0.40349164, 1.38791468],
[-1.11731035, 0.23476552],
[ 1.19891788, 0.0888684 ],
[-0.75439794, -0.90039992],
[ 0.12015895, 2.05996541],
[-0.20889423, 2.05313908]])}
"""
root = None
prev = None
for i in xrange(len(nodes)):
node = nodes[i]
curr = NodeFactory.build(node)
if not root:
root = curr
else:
__insert_node_at_leaf(curr, prev)
# prev.add_child(curr)
prev = curr
return root
