def _check_feature_ind(self, container):
if not isinstance(container, MultiLabelIndexCollection):
try:
if isinstance(container[0], tuple):
container = MultiLabelIndexCollection(
container, self.X.shape[1])
else:
container = MultiLabelIndexCollection.construct_by_1d_array(
container, label_mat_shape=self.X.shape)
except:
raise ValueError(
"Please pass a 1d array of indexes or MultiLabelIndexCollection (column major, start from 0)"
"or a list of tuples with 2 elements, in which, the 1st element is the index of instance "
"and the 2nd element is the index of features.")
return container
def _check_multi_label_ind(self, container):
"""Check if the given array is an array of multi label indexes."""
if not isinstance(container, MultiLabelIndexCollection):
try:
if isinstance(container[0], tuple):
container = MultiLabelIndexCollection(
container, self.y.shape[1])
else:
container = MultiLabelIndexCollection.construct_by_1d_array(
container, label_mat_shape=self.y.shape)
except:
raise ValueError(
"Please pass a 1d array of indexes or MultiLabelIndexCollection (column major, "
"start from 0) or a list "
"of tuples with 2 elements, in which, the 1st element is the index of instance "
"and the 2nd element is the index of label.")
return copy.copy(container)
print(a_ind)
# ---------MultiLabelIndexCollection-------------
from alipy.index import MultiLabelIndexCollection
multi_lab_ind1 = MultiLabelIndexCollection([(0, 1), (0, 2), (0, (3, 4)),
(1, (0, 1))],
label_size=5)
multi_lab_ind1.update((0, 0))
multi_lab_ind1.update([(1, 2), (1, (3, 4))])
multi_lab_ind1.update([(2, )])
multi_lab_ind1.difference_update([(0, )])
print(multi_lab_ind1)
# matlab style 1d index supporting
b = [1, 4, 11]
mi = MultiLabelIndexCollection.construct_by_1d_array(array=b,
label_mat_shape=(3, 4))
print(mi)
print('col major:', mi.get_onedim_index(order='F', ins_num=3))
print('row major:', mi.get_onedim_index(order='C'))
# mask supporting
mask = np.asarray([[0, 1], [1, 0], [1, 0]]) # 3 rows, 2 lines
mi = MultiLabelIndexCollection.construct_by_element_mask(mask=mask)
print(mi)
mi = MultiLabelIndexCollection([(0, 1), (2, 0), (1, 0)], label_size=2)
print(mi.get_matrix_mask(mat_shape=(3, 2), sparse=False))
# ---------Multi-label tools------------------
from alipy.index import flattern_multilabel_index
def hierarchical_multilabel_mark(multilabel_index, label_index, label_tree, y_true):
""""Complete instance-label information according to hierarchy in the label-tree.
Parameters
----------
label_index: {list, np.ndarray, MultiLabelIndexCollection}
The indexes of labeled samples. It should be a 1d array of indexes (column major, start from 0) or
MultiLabelIndexCollection or a list of tuples with 2 elements, in which,
the 1st element is the index of instance and the 2nd element is the index of labels.
multilabel_index: {list, np.ndarray, MultiLabelIndexCollection}
The indexes of labeled samples. It should be a 1d array of indexes (column major, start from 0) or
MultiLabelIndexCollection or a list of tuples with 2 elements, in which,
the 1st element is the index of instance and the 2nd element is the index of labels.
label_tree: np.ndarray
The hierarchical relationships among data features.
if node_i is the parent of node_j , then label_tree(i,j)=1
y_true: 2D array, optional (default=None)
Label matrix of the whole dataset. It is a reference which will not use additional memory.
shape [n_samples, n_classes]
Returns
-------
selected_ins_lab_pair: list
A list of tuples that contains the indexes of selected instance-label pairs.
"""
# try to convert the indexes
if not isinstance(multilabel_index, MultiLabelIndexCollection):
try:
if isinstance(multilabel_index[0], tuple):
container = MultiLabelIndexCollection(multilabel_index, np.shape(y_true)[1])
else:
container = MultiLabelIndexCollection.construct_by_1d_array(multilabel_index, label_mat_shape=np.shape(y_true))
except:
raise ValueError(
"Please pass a 1d array of indexes or MultiLabelIndexCollection (column major, "
"start from 0) or a list "
"of tuples with 2 elements, in which, the 1st element is the index of instance "
"and the 2nd element is the index of label.")
multilabel_index = copy.deepcopy(container)
if not isinstance(label_index, MultiLabelIndexCollection):
try:
if isinstance(label_index[0], tuple):
container = MultiLabelIndexCollection(label_index, np.shape(y_true)[1])
else:
container = MultiLabelIndexCollection.construct_by_1d_array(label_index, label_mat_shape=np.shape(y_true))
except:
raise ValueError(
"Please pass a 1d array of indexes or MultiLabelIndexCollection (column major, "
"start from 0) or a list "
"of tuples with 2 elements, in which, the 1st element is the index of instance "
"and the 2nd element is the index of label.")
label_index = copy.deepcopy(container)
n_classes = multilabel_index._label_size
assert(np.shape(label_tree)[0] == n_classes and np.shape(label_tree)[1] == n_classes)
add_label_index = MultiLabelIndexCollection(label_size=n_classes)
for instance_label_pair in multilabel_index:
i_instance = instance_label_pair[0]
j_label = instance_label_pair[1]
if y_true[instance_label_pair] == 1:
for descent_label in range(n_classes):
if label_tree[j_label][descent_label] == 1:
if (not (i_instance, descent_label) in label_index):
add_label_index.update((i_instance, descent_label))
elif y_true[instance_label_pair] == -1:
for parent_label in range(n_classes):
if label_tree[parent_label][j_label] == 1:
if (not (i_instance, parent_label) in label_index):
add_label_index.update((i_instance, parent_label))
for i in add_label_index:
if not i in multilabel_index:
multilabel_index.update(i)
return multilabel_index