# -*- coding: utf-8 -*-
from builtins import object
from ..utils import get_matrix_in_format
from sklearn.base import BaseEstimator
[docs]class GraphBuilderBase(object):
"""An abstract base class for a graph building class used in Label Space clustering.
Inherit it in your classifier according to`developer guide <../developer.ipynb>`_.
"""
def __init__(self):
super(GraphBuilderBase, self).__init__()
[docs]class LabelSpaceClustererBase(BaseEstimator):
"""An abstract base class for Label Space clustering
Inherit it in your classifier according to`developer guide <../developer.ipynb>`_.
"""
def __init__(self):
super(LabelSpaceClustererBase, self).__init__()
[docs] def fit_predict(self, X, y):
""" Abstract method for clustering label space
Implement it in your classifier according to`developer guide <../developer.ipynb>`_.
Raises
------
NotImplementedError
this is an abstract method
"""
raise NotImplementedError("LabelSpaceClustererBase::fit_predict()")
[docs]class LabelGraphClustererBase(object):
"""An abstract base class for Label Graph clustering
Inherit it in your classifier according to`developer guide <../developer.ipynb>`_.
"""
def __init__(self, graph_builder):
"""
Attributes
----------
graph_builder : a GraphBuilderBase derivative class
a graph building class for the clusterer
"""
super(LabelGraphClustererBase, self).__init__()
self.graph_builder = graph_builder
[docs] def fit_predict(self, X, y):
""" Abstract method for clustering label space
Implement it in your classifier according to`developer guide <../developer.ipynb>`_.
Raises
------
NotImplementedError
this is an abstract method
"""
raise NotImplementedError("LabelGraphClustererBase::fit_predict()")
[docs]class LabelCooccurrenceGraphBuilder(GraphBuilderBase):
"""Base class providing API and common functions for all label
co-occurence based multi-label classifiers.
This graph builder constructs a Label Graph based on the output matrix where two label nodes are connected
when at least one sample is labeled with both of them. If the graph is weighted, the weight of an edge between two
label nodes is the number of samples labeled with these two labels. Self-edge weights contain the number of samples
with a given label.
Parameters
----------
weighted: bool
decide whether to generate a weighted or unweighted graph.
include_self_edges : bool
decide whether to include self-edge i.e. label 1 - label 1 in
co-occurrence graph
normalize_self_edges: bool
if including self edges, divide the (i, i) edge by 2.0, requires include_self_edges=True
References
----------
If you use this graph builder please cite the clustering paper:
.. code:: latex
@Article{datadriven,
author = {Szymański, Piotr and Kajdanowicz, Tomasz and Kersting, Kristian},
title = {How Is a Data-Driven Approach Better than Random Choice in
Label Space Division for Multi-Label Classification?},
journal = {Entropy},
volume = {18},
year = {2016},
number = {8},
article_number = {282},
url = {http://www.mdpi.com/1099-4300/18/8/282},
issn = {1099-4300},
doi = {10.3390/e18080282}
}
Examples
--------
A full example of building a modularity-based label space division based on the Label Co-occurrence Graph and
classifying with a separate classifier chain per subspace.
.. code :: python
from skmultilearn.cluster import LabelCooccurrenceGraphBuilder, NetworkXLabelGraphClusterer
from skmultilearn.ensemble import LabelSpacePartitioningClassifier
from skmultilearn.problem_transform import ClassifierChain
from sklearn.naive_bayes import GaussianNB
graph_builder = LabelCooccurrenceGraphBuilder(weighted=True, include_self_edges=False, normalize_self_edges=False)
clusterer = NetworkXLabelGraphClusterer(graph_builder, method='louvain')
classifier = LabelSpacePartitioningClassifier(
classifier = ClassifierChain(classifier=GaussianNB()),
clusterer = clusterer
)
classifier.fit(X_train, y_train)
prediction = classifier.predict(X_test)
For more use cases see `the label relations exploration guide <../labelrelations.ipynb>`_.
"""
def __init__(self, weighted=None, include_self_edges=None, normalize_self_edges=None):
super(LabelCooccurrenceGraphBuilder, self).__init__()
if weighted not in [True, False]:
raise ValueError("Weighted needs to be a boolean")
if include_self_edges not in [True, False]:
raise ValueError(
"Decision whether to include self edges needs to be a boolean")
if include_self_edges and (normalize_self_edges not in [True, False]):
raise ValueError("Decision whether to normalize self edges needs to be a boolean")
if normalize_self_edges and not include_self_edges:
raise ValueError("Include self edges must be set to true if normalization is true")
if normalize_self_edges and not weighted:
raise ValueError("Normalizing self-edge weights_ does not make sense in an unweighted graph")
self.is_weighted = weighted
self.include_self_edges = include_self_edges
self.normalize_self_edges = normalize_self_edges