|
Methods defined here:
- __init__(self)
- cluster_graph(self, graph_to_cluster=None, clustered_graph_generator=None, similarity_function=None, stop_condition=None, clustering_print_mode=None, output_dir=None, output_prefix=None, root_protein=None, original_graph=None, call_do_action=0)
- Method that clusters a given Graph graph_to_cluster
Returns the clustered graph at the point where the stop condition has been met
"graph to cluster": a graph witch we want to cluster
"clustered_graph_generator" is a Class that returns an empty GraphCluster (or a child class) when called with get_new_graph_cluster()
-> this allows the user to control which kind of GraphCluster is going to use
"similarity_function": a ClusteringSimilarityFunction object
"stop_condition": a ClusteringStopCondition object
"clustering_print_mode" is used to tell this method which results have to be printed out
- "all" : will print to files with output_prefix the network, clusters composition and their interactions at all levels
- None: won't print anything to output_prefix files
- "final": will print to files with output_prefix the clusters composition and their interactions at the final level
(ie. when stop condition met)
"output_dir": directory where results files will be created (must end with slash eg ./)
"output_prefix": prefix that will be appended to results files
"root_protein": when training, this is the protein for which the results are being generated
"original_graph" is a Graph (might be of use for some similarity functions: set it to None if not useful)
if "call_do_action" is 1, then the method do_action() of the GraphCluster being used is called
- initialize_from_graph(self, graph_to_cluster=None, clustered_graph_generator=None)
- Initializes the GraphCluster from a Graph object "graph"
Taking as input a graph, object, creates a cluster graph with
one node attribute per cluster. This cluster graph object is
then clusterized with method cluster_graph()
"graph_to_cluster": graph to transform to a GraphCluster object
- print_similarity_matrix(self, output_target, similarity_function, similarity_matrix)
- prints similarity matrix using node ids
(only prints terms which are different from 0
Data and other attributes defined here:
- __dict__ = <dictproxy object>
- dictionary for instance variables (if defined)
- __weakref__ = <attribute '__weakref__' of 'Clustering' objects>
- list of weak references to the object (if defined)
|