API Reference¶

This is the class and function reference of GraKeL. In order for the user to understand how to use the package, we suggest he reads Documentation section.

`grakel.graph`: Graph class with its utility functions¶

Base Class¶

Graph([initialization_object, node_labels, …])

The general graph class.

Utility Functions¶

`graph.is_adjacency`(g[, transform])	Define if input is in a valid adjacency matrix format.
`graph.is_edge_dictionary`(g[, transform])	Define if input is in a valid edge dictionary format.
`graph.laplacian`(csgraph[, normed, …])	Return the Laplacian matrix of a directed graph.
`graph.floyd_warshall`(adjacency_matrix)	Calculate the Floyd Warshall, shortest path matrix.

User guide: See the Graph (class) section for further details.

`grakel.graph_kernels`: A kernel decorator¶

Graph Kernel (decorator)¶

grakel.GraphKernel([kernel, normalize, …])

A generic wrapper for graph kernels.

User guide: See the GraphKernel (class) section for further details.

`grakel.kernels`: A collection of graph kernels¶

Kernels¶

`Kernel`([n_jobs, normalize, verbose])	A general class for graph kernels.
`RandomWalk`([n_jobs, normalize, verbose, …])	The random walk kernel class.
`RandomWalkLabeled`([n_jobs, normalize, …])	The labeled random walk kernel class.
`PyramidMatch`([n_jobs, normalize, verbose, …])	Pyramid match kernel class.
`NeighborhoodHash`([n_jobs, normalize, …])	Neighborhood hashing kernel as proposed in [HK09].
`ShortestPath`([n_jobs, normalize, verbose, …])	The shortest path kernel class.
`ShortestPathAttr`([n_jobs, normalize, …])	The shortest path kernel for attributes.
`GraphletSampling`([n_jobs, normalize, …])	The graphlet sampling kernel.
`SubgraphMatching`([n_jobs, verbose, …])	Calculate the subgraph matching kernel.
`WeisfeilerLehman`([n_jobs, verbose, …])	Compute the Weisfeiler Lehman Kernel.
`HadamardCode`([n_jobs, verbose, normalize, …])	The simple Hadamard code kernel, as proposed in [KI16].
`NeighborhoodSubgraphPairwiseDistance`([…])	The Neighborhood subgraph pairwise distance kernel.
`LovaszTheta`([n_jobs, normalize, verbose, …])	Lovasz theta kernel as proposed in [JJDB14].
`SvmTheta`([n_jobs, normalize, verbose, …])	Calculate the SVM theta kernel.
`Propagation`([n_jobs, verbose, normalize, …])	The Propagation kernel for fully labeled graphs.
`PropagationAttr`([n_jobs, verbose, …])	The Propagation kernel for fully attributed graphs.
`OddSth`([n_jobs, normalize, verbose, h])	ODD-Sth kernel as proposed in [DSMNS12].
`MultiscaleLaplacian`([n_jobs, normalize, …])	Laplacian Graph Kernel as proposed in [KP16].
`HadamardCode`([n_jobs, verbose, normalize, …])	The simple Hadamard code kernel, as proposed in [KI16].
`VertexHistogram`([n_jobs, normalize, …])	Vertex Histogram kernel as found in [SB15].
`EdgeHistogram`([n_jobs, normalize, verbose, …])	Edge Histogram kernel as found in [SB15].
`GraphHopper`([n_jobs, normalize, verbose, …])	Graph Hopper Histogram kernel as found in [FKP+13].
`CoreFramework`([n_jobs, verbose, normalize, …])	The core kernel framework, as proposed in [NMLV18].
`WeisfeilerLehmanOptimalAssignment`([n_jobs, …])	Compute the Weisfeiler Lehman Optimal Assignment Kernel.

User guide: See the Kernels (between graphs) section for further details.

`grakel.datasets`: Datasets¶

Fetch¶

fetch_dataset(name[, verbose, data_home, …])

Access a large collection of benchmark datasets from TU Dortmund [KKMMN2016].

get_dataset_info(dataset_name[, default])

Return the info concerning the existence of a certain dataset.

User guide: See the Dataset loading utilities section for further details.

`grakel`: Utils¶

Use a kernel matrix as a transformer¶

KMTransformer([K])

A Kernel Matrix Transformer.

Cross Validation¶

cross_validate_Kfold_SVM(K, y[, n_iter, …])

Cross Validate a list of precomputed kernels with an SVM.

Load from other file formats¶

`graph_from_networkx`(X[, node_labels_tag, …])	Transform an iterable of networkx objects to an iterable of Graphs.
`graph_from_pandas`(edge_df[, node_df, …])	Produces a collection of Graph Objects from pandas dataframes.
`graph_from_csv`(edge_files[, node_files, …])	Produces a collection of Graph Objects from a collection of csv files.

User guide: Usefull functions for applying to existing datasets, of other formats.