pygsp
pygsp copied to clipboard
epfl-lts2
Graph Signal Processing in Python
The edge weights are not propagated to the nodes when using the LineGraph method. I specifically want to get the edge weights of a graph G as the node signal...
The API example for the from_networkx() method is: ``` import networkx as nx graph = nx.Graph() graph.add_edge(1, 2, weight=0.2) graph.add_edge(2, 3, weight=0.9) graph.add_node(4, sig=3.1416) graph.nodes() graph = pygsp.graphs.Graph.from_networkx(graph) graph.W.toarray() graph.signals...
Hi, I cannot use the inverse method of filterbanks. I did use the exact codes in the commented part of the inverse method in python files and still get the...
The magnetic laplacian provides an alternative to symmetrizing the adjacency matrix for directed graphs. See e.g. "Graph Signal Processing for Directed Graphs based on the Hermitian Laplacian".
Hi everyone. I just found myself having trouble with the `pygsp.reduction.interpolate` function, and the reason was in line 173 of the `reduction.py` file: ```python K_reg = getattr(G.mr, 'K_reg', kron_reduction(L_reg, keep_inds))...
GraphWave?
From @pulquero []: > Btw, I have an implementation of graphwave (about 10 lines), if that would also be of interest.
It seems to have to be corrected from `ch[0] = (2/(np.pi))*(np.arccos(filter_bounds[0])-np.arccos(filter_bounds[1]))` to `ch[0] = (1/(np.pi))*(np.arccos(filter_bounds[0])-np.arccos(filter_bounds[1]))`.
The release we get with pypi is 0.5.1 and the version on the master branch is also tagged 0.5.1 even if it has many new features. It confuses people, especially...
It looks like a factor of `pi` is missing in the numerical integration in https://github.com/epfl-lts2/pygsp/blob/d78095438a14a74d2195d4600fc00f8f1115005f/pygsp/filters/approximations.py#L52 compared Eq 8 https://arxiv.org/pdf/1105.1891.pdf throwing off the Chebyshev coefficients by a factor of `pi`.
Contains PR #21 with some improvements. Major fixes: * correct symmetrization of distance matrix (695272b1b73e2f55b0f31fc351121d82470af576) * squared width in gaussian kernel (f544e1e8d82b3b9faf9f58e61807a1494dc5555b) * FLANN returns distance^p for a p-norm (8cc3539d920a7a97c9a4050e8ff6eca402321642)...