pathpyG icon indicating copy to clipboard operation
pathpyG copied to clipboard

GPU-accelerated Next-Generation Network Analytics and Graph Learning for Time Series Data on Complex Networks.

Results 71 pathpyG issues
Sort by recently updated
recently updated
newest added

I just saw that `PyG` is planning to integrate all time-related stuff into `Data`, thus, deprecating `TemporalData`. We need to modify our `TemporalGraph` accordingly. (see https://github.com/pyg-team/pytorch_geometric/issues/3230) BTW: This is also...

refactor

Numpy released the version 2.0 recently. This currently leads to the following problem: ``` A module that was compiled using NumPy 1.x cannot be run in NumPy 2.0.0 as it...

dependencies

As far as I am aware, we reused the PathPy3 code for the implementation of the random walks. I noticed the following problems that need to be fixed: - [x]...

bug
documentation
help wanted
dagstuhl

Implemented new netzschleuder support, which addresses the following issues: - [x] simplify implementation by downloading CSV data that are parsed based on new pandas interface - [x] improve robustness of...

bug
enhancement

Turning a directed graph with isolated nodes into an undirected graph yields an error: Minimal example ``` import pathpyG as pp g = pp.Graph.from_edge_list([('a', 'b')], num_nodes=3) g_u = g.to_undirected() ```...

bug

Replace code that parses graphtool binary format by code that downloads network in csv-based format - [ ] move graphtool parser to optional function or separate module in io -...

bug
enhancement

The task would be to implement a set of basic community detection algorithms, such as: - [ ] [InfoMap](https://www.mapequation.org/assets/publications/RosvallBergstromPNAS2008Full.pdf) - [ ] [Louvain method](https://iopscience.iop.org/article/10.1088/1742-5468/2008/10/P10008) - [ ] [Modularity Optimization](https://www.pnas.org/doi/full/10.1073/pnas.0601602103) -...

enhancement
student project

The task would be to implement the higher-order force-directed layout algorithm from the following paper: Perri, V., Scholtes, I. (2020). HOTVis: Higher-Order Time-Aware Visualisation of Dynamic Graphs. In: Auber, D.,...

enhancement
student project

The task would be to implement, test, and evaluate the Bayesian model selection procedure described in the following paper: Luka V. Petrovic and Ingo Scholtes. 2022. Learning the Markov Order...

enhancement
student project

The model selection fails with an IndexError for the London Tube data set. Minimal code to reproduce the error: ``` import pathpyG as pp paths_tube = pp.PathData.from_ngram('../data/tube_paths_train.ngram', sep=',', weight=True) m...

bug