[katelatte]

Yes, I work for Memgraph, I am a developer there and I wrote this, and all of the previously published articles. I was comparing NetworkX to Memgraph algorithms, since that was the point of the whole article. I am mostly using Python in my day-to-day job and I love what they did with NetworkX. This article was influenced by many people who use NetworkX and are a part of Memgraph community. I just wanted to see how much of a difference does the underlying C++ implementation of Memgraph makes. Since I work with Python tools and Memgraph every day, and talk with a bunch of people working on graph analytics, it makes sense to compare by myself and get the facts right.

[rkwz]

Thanks for the context.

Offtopic, does Memgraph have something similar to NetworkX's connected components [1]? Wondering what's the performance difference between both for different sizes of graphs.

[1] https://networkx.org/documentation/stable/reference/algorith...

[katelatte]

We do have our own implementation of weakly connected components [1]. Currently, we only have NetworkX strongly connected components algorithm [2] as a part of the nxalg module (set of procedures) in MAGE (our graph algorithms library). I did not compare it yet, let me know if you do! We definitely need to create official benchmarks. Lot of work!

[1] https://memgraph.com/docs/mage/query-modules/cpp/weakly-conn... [2] https://memgraph.com/docs/mage/query-modules/python/nxalg#st...

[katelatte]

I forgot to mention: we do have biconnected components algorithm [1], and since all biconnected graphs are strongly connected, it can be useful.

[1] https://memgraph.com/docs/mage/query-modules/cpp/biconnected...