What is process mining? The GH repo assumes that you already have the context (I appreciate them including a worked example, but it still doesn't tell me what they're trying to do), https://pm4py.fit.fraunhofer.de/ has docs but all of them start with "this lets you do process mining", and examples don't quite make enough sense to try and infer it. About page has the same issue.
Process mining is a field related to data science. Basically you take an event log, put it into PM algorithms (e.g. heuristic miner or inductive miner) and you get a model of the underlaying process eventually (think of it as a flow chart). On top of that you can run analysis that look for bottlenecks, for example.
I'm not quite happy with the ecosystem though. Most tools are either cloud based like Celonis or organically grown Java bloatware (PROM, Disco). PM4Py also looks like a Java project that was tweaked until it was syntactically correct Python. However, it's probably the most usable free tool for PM out there. And to be fair, it's a quite young project also, docs looked much worse half a year ago.
In short it is a way to map how people travel through a process. It could be how people use your website, a sales funnel, an onboarding process, compliance to process etc.
agree, the code example does what exactly? it looks like it imports some stuff and graphs it but without showing the input and output it doesn’t communicate usefulness.
A message from one of the founders of PM4Py.
Cool that we are mentioned here, quite an honor actually.
Since we are an academic project, we have limited resources to generate more elaborate 'getting started'-type of documentation, etc.
However, it is on our todo list.
If you have any requests or ideas, let us know, it helps us to prioritize what is most useful.
W.r.t. the java project. The first lines of code are written by someone with a few years of primarily Java experience, I guess that explains.
5 comments
[ 3.2 ms ] story [ 17.7 ms ] threadI'm not quite happy with the ecosystem though. Most tools are either cloud based like Celonis or organically grown Java bloatware (PROM, Disco). PM4Py also looks like a Java project that was tweaked until it was syntactically correct Python. However, it's probably the most usable free tool for PM out there. And to be fair, it's a quite young project also, docs looked much worse half a year ago.
Edit: added PM tools
You may like to watch some of the early videos https://www.coursera.org/learn/process-mining
We started with pm4py it has a lot of the functionality the paid tools have.
A message from one of the founders of PM4Py. Cool that we are mentioned here, quite an honor actually.
Since we are an academic project, we have limited resources to generate more elaborate 'getting started'-type of documentation, etc. However, it is on our todo list. If you have any requests or ideas, let us know, it helps us to prioritize what is most useful.
W.r.t. the java project. The first lines of code are written by someone with a few years of primarily Java experience, I guess that explains.