Pycelonis is a python library built and managed by Celonis that allows easy interaction with Celonis pre-processed data as well as include functions to support building process-specific custom machine learning algorithms in python.
This new release (Pycelonis 1.5.1) introduces some amazing new features that will help you quickly build your own custom usecases. Following is a sneak peak into some of the highlights:
Data Deduplication
We have added a data deduplication module in pycelonis that helps you find any kind of duplicates in any process. We have also added tutorial notebooks of specific deduplication usecases such as Vendor Deduplication and Material Deduplication to help you get started. In order to get started, you get the new notebooks by execution the following import inside your python notebook after updating pycelonis to the latest version.
from pycelonis.notebooks import data_deduplicationRoot Cause Analysis
We have also added a root cause analysis module in pycelonis that helps you find the correlation between different process KPIs and attributes to help root cause an increase or decrease of a specific KPI. To get started you can get the tutorial notebook for the root cause analysis module by importing the following:
from pycelonis.notebooks import root_cause_analysisStudio Support
We have also added studio integration in Pycelonis. You can now create your studio packages also via python. In addition to that, you can also add and remove objects from the knowledge model as well as extract KPIs and execute them as PQL via your python script with the help of the latest pycelonis release. This helps in easily integrating your custom ML usecases to the studio assets.
Data Pipeline Updates
We have introduced an option to apply automatic chunking while pulling data from Celonis to support the data export for files larger than 1 GB.
For more details on what is included in the latest release and how can you use it, please have a look at pycelonis documentation .
Best Regards,
Celonis Product Team