- - Knowledge base overview
Product Updates

Welcome to the Celonis Community

1 month ago

Home
Community
Product Q&A
AI

AI

Ask questions and discuss using AI copilots, annotations, and machine learning tools for smarter automation and data insights.

83 Topics
295 Replies

When you subscribe we will email you when there is a new topic in this category

83 Topics

Recently active

Most replies Most views Newest first

.14600919Level 2

asked in AI

Machine Learning Training - Missing permissions (datamodel)

3 years ago

vivek.mLevel 4

asked in AI

ML Dataset example to try with Celonis?

Hi All, Am currently working on ML. Can I get the sample Dataset for the ServiceNow or SAP Applications ? Br/VM

3 years ago

latife.atalaLevel 2

asked in AI

ML Suite Samples

Hello, All. We were working on the examples that once you published your ML suite website. Such as, Anomaly Detection, Duplicate Payments, Root Cause Analysis However, yesterday when I visit the website I couldnt find the samples. Coul you please let me know where can I find them? Since we are trying to adapt those logics into our P2P and AP processes. Thank you! Latife

3 years ago

nabaa.refaiLevel 1

asked in AI

Python API: Find and replace field names within an analysis

Hi, is there a way we can use the python API to find and replace field names specified in PQL within an analysis? For example, Im linking an existing analysis to a new data model and some of the field names differ slightly e.g. BSEG.TS_AUGDT is now BSEG.AUGDT. Is there a way I can easily update the PQL to use the new fieldname definition via the API without having to update manually via the front end?

3 years ago

amruth.mudda11Level 2

asked in AI

PQL Query Celonis ML

Hi Team , Is there any simple way to write a PQL query for select * from table name in celonis ML for get_data_frame(query). As of now we need to add all the column names separately one after the other PQLColumns(). Any suggestions would be helpful. Thank you Amruth

3 years ago

milos.markoLevel 1

asked in AI

On time delivery, feature recommender issue

Dear Team, I try to perform a on time delivery machine learning technique with the *cel11920939 217 KB *" but I receive error on my data set. I wanted to ask is there a tutorial on how should we do whole procedure, for example I tried to import tables connected with foreign key, but I do not know is that proper connection, is the data set I am using proper (it has activity name, timestamp, index etc) should I try to execute it in training.celonis.cloud or it does not play any role. Please if you have datasets you could share with me or whole tutorial of on time delivery and not just in .ipynb file, I am getting KeyError: Model Setup 5/5 (see picture) Best regards Milos Markovic WU Vienna

3 years ago

theresa.wettiLevel 1

asked in AI

Long loading time for opening empty app in ML workbench

Dear team,is it normal that it takes more than 20 min to open an (empty, newly created) app (smallest memory, storage and CPU limit). If not, what might be the reason? Thank you very much in advance.

3 years ago

rahul.bhat11Level 3

asked in AI

Access logs from front end

Hi team, I am trying to do a usage-statistics datamodel in the front end using the Access_logging with python . I had got a folder of access_logs before i started developement. But now i need the updated versions of access logs for this usage statistics datamodel. Does someone know where this is stored or how we can access for a perticular server? Thanks in advance. image1037258 17.9 KB

3 years ago

rahul.bhat11Level 3

asked in AI

Celonis_ml package source files

Hello all,I was going through various packages in the celonis and i found out that there is a package called "Celonis_ml" with no other documentation. Where can we access the documentation / source files for the Celonis_ml package.Thank you

3 years ago

jasmin.wolff11Level 3

asked in AI

Which components of Studio are able to use backup_content?

Dear all, I tried to use the backup_content function for Knowledge Models, so that I can store the YAML Code for worst case szenarios (package gets accidentially deleted). I am able to access the Spaces/Packages/Knowledge Models via .content but for backup_content it says the follwoing:AttributeError: 'KnowledgeModel' object has no attribute 'backup_content' Which components are enabled for backup_content?

3 years ago

rahul.bhat11Level 3

asked in AI

Extend SQL Result to more than 100 rows?

Hi team,How to extend the result rows for more than 100 or to export the transformation query result to excel?If not from transformation, is it possible to do it via Machine Learning workspace? Is it allowed?Thank you

3 years ago

rahul.bhat11Level 3

asked in AI

Python Login in IBC

Hi team, Our group has been recently migrated to IBC. Now i am trying to access the analysis and datamodels of IBC via python from my local system. But i am unable to login . I was using python in the old environment , and i was using API_ID and API_token, now which API_ID isnt availble for me. Is API_ID required to login? or is just API_token along with the URL is enough? Please suggest Code that i have tried: from pycelonis import get_celonis login = {celonis_url: my_url, api_token: my_api_token} c_source = get_celonis(**login) Thank you.

3 years ago

joos.buijsLevel 6

asked in AI

Python API: automating transports from DEV to PRD

Hi all, We have 2 (on premise, so not IBC) Celonis environments running: one where we develop our dashboards, and one production environment where finished and tested dashboards run. Transporting dashboards from DEV to PRD is only done by us, on request. However, were looking into automating the manual steps to reduce errors. Creating the transports from one or more dashboards and/or datamodels seems to be feasible through the Python API. However, Im wondering if the overwrite option is available in the Python API when uploading transports. The documentation does not mention this. Does anyone have any insights/ideas/suggestions?

114

3 years ago

dave.benneLevel 2

asked in AI

Machine Learning Training - Missing Permissions

Im following the Machine Learning training and am having problems with permissions. Ive created and entered the API token, but get this error: WARNING : the Application key of this App is missing the necessary Process Analytics permissions to use this App properly. I have added these permissions, but still get the error and when I try to Fetch Data Preview not data is returned. Is this a known problem or am I missing a step to add additional permissions? Dave

3 years ago

.14600902Level 2

asked in AI

Machine Learning training course - Duplicate Checker does not deploy

Hi everyone, I am not able to deploy the duplicate checker prebuild model. I am currently doing the ML training course and the app does not start. The issue has been discovered last Friday (24.7.20). The screen looks like the picture below. I have provided permission to access the dataset and gave the app further permissions as a Data Engineer, but this did not solve my problem. I am able to deploy a Jupyter Notebook app. This seems to work fine. image1380282 6.1 KB What can I do to solve this issue? Kind Regards Simon

115

3 years ago

lingzhi.lingzLevel 2

asked in AI

FileNotFound when trying to read csv file using python

Where should I put the file so that I can using python to read csv file in machine learning?

4 years ago

rahul.bhat11Level 3

asked in AI

Python:Database Type:unavailable

Hi team, I have been doing the auto-assignment of tables and DBconnection for the datamodel from python. But i am getting a problem in which the store type for a table is appearing as unavialable. This happens only some times when the datamodel is copied from some other server. But this completely removes the object of doing this in the first place. below is the screenshot. Any help would be appriciated. image722226 35.9 KB Edit: It should be as below image701141 39.7 KB

4 years ago

dayvson.nasciLevel 1

asked in AI

Error running ML suite examples fom ML workbench

Hello there, Im trying to use the notebooks from the examples_ml-suite folder, specifically the 04_root_cause_analysis.ipynb notebook, but Im facing the following error when running the cell: image1636228 38.8 KB image1359568 104 KB

4 years ago

benedikt.burgs11Level 2

asked in AI

Pull Data from Data Pool via ML WB

Hi there, in the ML workbench, there is an API call to push data to a data pool data_pool.push_table(...) Is there also a way to pull data (eg a specific table) from the data pool? Couldnt find something like data_pool.pull_table(...) Best, Benedikt

014

4 years ago

joão.francLevel 3

asked in AI

Partial load API - Can’t connect to celonis

In the sandbox, environment following the notebooks, when I run: "from pycelonis import get_celonis celonis = get_celonis()" it tells me i dont have permissions: "WARNING:pycelonis:The IBC did not accept the credentials: " I have given the application key all permissions in the team settings and in the event collection. What am i doing wrong?

4 years ago

Anonymous

asked in AI

Pycelonis get_data_frame method failed when column name is like “#{VBAP.PSTYV}”

Dear Celonis development team, I tried to connect and extract data from IBC to my Colaboratory python environment using Pyceonis. Normally it worked correctly with below scripts. from pycelonis import get_celonis login = {celonis_url: my_url, api_token: my_token} celonis = get_celonis(**login) analysis = celonis.analyses.find('id of my analysis) sheet = analysis.published.sheets.find(id of my sheet) component = sheet.components.find(id of my component) df = component.get_data_frame() But sometimes get_data_frame method returned exception. Exception Traceback (most recent call last) in () ----> 1 df = component.get_data_frame() 2 df 2 frames /usr/local/lib/python3.6/dist-packages/pycelonis/objects_base.py in get_data_file(self, pql_query, file_path, export_type, variables) 647 648 if r[exportStatus] != DONE: > 649 raise Exception(f"Export failed. Status: {r} \\n\\n Query: {pql_query}") 650 else: 651

4 years ago

eike.wellmLevel 2

asked in AI

TypeError: astype() got an unexpected keyword argument ‘skipna’

Hi there, while pushing a dataframe into a datamodel i got the above mentioned error. By checking the parquet_utils.py and a quick research I found out that this (skipna) argument is obsolete and no longer supported. Iam using python 3.7.6, panas 1.0.1 and pycelonis 1.2.8 Is there a workaround for this issue? Best regards, Eike

4 years ago

vahide.öztürLevel 3

asked in AI

How to implement “Use case: O2C - On Time Delivery Prediction” on Premise

Dear Celonis Community, We would like to implement Use case: O2C - On Time Delivery Prediction on our on-premise AS which is version 4.5 We checked the sample coding but it seems its prepared for cloud, Unfortunately we couldnt adapt sample use case for our data. Many thanks in advance, Best Regards, Vahide.

4 years ago

daniel.danie12Level 3

asked in AI

Prescriptive Analytics in IBC?

Dear Celonis community, I was wondering whether prescriptive analytics / recommendations (which are not out-of-the-box) are possible in Celonis? E.g. is it possible to define a goal (a particular performance indicator) and suggest possible actions to choose from (e.g. option A, B, C) in order to reach that goal? Example: As a production manager I would like to cut throughput times by 15% - What should I do next in order to best achieve my goal? Thanks in advance! Best, Daniel

4 years ago

joos.buijsLevel 6

asked in AI

Analysis <-> ML interaction

Hi all, Our use case: We would like to allow our end-users of the Celonis analyses to test hypotheses themselves (does attribute X correlate with KPI y?). Question: As we are currently still on-premise we are investigating connecting Celonis to an R-Server to enable the RCALL function. This would allows us to dynamically build the data set to pass to R and then present the result in a user-friendly way. However, as we might move to the IBC in the (near or far) future, we wondering if such analysis <-> ML interaction is also possible with the ML Workbench. Concretely, can we pass parameters from the analysis to a stored ML function/notebook which then returns the results to be presented in the analysis? An alternative would be to pre-calculate every possible combination of attribute (sets) and KPIs, which I guess is not handy. Looking forward to some inspiration! Cheers, Joos

4 years ago

Page 3 / 4

Badge winners

el.mostafa.janahhas earned the badge Celonis Certified Data Analyst
jumbo.szkhas earned the badge Masterclass in Implementation
makun.sharmhas earned the badge Masterclass in Implementation
yuya.sasathas earned the badge Masterclass in Implementation
isabella.pau11has earned the badge Celonis Certified Data Engineer

Show all badges

Terms & Conditions

Sign up

Already have an account? Login

Login with SSO

Login to the community

Login with SSO

Enter your E-mail address. We'll send you an e-mail with instructions to reset your password.

Enter your e-mail address

Back to overview

Scanning file for viruses.

Sorry, we're still checking this file's contents to make sure it's safe to download. Please try again in a few minutes.

This file cannot be downloaded

Sorry, our virus scanner detected that this file isn't safe to download.

ANY QUESTION?

Talk to an expert

FAQs

MORE CELONIS

Academy arrow_outward

Documentation arrow_outward

Support Center arrow_outward

Partner Portal arrow_outward

Marketplace arrow_outward

CHECK US IN

YouTube

Instagram

Facebook