Getting started

Project “Sailor” allows you to easily access data from your SAP Digital Supply Chain software products for data science projects like predictive maintenance or master data analysis.

Once your data is available, it is your choice how to work with it. Project “Sailor” comes with several predefined functions to support you in exploring your data. Adding to that you can create custom plots or even build your own machine learning models. You can learn more about that on our tutorial page. “Sailor” provides you with a set of functions out of the box, but most importantly it facilitates flexibility and extensibility.


You need access to SAP Asset Central and the SAP IoT services in order to use “Sailor”.

Since the project “Sailor” is implemented in Python you need to have Python installed. Currently we support Python >=3.8. The required python packages are automatically installed while installing “Sailor”.


Install the package with pip

pip install sailor


“Sailor” talks to two services: SAP Asset Central and SAP IoT. You have two options of specifying the configuration:

  1. Environment

  2. YAML file

The above order is honoured when “Sailor” checks for the configuration.


A JSON string can be provided with the environment variable SAILOR_CONFIG_JSON. Example:

os.environ['SAILOR_CONFIG_JSON'] = json.dumps({
    'asset_central': {
        'client_id': 'ACexampleId',
        'client_secret': 'ACexampleSecret',
        'application_url': 'https://<system>.cfapps.<landscape>',
        'access_token_url': 'https://authentication.<landscape>',
        'subdomain': 'account-name'
    'sap_iot': {
        'client_id': 'IoTexampleId',
        'client_secret': 'IoTexampleSecret',
        'extension_url': 'https://iot-extension-sap-<space>.cfapps.<landscape>',
        'export_url': 'https://coldstore-export-sap-<space>.cfapps.<landscape>',
        'download_url': 'https://coldstore-downloader-sap-<space>.cfapps.<landscape>',
        'access_token_url': 'https://authentication.<landscape>',
        'subdomain': 'account-name'
    'predictive_asset_insights': {
        'client_id': 'PAIexampleId',
        'client_secret': 'PAIexampleSecret',
        'application_url': https://<system>.cfapps.<landscape>,
        'access_token_url': https://authentication.<landscape>,
        'subdomain': 'account-name',

YAML file

Specify the location of a YAML file via environment variable (e.g.: SAILOR_CONFIG_PATH=/home/my_sailor_config.yml). Alternatively you can put a YAML file named config.yml next to your main script/notebook without setting the SAILOR_CONFIG_PATH. Example YAML file:

  client_id: ACexampleId
  client_secret: ACexampleSecret
  application_url: https://<system>.cfapps.<landscape>
  access_token_url: https://authentication.<landscape>
  subdomain: account-name
  client_id: IoTexampleId
  client_secret: IoTexampleSecret
  extension_url: https://iot-extension-sap-<space>.cfapps.<landscape>
  export_url: https://coldstore-export-sap-<space><landscape>
  download_url: https://coldstore-downloader-sap-<space>.cfapps.<landscape>
  access_token_url: https://authentication.<landscape>
  subdomain: account-name
  client_id: PAIexampleId
  client_secret: PAIexampleSecret
  application_url: https://<system>.cfapps.<landscape>
  access_token_url: https://authentication.<landscape>
  subdomain: account-name

Quickstart Example

The following code snippet can be used to quickly get started with “Sailor”. It shows you how to read data of equipments, notifications and sensor data from your SAP backends. In addition to that there are predefined plotting functions which can be used to explore your data.

For a detailed example please visit our tutorial page. It will walk you through the functionality offered by project “Sailor” step by step.

import pandas as pd
from sailor.assetcentral import find_equipment, find_notifications

# find equipments and plot them
equipment_set = find_equipment(model_name='my_model_name')

# get sensor data from equipment
timeseries_data = equipment_set.get_indicator_data('2020-10-01 00:00:00+00:00', '2021-01-01 00:00:00+00:00')

# find notifications and plot them
notification_set = equipment_set.find_notifications(extended_filters=['malfunction_start_date > "2020-08-01"'])


Currently we do not support parallel data processing frameworks. You are bound by the limitations of the pandas DataFrame and the computing hardware running our code.

Known Issues

There are currently no known issues. All upcoming issues are tracked as GitHub Issues in the repository.

How to obtain support

If you encountered a bug or have a feature request, please create a GitHub Issue in the repository. You can also get in touch with the developers directly by reaching out to in order to obtain support.


We welcome all contributions either in form of issues, code contributions, questions or any other formats. For details please refer to the Contributing Page in the documentation.


Please see our LICENSE for copyright and license information. Detailed information including third-party components and their licensing/copyright information is available via the REUSE tool.