KNIME Analytics Platform 4.1 is now available!

KNIME just got stronger in guided analytics, sharing knowledge, and enterprise usage. The 2019 Santa Claus release strengthens the way to share, search, and reuse knowledge on the KNIME Hub with components. It adds guided labeling, and includes many additional nodes, integrations like Google Cloud Services, Databricks, Power BI, and OAuth authorization.

Leverage your data with Guided Labeling

We believe that data science shouldn’t be a black box. The data scientist should be able to build powerful analytical applications that allow interaction with the domain expert whenever their expertise and feedback is required. We call this Guided Analytics. Now, in this release we introduce Guided Labeling. Using machine learning (ML) techniques (active learning, weak supervision), the domain expert can efficiently label unlabeled data in a guided setting, saving hugely on resources and getting the right data fast. This solves one of the big problems in ML: you need a lot of labeled data to get meaningful models. Find the details on our what’s new page.

What about new nodes?

There’s a new addition to the ML Interpretability Extension - the Binary Classification Inspector - that makes comparison of binary classifiers easier, applying the best thresholds for each different machine learning algorithm. The WebRetriever node is new too. Use it to issue HTTP GET requests and parse the requested HTML web pages. Tucked into the KNIME Labs Extensions, you’ll now find a Row Filter (Labs) node for filtering data based on multiple conditions. Find the complete list of new nodes in the changelog.

Share, find, and reuse knowledge on the Hub

Are you already using the KNIME Hub - our central resource for data science expertise? Since the summer we’ve increased its functionality. Sharing components, for example: Shared in your public space, you provide your colleagues and the KNIME community with ready-made building blocks to perform repetitive or difficult data science tasks easily. Shared in your private space, your components are stored in a central easy to access location. 

Now, in addition to new input filtering and validation, this release enables component editing outside of a workflow, adding component descriptions, plus an image and category (or color). Learn more here.

Even more Cloud Connectivity and Databricks

Organizations are using cloud services more and more to attain top levels of scalability, security, and performance. You can now interact with the popular Google Cloud services such as Google BigQuery, Google Cloud Storage, and Google Cloud Dataproc. Another new integration to give more flexibility is support to connect to your Databricks cluster on Microsoft Azure or Amazon AWS. And… in addition to our AWS Comprehend nodes, this release provides AWS Personalization nodes to increase support for AWS machine learning services. Power BI is a further integration: datasets created through KNIME can be uploaded to Power BI dashboards. See the specs here

SSO and more flexibility for the enterprise

KNIME Server now supports the open standard for authorization: OAuth identification. When set up for KNIME Servers, Single Sign-On is also supported for connections from KNIME Analytics Platform clients. It can also be used together with the KNIME WebPortal.

By popular request, we’ve tweaked our Server Managed Customization: You can host one or more update sites in your own network, giving easy access to all users who need to install additional extensions.

It’s also now easier to configure workflows running on KNIME Server. You can directly access configuration node dialogs (introduced in KNIME Analytics Platform 4.0) to adjust settings ad hoc: change credentials, for example, or file selections. Learn more about this KNIME Server release here.

More? Yes more!

Here, we’ve highlighted just some of the new functionality provided in the 2019 Santa Claus release. Read more on our what’s new page and the complete list of new nodes, enhancements, and bug fixes in our changelog

News date