Categories

Versions

You are viewing the RapidMiner Studio documentation for version 9.2 - Check here for latest version

What's new in RapidMiner Studio 9.2

New charts and visualizations

Gain a productivity boost as you make use of the new charting framework which offers a huge variety of appealing charts. There is no need any more to waste time and switch to Excel or the like to present your findings – the new charts provide a richness of customization options for colors, plot types, legends and axes, etc. as well as export to various file formats. You can also forget the pain of creating charts from scratch every time as you can easily save and load charts configurations to start again from where you left off.

Handle Text Data in Auto Model

Tackle use cases involving textual data like customer complaint routing or sentiment analysis. The new enhanced Auto Model automatically identifies, preprocesses and incorporates textual data for modeling. Leverage text data for prediction or clustering, run pre-built sentiment analysis or language detection and gain insights from text-specific visualizations.

More Auto Model enhancements

Cover more diverse predictive use cases with Auto Model leveraging Automatic Feature Engineering for clustering, improved extraction of features from date columns and the now incorporated Fast Large Margin and Multiclass Logistic Regression learners. Furthermore, use correlation as a performance criterion for regression and understand regression performance through a new chart showing predictions vs. actual values.

Enhanced Time Series capabilities

Extend your time series modeling toolbox with new operators providing exponential smoothing, allowing to calculated a lagged time series or extracting polynominal fit coefficients.

Connectivity to Azure Data Lake Storage

Access data in Azure Data Lake Storage with new operators allowing to read, write and loop files.

Enhancements and bug fixes

The following pages describe the enhancements and bug fixes in RapidMiner Studio 9.2 releases: