Operator ToolboxOperator Toolbox

This extension couples some useful additional Operators together.

This extension adds a bunch of new Operators to RapidMiner.They range from utility Operators to improve the flexibility and usability of the process design over additional outlier detection algorithm and additional performance criteria to advanced analysis methods like Local Interpretation or the SMOTE algorithm.

Currently the extension provides the following Operators:

  • Blending

    • Collect and Persist

    • Extract Statistics

    • Generate Levenshtein Distance

    • Generate Phonetic Encoding

    • Group Into Collection

    • Merge Attributes

    • Replace Rare Values

    • SMOTE Upsampling

    • t-SNE (new in 1.0.0)

    • Weight of Evidence

  • Data Access:

    • Read Excel Sheet Names

    • SFTP Download File (new in 1.0.0)

    • SFTP Upload File (new in 1.0.0)

  • Data Generator:

    • Create ExampleSet (this is a new unified data generator operator)

  • Macros:

    • Extract Last Modifying Operator

    • Set Macros from ExampleSet

  • Models:

    • Apply Dictionary-Based Sentiment

    • Dictionary-Based Sentiment

    • Get Decision Tree Path

    • Get Local Interpretation

    • Parametric Probability Estimator

    • Random Forest Encoder

  • Outliers:

    • Tukey Test

  • Parameters:

    • Get Parameters

    • Set Parameters from ExampleSet

  • Performance

    • Performance (AUPRC)

  • Text Processing:

    • Extract Topics from Document (LDA) (new in 1.0.0)

    • Filter Tokens Using ExampleSet

    • Split Document into Collection

    • Stem Tokens Using ExampleSet

    • Apply Model (Documents) (new in 1.0.0)

Version 1.0.0 (2018-03-23)

  • New Operator t-sne (t-Distributed Stochastic Neighbor Embedding)
  • New Operator LDA (Latent Dirichlet Allocation)
    • New LDA Model
  • New Operator Apply Model (Documents) - currently only for LDA Model
  • New Operator Create ExampleSet
    • replacing outdated Create ExampleSet from Doc, Generate Univariate Series, Generate Date Series
  • New Tukey Test Model as Preprocessing Model 
  • New Operator SFTP Download File
  • New Operator SFTP Upload File
  • Large refurbishing of the existing Operators
    • adaption of parameter names (and automatic replacement for older processes)
    • improved documentation/help text for most of the operators
    • adaption of operator keys (and automatic replacement for older processes)
    • operators in the operator tree are now ordered alphabetically
    • automatic replacement for Create ExampleSet from Doc, Generate Univariate Series and Generate Date Series to the new Create ExampleSet operator in older processes.
      • parameters are kept (if possible)
    • improved UserError handling and meta data propagation
    • bugfixes in GroupIntoCollection and Merge
    • small improvements for Extract Statistics, Extract Last Modifying Operator and Filter Tokens Using ExampleSet
    • consistent serialization of IOObjects (unfortunately no backward compatibility)

Version 0.9.0 (2018-02-02)

  • New Operator Read Excel Sheet Names
  • New Operator Random Forest Encoder
  • Improved Dictionary Based Sentiment
    • It can now handle negation words by using a 'negation' dictionary
  • Improved Group Into Collection
    • Additional option to sort the Collection
  • Improved Create ExampleSet
    • Additional option to trim attribute names
    • Added Meta Data handling

Version 0.8.0 (2017-12-22)

  • New Operator Replace Rare Values
  • New Operator Merge
  • Improved Operator Parameteric Probability Estimator
    • Automatic capabilities check
    • Added calculation of pValues for each new Attribute. pValues are provided as AttributeWeights by a new weigths output port
    • Added possibility to apply a threshold on this pValues, so that only matching Attributes are created
  • Enhancements: Improved documentation and tutorial processes, Create ExampleSet uses now nominal as value type for text-input data

Version 0.7.0 (2017-11-28)

  • New Operator Parameteric Probability Estimator
  • Enhancement: Apply Dictionary Based Sentiment: Added number of positive, negative and the total number of tokens
  • Bugfix: Group Into Collection: Fixed a bug with weird entries for special Attributes.

Product Details

Version 1.0.0
File size 10 MB
Downloads 17253 (136 Today)17253 downloads
Vendor RapidMiner Labs
Category Operators
Released 3/23/18
Last Update 3/23/18 2:54 PM
(Changes)
License AGPL
Product web site
Rating 0.0 stars(0)