Text Classifier Model to Table

Go to Product

This node allows to transform the content of a model, which was created using the Palladian text classifier, to a KNIME table. The KNIME table contains the tokens (words, n-grams), as rows and columns for each category. Each cell for a (token, category) combination contains either an absolute or relative co-occurrence count, depending on this node’s settings. The last column gives an absolute count of the token in the trained data set.

Options

Relative counts
If enabled, the counts for the categories are given as relative values (so that they sum up to one for each term)

Input Ports

Icon
The model data of the trained classifier.

Output Ports

Icon
A table which contains to token-category co-occurrence matrix
Icon
A table which contains the category priors counts/probabilities as determined by the single documents

Views

This node has no views

Workflows

  • No workflows found

Further Links

Developers

You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.