predict.mnlm

An output object from the <code>mnlm</code> function.

object

An <code>nrow(object$loadings)</code>-column matrix of multinomial phrase/category counts for new documents/observations. 
Can be either a simple <code>matrix</code> or a <code>simple_triplet_matrix</code>.

newcounts

Additional arguments to the undocumented internal <code>tpx*</code> functions.

Predict function for Logistic Inverse Regression

A suite of tools for inference about text documents and
        associated sentiment.  This includes the `mnlm' function, for
        sparse multinomial inverse regression analysis of sentiment in
        text, `pls', a concise partial least squares routine, and the
        `topics' function (beta version), for efficient estimation and
        model selection in latent topic representations of text.

predict.mnlm: topic predict

Description

Usage

Arguments

Value

Details

References

See Also