Spark ML -- Latent Dirichlet Allocation

Usage

ml_lda(x, features = dplyr::tbl_vars(x), k = length(features), alpha = (50/k) + 1, beta = 0.1 + 1, ml.options = ml_options(), ...)

Arguments

x
An object coercable to a Spark DataFrame (typically, a tbl_spark).
features
The name of features (terms) to use for the model fit.
k
The number of topics to estimate.
alpha
Concentration parameter for the prior placed on documents' distributions over topics. This is a singleton which is replicated to a vector of length k in fitting (as currently EM optimizer only supports symmetric distributions, so all values in the vector should be the same). For Expectation-Maximization optimizer values should be > 1.0. By default alpha = (50 / k) + 1, where 50/k is common in LDA libraries and +1 follows from Asuncion et al. (2009), who recommend a +1 adjustment for EM.
beta
Concentration parameter for the prior placed on topics' distributions over terms. For Expectation-Maximization optimizer value should be > 1.0 and by default beta = 0.1 + 1, where 0.1 gives a small amount of smoothing and +1 follows Asuncion et al. (2009), who recommend a +1 adjustment for EM.
ml.options
Optional arguments, used to affect the model generated. See ml_options for more details.
...
Optional arguments; currently unused.

Description

Fit a Latent Dirichlet Allocation (LDA) model to a Spark DataFrame.

Note

The topics' distributions over terms are called "beta" in the original LDA paper by Blei et al., but are called "phi" in many later papers such as Asuncion et al., 2009.

For terminology used in LDA model see Spark LDA documentation.

References

Original LDA paper (journal version): Blei, Ng, and Jordan. "Latent Dirichlet Allocation." JMLR, 2003.

Asuncion et al. (2009)