Francesco Grossetti

High memory consumption when using sentiment() function

10

I am running some polarity computation through the function `sentiment()`. What I am experiencing is, even for small piece of text, a huge amount of allocated RAM. Sometimes I get...

docid returns a factor not a character

1

I noticed that the documentation of `docid()` says that the returned value is a character vector. That's a factor really. I couldn't do some operations and now I understand why....

Model diagnostics support for ETM

1

This is more of a _feature request_ rather than an issue. I was wondering if you are planning to implement any support for model diagnostics of topic models in embedded...

I have seen that your functions are pretty fast in reading a file in memory. What about reading a connection? Is it possible to fully mimic the behaviour of `readLines()`?

Add goodness of fit metrics

12

I would like to know if there is any implementation of the standard goodness-of-fit metrics for your `textmodel_lda` class. For instance, [here is a SO post](https://stackoverflow.com/questions/69817462/diagnostics-perplexity-loglik-etc-for-lda-topic-model-with-textmodel-seededl) which didn't get much...