search

wd60622 / latent-calendar

Analyze and model weekly calendar distributions using latent components
https://wd60622.github.io/latent-calendar/
BSD 3-Clause "New" or "Revised" License
4 stars 1 forks source link

Bayesian `LDA` #9

Open wd60622 opened 1 year ago

wd60622 commented 1 year ago

Need a fully Bayesian LDA in order to make use of custom priors.

Building off the examples here


# (n_components, n_time_slots)
prior = df_segments.to_numpy()

from latent_calendar import BayesianLatentCalendar

model = BayesianLatentCalendar(prior=prior)
model.fit(df_model)