kzhai / InfVocLDA

Online Latent Dirichlet Allocation with Infinite Vocabulary using Variational Inference
https://github.com/kzhai/InfVocLDA
Apache License 2.0
74 stars 19 forks source link

how to evaluate whather output is good or bad? #7

Open gauravkoradiya opened 5 years ago

gauravkoradiya commented 5 years ago

I got output after running the programme. Output of in file have same word in each topic. I should should change to time by time. while i run it on news dataset. I want to share my output here. image I am also sharing a gamma distribution here. hyper_parameter : input_directory=../../input/de-news corpus_name=de-news dictionary_file=None number_of_documents=9800 number_of_topics=10 truncation_level=1000 vocab_prune_interval=2 snapshot_interval=10 batch_size=100 online_iterations=98 tau=64.0 kappa=0.75 alpha_theta=0.1 alpha_beta=1000.0

I want to know how to evaluate this output. and why word is not changing over time here?