time_slices=times, **dtm_defaults)
mod.save(os.path.join(PKLDIR, key))
return mod
# DTM Analysis
nips = NipsData()
dat = nips.load_data(sample_frac=1)
sections = ['title', 'abstract']
ncomps = dtm_defaults['num_topics']
dat = nips.combined_sections(sections, data=dat)
yrs, cnts = papers_per_year(nips.raw)
sname = get_save_name(sections)
docs = lda_get_corpus(dat, name=sname, save=True)
d, bow = lda_get_dictionary(dat, name=sname, save=True)
## mod = dtm_run(dat, cnts, dtm_path, name=sname, save=True)
mod = DtmModel.load(os.path.join(PKLDIR, 'lda_dtm_15_title_abstract'))
def print_dtm_top_words_for_year(model, years, n_topics, n_words):
"""Print top n_words from top n_topics for year in years."""
print(f"Top {n_words} from top {n_topics} for year(s) {years}:")
yrs = enumerate(range(1987, 2018))
inds = [(i,yr) for i, yr in yrs if yr in years]
for i, yr in inds:
print(f"Year {yr}:")
for topic, words in enumerate(model.dtm_coherence(i, n_words)[:n_topics]):
print(f" Topic #{topic}: " + ', '.join(words))
def dtm_coherence(model, corpus, d, year):
"""Get coherence for DTM model at year."""
def load_model(self):
# Load model
self.model = DtmModelClass.load(self.output_file_path)
print(f"Model loaded from {self.output_file_path}")
def loadDTM(amounttopics):
modelAmountTopics = DtmModel.load(f'./Models/model{amounttopics}Topics')
return modelAmountTopics