def test_align_to_target(self):
full_corpus = get_test_corpus()
corpus = full_corpus.remove_categories(['swift'])
priors = PriorFactory(full_corpus).use_all_categories().get_priors()
with self.assertRaises(ValueError):
(LogOddsRatioInformativeDirichletPrior(priors).get_scores(
*corpus.get_term_freq_df().values.T))
priors = (PriorFactory(full_corpus).use_all_categories().
align_to_target(corpus).get_priors())
(LogOddsRatioInformativeDirichletPrior(priors).get_scores(
*corpus.get_term_freq_df().values.T))
import scattertext as st
from scattertext import LogOddsRatioInformativeDirichletPrior
fn = 'rotten_fresh2.html'
df = st.SampleCorpora.RottenTomatoes.get_data()
corpus = (st.CorpusFromPandas(df,
category_col='category',
text_col='text',
nlp=st.whitespace_nlp_with_sentences).build())
priors = (st.PriorFactory(corpus,
category='fresh',
not_categories=['rotten'],
starting_count=1).use_general_term_frequencies().
use_all_categories().get_priors())
(open(fn, 'wb').write(
st.produce_fightin_words_explorer(
corpus,
category='fresh',
not_categories=['rotten'],
metadata=df['movie_name'],
term_scorer=LogOddsRatioInformativeDirichletPrior(priors, alpha_w=10),
).encode('utf-8')))
print(fn)
from scattertext.termcompaction.CompactTerms import CompactTerms
import scattertext as st
from scattertext import LogOddsRatioInformativeDirichletPrior
fn = 'demo_log_odds_ratio_prior.html'
df = st.SampleCorpora.RottenTomatoes.get_data()
corpus = (st.CorpusFromPandas(df,
category_col='category',
text_col='text',
nlp=st.whitespace_nlp_with_sentences)
.build())
priors = (st.PriorFactory(corpus,
category='fresh',
not_categories=['rotten'],
starting_count=1)
#.use_general_term_frequencies()
.use_all_categories()
.get_priors())
(open(fn, 'wb')
.write(
st.produce_frequency_explorer(
corpus,
category='fresh',
not_categories=['rotten'],
metadata=df['movie_name'],
term_scorer=LogOddsRatioInformativeDirichletPrior(priors, 1),
).encode('utf-8'))
)
print(fn)