def test_get_p_vals(self): tdm = build_hamlet_jz_term_doc_mat() df = tdm.get_term_freq_df() X = df[['hamlet freq', 'jay-z/r. kelly freq']].values pvals = LogOddsRatioUninformativeDirichletPrior().get_p_vals(X) self.assertGreaterEqual(min(pvals), 0) self.assertLessEqual(min(pvals), 1)
def get_thresholded_score(cat_word_counts,
not_cat_word_counts,
alpha_w=0.01,
threshold=0.1):
scores = (LogOddsRatioUninformativeDirichletPrior(
alpha_w).get_p_values_from_counts(cat_word_counts,
not_cat_word_counts)) * 2 - 1
# scores = (np.min(np.array([1 - scores, scores]), axis=0) <= threshold) * scores
return scores * ((scores < -(1. - (threshold * 2)))
| (scores > (1. - (threshold * 2))))
def get_score(cat_word_counts, not_cat_word_counts, alpha_w=0.01): X = LogOddsUninformativePriorScore. \ _turn_counts_into_matrix(cat_word_counts, not_cat_word_counts) p_vals = LogOddsRatioUninformativeDirichletPrior(alpha_w).get_p_vals(X) scores = LogOddsUninformativePriorScore._turn_pvals_into_scores(p_vals) return scores
def get_delta_hats(cat_word_counts, not_cat_word_counts, alpha_w=0.01): return (LogOddsRatioUninformativeDirichletPrior(alpha_w) .get_log_odds_with_prior(LogOddsUninformativePriorScore ._turn_counts_into_matrix(cat_word_counts, not_cat_word_counts)))