diff --git a/gensim/models/phrases.py b/gensim/models/phrases.py index ca8c1cfa3b..e143e364e4 100644 --- a/gensim/models/phrases.py +++ b/gensim/models/phrases.py @@ -676,6 +676,11 @@ def original_scorer(worda_count, wordb_count, bigram_count, len_vocab, min_count corpus_word_count : int Not used in this particular scoring technique. + Returns + ------- + float + Score for given bi-gram, greater than or equal to 0. + Notes ----- Formula: :math:`\frac{(bigram\_count - min\_count) * len\_vocab }{ (worda\_count * wordb\_count)}`. @@ -703,6 +708,11 @@ def npmi_scorer(worda_count, wordb_count, bigram_count, len_vocab, min_count, co corpus_word_count : int Total number of words in the corpus. + Returns + ------- + float + Score for given bi-gram, in the range -1 to 1. + Notes ----- Formula: :math:`\frac{ln(prop(word_a, word_b) / (prop(word_a)*prop(word_b)))}{ -ln(prop(word_a, word_b)}`,