在Gensim中为我的词汇计算tf-idf

Question

I have a set of words (n-grams) where I need to calculate tf-idf values. These words are;

myvocabulary = ['tim tam', 'jam', 'fresh milk', 'chocolates', 'biscuit pudding']

My corpus looks as follows.

corpus = {1: "making chocolates biscuit pudding easy first get your favourite biscuit chocolates", 2: "tim tam drink new recipe that yummy and tasty more thicker than typical milkshake that uses normal chocolates", 3: "making chocolates drink different way using fresh milk egg"}

I am currently getting tf-idf values for my n-grams in myvocabulary using sklearn as follows.

tfidf = TfidfVectorizer(vocabulary = myvocabulary, ngram_range = (1,3))
tfs = tfidf.fit_transform(corpus.values())

However, I am interested in doing the same in Gensim. Forall the examples I came across in Gensim;

1. uses only unigrams ( iwant it for bigrams and trigrams as well)
2. calculated for all the words (I only want to calculate for the words in myvocabulary )

Hence, please help me to find out how to do the above two things in Gensim.

Answer 1

In gensim, for a dictionary, you should use gensim.corpora.Dictionary class, look at examples

Unfortunately, we have no support ngrams in general, only bigrams for words with Phrases class