Not an easy question, but I will try to explain the problem. I have a list of word, Vocabulary, ordered by tf score. Below an example of a Vocabulary with few entries.

Say that I have a Document for which the same table is the following

I want to pick from the Document only the words present in the Vocabulary and build a dataframe with their respective TF (if the word of the Vocabulary is not in the Document, the TF will be zero for that word). The final result should look like this.