cosine-similarity | Computes the cosine similarity between two arrays | Topic Modeling library

I'm doing a semantic search to find the closest synonym in two text columns, in two different dataframes.

The code is as below,

I suspect this is something very fundamental I don't know or understand about this code; my only excuse is that I am a complete beginner in python.

I am trying some of the cosine similarity matrix calculations from this post:

What's the fastest way in Python to calculate cosine similarity given sparse matrix data?

One of them requires the calculation of the reciprocal of the diagonal of the initial matrix product.
Say that he initial matrix is m, each row of which represents an 'object', whose 'coordinates' are in the columns of the matrix. So you want to calculate cosine similarities between rows.
Then, to use the matrix product method, you do something like mp = numpy.dot(m, m.T).

Now, if there are no rows with only 0's in m, the diagonal of mp can never have any zero values, as each of its elements is the sum of the squared elements of the corresponding row of m.
The m I am using in my calculations has indeed no rows with all 0's.
And indeed, when I do:

I have been working with some R packages that calculate (cosine) (sparse) similarity matrices from sparse binary matrices, e.g. proxyC.

As I am now starting (and learning) to use python as well, and I was told it might even be faster, I would like to try and run the same calculations there.

I found this interesting post:

What's the fastest way in Python to calculate cosine similarity given sparse matrix data?

which describes a few methods.

I did try some of them out after writing out a small test matrix myself by hand.
Now I would like to try on 'real' data.
And that's where I encounter a problem I currently cannot solve.

My data come in tsv files that associate objects (ID's) to comma-separated lists of features (FP's). E.g.:

I have seen many stack overflow questions about similarity matrix but they deal with RDD or other cases and I could not find the direct answer to my problem and I decided to post a new question.

I have a list of movies and a list of tropes. To calculate the similarity between two movies, I am using cosine differences. If all the weights are even, then it simplifies pretty well:

I have trained my word2vec model from gensim and I am getting the nearest neighbors for some words in the corpus. Here are the similarity scores:

I have two tensors a & b of shape (m,n), and I would like to compute a distance matrix m using some distance metric d. That is, I want m[i][j] = d(a[i], b[j]). This is somewhat like cdist(a,b) but assuming a generic distance function d which is not necessarily a p-norm distance. Is there a generic way to implement this in PyTorch?

And a more specific side question: Is there an efficient way to perform this with the following metric

I am trying to implement textrank algorithm where I am calculating cosine-similarity matrix for all the sentences.I want to parallelize the task of similarity matrix creation using Spark but don't know how to implement it.Here is the code:

I have trained fasttext model with Gensim over the corpus of very short sentences (up to 10 words). I know that my test set includes words that are not in my train corpus, i.e some of the words in my corpus are like "Oxytocin" "Lexitocin", "Ematrophin",'Betaxitocin"

given a new word in the test set, fasttext knows pretty well to generate a vector with high cosine-similarity to the other similar words in the train set by using the characters level n-gram

How do i incorporate the fasttext model inside a LSTM keras network without losing the fasttext model to just a list of vectors in the vocab? because then I won't handle any OOV even when fasttext do it well.

Any idea?