similarity_matrix.py

#Function to compute all embeddings and distance between all possible quote pairs:
def similarity_matrix(merge_list):
    #initialize distance array:
    similarity_matrix = np.zeros([len(merge_list), len(merge_list)])
    #initialize embeddings array:
    emb_all = np.zeros([len(merge_list),512])
    #Outer for loop
    for i in range(0,len(merge_list)):
        #Here is where we run the previously started session, so it is important to run previous step succesfully:
        i_emb = session.run(embedded_text, feed_dict={text_input: [merge_list[i]]})
        emb_all[i,:] = i_emb
        #Inner for loop
        for j in range(0,len(merge_list)):
            j_emb = session.run(embedded_text, feed_dict={text_input: [merge_list[j]]})
            # print(j)
            similarity_matrix[i,j] = np.inner(i_emb,j_emb)
    return similarity_matrix, emb_all