How to remove a word completely from a Word2Vec model in gensim?

Question

Given a model, e.g.

from gensim.models.word2vec import Word2Vec


documents = [\"Human machine interface for lab abc computer applications\",
\"A survey of u         


        

Answer 1

Have tried and felt that the most straightforward way is as follows:

1. Get the Word2Vec embeddings in text file format.
2. Identify the lines corresponding to the word vectors that you would like to keep.
3. Write a new text file Word2Vec embedding model.
4. Load model and enjoy (save to binary if you wish, etc.)...

My sample code is as follows:

line_no = 0 # line0 = header
numEntities=0
targetLines = []

with open(file_entVecs_txt,'r') as fp:
    header = fp.readline() # header

    while True:
        line = fp.readline()
        if line == '': #EOF
            break
        line_no += 1

        isLatinFlag = True
        for i_l, char in enumerate(line):
            if not isLatin(char): # Care about entity that is Latin-only
                isLatinFlag = False
                break
            if char==' ': # reached separator
                ent = line[:i_l]
                break

        if not isLatinFlag:
            continue

        # Check for numbers in entity
        if re.search('\d',ent):
            continue

        # Check for entities with subheadings '#' (e.g. 'ENTITY/Stereotactic_surgery#History')
        if re.match('^ENTITY/.*#',ent):
            continue

        targetLines.append(line_no)
        numEntities += 1

# Update header with new metadata
header_new = re.sub('^\d+',str(numEntities),header,count=1)

# Generate the file
txtWrite('',file_entVecs_SHORT_txt)
txtAppend(header_new,file_entVecs_SHORT_txt)

line_no = 0
ptr = 0
with open(file_entVecs_txt,'r') as fp:
    while ptr < len(targetLines):
        target_line_no = targetLines[ptr]

        while (line_no != target_line_no):
            fp.readline()
            line_no+=1

        line = fp.readline()
        line_no+=1
        ptr+=1
        txtAppend(line,file_entVecs_SHORT_txt)

FYI. FAILED ATTEMPT I tried out @zsozso's method (with the np.array modifications suggested by @Taegyung), left it to run overnight for at least 12 hrs, it was still stuck at getting new words from the restricted set...). This is perhaps because I have a lot of entities... But my text-file method works within an hour.

FAILED CODE

# [FAILED] Stuck at Building new vocab...
def restrict_w2v(w2v, restricted_word_set):
    new_vectors = []
    new_vocab = {}
    new_index2entity = []
    new_vectors_norm = []

    print('Building new vocab..')

    for i in range(len(w2v.vocab)):

        if (i%int(1e6)==0) and (i!=0):
            print(f'working on {i}')

        word = w2v.index2entity[i]
        vec = np.array(w2v.vectors[i])
        vocab = w2v.vocab[word]
        vec_norm = w2v.vectors_norm[i]
        if word in restricted_word_set:
            vocab.index = len(new_index2entity)
            new_index2entity.append(word)
            new_vocab[word] = vocab
            new_vectors.append(vec)
            new_vectors_norm.append(vec_norm)

    print('Assigning new vocab')
    w2v.vocab = new_vocab
    print('Assigning new vectors')
    w2v.vectors = np.array(new_vectors)
    print('Assigning new index2entity, index2word')
    w2v.index2entity = new_index2entity
    w2v.index2word = new_index2entity
    print('Assigning new vectors_norm')
    w2v.vectors_norm = np.array(new_vectors_norm)