SIF_Variant_3.py

def sif_embeddings(sentences, model):
	""" Precomputes the sif_vectors in a separate matrix
	"""
	vlookup = model.wv.vocab
	vectors = model.wv.sif_vectors
	# The sif_vectors are pre-computed as:
	# sif_vectors = (model.wv.vectors * model.wv.sif[:, None])
	output = []
	for s in sentences:
	    idx = [vlookup[w].index for w in s if w in vlookup]
	    v = np.sum(vectors[idx], axis=0)
	    if len(idx) > 0:
	        v *= 1/len(idx)
	    output.append(v)
	return np.vstack(output).astype(REAL)