w2v_find_similar_words

w2v_find_similar_words.py

# Find similar words
w2v.vec_sim("machine", 3)

class word2vec():
  ## Removed##
  
  # Input vector, returns nearest word(s)
  def vec_sim(self, word, top_n):
    v_w1 = self.word_vec(word)
    word_sim = {}

    for i in range(self.v_count):
      # Find the similary score for each word in vocab
      v_w2 = self.w1[i]
      theta_sum = np.dot(v_w1, v_w2)
      theta_den = np.linalg.norm(v_w1) * np.linalg.norm(v_w2)
      theta = theta_sum / theta_den

      word = self.index_word[i]
      word_sim[word] = theta

    words_sorted = sorted(word_sim.items(), key=lambda kv: kv[1], reverse=True)

    for word, sim in words_sorted[:top_n]:
      print(word, sim)