word2vec_impl.py 文件源码

def testWord2Vec(testWords,weights,num_display=3):
    ##Generate inverse word mapping for easy lookup
    invWordDict = {v: k for k, v in wordDict.iteritems()}

    ## Normalize the trained weights for cosine similarity
    trainedWeights = normalize(weights,norm = 'l2', axis = 1)
    for word in testWords:
        try:
            embedding = trainedWeights[wordDict[word],:]
            prox = np.argsort(np.dot(embedding,trainedWeights.transpose())/np.linalg.norm(embedding))[-num_display:].tolist()       
            prox.reverse()
            print 'Closest word vector (by cosine similarity) for %s : '%word, [invWordDict[item] for item in prox]

        except KeyError:
            print '"%s" not found in the Trained Word Embeddings. Skipping...'%word
            pass