ValueError：缓冲区数据类型不匹配，预期为“双”，但得到“浮动”

Question

def cast_vector(row):
    return np.array(list(map(lambda x: x.astype('float32'), row)))

words = pd.DataFrame(word_vectors.vocab.keys())
words.columns = ['words']
words['vectors'] = words.words.apply(lambda x: word_vectors.wv[f'{x}'])
words['vectors_typed'] = words.vectors.apply(cast_vector)
words['cluster'] = words.vectors_typed.apply(lambda x: model.predict([np.array(x)]))
#words.cluster = words.cluster.apply(lambda x: x[0])

虽然是float32，为什么会出错？

Answer 1

对我来说，改变 kmeans 定义以使用单词向量作为 double 是有效的。结果代码是：

from sklearn.cluster import KMeans

word_vectors = Word2Vec.load("../models/word2vec.model").wv

kmeans = KMeans(n_clusters=2, max_iter=1000, random_state=True, n_init=50).fit(X=word_vectors.vectors.astype('double'))

def cast_vector(row):
    return np.array(list(map(lambda x: x.astype('double'), row)))

words = pd.DataFrame(word_vectors.vocab.keys())
words.columns = ['words']
words['vectors'] = words.words.apply(lambda x: word_vectors[f'{x}'])
words['vectors_typed'] = words.vectors.apply(cast_vector)
words['cluster'] = words.vectors_typed.apply(lambda x: kmeans.predict([np.array(x)]))
words.cluster = words.cluster.apply(lambda x: x[0])
words['cluster_value'] = [1 if i==0 else -1 for i in words.cluster]
words['closeness_score'] = words.apply(lambda x: 1/(model.transform([x.vectors]).min()), axis=1)
words['sentiment_coeff'] = words.closeness_score * words.cluster_value

words.head(10)