我是pyspark的新手,我想对一组文档进行聚类(20个聚类)。为此,我需要执行以下操作:
因此我创建了word2vec表示形式,但是我没有设法使用spark将每个文档映射到其对应的矢量。
我尝试了以下操作:
from pyspark.mllib.feature import Word2Vec
word2vec = Word2Vec()
model = word2vec.fit(docs)
dic = model.getVectors()
import numpy as np
def calcAverage(x, dic):
ans = np.zeros(100)
for word in x:
if word in dic:
ans += np.array(dic[word])
return tuple(ans / len(x))
vectors = docs.map(lambda x: calcAverage(x, dic))
vectors.collect()
但是它不起作用,代码在以下行失败:vectors = docs.map(lambda x: calcAverage(x, dic))
,有什么建议吗?
我遇到以下错误:
PicklingError: Could not serialize object: Py4JError: An error occurred while calling o73192.__getstate__. Trace:
py4j.Py4JException: Method __getstate__([]) does not exist
at py4j.reflection.ReflectionEngine.getMethod(ReflectionEngine.java:318)
at py4j.reflection.ReflectionEngine.getMethod(ReflectionEngine.java:326)
at py4j.Gateway.invoke(Gateway.java:274)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:748)