Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/2819#discussion_r19455165 --- Diff: python/pyspark/mllib/feature.py --- @@ -95,33 +385,26 @@ class Word2Vec(object): >>> localDoc = [sentence, sentence] >>> doc = sc.parallelize(localDoc).map(lambda line: line.split(" ")) >>> model = Word2Vec().setVectorSize(10).setSeed(42L).fit(doc) + >>> syms = model.findSynonyms("a", 2) - >>> str(syms[0][0]) - 'b' - >>> str(syms[1][0]) - 'c' - >>> len(syms) - 2 + >>> [s[0] for s in syms] + [u'b', u'c'] >>> vec = model.transform("a") - >>> len(vec) - 10 >>> syms = model.findSynonyms(vec, 2) - >>> str(syms[0][0]) - 'b' - >>> str(syms[1][0]) - 'c' - >>> len(syms) - 2 + >>> [s[0] for s in syms] + [u'b', u'c'] """ def __init__(self): """ Construct Word2Vec instance """ + import random # this can't be on the top because of mllib.random + self.vectorSize = 100 self.learningRate = 0.025 self.numPartitions = 1 self.numIterations = 1 - self.seed = 42L + self.seed = random.randint(0, sys.maxint) --- End diff -- ok
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org