From 25f574eb9a3cb9b93b7d9194a8ec16e00ce2c036 Mon Sep 17 00:00:00 2001 From: Feynman Liang Date: Sun, 28 Jun 2015 22:26:07 -0700 Subject: [SPARK-7212] [MLLIB] Add sequence learning flag Support mining of ordered frequent item sequences. Author: Feynman Liang Closes #6997 from feynmanliang/fp-sequence and squashes the following commits: 7c14e15 [Feynman Liang] Improve scalatests with R code and Seq 0d3e4b6 [Feynman Liang] Fix python test ce987cb [Feynman Liang] Backwards compatibility aux constructor 34ef8f2 [Feynman Liang] Fix failing test due to reverse orderering f04bd50 [Feynman Liang] Naming, add ordered to FreqItemsets, test ordering using Seq 648d4d4 [Feynman Liang] Test case for frequent item sequences 252a36a [Feynman Liang] Add sequence learning flag --- python/pyspark/mllib/fpm.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'python/pyspark') diff --git a/python/pyspark/mllib/fpm.py b/python/pyspark/mllib/fpm.py index bdc4a132b1..b7f00d6006 100644 --- a/python/pyspark/mllib/fpm.py +++ b/python/pyspark/mllib/fpm.py @@ -39,8 +39,8 @@ class FPGrowthModel(JavaModelWrapper): >>> data = [["a", "b", "c"], ["a", "b", "d", "e"], ["a", "c", "e"], ["a", "c", "f"]] >>> rdd = sc.parallelize(data, 2) >>> model = FPGrowth.train(rdd, 0.6, 2) - >>> sorted(model.freqItemsets().collect()) - [FreqItemset(items=[u'a'], freq=4), FreqItemset(items=[u'c'], freq=3), ... + >>> sorted(model.freqItemsets().collect(), key=lambda x: x.items) + [FreqItemset(items=[u'a'], freq=4), FreqItemset(items=[u'a', u'c'], freq=3), ... """ def freqItemsets(self): -- cgit v1.2.3