我在列表中有一组大小为3的元组,表示窗口序列。 我需要的是使用pyspask能够得到(给定元组的两个第一部分)第三个部分。
所以我需要它根据频率创建三个元素的序列。
这就是我在做的事情:
data = [[['a','b','c'],['b','c','d'],['c','d','e'],['d','e','f'],['e','f','g'],['f','g','h'],['a','b','c'],['d','e','f'],['a','b','c'],['b','c','d'],['f','g','h'],['d','e','f'],['b','c','d']]]
rdd = spark.sparkContext.parallelize(data,2)
rdd.cache()
model = PrefixSpan.train( rdd, 0.2, 3)
print(sorted(model.freqSequences().take(100)))
虽然,我希望看到它们的序列和频率遵循字母表,但它们不会。
我得到的序列如下:
FreqSequence(sequence=[[u'c'], [u'd'], [u'b']], freq=1)
FreqSequence(sequence=[[u'g'], [u'c'], [u'c']], freq=1)
未出现在已定义的那些中。显然,我构建我的功能的方式存在问题,或者我在这个算法的目的和功能上缺少一些东西。
谢谢!
答案 0 :(得分:1)
首先让我们看看你的输入:
rdd.count()
1
如您所见,您创建的数据集只包含一个序列。它可以描述为:
<(abc)(bcd)(cde)(def)(efg)(fgh)(abc)(def)(abc)(bcd)(fgh)(def)(bcd)>
因此,根据输入,您获得的模式确实是正确的。例如
FreqSequence(sequence=[[u'c'], [u'd'], [u'b']], freq=1)
对应于:
...(abc)(def)(abc)...
如果数据集的每个元素代表单个序列数据,则可以具有以下形状:
rdd = sc.parallelize([
[['a'], ['b'], ['c']], [['b'], ['c'], ['d']], [['c'], ['d'], ['e']],
[['d'], ['e'], ['f']], [['e'], ['f'], ['g']], [['f'], ['g'], ['h']],
[['a'], ['b'], ['c']], [['d'], ['e'], ['f']], [['a'], ['b'], ['c']],
[['b'], ['c'], ['d']], [['f'], ['g'], ['h']], [['d'], ['e'], ['f']],
[['b'], ['c'], ['d']]
])
rdd.count()
13
rdd.first()
[['a'], ['b'], ['c']]
其中:
数据结构如下:
model = PrefixSpan.train(rdd, 0.2, 3)
model.freqSequences().top(5, key=lambda x: len(x.sequence))
[FreqSequence(sequence=[['d'], ['e'], ['f']], freq=3),
FreqSequence(sequence=[['b'], ['c'], ['d']], freq=3),
FreqSequence(sequence=[['a'], ['b'], ['c']], freq=3),
FreqSequence(sequence=[['f'], ['g']], freq=3),
FreqSequence(sequence=[['d'], ['f']], freq=3)]
model.freqSequences().top(5, key=lambda x: x.freq)
[FreqSequence(sequence=[['d']], freq=7),
FreqSequence(sequence=[['c']], freq=7),
FreqSequence(sequence=[['f']], freq=6),
FreqSequence(sequence=[['b']], freq=6),
FreqSequence(sequence=[['b'], ['c']], freq=6)]