PrefixSpan

class pyspark.mllib.fpm.PrefixSpan[source]

A parallel PrefixSpan algorithm to mine frequent sequential patterns. The PrefixSpan algorithm is described in Jian Pei et al (2001) [1]

New in version 1.6.0.

1

Jian Pei et al., “PrefixSpan,: mining sequential patterns efficiently by prefix-projected pattern growth,” Proceedings 17th International Conference on Data Engineering, Heidelberg, Germany, 2001, pp. 215-224, doi: https://doi.org/10.1109/ICDE.2001.914830

Methods

train(data[, minSupport, maxPatternLength, …])

Finds the complete set of frequent sequential patterns in the input sequences of itemsets.

Methods Documentation

classmethod train(data: pyspark.rdd.RDD[List[List[T]]], minSupport: float = 0.1, maxPatternLength: int = 10, maxLocalProjDBSize: int = 32000000)pyspark.mllib.fpm.PrefixSpanModel[T][source]

Finds the complete set of frequent sequential patterns in the input sequences of itemsets.

New in version 1.6.0.

Parameters
datapyspark.RDD

The input data set, each element contains a sequence of itemsets.

minSupportfloat, optional

The minimal support level of the sequential pattern, any pattern that appears more than (minSupport * size-of-the-dataset) times will be output. (default: 0.1)

maxPatternLengthint, optional

The maximal length of the sequential pattern, any pattern that appears less than maxPatternLength will be output. (default: 10)

maxLocalProjDBSizeint, optional

The maximum number of items (including delimiters used in the internal storage format) allowed in a projected database before local processing. If a projected database exceeds this size, another iteration of distributed prefix growth is run. (default: 32000000)