FrequentSequences: A function to find frequent sequences using the wonderful...

In MGousseff/r2spmf: Links R 2 the SPMF Library for frequent itemsets and sequences mining

Description

This function sends a list of sequences to spmf and gets back the most frequent sequences with their support and frequence.

Usage

FrequentSequences(x, algo, minsup = 0.5, nbEventMax = "", showID = "",
  clean = T, minTime = "", maxTime = "", minWhole = "", maxWhole = "")

Arguments

x	is the output of the function df2SPMFSequence function. It must contains a toSendSPMF storing a tibble with a basket column. This basket is sent to spmf java library.
algo	is the name of the algorithm to be used. The possible values are : Please check SPMF documentation at http://www.philippe-fournier-viger.com/spmf/index.php?link=documentation.php
minsup	is the value of the minimum support for a sequence to be seen as frequent. To get all the sequences present in more than 40 percent of the database sequences, type either "40%" or "0.4"
clean	if clean=F the text files sent to and received from spmf will be kept in the working directory.
minTime	is the minimum time interval for 2 items to be considered as belonging to the same sequence
maxTime	is the maximum time interval for 2 items to be considered as belonging to the same sequence
minWhole	is the minimum length of time for a whole sequence to be counted
maxWhole	is the maximum length of time for a whole sequence to be counted
Those	time parameters are only considered when the input is a timed sequence. The only algorithme to be used are then "Fournier08-Closed+time" and "HirateYamana"

Value

a dataframe with three columns. sequence contains all the frequent sequences. support is the number of times this sequence occurs, and frequence is support divided by the total number of sequences

MGousseff/r2spmf documentation built on May 26, 2019, 11:58 p.m.