.sessions/ruby_classes_session .sessions/session .sessions/session2 Rakefile attic/test.c ext/Apriori.c ext/Makefile ext/apriori_wrapper.c ext/apriori_wrapper.h ext/extconf.rb test/apriori_test.rb test/fixtures/results.txt test/fixtures/sample.txt @@ -17,3 +17,61 @@ This will build the extension and run the "test" Nate Murray nate@natemurray.com + + +notes... + += What options we are going to support at first: +* at first, association rules + +:min_items -m# minimal number of items per set/rule/hyperedge (default: 1) +:max_items -n# maximal number of items per set/rule/hyperedge (default: no limit) +:min_support -s# minimal support of a set/rule/hyperedge (default: 10%) +:max_support -S# maximal support of a set/rule/hyperedge (default: 100%) +:min_confidence -c# minimal confidence of a rule/hyperedge (default: 80%) + +:show_absolute_support (bool) -a print absolute support (number of transactions) + +infile infile file to read transactions from +outfile outfile file to write item sets/association rules/hyperedges to + +puts find_association_rules(infile, outfile, opts={}) + += What options to support later: + +-t# target type (default: association rules) + (s: item sets, c: closed item sets, m: maximal item sets, + r: association rules, h: association hyperedges) +-k# item separator for output (default: " ") +-p# output format for support/confidence (default: "%.1f") +-y print lift value (confidence divided by prior) +-g write output in scanable form (quote certain characters) + +-q# sort items w.r.t. their frequency (default: 2) + (1: ascending, -1: descending, 0: do not sort, + 2: ascending, -2: descending w.r.t. transaction size sum) +-b/f/r# blank characters, field and record separators + (default: " \t\r", " \t", "\n") +appfile file stating item appearances (optional) + + += What options to support even later: +-e# additional evaluation measure (default: none) +-! print a list of additional evaluation measures +-d# minimal value of additional evaluation measure (default: 10%) +-v print value of additional rule evaluation measure +-l do not load transactions into memory (work on input file) +-u# filter unused items from transactions (default: 0.1) + (0: do not filter items w.r.t. usage in sets, + <0: fraction of removed items for filtering, + >0: take execution times ratio into account) +-h do not organize transactions as a prefix tree +-j use quicksort to sort the transactions (default: heapsort) +-z minimize memory usage (default: maximize speed) +-C# comment characters (default: "#") + + +Don't even know what they do: +-o use original definition of the support of a rule (body & head) +-x extended support output (print both rule support types) + README ruby/apriori/.sessions/ruby_classes_session ruby/apriori/.sessions/session ruby/apriori/.sessions/session2 ruby/apriori/Apriori/Apriori.c ruby/apriori/Apriori/Makefile ruby/apriori/Apriori/apriori_wrapper.c ruby/apriori/Apriori/apriori_wrapper.h ruby/apriori/Apriori/extconf.rb ruby/apriori/Apriori/test.c ruby/apriori/README ruby/apriori/Rakefile ruby/apriori/apriori_test.rb ruby/apriori/test/sample.txt 646837e53868c7cc58b5d6e5857f9c79d9c22e0e Nate Murray nate@natemurray.com http://github.com/jashmenn/apriori/commit/d031ca604577719ff9d18982e994d5e46b8edfc2 d031ca604577719ff9d18982e994d5e46b8edfc2 2008-08-30T10:48:45-07:00 2008-08-30T10:48:45-07:00 continued work on the major reorganization c329c3cba954006b2ff18687f10e09079118b10f Nate Murray nate@natemurray.com