def test_fpgrowth_pruning_off(self):
ts1 = perftesting.get_default_transactions()
fp_input = itemmining.get_fptree(ts1)
report = itemmining.fpgrowth(fp_input, 2, pruning=False)
self.assertEqual(17, len(report))
self.assertEqual(6, report[frozenset(['b', 'd'])])
ts2 = perftesting.get_default_transactions_alt()
fp_input = itemmining.get_fptree(ts2)
report = itemmining.fpgrowth(fp_input, 2, pruning=False)
self.assertEqual(19, len(report))
self.assertEqual(5, report[frozenset(['a', 'b'])])
def test_fpgrowth_pruning_off(self):
ts1 = perftesting.get_default_transactions()
fp_input = itemmining.get_fptree(ts1)
report = itemmining.fpgrowth(fp_input, 2, pruning=False)
self.assertEqual(17, len(report))
self.assertEqual(6, report[frozenset(['b', 'd'])])
ts2 = perftesting.get_default_transactions_alt()
fp_input = itemmining.get_fptree(ts2)
report = itemmining.fpgrowth(fp_input, 2, pruning=False)
self.assertEqual(19, len(report))
self.assertEqual(5, report[frozenset(['a', 'b'])])
def test_fpgrowth(should_print=False, ts=None, support=2, pruning=False):
if ts is None:
ts = get_default_transactions()
fptree = get_fptree(ts, lambda e: e, support)
fis = set()
report = {}
n = _fpgrowth(fptree, fis, report, support, pruning)
if should_print:
print(n)
print(report)
return (n, report)
def test_fpgrowth(should_print=False, ts=None, support=2, pruning=False):
if ts is None:
ts = get_default_transactions()
fptree = get_fptree(ts, lambda e: e, support)
fis = set()
report = {}
n = _fpgrowth(fptree, fis, report, support, pruning)
if should_print:
print(n)
print(report)
return (n, report)
def mine_rules_fp(self, baskets):
print "preparing fptree"
fptree = itemmining.get_fptree(baskets, min_support = len(baskets) * self.min_support)
print "finding itemsets"
self.item_sets = itemmining.fpgrowth(fptree, min_support = len(baskets) * self.min_support)
print "found {} frequent sequences".format(len(self.item_sets))
print "finding association rules"
self.rules = assocrules.mine_assoc_rules(self.item_sets, len(baskets),
min_support = self.min_support, min_confidence = self.min_confidence,
min_lift = self.min_lift)
# sort by support
self.nonmax_suppression()
self.max_rules = sorted(self.max_rules, key = lambda x: -x[2])
print "found {} maximal rules with sufficient lift".format(len(self.max_rules))
def freq_items(self):
fp_input = itemmining.get_fptree(self.transactions)
item_sets = itemmining.fpgrowth(fp_input, self.min_sup)
return item_sets
def fp_growth(self):
fpgrowth_input = itemmining.get_fptree(self.transactions, None, 100)
item_sets = itemmining.fpgrowth(fpgrowth_input, self.min_sup)
return item_sets