usage = "usage: %prog [options] filename"
parser = OptionParser(usage)
parser.add_option("-d", "--debug",
action="store_true", dest="debug")
(options, args) = parser.parse_args()
if len(args) != 3:
parser.error("You must give the filename, label support symbol, and minimum support.")
print "Mining from file %s..." % args[0]
print "Using label support symbol %s..." % args[1]
print "Using support of %s..." % args[2]
database = TransactionDatabase.loadFromFile(args[0],args[1],int(float(args[2])))
miner = DDPMine(debug=False)
miner.mine(database,int(float(args[2])))
"""
database = TransactionDatabase.loadFromFile("test.csv")
database.cleanAndPrune(2)
print "Cleaned database:"
print database
print "\nItems in FP tree and corresponding nodes:"
tree = FPTree()
for t in database:
tree.add(t)
print str(tree)
#run_ddpmine()
"""
def run_ddpmine():
# Just some placeholder data
miner = DDPMine(["a", "b"])
miner.mine()
database = TransactionDatabase.loadFromFile("./data/train_adt.csv", ['97'],
100)
data = TransactionDatabase.loadFromFile("./data/train_adt.csv", ['97'], 1)
data1 = TransactionDatabase.loadFromFile("./data/test_adt.csv", ['97'], 1)
# database.cleanAndPrune(2)
# print ("Cleaned database:")
# for transaction in database.transactions:
# print(str(transaction.label))
# print ("\nItems in FP tree and corresponding nodes:")
tree = FPTree()
for t in database:
tree.add(t)
# print(str(tree))
miner = DDPMine(debug=True)
start = time.clock()
Pt = miner.mine(database, 100)
elapsed = time.clock() - start
print("Time Total:%f" % elapsed)
print(Pt)
for row in Pt:
print("Pattern:%s label:%s" % (row[0], row[1]))
for row in Pt:
lb1 = 0
lb2 = 0
for transaction in data.transactions:
if set(row[0]).issubset(set(transaction.itemset)):
if transaction.label == "96":
