def runTest():
train = 'train.csv'
test = 'test.csv'
output = 'prediciton.txt'
M = readHelper.readTrainMemory(train)
query, tuples = readHelper.readQueryMemory(test)
k = 100
func = 'dotp'
func_w = 'mean'
pred = memory.pccMemoryCF(M, query, k, func, func_w)
writeHelper.writePredMemory(output, pred, tuples)
return
def main():
start_time = time.time()
parser = argparse.ArgumentParser(description = "collaborative filtering")
parser.add_argument("-t", help = "if running test", action = 'store_true', default = False)
parser.add_argument("-m", help = "memory-based or model collaborative filtering", choices = ['memory','model'])
parser.add_argument("-k", help = "number of k nearest neighborhood", type = int, choices = [10,100,500])
parser.add_argument("-s", help = "similarity metric used for knn ", choices = ['dotp','cosine'])
parser.add_argument("-w", help = "approach for combining prediction given knn", choices = ['mean','weight'])
parser.add_argument("-p", help = "if standardization used", action = 'store_true', default = False)
parser.add_argument("-b", help = "if bipartite clustering userd", action = "store_true", default = False)
args = parser.parse_args()
print args
if not args.t:
output = "-".join([args.m, str(args.k), args.s, args.w])
if args.p:
output += '-pcc'
if args.b:
output += '-bi'
output += '.txt'
train = 'train.csv'
dev = 'dev.csv'
if args.m == 'memory' and not args.b:
M = readHelper.readTrainMemory(train)
query, tuples = readHelper.readQueryMemory(dev)
if args.p:
pred = memory.pccMemoryCF(M, query, args.k, args.s, args.w)
else:
pred = memory.memoryCF(M, query, args.k, args.s, args.w)
writeHelper.writePredMemory(output, pred, tuples)
elif args.m == 'model' and not args.b:
M = readHelper.readTrainModel(train)
tuples = readHelper.readQueryModel(dev)
if args.p:
pred = model.pccModelCF(M, tuples, args.k, args.s, args.w)
else:
pred = model.modelCF(M, tuples, args.k, args.s, args.w)
writeHelper.writePredModel(output, pred)
if args.b:
M = readHelper.readTrainModel(train)
tuples = readHelper.readQueryModel(dev)
if args.m == 'model':
pred = BiCF.bi_item(M, tuples, args.k, args.s, args.w)
else:
pred = BiCF.bi_user(M, tuples, args.k, args.s, args.w)
writeHelper.writePredModel(output, pred)
print 'time: %s seconds' % (time.time()-start_time)
else:
runTest()
def runTest():
train = 'train.csv'
test = 'test.csv'
output = 'prediciton.txt'
M = readHelper.readTrainMemory(train)
query, tuples = readHelper.readQueryMemory(test)
k = 100
func = 'dotp'
func_w = 'mean'
pred = memory.pccMemoryCF(M, query, k, func, func_w)
writeHelper.writePredMemory(output, pred, tuples)
return
def main():
start_time = time.time()
parser = argparse.ArgumentParser(description="collaborative filtering")
parser.add_argument("-t",
help="if running test",
action='store_true',
default=False)
parser.add_argument("-m",
help="memory-based or model collaborative filtering",
choices=['memory', 'model'])
parser.add_argument("-k",
help="number of k nearest neighborhood",
type=int,
choices=[10, 100, 500])
parser.add_argument("-s",
help="similarity metric used for knn ",
choices=['dotp', 'cosine'])
parser.add_argument("-w",
help="approach for combining prediction given knn",
choices=['mean', 'weight'])
parser.add_argument("-p",
help="if standardization used",
action='store_true',
default=False)
parser.add_argument("-b",
help="if bipartite clustering userd",
action="store_true",
default=False)
args = parser.parse_args()
print args
if not args.t:
output = "-".join([args.m, str(args.k), args.s, args.w])
if args.p:
output += '-pcc'
if args.b:
output += '-bi'
output += '.txt'
train = 'train.csv'
dev = 'dev.csv'
if args.m == 'memory' and not args.b:
M = readHelper.readTrainMemory(train)
query, tuples = readHelper.readQueryMemory(dev)
if args.p:
pred = memory.pccMemoryCF(M, query, args.k, args.s, args.w)
else:
pred = memory.memoryCF(M, query, args.k, args.s, args.w)
writeHelper.writePredMemory(output, pred, tuples)
elif args.m == 'model' and not args.b:
M = readHelper.readTrainModel(train)
tuples = readHelper.readQueryModel(dev)
if args.p:
pred = model.pccModelCF(M, tuples, args.k, args.s, args.w)
else:
pred = model.modelCF(M, tuples, args.k, args.s, args.w)
writeHelper.writePredModel(output, pred)
if args.b:
M = readHelper.readTrainModel(train)
tuples = readHelper.readQueryModel(dev)
if args.m == 'model':
pred = BiCF.bi_item(M, tuples, args.k, args.s, args.w)
else:
pred = BiCF.bi_user(M, tuples, args.k, args.s, args.w)
writeHelper.writePredModel(output, pred)
print 'time: %s seconds' % (time.time() - start_time)
else:
runTest()