def test():
theta = readTheta()
count = 0
reader = BinReader(FILENAME)
reader.open()
result = [0] * reader.LineCount
for i in xrange(reader.LineCount):
(x, userid, itemid, label) = reader.readline()
x[0] = 1
y = np.dot(x[:37], theta)
result[i] = (userid, itemid, y)
if i % 10000 == 0:
print '%d/%d' % (i, reader.LineCount)
result.sort(key=lambda x: x[2], reverse=True)
result = result[:6500]
print ur'样本总数:', count
print ur'正在输出...'
with open('result.csv', 'w') as f:
for item in result:
f.write('%d,%d\n' % (item[0], item[1]))
print ur'测试结束，输出个数:', 6500
def __init__(self, filename):
self.filename = filename
self.reader = BinReader(filename)
action='store_true',
help="Don't print file info")
args = argsp.parse_args()
if args.construct and args.destruct:
print("--construct and --destruct are mutually exclusive!")
argsp.print_help()
sys.exit(1)
# When destructing, we need to make the directory if it doesn't exist
if args.destruct:
if not os.path.exists(args.destruct):
os.makedirs(args.destruct)
fh = FCH_Root()
with BinReader(args.path) as br:
fh.fromBinary(br)
if not args.quiet:
fh.printInfo()
fh.destruct(args.destruct, overwrite=args.overwrite)
elif args.construct:
fh = FCH_Root()
fh.construct(args.construct)
with BinWriter(args.path, overwrite=args.overwrite) as wr:
fh.toBinary(wr)
# Sanity read it again!
with BinReader(args.path) as br:
fh.fromBinary(br)
if not args.quiet:
fh.printInfo()
else:
import numpy as np
from sklearn.ensemble.gradient_boosting import GradientBoostingRegressor
path_train = ur'data\temp_train.bin'
path_test = ur'data\temp_test.bin'
(data, label, items) = BinReader.readData(path_train)
X_train = np.array(data)
label = [item[0] for item in label]
y_train = np.array(label)
est = GradientBoostingRegressor(n_estimators=150, learning_rate=0.1, max_depth=3, random_state=0, loss='ls',
verbose=1).fit(X_train, y_train)
print 'testing...'
reader = BinReader(path_test)
reader.open()
result = [0] * reader.LineCount
for i in xrange(reader.LineCount):
(x, userid, itemid, label) = reader.readline()
x[0] = 1
y = est.predict([x])[0]
result[i] = (userid, itemid, y)
if i % 10000 == 0:
print '%d/%d' % (i, reader.LineCount)
result.sort(key=lambda x: x[2], reverse=True)
result = result[:7000]
print "input"
with open('result.csv', 'w') as f:
