def stack_method():
if "mean" in args.model:
all_preds = [
"data/te.ins5.ffm.out",
"data/xgb5_test.out",
"data/te.ins_bag.ffm.out",
"data/te.ins5.fm.out",
"data/te.ins3.ffm.out",
"data/te.ins20.ffm.out",
"data/xgb3_test.out",
"data/te.ins.ffm.out",
]
else:
all_preds = [
"data/te.ins5.ffm.out",
"data/xgb5_test.out",
"data/te.ins_bag.ffm.out",
"data/te.ins5.fm.out",
"data/te.ins3.ffm.out",
"data/te.ins20.ffm.out",
"data/xgb3_test.out",
"data/te.ins.ffm.out",
"data/te.ins2.ffm.out",
]
delta = 1
now = datetime.now()
X = []
true_y = []
for t, preds in enumerate(read_preds(all_preds)):
if "nn" in args.model or "xgb" in args.model:
preds = map(lambda x: relogit(x), preds)
X.append(preds)
true_y.append(0)
if t == delta:
print "%s: %s" % (t, datetime.now() - now)
delta *= 2
if "nn" in args.model:
model = read_dump("%s_model.dump" % args.model)
X = np.array(X).astype(np.float32)
preds = model.predict_proba(X)[:, 1]
elif "xgb" in args.model:
dtrain = xgb.DMatrix(np.array(X), label=true_y)
bst = xgb.Booster({"nthread": 9})
bst.load_model("%s_model.dump" % args.model)
preds = bst.predict(dtrain)
elif args.model == "mean":
X = np.array(X).astype(np.float32)
preds = np.mean(X, 1)
with open("result_%s.csv" % args.model, "w") as outfile:
outfile.write("ID,IsClick\n")
avg_p = 0
cnt = 0
for ID, p in izip(read_sample("data/sampleSubmission.csv"), preds):
avg_p += p
cnt += 1
outfile.write("%s,%s\n" % (ID, str(p)))
print cnt, avg_p / cnt
def stack_method():
if "mean" in args.model:
all_preds = [
"data/te.ins5.ffm.out",
"data/xgb5_test.out",
"data/te.ins_bag.ffm.out",
"data/te.ins5.fm.out",
"data/te.ins3.ffm.out",
"data/te.ins20.ffm.out",
"data/xgb3_test.out",
"data/te.ins.ffm.out",
]
else:
all_preds = [
"data/te.ins5.ffm.out",
"data/xgb5_test.out",
"data/te.ins_bag.ffm.out",
"data/te.ins5.fm.out",
"data/te.ins3.ffm.out",
"data/te.ins20.ffm.out",
"data/xgb3_test.out",
"data/te.ins.ffm.out",
"data/te.ins2.ffm.out",
]
delta = 1
now = datetime.now()
X = []
true_y = []
for t, preds in enumerate(read_preds(all_preds)):
if "nn" in args.model or "xgb" in args.model:
preds = map(lambda x: relogit(x), preds)
X.append(preds)
true_y.append(0)
if t == delta:
print "%s: %s" % (t, datetime.now() - now)
delta *= 2
if "nn" in args.model:
model = read_dump("%s_model.dump" % args.model)
X = np.array(X).astype(np.float32)
preds = model.predict_proba(X)[:, 1]
elif "xgb" in args.model:
dtrain = xgb.DMatrix(np.array(X), label=true_y)
bst = xgb.Booster({'nthread': 9})
bst.load_model("%s_model.dump" % args.model)
preds = bst.predict(dtrain)
elif args.model == "mean":
X = np.array(X).astype(np.float32)
preds = np.mean(X, 1)
with open("result_%s.csv" % args.model, 'w') as outfile:
outfile.write('ID,IsClick\n')
avg_p = 0
cnt = 0
for ID, p in izip(read_sample("data/sampleSubmission.csv"), preds):
avg_p += p
cnt += 1
outfile.write('%s,%s\n' % (ID, str(p)))
print cnt, avg_p / cnt
parser.add_argument('--seed', type=int, default=9)
parser.add_argument('--date', type=int, default=0)
parser.add_argument('--log', type=int, default=1)
args = parser.parse_args()
if args.mongo:
from pymongo import MongoClient
import functools32 as functools
client = MongoClient('localhost', 27017)
db = client.test
@functools.lru_cache(maxsize=1000000)
def get_ad_info(aid):
ad_info = db.ad_info.find_one({"AdID": aid})
return trans_ad_info(ad_info)
uid_cnt_dict = read_dump("data/uid_cnt.dump")
adid_cnt_dict = read_dump("data/adid_cnt.dump")
ipid_cnt_dict = read_dump("data/ipid_cnt.dump")
query_cnt_dict = read_dump("data/query_cnt.dump")
title_cnt_dict = read_dump("data/title_cnt.dump")
query_param_cnt_dict = read_dump("data/query_param_cnt.dump")
ad_param_cnt_dict = read_dump("data/ad_param_cnt.dump")
user_info_map = get_user_info()
category_map = get_category()
user_cnt_iter = read_tsv("data/user_cnt.csv", delimiter=",")
user_aid_cnt_iter = next_row(read_tsv("data/user_aid_cnt.csv", delimiter=","))
main()
parser.add_argument('--seed', type=int, default=9)
parser.add_argument('--date', type=int, default=0)
parser.add_argument('--log', type=int, default=1)
args = parser.parse_args()
if args.mongo:
from pymongo import MongoClient
import functools32 as functools
client = MongoClient('localhost', 27017)
db = client.test
@functools.lru_cache(maxsize=1000000)
def get_ad_info(aid):
ad_info = db.ad_info.find_one({"AdID": aid})
return trans_ad_info(ad_info)
uid_cnt_dict = read_dump("data/uid_cnt.dump")
adid_cnt_dict = read_dump("data/adid_cnt.dump")
ipid_cnt_dict = read_dump("data/ipid_cnt.dump")
query_cnt_dict = read_dump("data/query_cnt.dump")
title_cnt_dict = read_dump("data/title_cnt.dump")
query_param_cnt_dict = read_dump("data/query_param_cnt.dump")
ad_param_cnt_dict = read_dump("data/ad_param_cnt.dump")
user_info_map = get_user_info()
category_map = get_category()
user_cnt_iter = read_tsv("data/user_cnt.csv", delimiter=",")
user_aid_cnt_iter = next_row(
read_tsv("data/user_aid_cnt.csv", delimiter=","))
main()
parser.add_argument('--seed', type=int, default=9)
parser.add_argument('--date', type=int, default=0)
parser.add_argument('--log', type=int, default=1)
args = parser.parse_args()
if args.mongo:
from pymongo import MongoClient
import functools32 as functools
client = MongoClient('localhost', 27017)
db = client.test
@functools.lru_cache(maxsize=1000000)
def get_ad_info(aid):
ad_info = db.ad_info.find_one({"AdID": aid})
return trans_ad_info(ad_info)
uid_cnt_dict = read_dump("uid_cnt.dump")
adid_cnt_dict = read_dump("adid_cnt.dump")
ipid_cnt_dict = read_dump("ipid_cnt.dump")
query_cnt_dict = read_dump("query_cnt.dump")
title_cnt_dict = read_dump("title_cnt.dump")
query_param_cnt_dict = read_dump("query_param_cnt.dump")
ad_param_cnt_dict = read_dump("ad_param_cnt.dump")
user_info_map = get_user_info()
category_map = get_category()
user_cnt_iter = read_tsv("data/user_cnt.csv", delimiter=",")
user_aid_cnt_iter = next_row(read_tsv("data/user_aid_cnt.csv", delimiter=","))
main()
