def main():
if len(sys.argv) < 3:
print "Usage python test_lr.py campaign_id learn_rate (budget_prop)"
exit(-1)
data_folder = "../../make-ipinyou-data/"
config.campaign_id = int(sys.argv[1])
# print config.campaign
# print config.campaign_id
# exit(-1)
config.lr_alpha = float(sys.argv[2])
if len(sys.argv) == 4:
config.budget_prop = int(sys.argv[3])
train_path = data_folder + ` config.campaign_id ` + "/train.yzx.txt"
test_path = data_folder + ` config.campaign_id ` + "/test.yzx.txt"
train_data = Dataset(train_path, config.campaign_id)
train_data.shuffle() # make train data shuffled
test_data = Dataset(test_path, config.campaign_id)
print "Load done."
lr_model = LrModel(train_data, test_data)
print "campaign v = " + ` lr_model.camp_v `
print "learn_rate = " + ` config.lr_alpha `
print "budget = " + ` lr_model.budget `
if config.ds_ratio > 0:
print "Need calibration."
else:
print "No calibration."
print "Begin training ..."
for i in range(0, config.lr_train_round):
lr_model.train()
lr_model.test()
print "Round " + ` i + 1 ` + "\t" + ` tool.get_last_log(
lr_model.test_log)['performance'] `
if tool.judge_stop(lr_model.test_log):
break
print "Train done."
log_file = ` config.campaign_id ` + "_lrlin_" + ` config.lr_alpha ` + "_" + ` config.budget_prop ` + ".csv"
fo = open("../output/" + log_file, 'w')
print "Begin log ..."
header = "camp_id\tmodel\tdataset\trevenue\tctr\tcpc\tauc\trmse\tcpm\tbids\timps\tclks\tlaplace\tinterval\tlearn_rate\tnds_ratio\tbudget_prop"
best_test_log = lr_model.get_best_test_log()
best_test_line = `config.campaign_id` + "\t" + "LR\ttest\t" \
+ tool.gen_performance_line(best_test_log) + "\t" \
+ 'None' + "\t" + "None" + "\t" + `config.lr_alpha` + "\t" \
+ "None" + "\t" + `config.budget_prop`
fo.write(header + "\n")
fo.write(best_test_line + "\n")
# search for best linear parameter
opt_param = lr_model.lin_bid(best_test_log['weight'])
fo.write(
"prop\trevenue\troi\tctr\tcpc\tauc\trmse\tcpm\timps\tclks\tlin_param\n"
)
for prop in config.budget_props:
performance = lr_model.replay(best_test_log['weight'],
lr_model.test_data, prop)
fo.write( ` prop `)
fo.write("\t")
fo.write( ` performance['revenue'] `)
fo.write("\t")
fo.write( ` performance['roi'] `)
fo.write("\t")
fo.write( ` performance['ctr'] `)
fo.write("\t")
fo.write( ` performance['cpc'] `)
fo.write("\t")
fo.write( ` performance['auc'] `)
fo.write("\t")
fo.write( ` performance['rmse'] `)
fo.write("\t")
fo.write( ` performance['cpm'] `)
fo.write("\t")
fo.write( ` performance['imps'] `)
fo.write("\t")
fo.write( ` performance['clks'] `)
fo.write("\t")
fo.write( ` opt_param `)
fo.write("\n")
fo.write("\n")
fo.write("Round\tTest\tctr\tcpc\tauc\trmse\tcpm\tclks\timps\tbids\n")
for i in range(0, len(lr_model.test_log)):
test_log = lr_model.test_log[i]
line = `i+1` + "\t" + `test_log['performance']['revenue']` \
+ "\t" + `test_log['performance']['ctr']` \
+ "\t" + `test_log['performance']['cpc']` \
+ "\t" + `test_log['performance']['auc']` \
+ "\t" + `test_log['performance']['rmse']` \
+ "\t" + `test_log['performance']['cpm']` \
+ "\t" + `test_log['performance']['clks']` \
+ "\t" + `test_log['performance']['imps']` \
+ "\t" + `test_log['performance']['bids']`
fo.write(line + "\n")
fo.close()
print "Log done."
weight_path = `config.campaign_id` + "_" + "lrlin_best_weight" \
+ "_" + `config.lr_alpha` + "_" + `config.budget_prop` \
+ ".weight"
lr_model.output_weight(best_test_log['weight'], "../output/" + weight_path)
def main():
if len(sys.argv) < 5:
print "Usage: python test_prectr_joint.py campaign_id laplace eu_scale ds_ratio mkt_alpha mkt_lambda"
exit(-1)
config.campaign_id = int(sys.argv[1]) if int(
sys.argv[1]) in config.campaign_list else config.campaign_id
config.laplace = int(
sys.argv[2]) if int(sys.argv[2]) > 0 else config.laplace
config.eu_scale = float(
sys.argv[3]) if float(sys.argv[3]) > 0 else config.eu_scale
config.ds_ratio = float(sys.argv[4]) if float(sys.argv[4]) > 0 else 0
config.market_alpha = float(sys.argv[5])
config.market_lambda = float(sys.argv[6])
print "camp_id\tlaplace\tscale\tds_ratio\tmkt_alpha\tmkt_lambda"
print `config.campaign_id` + "\t" \
+ `config.laplace` + "\t" \
+ `config.eu_scale` + "\t" \
+ `config.ds_ratio` + "\t" \
+ `config.market_alpha` + "\t" \
+ `config.market_lambda`
# judge if log and weight existed !!!
log_file = `config.campaign_id` + "_prectr_joint" \
+ "_" + `config.laplace` \
+ "_" + `config.eu_scale` \
+ "_" + `config.ds_ratio` \
+ "_" + `config.market_alpha` \
+ "_" + `config.market_lambda`\
+ ".csv"
if tool.judge_file_exists("../output/", log_file):
print "Existed " + log_file
exit(0)
train_path = config.data_folder + ` config.campaign_id ` + "/train.yzx.txt"
test_path = config.data_folder + ` config.campaign_id ` + "/test.yzx.txt"
train_data = Dataset(train_path, config.campaign_id)
train_data.shuffle() # make train data shuffled
test_data = Dataset(test_path, config.campaign_id)
if config.INTVL:
IntervalLandscape(train_data, train_data.get_camp_id(), config.laplace,
3)
IntervalLandscape(test_data, test_data.get_camp_id(), config.laplace,
3)
else:
BidLandscape(train_data, train_data.get_camp_id(), config.laplace)
BidLandscape(test_data, test_data.get_camp_id(), config.laplace)
print "Load done."
# downsampling
if config.ds_ratio > 0:
train_data_ds = train_data.down_sampling(config.ds_ratio)
else:
train_data_ds = train_data
print "Down sampled."
print train_data_ds.get_statistics()
eu_model = EuModel(train_data_ds, test_data)
print "campaign v = " + ` eu_model.camp_v `
# pre-train
print "Begin ctr pre-training ..."
pre_train_log = []
for i in range(0, config.eu_train_round):
eu_model.train()
eu_model.test()
pre_train_log.append(copy.deepcopy(eu_model.test_log[-1]))
print "Round " + ` i + 1 ` + "\t" + ` tool.get_last_log(
eu_model.test_log)['performance'] `
if tool.judge_stop(eu_model.test_log):
break
print "Ctr pre-training done."
pre_train_round = len(eu_model.test_log)
tri_model = TriModel(train_data_ds, test_data, eu_model, None, 'eu')
eu_model.weight = copy.deepcopy(
tri_model.get_best_log(pre_train_log)['weight'])
mkt_model = LinMarket(train_data, test_data)
mkt_model.set_camp_v(eu_model.camp_v) # !!! nds camp value
mkt_model.set_ctr_model(eu_model)
mkt_model.set_bid_strategy(eu_model.get_bid_strategy())
print "campaign v = " + ` eu_model.camp_v `
train_data_ds.set_landscape(mkt_model)
train_data.set_landscape(mkt_model)
# train
print "Begin joint training ..."
config.PARAM_MARKET = True
recent_eu_weight = []
all_anlp = []
for i in range(0, config.eu_train_round):
mkt_model.joint_train()
test_anlp = mkt_model.calc_total_anlp(test_data)
print "Round " + ` i + 1 ` + " test_anlp: " + ` test_anlp `
all_anlp.append(test_anlp)
eu_model.train()
eu_model.test()
print "%d %d" % (len(all_anlp), len(eu_model.test_log))
if i + 1 > 3:
del recent_eu_weight[0]
recent_eu_weight.append(copy.deepcopy(eu_model.weight))
print "Round " + ` i + 1 ` + "\t" + ` tool.get_last_log(
eu_model.test_log)['performance'] `
if tool.judge_stop(eu_model.test_log):
break
if (len(recent_eu_weight) == 3):
eu_model.weight = recent_eu_weight[0]
print "Joint train done."
fo = open("../output/" + log_file, 'w')
print "Begin log ..."
header = "camp_id\tmodel\tdataset\trevenue\tctr\tcpc\tauc\trmse\tcpm\tbids\timps\tclks\tlaplace\tinterval\teu_scale\tnds_ratio"
best_test_log = eu_model.get_best_test_log()
best_test_line = `config.campaign_id` + "\t" + "PRECTR_JOINT\ttest\t" \
+ tool.gen_performance_line(best_test_log) + "\t" \
+ `config.laplace` + "\t" + "None" + "\t" + `config.eu_scale` + "\t" + `config.ds_ratio` + "\t" \
+ `config.market_alpha` + "\t" + `config.market_lambda`
fo.write(header + "\n")
fo.write(best_test_line + "\n")
fo.write("\n")
fo.write("Ctr Pre-train Log:")
fo.write("Round\tTest\tctr\tcpc\tauc\trmse\tcpm\tclks\timps\tbids\n")
for i in range(0, pre_train_round):
test_log = eu_model.test_log[i]
line = `i+1` + "\t" + `test_log['performance']['revenue']` \
+ "\t" + `test_log['performance']['ctr']` \
+ "\t" + `test_log['performance']['cpc']` \
+ "\t" + `test_log['performance']['auc']` \
+ "\t" + `test_log['performance']['rmse']` \
+ "\t" + `test_log['performance']['cpm']` \
+ "\t" + `test_log['performance']['clks']` \
+ "\t" + `test_log['performance']['imps']` \
+ "\t" + `test_log['performance']['bids']`
fo.write(line + "\n")
print "Pre-train Log done."
fo.write("Train Log:")
fo.write("Round\tTest\tctr\tcpc\tauc\trmse\tcpm\tclks\timps\tbids\tanlp\n")
for i in range(0, len(all_anlp)):
test_log = eu_model.test_log[pre_train_round + i]
line = `i+1` + "\t" + `test_log['performance']['revenue']` \
+ "\t" + `test_log['performance']['ctr']` \
+ "\t" + `test_log['performance']['cpc']` \
+ "\t" + `test_log['performance']['auc']` \
+ "\t" + `test_log['performance']['rmse']` \
+ "\t" + `test_log['performance']['cpm']` \
+ "\t" + `test_log['performance']['clks']` \
+ "\t" + `test_log['performance']['imps']` \
+ "\t" + `test_log['performance']['bids']` \
+ "\t" + `all_anlp[i]`
fo.write(line + "\n")
fo.close()
print "Train Log done."
weight_path = `config.campaign_id` + "_" + "prectr_joint_best_weight" \
+ "_" + `config.laplace` \
+ "_" + `config.eu_scale` \
+ "_" + `config.ds_ratio` \
+ "_" + `config.market_alpha` \
+ "_" + `config.market_lambda` \
+ ".weight"
eu_model.output_weight(best_test_log['weight'], "../output/" + weight_path)
def main():
if len(sys.argv) < 3:
print "Usage python test_sqlr.py campaign_id learn_rate (budget_prop)"
exit(-1)
data_folder = "../../make-ipinyou-data/"
config.campaign_id = int(sys.argv[1])
config.lr_alpha = float(sys.argv[2])
if len(sys.argv) == 4:
config.budget_prop = int(sys.argv[3])
train_path = data_folder + ` config.campaign_id ` + "/train.yzx.txt"
test_path = data_folder + ` config.campaign_id ` + "/test.yzx.txt"
print "Camp_id\tlearn_alpha"
print ` config.campaign_id ` + "\t" + ` config.lr_alpha `
train_data = Dataset(train_path, config.campaign_id)
train_data.shuffle()
test_data = Dataset(test_path, config.campaign_id)
print "Load done."
lr_model = SqlrModel(train_data, test_data)
print "campaign v = " + ` lr_model.camp_v `
print "budget = " + ` lr_model.budget `
log_file = ` config.campaign_id ` + "_sqlr_" + ` config.lr_alpha ` + "_" + ` config.budget_prop ` + ".csv"
fo = open("../output/" + log_file, 'w')
print "Begin training ..."
for i in range(0, config.lr_train_round):
lr_model.train()
lr_model.test()
print "Round " + ` i + 1 ` + "\t" + ` tool.get_last_log(
lr_model.test_log)['performance'] `
if tool.judge_stop(lr_model.test_log):
break
print "Train done."
print "Begin log ..."
header = "camp_id\tmodel\tdataset\trevenue\tctr\tcpc\tauc\trmse\tcpm\tbids\timps\tclks\tlaplace\tinterval\tlearn_rate\tnds_ratio"
best_test_log = lr_model.get_best_test_log()
best_test_line = `config.campaign_id` + "\t" + "SQ\ttest\t" \
+ tool.gen_performance_line(best_test_log) + "\t" \
+ `config.laplace` + "\t" + "None" + "\t" \
+ `config.lr_alpha` + "\t" + "None"
fo.write(header + "\n")
fo.write(best_test_line + "\n")
fo.write("\n")
fo.write("Round\tTest\tctr\tcpc\tauc\trmse\tcpm\tclks\timps\tbids\n")
for i in range(0, len(lr_model.test_log)):
test_log = lr_model.test_log[i]
line = `i+1` + "\t" + `test_log['performance']['revenue']` \
+ "\t" + `test_log['performance']['ctr']` \
+ "\t" + `test_log['performance']['cpc']` \
+ "\t" + `test_log['performance']['auc']` \
+ "\t" + `test_log['performance']['rmse']` \
+ "\t" + `test_log['performance']['cpm']` \
+ "\t" + `test_log['performance']['clks']` \
+ "\t" + `test_log['performance']['imps']` \
+ "\t" + `test_log['performance']['bids']`
fo.write(line + "\n")
fo.close()
print "Log done."
# weight_path = `config.campaign_id` + "_sqlr_best_weight_" + `config.lr_alpha` + "_" + `config.budget_prop` + ".txt"
# lr_model.output_weight(best_test_log['weight'], "../output/" + weight_path)
weight_path = `config.campaign_id` + "_" + "sqlr_best_weight" \
+ "_" + `config.laplace` \
+ "_" + `config.eu_scale` \
+ "_" + `config.ds_ratio` \
+ ".weight"
lr_model.output_weight(best_test_log['weight'], "../output/" + weight_path)
def main():
if len(sys.argv) < 5:
print "Usage: python test_eu.py campaign_id laplace eu_scale ds_ratio"
exit(-1)
config.campaign_id = int(sys.argv[1]) if int(
sys.argv[1]) in config.campaign_list else config.campaign_id
config.laplace = int(
sys.argv[2]) if int(sys.argv[2]) > 0 else config.laplace
config.eu_scale = float(
sys.argv[3]) if float(sys.argv[3]) > 0 else config.eu_scale
config.ds_ratio = float(sys.argv[4]) if float(sys.argv[4]) > 0 else 0
print "camp_id\tlaplace\tscale\tds_ratio"
print ` config.campaign_id ` + "\t" + ` config.laplace ` + "\t" + ` config.eu_scale ` + "\t" + ` config.ds_ratio `
train_path = config.data_folder + ` config.campaign_id ` + "/train.yzx.txt"
test_path = config.data_folder + ` config.campaign_id ` + "/test.yzx.txt"
train_data = Dataset(train_path, config.campaign_id)
train_data.shuffle() # make train data shuffled
test_data = Dataset(test_path, config.campaign_id)
if config.INTVL:
IntervalLandscape(train_data, train_data.get_camp_id(), config.laplace,
3)
IntervalLandscape(test_data, test_data.get_camp_id(), config.laplace,
3)
else:
BidLandscape(train_data, train_data.get_camp_id(), config.laplace)
BidLandscape(test_data, test_data.get_camp_id(), config.laplace)
print "Load done."
# downsampling
if config.ds_ratio > 0:
train_data_ds = train_data.down_sampling(config.ds_ratio)
else:
train_data_ds = train_data
print "Down sampled."
print train_data_ds.get_statistics()
eu_model = EuModel(train_data_ds, test_data)
print "campaign v = " + ` eu_model.camp_v `
# train
print "Begin training ..."
for i in range(0, config.eu_train_round):
eu_model.train()
eu_model.test()
print "Round " + ` i + 1 ` + "\t" + ` tool.get_last_log(
eu_model.test_log)['performance'] `
if tool.judge_stop(eu_model.test_log):
break
print "Train done."
# eu_2997_3_0.1_0.05.csv
log_file = `config.campaign_id` + "_eu" \
+ "_" + `config.laplace` \
+ "_" + `config.eu_scale` \
+ "_" + `config.ds_ratio` \
+ ".csv"
fo = open("../output/" + log_file, 'w')
print "Begin log ..."
header = "camp_id\tmodel\tdataset\trevenue\tctr\tcpc\tauc\trmse\tcpm\tbids\timps\tclks\tlaplace\tinterval\teu_scale\tnds_ratio"
best_test_log = eu_model.get_best_test_log()
best_test_line = `config.campaign_id` + "\t" + "EU\ttest\t" \
+ tool.gen_performance_line(best_test_log) + "\t" \
+ `config.laplace` + "\t" + "None" + "\t" + `config.eu_scale` + "\t" + `config.ds_ratio`
fo.write(header + "\n")
fo.write(best_test_line + "\n")
fo.write("\n")
fo.write("Round\tTest\tctr\tcpc\tauc\trmse\tcpm\tclks\timps\tbids\n")
for i in range(0, len(eu_model.test_log)):
test_log = eu_model.test_log[i]
line = `i+1` + "\t" + `test_log['performance']['revenue']` \
+ "\t" + `test_log['performance']['ctr']` \
+ "\t" + `test_log['performance']['cpc']` \
+ "\t" + `test_log['performance']['auc']` \
+ "\t" + `test_log['performance']['rmse']` \
+ "\t" + `test_log['performance']['cpm']` \
+ "\t" + `test_log['performance']['clks']` \
+ "\t" + `test_log['performance']['imps']` \
+ "\t" + `test_log['performance']['bids']`
fo.write(line + "\n")
fo.close()
print "Log done."
weight_path = `config.campaign_id` + "_" + "eu_best_weight" \
+ "_" + `config.laplace` \
+ "_" + `config.eu_scale` \
+ "_" + `config.ds_ratio` \
+ ".weight"
eu_model.output_weight(best_test_log['weight'], "../output/" + weight_path)
def main():
if len(sys.argv) < 7:
print "Usage: python test_tri.py campaign_id model_name laplace x_scale ds_ratio budget_prop train_option mkt_alpha mkt_lambda"
exit(-1)
config.campaign_id = int(sys.argv[1])
model_name = sys.argv[2]
if not model_name in config.model_list:
print "Wrong model name."
exit(-1)
config.model_name = model_name
config.laplace = int(sys.argv[3])
config.eu_scale = float(sys.argv[4])
config.ds_ratio = float(sys.argv[5]) if float(sys.argv[5]) > 0 else 0
config.budget_prop = int(sys.argv[6])
train_option = int(sys.argv[7])
print "cam_id\tmodel\tlaplace\tscale\tds_ratio\tbudget_prop\ttrain_option\tmkt_alpha\tmkt_lambda"
print `config.campaign_id` + "\t" + `model_name` \
+ "\t" + `config.laplace` + "\t" + `config.eu_scale` \
+ "\t" + `config.ds_ratio` + "\t" + `config.budget_prop` \
+ "\t" + `train_option` + "\t" + `config.market_alpha` + "\t" + `config.market_lambda`
train_path = config.data_folder + ` config.campaign_id ` + "/train.yzx.txt"
test_path = config.data_folder + ` config.campaign_id ` + "/test.yzx.txt"
train_data = Dataset(train_path, config.campaign_id)
train_data.shuffle() # make train data shuffled
test_data = Dataset(test_path, config.campaign_id)
# downsampling
train_data_ds = train_data.down_sampling(
config.ds_ratio) if config.ds_ratio > 0 else train_data
print train_data_ds.get_statistics()
print "Down sampled."
# eu_model mkt_model tri_model
eu_model = EuModel(train_data_ds, test_data)
mkt_model = LinMarket(train_data, test_data)
tri_model = TriModel(train_data_ds, test_data, eu_model, mkt_model,
model_name)
eu_model.bid_strategy = tri_model.bid_strategy
mkt_model.set_camp_v(eu_model.camp_v) # !!! nds camp value
mkt_model.set_ctr_model(eu_model)
mkt_model.set_bid_strategy(eu_model.get_bid_strategy())
print "campaign v = " + ` eu_model.camp_v `
# bid landscape initialization
# pre-train
# 1. CTR pre-train
if train_option in {1, 3}:
# temporarily init counting-based landscape
BidLandscape(train_data, train_data.get_camp_id(), config.laplace)
train_data_ds.init_landscape(train_data.get_landscape())
eu_model.train()
eu_model.test()
#print "Round 0" + "\t" + `tool.get_last_log(eu_model.test_log)['performance']`
# add back parameterized landscape
# 2. MKT pre-train
if train_option > 1:
mkt_model.train()
train_anlp = mkt_model.calc_total_anlp(train_data)
test_anlp = mkt_model.calc_total_anlp(test_data)
#print "Market Model pre-train ANLP train: %.3f, test: %.3f." % (train_anlp, test_anlp)
train_data_ds.set_landscape(mkt_model)
train_data.set_landscape(mkt_model)
# train
print "Begin training ..."
config.PARAM_MARKET = True
for i in range(0, config.em_round):
#print "Tri Round starts:"
recent_mkt_weight = []
recent_ctr_weight = []
for j in range(0, config.eu_train_round):
mkt_model.joint_train()
test_anlp = mkt_model.calc_total_anlp(test_data)
print "Tri Round " + ` i + 1 ` + " Round " + ` j + 1 ` + " test_anlp: " + ` test_anlp `
eu_model.train()
eu_model.test()
print "Tri Round " + ` i + 1 ` + " Round " + ` j + 1 ` + "\t" + ` tool.get_last_log(
eu_model.test_log)['performance'] `
if (j + 1 > 3):
del recent_mkt_weight[0]
del recent_ctr_weight[0]
recent_mkt_weight.append(copy.deepcopy(mkt_model.weight))
recent_ctr_weight.append(copy.deepcopy(eu_model.weight))
if tool.judge_stop(eu_model.test_log):
break
mkt_model.weight = recent_mkt_weight[0]
eu_model.weight = recent_ctr_weight[0]
tri_model.train()
print "Tri Round " + ` i + 1 ` + "\t" + ` tool.get_last_log(
tri_model.em_log)['performance'] `
if tool.judge_stop(tri_model.em_log):
break
print "Train done."
# em_rr_2997_3_0.1_0.csv
log_file = "tri_" + model_name \
+ "_" + `config.campaign_id` \
+ "_" + `config.budget_prop` \
+ "_" + `config.laplace` \
+ "_" + `config.eu_scale` \
+ "_" + `config.ds_ratio` \
+ ".csv"
fo = open("../../output/Tri" + log_file, 'w')
print "Begin log ..."
header = "camp_id\tmodel\tdataset\trevenue\troi\tctr\tcpc\tauc\trmse\tcpm\tbids\timps\tclks\tlaplace\tinterval\tscale\tds_ratio\tbudget_prop\tem_round\tmu"
best_em_log = tri_model.get_best_log(tri_model.em_log)
best_em_line = `config.campaign_id` + "\t" + "em"+model_name + "\ttest\t" \
+ tool.gen_performance_line(best_em_log) + "\t" \
+ `config.laplace` + "\t" + "None" + "\t" + `config.eu_scale` + "\t" \
+ (`config.ds_ratio` if config.ds_ratio>0 else "None") + "\t" \
+ `config.budget_prop` +"\t" \
+ `len(tri_model.em_log)` + "\t" + `best_em_log['mu']`
fo.write(header + "\n")
fo.write(best_em_line + "\n")
fo.write("Test with Budget Constraints\n")
# # reset mu
# em_model.mu = best_em_log['mu']
# em_model.bid_strategy.set_mu(em_model.mu)
# # replay
# fo.write("prop\trevenue\troi\tctr\tcpc\tauc\trmse\tcpm\timps\tclks\n")
# for prop in config.budget_props:
# performance = em_model.replay(best_em_log['weight'], em_model.test_data, prop)
# fo.write(`prop`); fo.write("\t")
# fo.write(`performance['revenue']`); fo.write("\t")
# fo.write(`performance['roi']`); fo.write("\t")
# fo.write(`performance['ctr']`); fo.write("\t")
# fo.write(`performance['cpc']`); fo.write("\t")
# fo.write(`performance['auc']`); fo.write("\t")
# fo.write(`performance['rmse']`); fo.write("\t")
# fo.write(`performance['cpm']`); fo.write("\t")
# fo.write(`performance['imps']`); fo.write("\t")
# fo.write(`performance['clks']`); fo.write("\t")
# fo.write("\n")
fo.write("\n")
fo.write("Round\trevenue\troi\tcpc\tctr\tauc\trmse\timps\ttruncate\tmu\n")
for i in range(0, len(tri_model.em_log)):
tri_log = tri_model.em_log[i]
line = `i+1` + "\t" + `tri_log['performance']['revenue']` + "\t" \
+ `tri_log['performance']['roi']` + "\t" \
+ `tri_log['performance']['cpc']` + "\t" \
+ `tri_log['performance']['ctr']` + "\t" \
+ `tri_log['performance']['auc']` + "\t" \
+ `tri_log['performance']['rmse']` + "\t" \
+ `tri_log['performance']['imps']` + "\t" \
+ `tri_log['weight'][0]` + "\t" \
+ `tri_log['mu']`
fo.write(line + "\n")
fo.write("\n")
for i in range(0, len(tri_model.test_log)):
test_log = tri_model.test_log[i]
line = `i+1` + "\t" + `test_log['performance']['revenue']` + "\t" \
+ `test_log['performance']['roi']` + "\t" \
+ `test_log['performance']['cpc']` + "\t" \
+ `test_log['performance']['ctr']` + "\t" \
+ `test_log['performance']['auc']` + "\t" \
+ `test_log['performance']['rmse']` + "\t" \
+ `test_log['performance']['imps']` + "\t" \
+ `test_log['weight'][0]`
if 'm' in test_log:
line = line + "\tm"
fo.write(line + "\n")
fo.close()
print "Log done."
def main():
if len(sys.argv) < 5:
print "Usage: python test_stat_bin.py campaign_id laplace eu_scale ds_ratio train_option (DEBUG)"
exit(-1)
weight_path_dict = {'1458': 'campaign_1458_alpha_1e-9_beta_1e-4.txt',
'2259': 'campaign_2259_alpha_1e-9_beta_5e-3.txt',
'2261': 'campaign_2261_alpha_5e-9_beta_1e-4.txt',
'2821': 'campaign_2821_alpha_1e-9_beta_5e-7.txt',
'2997': 'campaign_2997_alpha_5e-9_beta_1e-7.txt',
'3358': 'campaign_3358_alpha_1e-9_beta_1e-8.txt',
'3386': 'campaign_3386_alpha_5e-10_beta_5e-5.txt',
'3427': 'campaign_3427_alpha_5e-10_beta_1e-2.txt',
'3476': 'campaign_3476_alpha_5e-10_beta_5e-3.txt'}
config.campaign_id = int(sys.argv[1]) if int(sys.argv[1]) in config.campaign_list else config.campaign_id
config.laplace = int(sys.argv[2]) if int(sys.argv[2])>0 else config.laplace
config.eu_scale = float(sys.argv[3]) if float(sys.argv[3])>0 else config.eu_scale
config.ds_ratio = float(sys.argv[4]) if float(sys.argv[4])>0 else 0
if len(sys.argv) > 8:
config.DEBUG = bool(sys.argv[8])
if len(sys.argv) > 5:
options = {0,1,2,3}
option_dict = {
0: 'directly joint train',
1: 'CTR pre-train',
2: 'MKT pre-train',
3: 'all pre-train' }
train_option = int(sys.argv[5])
if not train_option in options:
print "ERROR: Train Option Error!"
exit(-1)
config.mkt_weight_path = '../lin_weight/' + weight_path_dict[`config.campaign_id`]
print "camp_id\tlaplace\tscale\tds_ratio\ttrain_option\tmkt_alpha\tmkt_lambda"
print `config.campaign_id` + "\t" \
+ `config.laplace` + "\t" \
+ `config.eu_scale` + "\t" \
+ `config.ds_ratio` + "\t" \
+ option_dict[train_option] + "\t" \
+ `config.mkt_weight_path`
train_path = config.data_folder + `config.campaign_id` + "/train.yzx.txt"
test_path = config.data_folder + `config.campaign_id` + "/test.yzx.txt"
train_data = Dataset(train_path, config.campaign_id)
train_data.shuffle() # make train data shuffled
test_data = Dataset(test_path, config.campaign_id)
print "Dataset load done."
# downsampling
if config.ds_ratio>0:
train_data_ds = train_data.down_sampling(config.ds_ratio)
else:
train_data_ds = train_data
print "Down sampled."
print train_data_ds.get_statistics()
eu_model = EuModel(train_data_ds, test_data)
mkt_model = LinMarket(train_data, test_data)
if mkt_model.load_weight(config.mkt_weight_path):
test_anlp = mkt_model.calc_total_anlp(test_data)
print "Market model weight loaded. The overall ANLP = " + `test_anlp`
mkt_model.set_camp_v(eu_model.camp_v) # !!! nds camp value
mkt_model.set_ctr_model(eu_model)
mkt_model.set_bid_strategy(eu_model.get_bid_strategy())
print "campaign v = " + `eu_model.camp_v`
# bid landscape initialization
# pre-train
# 1. CTR pre-train
if train_option in {1, 3}:
# temporarily init counting-based landscape
BidLandscape(train_data, train_data.get_camp_id(), config.laplace)
train_data_ds.init_landscape(train_data.get_landscape())
eu_model.train()
eu_model.test()
print "Round 0" + "\t" + `tool.get_last_log(eu_model.test_log)['performance']`
# add back parameterized landscape
# 2. MKT pre-train
if train_option > 1:
mkt_model.train()
train_anlp = mkt_model.calc_total_anlp(train_data)
test_anlp = mkt_model.calc_total_anlp(test_data)
print "Market Model pre-train ANLP train: %.3f, test: %.3f." % (train_anlp, test_anlp)
train_data_ds.set_landscape(mkt_model)
train_data.set_landscape(mkt_model)
# # set up bid landscape model
# mkt_model = LinMarket(train_data_ds, test_data)
# if mkt_model.load_weight(weight_path): print "Market parameter loaded."
# train_data_ds.init_landscape(mkt_model)
# print mkt_model.weight[0]
# print "Parameterized landscape initialized."
# raw_input("pause ...")
# train
print "Begin training ..."
config.PARAM_MARKET = True
for i in range(0, config.eu_train_round):
# mkt_model.joint_train()
print "Round " + `i+1` + " test_anlp: " + `test_anlp`
eu_model.train()
eu_model.test()
print "Round " + `i+1` + "\t" + `tool.get_last_log(eu_model.test_log)['performance']`
if tool.judge_stop(eu_model.test_log):
break;
print "Train done."
# eu_2997_3_0.1_0.05.csv
log_file = `config.campaign_id` + "_eu" \
+ "_" + `config.laplace` \
+ "_" + `config.eu_scale` \
+ "_" + `config.ds_ratio` \
+ ".stat.csv"
fo = open("../output/"+log_file, 'w')
print "Begin log ..."
header = "camp_id\tmodel\tdataset\trevenue\tctr\tcpc\tauc\trmse\tcpm\tbids\timps\tclks\tlaplace\tinterval\teu_scale\tnds_ratio"
best_test_log = eu_model.get_best_test_log()
best_test_line = `config.campaign_id` + "\t" + "EU-stat\ttest\t" \
+ tool.gen_performance_line(best_test_log) + "\t" \
+ `config.laplace` + "\t" + "None" + "\t" + `config.eu_scale` + "\t" + `config.ds_ratio`
fo.write(header+"\n")
fo.write(best_test_line+"\n")
fo.write("\n")
fo.write("Round\tTest\tctr\tcpc\tauc\trmse\tcpm\tclks\timps\tbids\n")
for i in range(0, len(eu_model.test_log)):
test_log = eu_model.test_log[i]
line = `i+1` + "\t" + `test_log['performance']['revenue']` \
+ "\t" + `test_log['performance']['ctr']` \
+ "\t" + `test_log['performance']['cpc']` \
+ "\t" + `test_log['performance']['auc']` \
+ "\t" + `test_log['performance']['rmse']` \
+ "\t" + `test_log['performance']['cpm']` \
+ "\t" + `test_log['performance']['clks']` \
+ "\t" + `test_log['performance']['imps']` \
+ "\t" + `test_log['performance']['bids']`
fo.write(line + "\n")
fo.close()
print "Log done."
weight_path = `config.campaign_id` + "_" + "eu_best_weight" \
+ "_" + `config.laplace` \
+ "_" + `config.eu_scale` \
+ "_" + `config.ds_ratio` \
+ ".stat_ctr.weight"
eu_model.output_weight(best_test_log['weight'], "../output/" + weight_path)
def main():
if len(sys.argv) < 7:
print "Usage: python test_em.py camp_id model_name laplace x_scale ds_ratio budget_prop"
exit(-1)
config.campaign_id = int(sys.argv[1])
model_name = sys.argv[2]
if not model_name in config.model_list:
print "Wrong model name."
exit(-1)
config.model_name = model_name
config.laplace = int(sys.argv[3])
config.em_scale = float(sys.argv[4])
config.ds_ratio = float(sys.argv[5]) if float(sys.argv[5]) > 0 else 0
config.budget_prop = int(sys.argv[6])
print "camp_id\tmodel\tlaplace\tscale\tds_ratio\tbudget_prop"
print `config.campaign_id` + "\t" + `model_name` \
+ "\t" + `config.laplace` + "\t" + `config.em_scale` \
+ "\t" + `config.ds_ratio` + "\t" + `config.budget_prop`
train_path = config.data_folder + ` config.campaign_id ` + "/train.yzx.txt"
test_path = config.data_folder + ` config.campaign_id ` + "/test.yzx.txt"
train_data = Dataset(train_path, config.campaign_id)
train_data.shuffle() # make train data shuffled
test_data = Dataset(test_path, config.campaign_id)
# no interval setting
BidLandscape(train_data, train_data.get_camp_id(), config.laplace)
BidLandscape(test_data, test_data.get_camp_id(), config.laplace)
print "Load done."
# downsampling
train_data_ds = train_data.down_sampling(
config.ds_ratio) if config.ds_ratio > 0 else train_data
print train_data_ds.get_statistics()
print "Down sampled."
em_model = EmModel(train_data_ds, test_data, model_name)
print "campaign v = " + ` em_model.camp_v `
# train
print "Begin training ..."
for i in range(0, config.em_round):
em_model.train()
print "EM Round " + ` i + 1 ` + "\t" + ` tool.get_last_log(
em_model.em_log)['performance'] `
if tool.judge_stop(em_model.em_log):
break
print "Train done."
# em_rr_2997_3_0.1_0.csv
log_file = "em_" + model_name \
+ "_" + `config.campaign_id` \
+ "_" + `config.budget_prop` \
+ "_" + `config.laplace` \
+ "_" + `config.em_scale` \
+ "_" + `config.ds_ratio` \
+ ".csv"
fo = open("../output/" + log_file, 'w')
print "Begin log ..."
header = "camp_id\tmodel\tdataset\trevenue\troi\tctr\tcpc\tauc\trmse\tcpm\tbids\timps\tclks\tlaplace\tinterval\tscale\tds_ratio\tbudget_prop\tem_round\tmu"
best_em_log = em_model.get_best_log(em_model.em_log)
best_em_line = `config.campaign_id` + "\t" + "em"+model_name + "\ttest\t" \
+ tool.gen_performance_line(best_em_log) + "\t" \
+ `config.laplace` + "\t" + "None" + "\t" + `config.em_scale` + "\t" \
+ (`config.ds_ratio` if config.ds_ratio>0 else "None") + "\t" \
+ `config.budget_prop` +"\t" \
+ `len(em_model.em_log)` + "\t" + `best_em_log['mu']`
fo.write(header + "\n")
fo.write(best_em_line + "\n")
fo.write("Test with Budget Constraints\n")
# # reset mu
# em_model.mu = best_em_log['mu']
# em_model.bid_strategy.set_mu(em_model.mu)
# # replay
# fo.write("prop\trevenue\troi\tctr\tcpc\tauc\trmse\tcpm\timps\tclks\n")
# for prop in config.budget_props:
# performance = em_model.replay(best_em_log['weight'], em_model.test_data, prop)
# fo.write(`prop`); fo.write("\t")
# fo.write(`performance['revenue']`); fo.write("\t")
# fo.write(`performance['roi']`); fo.write("\t")
# fo.write(`performance['ctr']`); fo.write("\t")
# fo.write(`performance['cpc']`); fo.write("\t")
# fo.write(`performance['auc']`); fo.write("\t")
# fo.write(`performance['rmse']`); fo.write("\t")
# fo.write(`performance['cpm']`); fo.write("\t")
# fo.write(`performance['imps']`); fo.write("\t")
# fo.write(`performance['clks']`); fo.write("\t")
# fo.write("\n")
fo.write("\n")
fo.write("Round\trevenue\troi\tcpc\tctr\tauc\trmse\timps\ttruncate\tmu\n")
for i in range(0, len(em_model.em_log)):
em_log = em_model.em_log[i]
line = `i+1` + "\t" + `em_log['performance']['revenue']` + "\t" \
+ `em_log['performance']['roi']` + "\t" \
+ `em_log['performance']['cpc']` + "\t" \
+ `em_log['performance']['ctr']` + "\t" \
+ `em_log['performance']['auc']` + "\t" \
+ `em_log['performance']['rmse']` + "\t" \
+ `em_log['performance']['imps']` + "\t" \
+ `em_log['weight'][0]` + "\t" \
+ `em_log['mu']`
fo.write(line + "\n")
fo.write("\n")
for i in range(0, len(em_model.test_log)):
test_log = em_model.test_log[i]
line = `i+1` + "\t" + `test_log['performance']['revenue']` + "\t" \
+ `test_log['performance']['roi']` + "\t" \
+ `test_log['performance']['cpc']` + "\t" \
+ `test_log['performance']['ctr']` + "\t" \
+ `test_log['performance']['auc']` + "\t" \
+ `test_log['performance']['rmse']` + "\t" \
+ `test_log['performance']['imps']` + "\t" \
+ `test_log['weight'][0]`
if 'm' in test_log:
line = line + "\tm"
fo.write(line + "\n")
fo.close()
print "Log done."
