def history_repeat_filter(bid_history_files, the_ctr_model, bid_model, candidate_paras,outfilename):
'''
这里仅有一个参数
历史重演，对一批历史数据进行模拟投放
paras:
bid_history_files:join文件列表
the_ctr_model:ctr模型
bid_model:出价模型
candidate_paras:候选参数
return:
paras_perf[camp_grp][para] =
{'impression':,'avg_pctr':,'click':,'cost':,'ctr':,'ecpc':,'cpm':}
'''
candidate_paras = {camp_grp:candidate_paras[camp_grp] for camp_grp in candidate_paras.keys() if len(candidate_paras[camp_grp]) == 1 }
if len(candidate_paras) == 0:
print 'there is no candidate parameter'
return
click_num = 0
imp_num = 0
cost = 0
click_num_old = 0
imp_num_old = 0
cost_old = 0
outfile=open(outfilename,'w')
for bid_history_file in bid_history_files:
for line in open(bid_history_file):
#line = line.rstrip('\n')
field_dict = join.get_field_dict(line)
if field_dict == None:
continue
win_price = float(field_dict['win_price'])
camp_grp = (field_dict['campaign_id'], field_dict['adgroup_id'])
if (not candidate_paras.has_key(camp_grp)) or (not bid_model.has_key(camp_grp)) or win_price == None or win_price <= 0:
continue
pctr = the_ctr_model.predict_ctr(field_dict['feature_values'])
candidate_bid_prices = bid_model[camp_grp].get_bids_auc(pctr, candidate_paras[camp_grp])
if candidate_bid_prices[0] >= win_price:
outfile.write(line)
imp_num += 1
click_num += (1 if field_dict['click_flag'] == True else 0)
cost += win_price
imp_num_old += 1
click_num_old += (1 if field_dict['click_flag'] == True else 0)
cost_old += win_price
cost = float(cost)/1000
cost_old = float(cost_old)/1000
print 'file%s' % bid_history_files
print 'old imp_num %d,click_num %d,cost %.4f' % (imp_num_old,click_num_old,cost_old)
print 'old cpm %.4f,ctr %.8f,cpc %.4f' % (1000*cost_old/imp_num_old,float(click_num_old)/imp_num_old,cost_old/click_num_old)
print 'imp_num %d,click_num %d,cost %.4f' % (imp_num,click_num,cost)
print 'cpm %.4f,ctr %.8f,cpc %.4f' % (1000*cost/imp_num,float(click_num)/imp_num,cost/click_num)
def history_repeat_conditional(bid_history_files, the_ctr_model, bid_model,
candidate_paras, condition_type, stat_result):
'''
历史重演，对一批历史数据进行模拟投放
paras:
bid_history_files:join文件名列表,list类型
the_ctr_model:ctr模型
bid_model:出价模型
candidate_paras:候选参数
return:
paras_perf[camp_grp][para] =
{'impression':,'avg_pctr':,'click':,'cost':,'ctr':,'ecpc':,'cpm':}
'''
candidate_paras = {
camp_grp: candidate_paras[camp_grp]
for camp_grp in candidate_paras.keys()
if len(candidate_paras[camp_grp]) != 0
}
bpo_logger.info(
'**************history_repeat function start**************')
bpo_logger.info('files:%s' % ','.join(bid_history_files))
bpo_logger.info('************** bid_model: %s**************' %
(bid_model.keys()))
bpo_logger.info('************** candidate_paras: %s**************' %
(candidate_paras))
bpo_logger.info('************** condition_type: %s**************' %
(condition_type))
stop_flag_idx = {}
result = {} #预制所有的键
for camp_grp in bid_model.keys():
#bid_model的camp_grp 为有效的adgroup，如果该条req的adgroup不在bid_model中，则continue
if (not candidate_paras.has_key(camp_grp)) or (
not bid_model.has_key(camp_grp)):
continue
if not condition_type.has_key(camp_grp):
continue
tmp_num = len(candidate_paras[camp_grp])
stop_flag_idx[camp_grp] = tmp_num
result[camp_grp] = [None] * tmp_num
for idx in range(0, tmp_num):
result[camp_grp][idx] = {
'impression': 0,
'avg_pctr': 0,
'click': 0,
'cost': 0
}
req_parser = join.Parser()
for bid_history_file in bid_history_files:
for line in open(bid_history_file):
req_parser.feed(line)
field_dict = req_parser.get_all()
if field_dict == None:
continue
win_price = float(field_dict['win_price'])
camp_grp = (field_dict['campaign_id'], field_dict['adgroup_id'])
if win_price == None or win_price <= 0:
continue
if not result.has_key(camp_grp):
continue
pctr = the_ctr_model.predict_ctr(field_dict['feature_values'])
candidate_bid_prices = bid_model[camp_grp].get_bids_auc(
ctr=pctr, variable_paras=candidate_paras[camp_grp])
first_ge_idx = binary_search(candidate_bid_prices, win_price)
#非累积方式
if first_ge_idx < stop_flag_idx[camp_grp]:
for tmp_idx in range(first_ge_idx, stop_flag_idx[camp_grp]):
result[camp_grp][tmp_idx]['impression'] += 1
result[camp_grp][tmp_idx]['avg_pctr'] += pctr
result[camp_grp][tmp_idx]['click'] += (
1 if field_dict['click_flag'] == True else 0)
result[camp_grp][tmp_idx]['cost'] += win_price
#指定资源限制方法:50%*总成本,50%*总点击
if condition_type[camp_grp] == 'cost':
stop_flag_idx[camp_grp] = binary_search([
result[camp_grp][idx]['cost']
for idx in range(0, stop_flag_idx[camp_grp])
], stat_result[camp_grp]['cost'] / 2)
elif condition_type[camp_grp] == 'click':
stop_flag_idx[camp_grp] = binary_search([
result[camp_grp][idx]['click']
for idx in range(0, stop_flag_idx[camp_grp])
], stat_result[camp_grp]['click'] / 2)
#计算ctr/avg_pctr/ecpc/cpm等衍生度量
for camp_grp in result:
for tmp_idx in range(0, len(result[camp_grp])):
result[camp_grp][tmp_idx]['cost'] /= 1000 # 修改单位,cpm为千次展示价格
tmp_dict = result[camp_grp][tmp_idx]
result[camp_grp][tmp_idx]['ctr'] = (
(tmp_dict['click'] + 0.0) /
tmp_dict['impression']) if tmp_dict['impression'] != 0 else 0
result[camp_grp][tmp_idx]['avg_pctr'] = (
(tmp_dict['avg_pctr'] + 0.0) /
tmp_dict['impression']) if tmp_dict['impression'] != 0 else 0
result[camp_grp][tmp_idx]['ecpc'] = (
tmp_dict['cost']
) / tmp_dict['click'] if tmp_dict['click'] != 0 else 0
result[camp_grp][tmp_idx][
'cpm'] = 1000 * tmp_dict['cost'] / tmp_dict[
'impression'] if tmp_dict['impression'] != 0 else 0
#提取出具体参数，而非参数索引
paras_perf = {
camp_grp: {
candidate_paras[camp_grp][idx]: result[camp_grp][idx]
for idx in range(0, len(candidate_paras[camp_grp]))
}
for camp_grp in result.keys()
}
#打印结果
bpo_logger.info('**************history_repeat function end**************')
formatter = 'paras_performance\ncampaign id:{camp}\nadgroup id:{grp}\nbid strategy:{strategy}\nbid strategy fixed parameter:{para}\n'
for camp_grp in paras_perf.keys():
log_perf_str = 'bid_history_files:%s\n' % ','.join(bid_history_files)
log_perf_str += formatter.format(
camp=camp_grp[0],
grp=camp_grp[1],
strategy=bid_model[camp_grp].bid_strategy_type,
para=bid_model[camp_grp].fixed_parameter)
log_perf_str += 'condition type:%s\n' % condition_type[camp_grp]
log_perf_str += 'para click imp cost cpc ctr avg_pctr cpm\n'
log_perf_str += 'unit: US dollar\n'
for para in sorted(paras_perf[camp_grp].keys()):
tmp_dict = paras_perf[camp_grp][para]
log_perf_str += str(
para
) + ' %(click)s %(impression)s %(cost)s %(ecpc)s %(ctr)s %(avg_pctr)s %(cpm)s\n' % tmp_dict
bpo_logger.info('************parameter performance start************')
bpo_logger.info(log_perf_str)
bpo_logger.info('************parameter performance end************')
return paras_perf
def history_repeat(bid_history_files, the_ctr_model, bid_model,
candidate_paras):
'''
历史重演，对一批历史数据进行模拟投放
paras:
bid_history_files:join文件列表
the_ctr_model:ctr模型
bid_model:出价模型
candidate_paras:候选参数
return:
paras_perf[camp_grp][para] =
{'impression':,'avg_pctr':,'click':,'cost':,'ctr':,'ecpc':,'cpm':}
'''
candidate_paras = {
camp_grp: candidate_paras[camp_grp]
for camp_grp in candidate_paras.keys()
if len(candidate_paras[camp_grp]) != 0
}
bpo_logger.info(
'**************history_repeat function start**************')
bpo_logger.info('files:%s' % ','.join(bid_history_files))
bpo_logger.info('************** bid_model: %s**************' %
(bid_model.keys()))
bpo_logger.info('************** candidate_paras: %s**************' %
(candidate_paras))
stop_flag_idx = {}
result = {}
for (camp_id, grp_id) in bid_model.keys():
tmp_num = len(candidate_paras[(camp_id, grp_id)])
stop_flag_idx[(camp_id, grp_id)] = tmp_num
result[(camp_id, grp_id)] = [None] * tmp_num
for idx in range(0, tmp_num):
result[(camp_id, grp_id)][idx] = {
'impression': 0,
'avg_pctr': 0,
'click': 0,
'cost': 0
}
req_parser = join.Parser()
total_time = 0
for bid_history_file in bid_history_files:
for line in open(bid_history_file):
req_parser.feed(line)
field_dict = req_parser.get_all()
if field_dict == None:
continue
win_price = float(field_dict['win_price'])
camp_grp = (field_dict['campaign_id'], field_dict['adgroup_id'])
#bid_model的camp_grp 为有效的adgroup，如果该条req的adgroup不再bid_model中，则continue
if (not candidate_paras.has_key(camp_grp)) or (
not bid_model.has_key(camp_grp)
) or win_price == None or win_price <= 0:
continue
pctr = the_ctr_model.predict_ctr(field_dict['feature_values'])
candidate_bid_prices = bid_model[camp_grp].get_bids_auc(
ctr=pctr, variable_paras=candidate_paras[camp_grp])
first_ge_idx = binary_search(candidate_bid_prices, win_price)
#非累积方式
#if first_ge_idx < stop_flag_idx[camp_grp]:
# for tmp_idx in range(first_ge_idx, stop_flag_idx[camp_grp]):
# result[camp_grp][tmp_idx]['impression'] += 1
# result[camp_grp][tmp_idx]['avg_pctr'] += pctr
# result[camp_grp][tmp_idx]['click'] += (1 if field_dict['click_flag'] == '1' else 0)
# result[camp_grp][tmp_idx]['cost'] += win_price
# 因为没有投放限制(比如总预算，总预订点击等)，下列语句被注释了
# 指定资源限制方法:这里是成本限制,50%*总成本
# print float(total_budget[camp_grp])/2
# stop_flag_idx[camp_grp] = binary_search([result[camp_grp][idx]['cost'] for idx in range(0,stop_flag_idx[camp_grp])],float(total_budget[camp_grp])/16)
# print stop_flag_idx[camp_grp]
#累积方式，累积方式是不能添加资源限制的。累计方式速度更快
if first_ge_idx < stop_flag_idx[camp_grp]:
result[camp_grp][first_ge_idx]['impression'] += 1
result[camp_grp][first_ge_idx]['avg_pctr'] += pctr
result[camp_grp][first_ge_idx]['click'] += (
1 if field_dict['click_flag'] == True else 0)
result[camp_grp][first_ge_idx]['cost'] += win_price
for camp_grp in result:
for idx in range(1, len(result[camp_grp])):
for tmp_metric in ['impression', 'avg_pctr', 'click', 'cost']:
result[camp_grp][idx][tmp_metric] += result[camp_grp][
idx - 1][tmp_metric]
#计算ctr/avg_pctr/ecpc/cpm等衍生度量
for camp_grp in result:
for tmp_idx in range(0, len(result[camp_grp])):
result[camp_grp][tmp_idx]['cost'] /= 1000 # 修改单位
# print result[camp_grp]
tmp_dict = result[camp_grp][tmp_idx]
result[camp_grp][tmp_idx]['ctr'] = (
(tmp_dict['click'] + 0.0) /
tmp_dict['impression']) if tmp_dict['impression'] != 0 else 0
result[camp_grp][tmp_idx]['avg_pctr'] = (
(tmp_dict['avg_pctr'] + 0.0) /
tmp_dict['impression']) if tmp_dict['impression'] != 0 else 0
result[camp_grp][tmp_idx]['ecpc'] = (
tmp_dict['cost']
) / tmp_dict['click'] if tmp_dict['click'] != 0 else 0
result[camp_grp][tmp_idx][
'cpm'] = 1000 * tmp_dict['cost'] / tmp_dict[
'impression'] if tmp_dict['impression'] != 0 else 0
#提取出具体参数，而非参数索引
paras_perf = {}
#for camp_grp in result.keys():
# paras_perf[camp_grp] = {}
# for idx in range(0, len(candidate_paras[camp_grp])):
# paras_perf[camp_grp][candidate_paras[camp_grp][idx]] = result[camp_grp][idx]
paras_perf = {
camp_grp: {
candidate_paras[camp_grp][idx]: result[camp_grp][idx]
for idx in range(0, len(candidate_paras[camp_grp]))
}
for camp_grp in result.keys()
}
#打印结果
bpo_logger.info('**************history_repeat function end**************')
formatter = 'paras_performance\ncampaign id:{camp}\nadgroup id:{grp}\nbid strategy:{strategy}\nbid strategy fixed parameter:{para}\n'
for camp_grp in paras_perf.keys():
log_perf_str = 'bid_history_files:%s\n' % ','.join(bid_history_files)
log_perf_str += formatter.format(
camp=camp_grp[0],
grp=camp_grp[1],
strategy=bid_model[camp_grp].bid_strategy_type,
para=bid_model[camp_grp].fixed_parameter)
log_perf_str += 'para click imp cost cpc ctr avg_pctr cpm\n'
log_perf_str += 'unit: US dollar\n'
for para in sorted(paras_perf[camp_grp].keys()):
tmp_dict = paras_perf[camp_grp][para]
log_perf_str += str(
para
) + ' %(click)s %(impression)s %(cost)s %(ecpc)s %(ctr)s %(avg_pctr)s %(cpm)s\n' % tmp_dict
bpo_logger.info('************parameter performance start************')
bpo_logger.info(log_perf_str)
bpo_logger.info('************parameter performance end************')
#print paras_perf
return paras_perf
def history_repeat_filter(bid_history_files, the_ctr_model, bid_model,
candidate_paras, outfilename):
'''
这里仅有一个参数
历史重演，对一批历史数据进行模拟投放
paras:
bid_history_files:join文件列表
the_ctr_model:ctr模型
bid_model:出价模型
candidate_paras:候选参数
return:
paras_perf[camp_grp][para] =
{'impression':,'avg_pctr':,'click':,'cost':,'ctr':,'ecpc':,'cpm':}
'''
candidate_paras = {
camp_grp: candidate_paras[camp_grp]
for camp_grp in candidate_paras.keys()
if len(candidate_paras[camp_grp]) == 1
}
if len(candidate_paras) == 0:
print 'there is no candidate parameter'
return
click_num = 0
imp_num = 0
cost = 0
click_num_old = 0
imp_num_old = 0
cost_old = 0
outfile = open(outfilename, 'w')
for bid_history_file in bid_history_files:
for line in open(bid_history_file):
#line = line.rstrip('\n')
field_dict = join.get_field_dict(line)
if field_dict == None:
continue
win_price = float(field_dict['win_price'])
camp_grp = (field_dict['campaign_id'], field_dict['adgroup_id'])
if (not candidate_paras.has_key(camp_grp)) or (
not bid_model.has_key(camp_grp)
) or win_price == None or win_price <= 0:
continue
pctr = the_ctr_model.predict_ctr(field_dict['feature_values'])
candidate_bid_prices = bid_model[camp_grp].get_bids_auc(
pctr, candidate_paras[camp_grp])
if candidate_bid_prices[0] >= win_price:
outfile.write(line)
imp_num += 1
click_num += (1 if field_dict['click_flag'] == True else 0)
cost += win_price
imp_num_old += 1
click_num_old += (1 if field_dict['click_flag'] == True else 0)
cost_old += win_price
cost = float(cost) / 1000
cost_old = float(cost_old) / 1000
print 'file%s' % bid_history_files
print 'old imp_num %d,click_num %d,cost %.4f' % (imp_num_old,
click_num_old, cost_old)
print 'old cpm %.4f,ctr %.8f,cpc %.4f' % (
1000 * cost_old / imp_num_old, float(click_num_old) / imp_num_old,
cost_old / click_num_old)
print 'imp_num %d,click_num %d,cost %.4f' % (imp_num, click_num, cost)
print 'cpm %.4f,ctr %.8f,cpc %.4f' % (
1000 * cost / imp_num, float(click_num) / imp_num, cost / click_num)
def history_repeat(bid_history_files, the_ctr_model, bid_model, candidate_paras):
'''
历史重演，对一批历史数据进行模拟投放
paras:
bid_history_files:join文件列表
the_ctr_model:ctr模型
bid_model:出价模型
candidate_paras:候选参数
return:
paras_perf[camp_grp][para] =
{'impression':,'avg_pctr':,'click':,'cost':,'ctr':,'ecpc':,'cpm':}
'''
candidate_paras = {camp_grp:candidate_paras[camp_grp] for camp_grp in candidate_paras.keys() if len(candidate_paras[camp_grp]) != 0 }
bpo_logger.info('**************history_repeat function start**************')
bpo_logger.info('files:%s' % ','.join(bid_history_files))
bpo_logger.info('************** bid_model: %s**************' % (bid_model.keys()))
bpo_logger.info('************** candidate_paras: %s**************' % (candidate_paras))
stop_flag_idx = {}
result = {}
for (camp_id, grp_id) in bid_model.keys():
tmp_num = len(candidate_paras[(camp_id, grp_id)])
stop_flag_idx[(camp_id, grp_id)] = tmp_num
result[(camp_id, grp_id)] = [None] * tmp_num
for idx in range(0, tmp_num):
result[(camp_id, grp_id)][idx] = {'impression':0, 'avg_pctr':0, 'click':0, 'cost':0}
req_parser = join.Parser()
total_time = 0
for bid_history_file in bid_history_files:
for line in open(bid_history_file):
req_parser.feed(line)
field_dict = req_parser.get_all()
if field_dict == None:
continue
win_price = float(field_dict['win_price'])
camp_grp = (field_dict['campaign_id'], field_dict['adgroup_id'])
#bid_model的camp_grp 为有效的adgroup，如果该条req的adgroup不再bid_model中，则continue
if (not candidate_paras.has_key(camp_grp)) or (not bid_model.has_key(camp_grp)) or win_price == None or win_price <= 0:
continue
pctr = the_ctr_model.predict_ctr(field_dict['feature_values'])
candidate_bid_prices = bid_model[camp_grp].get_bids_auc(ctr=pctr, variable_paras=candidate_paras[camp_grp])
first_ge_idx = binary_search(candidate_bid_prices, win_price)
#非累积方式
#if first_ge_idx < stop_flag_idx[camp_grp]:
# for tmp_idx in range(first_ge_idx, stop_flag_idx[camp_grp]):
# result[camp_grp][tmp_idx]['impression'] += 1
# result[camp_grp][tmp_idx]['avg_pctr'] += pctr
# result[camp_grp][tmp_idx]['click'] += (1 if field_dict['click_flag'] == '1' else 0)
# result[camp_grp][tmp_idx]['cost'] += win_price
# 因为没有投放限制(比如总预算，总预订点击等)，下列语句被注释了
# 指定资源限制方法:这里是成本限制,50%*总成本
# print float(total_budget[camp_grp])/2
# stop_flag_idx[camp_grp] = binary_search([result[camp_grp][idx]['cost'] for idx in range(0,stop_flag_idx[camp_grp])],float(total_budget[camp_grp])/16)
# print stop_flag_idx[camp_grp]
#累积方式，累积方式是不能添加资源限制的。累计方式速度更快
if first_ge_idx < stop_flag_idx[camp_grp]:
result[camp_grp][first_ge_idx]['impression'] += 1
result[camp_grp][first_ge_idx]['avg_pctr'] += pctr
result[camp_grp][first_ge_idx]['click'] += (1 if field_dict['click_flag'] == True else 0)
result[camp_grp][first_ge_idx]['cost'] += win_price
for camp_grp in result:
for idx in range(1,len(result[camp_grp])):
for tmp_metric in ['impression','avg_pctr','click','cost']:
result[camp_grp][idx][tmp_metric] += result[camp_grp][idx-1][tmp_metric]
#计算ctr/avg_pctr/ecpc/cpm等衍生度量
for camp_grp in result:
for tmp_idx in range(0, len(result[camp_grp])):
result[camp_grp][tmp_idx]['cost'] /= 1000 # 修改单位
# print result[camp_grp]
tmp_dict = result[camp_grp][tmp_idx]
result[camp_grp][tmp_idx]['ctr'] = ((tmp_dict['click'] + 0.0) / tmp_dict['impression']) if tmp_dict['impression'] != 0 else 0
result[camp_grp][tmp_idx]['avg_pctr'] = ((tmp_dict['avg_pctr'] + 0.0) / tmp_dict['impression']) if tmp_dict['impression'] != 0 else 0
result[camp_grp][tmp_idx]['ecpc'] = (tmp_dict['cost']) / tmp_dict['click'] if tmp_dict['click'] != 0 else 0
result[camp_grp][tmp_idx]['cpm'] = 1000 * tmp_dict['cost'] / tmp_dict['impression'] if tmp_dict['impression'] != 0 else 0
#提取出具体参数，而非参数索引
paras_perf = {}
#for camp_grp in result.keys():
# paras_perf[camp_grp] = {}
# for idx in range(0, len(candidate_paras[camp_grp])):
# paras_perf[camp_grp][candidate_paras[camp_grp][idx]] = result[camp_grp][idx]
paras_perf ={camp_grp:{ candidate_paras[camp_grp][idx]:result[camp_grp][idx] for idx in range(0, len(candidate_paras[camp_grp]))} for camp_grp in result.keys()}
#打印结果
bpo_logger.info('**************history_repeat function end**************')
formatter = 'paras_performance\ncampaign id:{camp}\nadgroup id:{grp}\nbid strategy:{strategy}\nbid strategy fixed parameter:{para}\n'
for camp_grp in paras_perf.keys():
log_perf_str = 'bid_history_files:%s\n' % ','.join(bid_history_files)
log_perf_str += formatter.format(
camp=camp_grp[0],
grp=camp_grp[1],
strategy=bid_model[camp_grp].bid_strategy_type,
para=bid_model[camp_grp].fixed_parameter)
log_perf_str += 'para click imp cost cpc ctr avg_pctr cpm\n'
log_perf_str += 'unit: US dollar\n'
for para in sorted(paras_perf[camp_grp].keys()):
tmp_dict = paras_perf[camp_grp][para]
log_perf_str += str(para) + ' %(click)s %(impression)s %(cost)s %(ecpc)s %(ctr)s %(avg_pctr)s %(cpm)s\n' % tmp_dict
bpo_logger.info('************parameter performance start************')
bpo_logger.info(log_perf_str)
bpo_logger.info('************parameter performance end************')
#print paras_perf
return paras_perf
def history_repeat_conditional(
bid_history_files, the_ctr_model, bid_model, candidate_paras, condition_type, stat_result
):
"""
历史重演，对一批历史数据进行模拟投放
paras:
bid_history_files:join文件名列表,list类型
the_ctr_model:ctr模型
bid_model:出价模型
candidate_paras:候选参数
return:
paras_perf[camp_grp][para] =
{'impression':,'avg_pctr':,'click':,'cost':,'ctr':,'ecpc':,'cpm':}
"""
candidate_paras = {
camp_grp: candidate_paras[camp_grp]
for camp_grp in candidate_paras.keys()
if len(candidate_paras[camp_grp]) != 0
}
bpo_logger.info("**************history_repeat function start**************")
bpo_logger.info("files:%s" % ",".join(bid_history_files))
bpo_logger.info("************** bid_model: %s**************" % (bid_model.keys()))
bpo_logger.info("************** candidate_paras: %s**************" % (candidate_paras))
bpo_logger.info("************** condition_type: %s**************" % (condition_type))
stop_flag_idx = {}
result = {} # 预制所有的键
for camp_grp in bid_model.keys():
# bid_model的camp_grp 为有效的adgroup，如果该条req的adgroup不在bid_model中，则continue
if (not candidate_paras.has_key(camp_grp)) or (not bid_model.has_key(camp_grp)):
continue
if not condition_type.has_key(camp_grp):
continue
tmp_num = len(candidate_paras[camp_grp])
stop_flag_idx[camp_grp] = tmp_num
result[camp_grp] = [None] * tmp_num
for idx in range(0, tmp_num):
result[camp_grp][idx] = {"impression": 0, "avg_pctr": 0, "click": 0, "cost": 0}
req_parser = join.Parser()
for bid_history_file in bid_history_files:
for line in open(bid_history_file):
req_parser.feed(line)
field_dict = req_parser.get_all()
if field_dict == None:
continue
win_price = float(field_dict["win_price"])
camp_grp = (field_dict["campaign_id"], field_dict["adgroup_id"])
if win_price == None or win_price <= 0:
continue
if not result.has_key(camp_grp):
continue
pctr = the_ctr_model.predict_ctr(field_dict["feature_values"])
candidate_bid_prices = bid_model[camp_grp].get_bids_auc(ctr=pctr, variable_paras=candidate_paras[camp_grp])
first_ge_idx = binary_search(candidate_bid_prices, win_price)
# 非累积方式
if first_ge_idx < stop_flag_idx[camp_grp]:
for tmp_idx in range(first_ge_idx, stop_flag_idx[camp_grp]):
result[camp_grp][tmp_idx]["impression"] += 1
result[camp_grp][tmp_idx]["avg_pctr"] += pctr
result[camp_grp][tmp_idx]["click"] += 1 if field_dict["click_flag"] == True else 0
result[camp_grp][tmp_idx]["cost"] += win_price
# 指定资源限制方法:50%*总成本,50%*总点击
if condition_type[camp_grp] == "cost":
stop_flag_idx[camp_grp] = binary_search(
[result[camp_grp][idx]["cost"] for idx in range(0, stop_flag_idx[camp_grp])],
stat_result[camp_grp]["cost"] / 2,
)
elif condition_type[camp_grp] == "click":
stop_flag_idx[camp_grp] = binary_search(
[result[camp_grp][idx]["click"] for idx in range(0, stop_flag_idx[camp_grp])],
stat_result[camp_grp]["click"] / 2,
)
# 计算ctr/avg_pctr/ecpc/cpm等衍生度量
for camp_grp in result:
for tmp_idx in range(0, len(result[camp_grp])):
result[camp_grp][tmp_idx]["cost"] /= 1000 # 修改单位,cpm为千次展示价格
tmp_dict = result[camp_grp][tmp_idx]
result[camp_grp][tmp_idx]["ctr"] = (
((tmp_dict["click"] + 0.0) / tmp_dict["impression"]) if tmp_dict["impression"] != 0 else 0
)
result[camp_grp][tmp_idx]["avg_pctr"] = (
((tmp_dict["avg_pctr"] + 0.0) / tmp_dict["impression"]) if tmp_dict["impression"] != 0 else 0
)
result[camp_grp][tmp_idx]["ecpc"] = (tmp_dict["cost"]) / tmp_dict["click"] if tmp_dict["click"] != 0 else 0
result[camp_grp][tmp_idx]["cpm"] = (
1000 * tmp_dict["cost"] / tmp_dict["impression"] if tmp_dict["impression"] != 0 else 0
)
# 提取出具体参数，而非参数索引
paras_perf = {
camp_grp: {
candidate_paras[camp_grp][idx]: result[camp_grp][idx] for idx in range(0, len(candidate_paras[camp_grp]))
}
for camp_grp in result.keys()
}
# 打印结果
bpo_logger.info("**************history_repeat function end**************")
formatter = "paras_performance\ncampaign id:{camp}\nadgroup id:{grp}\nbid strategy:{strategy}\nbid strategy fixed parameter:{para}\n"
for camp_grp in paras_perf.keys():
log_perf_str = "bid_history_files:%s\n" % ",".join(bid_history_files)
log_perf_str += formatter.format(
camp=camp_grp[0],
grp=camp_grp[1],
strategy=bid_model[camp_grp].bid_strategy_type,
para=bid_model[camp_grp].fixed_parameter,
)
log_perf_str += "condition type:%s\n" % condition_type[camp_grp]
log_perf_str += "para click imp cost cpc ctr avg_pctr cpm\n"
log_perf_str += "unit: US dollar\n"
for para in sorted(paras_perf[camp_grp].keys()):
tmp_dict = paras_perf[camp_grp][para]
log_perf_str += (
str(para) + " %(click)s %(impression)s %(cost)s %(ecpc)s %(ctr)s %(avg_pctr)s %(cpm)s\n" % tmp_dict
)
bpo_logger.info("************parameter performance start************")
bpo_logger.info(log_perf_str)
bpo_logger.info("************parameter performance end************")
return paras_perf
