123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242 |
- import yaml
- import pandas as pd
- from sqlalchemy import create_engine
- from urllib import parse
- from commonFunc import update_dict
- from functools import reduce
- from itertools import product
- from datetime import datetime
- class BayesFeatures(object):
- """
- 计算素材单维度的特征值
- """
- def __init__(self, signature, target_type, dim, dim_config):
- self.signature = signature
- self.target_type = target_type
- self.dim = dim
- self.dim_config = dim_config
- self.table = self.dim_config['table']
- self.file_name = self.dim_config['fieldName']
- self.dim_lst = self.dim_config['Lst']
- self.window_size = self.dim_config['windowSize']
- self.window_combine = []
- self.bayes_feature = {}
- def get_window_combine(self):
- """
- 根据size得到指定维度的滑窗组合。
- 如 age: ['18-23岁', '24-30岁','31-40岁',....] 和 size = 2
- 得到 ['18-23岁', '24-30岁'],['24-30岁','31-40岁'],......
- """
- start = 0
- while (start < len(self.dim_lst)) and (start + self.window_size <= len(self.dim_lst)):
- self.window_combine.append(self.dim_lst[start: start + self.window_size])
- start += 1
- # 添加一个全部的组合,等同于'不限'
- self.window_combine.append(['不限'])
- def get_bayes_feature(self):
- # 1、获取指定素材在指定维度下的人群数据(近一个月内的数据表现)
- sql = '''
- select signature,
- %s,
- sum(aclick) aclick,
- sum(bclick) bclick,
- sum(activation) activation
- from %s
- where signature = '%s'
- -- and datediff(now(),stat_date)<=30
- group by signature, %s
- ''' % (self.file_name, self.table, self.signature, self.file_name)
- df = pd.read_sql(sql, test_engine)
- if self.target_type == 'action_ratio':
- # 计算行为率(bclick/aclick)的组合特征值
- df['unbclick'] = df['aclick'] - df['bclick']
- sig_pos_pct = df['bclick'].sum() / df['aclick'].sum() # 素材曝光-点击的概率
- sig_neg_pct = 1 - sig_pos_pct # 素材曝光-未点击的概率
- self.bayes_feature['sig_pos_pct'] = sig_pos_pct
- self.bayes_feature['sig_neg_pct'] = sig_neg_pct
- for sub_combine in self.window_combine:
- if sub_combine != ['不限']:
- key = self.dim + '_' + '|'.join(sub_combine)
- if self.dim != 'city':
- pos_pct = df[df[self.file_name].isin(sub_combine)].bclick.sum() / df.bclick.sum()
- neg_pct = df[df[self.file_name].isin(sub_combine)].unbclick.sum() / df.unbclick.sum()
- if self.dim == 'city':
- # 获取 city_level 对应的 city_name
- city_lst = []
- for city_level in sub_combine:
- get_city_sql = """
- select city_name from ctop_kuaishou_city_level where city_level = '%s'
- """ % city_level
- city_df = pd.read_sql(get_city_sql, engine)
- city_lst.extend(city_df['city_name'].values)
- pos_pct = df[df[self.file_name].isin(city_lst)].bclick.sum() / df.bclick.sum()
- neg_pct = df[df[self.file_name].isin(city_lst)].unbclick.sum() / df.unbclick.sum()
- self.bayes_feature[key] = {'pos_pct': pos_pct, 'neg_pct': neg_pct}
- else:
- self.bayes_feature[self.dim + '_' + '不限'] = {'pos_pct': 1, 'neg_pct': 1}
- if self.target_type == 'convert_ratio':
- # 计算转化率(activation/bclick)的组合特征值
- df['unactivation'] = df['bclick'] - df['activation']
- sig_pos_pct = df['activation'].sum() / df['bclick'].sum() # 素材点击-转化的概率
- sig_neg_pct = 1 - sig_pos_pct # 素材点击-未转化的概率
- self.bayes_feature['sig_pos_pct'] = sig_pos_pct
- self.bayes_feature['sig_neg_pct'] = sig_neg_pct
- for sub_combine in self.window_combine:
- if sub_combine != '不限':
- key = self.dim + '_' + '|'.join(sub_combine)
- if self.dim != 'city':
- pos_pct = df[df[self.file_name].isin(sub_combine)].activation.sum() / df.activation.sum()
- neg_pct = df[df[self.file_name].isin(sub_combine)].unactivation.sum() / df.unactivation.sum()
- if self.dim == 'city':
- # 获取 city_level 对应的 city_name
- city_lst = []
- for city_level in sub_combine:
- get_city_sql = """
- select city_name from ctop_kuaishou_city_level where city_level = '%s'
- """ % city_level
- city_df = pd.read_sql(get_city_sql, engine)
- city_lst.extend(city_df['city_name'].values)
- pos_pct = df[df[self.file_name].isin(city_lst)].activation.sum() / df.activation.sum()
- neg_pct = df[df[self.file_name].isin(city_lst)].unactivation.sum() / df.unactivation.sum()
- self.bayes_feature[key] = {'pos_pct': pos_pct, 'neg_pct': neg_pct}
- else:
- self.bayes_feature[self.dim + '_' + '不限'] = {'pos_pct': 1, 'neg_pct': 1}
- class BayesCombine(object):
- """
- 依据特征值,计算多维度的组合预估值
- """
- def __init__(self, signature, project_id, target_type, dim_features):
- self.signature = signature
- self.project_id = project_id
- self.target_type = target_type
- self.dim_features = dim_features
- self.bayes_combine_df = pd.DataFrame()
- self.actual_prob = self.dim_features[0]['sig_pos_pct']
- def get_bayes_estimate(self):
- dim_combine_lst = [[key for key in fea.keys() if key not in ['sig_pos_pct', 'sig_neg_pct']] for fea in self.dim_features]
-
- self.dim_features = reduce(update_dict, self.dim_features)
-
- for ele in product(*dim_combine_lst):
- prob_pos = reduce(lambda x, y: self.dim_features[x]['pos_pct'] * self.dim_features[y]['pos_pct'], ele)
- prob_neg = reduce(lambda x, y: self.dim_features[x]['neg_pct'] * self.dim_features[y]['neg_pct'], ele)
- prob = (prob_pos * self.dim_features['sig_pos_pct']) / (prob_neg * self.dim_features['sig_neg_pct'])
- out_dict = dict(zip([e.split('_')[0] for e in ele], [e.split('_')[-1] for e in ele]))
- # TODO 调用人群预估覆盖接口,得到该组合的人群覆盖数
- out_dict['population_cnt'] = 1000
- out_dict['combine_estimate_prob'] = prob
- out_dict['actual_prob'] = self.actual_prob
- out_dict['signature'] = self.signature
- out_dict['project_id'] = self.project_id
- out_dict['target_type'] = self.target_type
- out_dict['stat_date'] = str(datetime.now().date())
- combine = pd.DataFrame([out_dict])
- self.bayes_combine_df = self.bayes_combine_df.append(combine, ignore_index=True)
- def write_to_db(self):
- self.bayes_combine_df.to_sql(name="ctop_ai_kuaishou_signature_recommended_target_combine",
- con=test_engine,
- if_exists='append',
- index=False)
- if __name__ == '__main__':
- # 1、读取配置文件
- with open('config/config.yaml', mode='r', encoding='utf-8') as f:
- config = yaml.load(f.read(), Loader=yaml.FullLoader)
- project_ids = config['projectId']
- target_types = config['targetType']
- online_db = config['onlineDB']
- test_db = config['testDB']
- material_rule = config['materialRule']
- bayes_dim = config['bayesDim']
- # 2、数据库连接引擎
- db_con_str = 'mysql+pymysql://%s:%s@%s:%d/%s' % \
- (online_db['username'], parse.quote_plus(online_db['password']), online_db['host'], online_db['port'],
- online_db['database'])
- engine = create_engine(db_con_str, connect_args={'charset': 'utf8'})
- db_con_str = 'mysql+pymysql://%s:%s@%s:%d/%s' % \
- (test_db['username'], parse.quote_plus(test_db['password']), test_db['host'], test_db['port'],
- test_db['database'])
- test_engine = create_engine(db_con_str, connect_args={'charset': 'utf8'})
- # 3、 参与定向组合的维度
- target_dim = [key for key in bayes_dim.keys() if bayes_dim[key]['isOn']]
- # 4、计算贝叶斯组合入库
- for project_id in project_ids:
- # 4.1 获取指定项目下当前活跃的素材信息, 如近3天内累计激活个数达到50个
- sql = '''
- select signature from ctop_kuaishou_report_daily_material
- where account_id in (select account_id from ctop_user_allocation where project_id = %s)
- and datediff(now(),stat_date) <= %s
- group by signature
- having sum(activation) >= %s
- ''' % (project_id, material_rule['days'], material_rule['activation'])
- df = pd.read_sql(sql, engine)
- signature_lst = df['signature'].values
- signature_lst = ['0070efb7557b2a04cf3d4a6f243c3cd8', '03b93728f0d82ea7865c3c7cf632bc1b']
- # 4.2 计算指定素材的贝叶斯特征
- for sig in signature_lst:
- for t_type in target_types:
- bayes_feature_lst = []
- for dimension in target_dim:
- cls = BayesFeatures(sig, t_type, dimension, bayes_dim[dimension])
- # 计算滑窗组合
- cls.get_window_combine()
- cls.get_bayes_feature()
- bayes_feature_lst.append(cls.bayes_feature)
- # 依据特征值,计算多维度的组合预估值
- cls = BayesCombine(sig, project_id, t_type, bayes_feature_lst)
- cls.get_bayes_estimate()
- cls.write_to_db()
|