import datetime import json import os import sys import traceback from itertools import product import pandas as pd import requests import yaml from loguru import logger curr_path = os.path.abspath(os.path.dirname(__file__)) project_root_path = curr_path[:curr_path.find("ai_target") + len("ai_target")] sys.path.append(project_root_path) from config.url_and_db import estimate_people_number_url, headers, jeecg_db, jeecg_product_db, application_product_db, application_inner_db from utils.BaseClass import NpEncoder from utils.commonFunc import age_code_transform, gender_code_transform logger.remove() # 删去 import logger之后自动产生的handler,不删除的话会出现重复输出的现象 logger.add("/data/pythonProject/ai_target/logs/bayes_combine.{time:YYYY-MM-DD}.log", rotation="00:00", format="{time:YYYY-MM-DD HH:mm:ss,SSS} [{process}] [{thread}] {level} {file} {line} - {message}", level="INFO") class GetSingleDimFeatures(object): """ 计算素材单维度滑窗组合转化占比情况 """ def __init__(self, signature, dim, dim_config, project_id): self.project_id = project_id self.signature = signature self.dim = dim self.dim_config = dim_config self.table = self.dim_config['table'] self.filed_name = self.dim_config['fieldName'] self.dim_value_lst = self.dim_config['Lst'] self.ratio_threshold = self.dim_config['ratio_threshold'] self.ratio_diff_threshold = self.dim_config['ratio_diff_threshold'] self.window_size = self.dim_config['windowSize'] self.window_combine = [] self.features = {} 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_value_lst)) and (start + self.window_size <= len(self.dim_value_lst)): self.window_combine.append(self.dim_value_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_features(self): # 1、获取素材在指定维度下的人群数据 get_audience_sql = f"select signature, {self.filed_name}, sum(activation) activation " \ f"from {self.table} where signature = '{self.signature}' and project_id = {self.project_id} " \ f"group by signature, {self.filed_name}" audience_df = pd.read_sql(get_audience_sql, application_inner_db) for combine in self.window_combine: if combine != ['不限']: self.features['|'.join(combine)] = round(audience_df[audience_df[self.filed_name].isin(combine)].activation.sum() / \ audience_df.activation.sum(), 4) else: if self.dim == 'gender': # 如果男/女 激活占比差异小于0.1, 说明素材的受众没有明显的性别倾向,可以对性别通投 male_ratio = audience_df[audience_df['gender'] == '男'].activation.sum() / audience_df.activation.sum() female_ratio = audience_df[audience_df['gender'] == '女'].activation.sum() / audience_df.activation.sum() if abs(male_ratio - female_ratio) <= self.ratio_diff_threshold: self.features['不限'] = 1 if self.dim == 'age': self.features['不限'] = 1 # 过滤得到占比达到 ratio_threshold 的组合值 self.features = {f"{self.dim}_{combine}": ratio for combine, ratio in self.features.items() if ratio > self.ratio_threshold} class GetCompositeDimFeatures(object): """ """ def __init__(self, signature, feature_lst, project_id): self.signature = signature self.feature_lst = feature_lst self.project_id = project_id def get_composite_features(self): feature_combine_lst = [list(item.keys()) for item in self.feature_lst] fea_combine_df = pd.DataFrame() for ele in product(*feature_combine_lst): fea_combine = dict(zip([e.split('_')[0] for e in ele], [e.split('_')[-1] for e in ele])) fea_combine['unlimited_cnt'] = list(fea_combine.values()).count('不限') fea_combine['features'] = str([(e.split('_')[0], e.split('_')[1], item[e]) for e in ele for item in self.feature_lst if e in item.keys()]) try: get_open_account_sql = f"select account_id from ctop_user_allocation where project_id = {self.project_id} and " \ f"account_status = 0 limit 1" account_df = pd.read_sql(get_open_account_sql, jeecg_product_db) account_id = account_df.account_id.values[0] # account_id = 9774238 request_data = {'ages_range': age_code_transform(fea_combine.get('age')), 'gender': gender_code_transform(fea_combine.get('gender')), 'advertiser_id': account_id} request = requests.post(url=estimate_people_number_url, headers=headers, data=json.dumps(request_data, cls=NpEncoder)) response_data = json.loads(request.text) if response_data['code'] == 0: fea_combine['crowd_coverage_cnt'] = response_data['data'].get('audience_prediction_num') except: logger.error(f"人群预估覆盖接口调用报错,请求数据: {request_data}, 返回数据: {request.text}, 异常信息: {traceback.format_exc()}") fea_combine_df = fea_combine_df.append(pd.DataFrame([fea_combine]), ignore_index=True) # 计算结果写入数据库中 fea_combine_df['signature'] = self.signature fea_combine_df['stat_date'] = str(datetime.datetime.now().date()) fea_combine_df['project_id'] = self.project_id fea_combine_df.to_sql(name="ctop_ai_kuaishou_signature_recommended_target_combine_v2", con=jeecg_db, if_exists='append', index=False) if __name__ == '__main__': # 1、读取配置文件 with open('/data/pythonProject/ai_target/config/config.yaml', mode='r', encoding='utf-8') as f: config = yaml.load(f.read(), Loader=yaml.FullLoader) # 2、 参与定向组合的维度 target_dim = [key for key in config['bayesDim'].keys() if config['bayesDim'][key]['isOn']] # 4、计算贝叶斯组合入库 for project_id in config['projectId']: logger.info(f"开始获取项目{project_id}的当前活跃素材") # 4.1 获取指定项目下当前活跃的素材信息 # 如近60天内累计激活个数达到100个(开发环境或者生产环境,这部分都读取生产数据库) days = config['activeMaterialFilterRule']['days'] activation_sum = config['activeMaterialFilterRule']['activation'] pay_first_pct = config['activeMaterialFilterRule']['event_pay_first_day_pct'] sql = f"select signature from kuaishou_material_video_report_daily_dw where project_id = {project_id} " \ f"and stat_date >= date_format(date_sub(now(), interval {days} DAY),'%%Y%%m%%d') group by signature " \ f"having sum(activation) >= {activation_sum} " \ f"and sum(event_pay_first_day) / sum(activation) >= {pay_first_pct}" df = pd.read_sql(sql, application_inner_db) active_signatures = list(df[~df.signature.isnull()].signature.values) active_signatures = active_signatures * 2 if len(active_signatures) == 1 else active_signatures # 4.2 在素材人群报表筛选里面累计100个激活 logger.info(f"开始获取项目{project_id}的活跃素材的人群分析报表") sql = f"select signature from kuaishou_unit_audience_age_report_daily_d where signature in {tuple(active_signatures)} " \ f"and project_id = {project_id} " \ f"group by signature having sum(activation) >= {config['getBaysCombineMaterialFilterRule']['activation']}" df = pd.read_sql(sql, application_inner_db) signature_lst = df['signature'].values # 这行代码用于测试 # signature_lst = ['f7adee9229e58176d132cf0bd7590a95'] # 4.2 计算指定素材定向 for sig in signature_lst: try: feature_lst = [] for dimension in target_dim: get_single_fea_ins = GetSingleDimFeatures(sig, dimension, config['bayesDim'][dimension], project_id) # 计算滑窗组合 get_single_fea_ins.get_window_combine() get_single_fea_ins.get_features() feature_lst.append(get_single_fea_ins.features) # 依据特征值,计算多维度的组合预估值 get_composite_fea_ins = GetCompositeDimFeatures(sig, feature_lst, project_id) get_composite_fea_ins.get_composite_features() logger.info('project_id=%s, signature= %s 完成贝叶斯组合计算!' % (project_id, sig)) except: logger.error('project_id=%s, signature=%s 贝叶斯组合计算出错,异常信息为%s!' % (project_id, sig, traceback.format_exc())) logger.info('project_id is %s 完成贝叶斯组合计算!' % project_id)