|
@@ -0,0 +1,239 @@
|
|
|
|
+import os
|
|
|
|
+import yaml
|
|
|
|
+from common_func import get_db_engine
|
|
|
|
+import pandas as pd
|
|
|
|
+from sklearn.preprocessing import StandardScaler
|
|
|
|
+from sklearn.neighbors import NearestNeighbors
|
|
|
|
+import numpy as np
|
|
|
|
+import sys
|
|
|
|
+import pickle
|
|
|
|
+import logging
|
|
|
|
+from concurrent_log import ConcurrentTimedRotatingFileHandler
|
|
|
|
+
|
|
|
|
+log_formatter = logging.Formatter('%(asctime)s %(levelname)s %(message)s', '%Y/%m/%d %I:%M:%S %p')
|
|
|
|
+log_handler = ConcurrentTimedRotatingFileHandler("/data/pythonProject/similar_material/logs/historical_material.log", when="midnight",
|
|
|
|
+ backupCount=100)
|
|
|
|
+log_handler.setFormatter(log_formatter)
|
|
|
|
+logger = logging.getLogger('historical_material_logger')
|
|
|
|
+logger.addHandler(log_handler)
|
|
|
|
+logger.setLevel(logging.DEBUG)
|
|
|
|
+logger.info("historical_material_logger started!")
|
|
|
|
+print('id of historical_material_logger %s' % id(logger))
|
|
|
|
+
|
|
|
|
+
|
|
|
|
+def scaler_feature(data, axis=0):
|
|
|
|
+ """
|
|
|
|
+ :param data: pd.DataFrame
|
|
|
|
+ :param axis: 0-横向归一化 , 1-纵向归一化
|
|
|
|
+ :return: z = (x - u) / s
|
|
|
|
+ """
|
|
|
|
+ scaler = StandardScaler()
|
|
|
|
+ scaler_data = None
|
|
|
|
+ if axis == 0:
|
|
|
|
+ scaler_data = scaler.fit_transform(data.T).T
|
|
|
|
+ if axis == 1:
|
|
|
|
+ scaler_data = scaler.fit_transform(data)
|
|
|
|
+
|
|
|
|
+ scaler_df = pd.DataFrame(scaler_data)
|
|
|
|
+ scaler_df.index = data.index
|
|
|
|
+ scaler_df.columns = [col + '_scaler' for col in data.columns]
|
|
|
|
+ return scaler_df
|
|
|
|
+
|
|
|
|
+
|
|
|
|
+def get_segment_features(table, signature, dim_col, project_id, col_prefix):
|
|
|
|
+ # 1 获取原始数据
|
|
|
|
+ get_org_data_sql = """
|
|
|
|
+ select signature, aclick, bclick, activation, charge, %s from %s
|
|
|
|
+ where signature in %s and project_id = %s
|
|
|
|
+ """ % (dim_col, table, tuple(signature), project_id)
|
|
|
|
+ org_df = pd.read_sql(get_org_data_sql, read_engine)
|
|
|
|
+
|
|
|
|
+ # 2 计算各分段的 行为率、激活率、激活成本,并进行横向归一化
|
|
|
|
+ g = org_df.groupby(['signature', dim_col]).agg({'activation': sum, 'aclick': sum, 'bclick': sum, 'charge': sum}).unstack()
|
|
|
|
+ # 该维度下有哪些分段值:如 gender维度下有:男、女、其他 , 需要去掉 '其他',因为业务含义不明确,没法解释模型效果
|
|
|
|
+ segment_cols = g['charge'].columns
|
|
|
|
+ if '其他' in segment_cols:
|
|
|
|
+ segment_cols.remove('其他')
|
|
|
|
+
|
|
|
|
+ segment_fea_df = pd.DataFrame()
|
|
|
|
+ for col in segment_cols:
|
|
|
|
+ segment_fea_df[col + '_bclick_aclick_pct'] = g[('bclick', col)] / g[('aclick', col)]
|
|
|
|
+ segment_fea_df[col + '_activation_bclick_pct'] = g[('activation', col)] / g[('bclick', col)]
|
|
|
|
+ segment_fea_df[col + '_cost'] = g[('charge', col)] / g[('activation', col)]
|
|
|
|
+
|
|
|
|
+ # 3 计算累计激活中各分段的激活个数占比,并进行横向归一化
|
|
|
|
+ for col in segment_cols:
|
|
|
|
+ segment_fea_df[col + '_activation_pct'] = g[('activation', col)] / (g[[('activation', item) for item in segment_cols]].sum(axis=1))
|
|
|
|
+
|
|
|
|
+ # 4 对 np.nan 和 np.inf 进行处理
|
|
|
|
+ # 4-1 cost
|
|
|
|
+ # np.inf : 分子>0/分母=0, 表示有消耗但是没有激活数,填充为 999
|
|
|
|
+ # np.nan :分子=0/分母=0, 表示没有消耗也没有激活数,填充为 -1
|
|
|
|
+ cost_cols = [col for col in segment_fea_df.columns if 'cost' in col]
|
|
|
|
+ segment_fea_df[cost_cols] = segment_fea_df[cost_cols].replace({np.nan: -1, np.inf: 999})
|
|
|
|
+
|
|
|
|
+ # 4-2 占比类
|
|
|
|
+ # np.inf :分子>0/分母=0 ,如行为率:表示有点击但没有曝光,属于数据bug情况。需要剔除该素材并写入日志
|
|
|
|
+ # np.nan :分子=0/分母=0 ,如激活率:表示没有激活也没有点击,填充为 0
|
|
|
|
+ pct_cols = [col for col in segment_fea_df.columns if 'pct' in col]
|
|
|
|
+ segment_fea_df[pct_cols] = segment_fea_df[pct_cols].replace({np.nan: 0})
|
|
|
|
+
|
|
|
|
+ inf_df = np.isinf(segment_fea_df[pct_cols]).sum(axis=1)
|
|
|
|
+ remove_sig_lst = inf_df[inf_df >= 1].index
|
|
|
|
+ # TODO 添加日志 记录数据存在问题的素材
|
|
|
|
+ if len(remove_sig_lst):
|
|
|
|
+ print(remove_sig_lst)
|
|
|
|
+
|
|
|
|
+ segment_fea_df = segment_fea_df[~segment_fea_df.index.isin(remove_sig_lst)]
|
|
|
|
+
|
|
|
|
+ # 5 对特征进行横向归一化
|
|
|
|
+ segment_fea_scaler_df = pd.DataFrame()
|
|
|
|
+ for col in ['bclick_aclick_pct', 'activation_bclick_pct', 'cost', 'activation_pct']:
|
|
|
|
+ tmp_df = segment_fea_df.filter(like=col)
|
|
|
|
+ scaler_df = scaler_feature(tmp_df, axis=0)
|
|
|
|
+ segment_fea_scaler_df = pd.concat([segment_fea_scaler_df, scaler_df], axis=1)
|
|
|
|
+
|
|
|
|
+ # 6 col_prefix and index
|
|
|
|
+ segment_fea_scaler_df.columns = [col_prefix + col for col in segment_fea_scaler_df.columns]
|
|
|
|
+ segment_fea_scaler_df.index = g.index
|
|
|
|
+ return segment_fea_scaler_df
|
|
|
|
+
|
|
|
|
+
|
|
|
|
+def get_signature_features(signature, project_id):
|
|
|
|
+ """
|
|
|
|
+ 计算素材整体的 行为率、激活率、激活成本
|
|
|
|
+ :param project_id:
|
|
|
|
+ :param signature:
|
|
|
|
+ :return:
|
|
|
|
+ """
|
|
|
|
+ get_data_sql = """ select signature, sum(aclick) aclick, sum(bclick) bclick, sum(activation) activation, sum(charge) charge
|
|
|
|
+ from ctop_kuaishou_audience_report_daily_age_material
|
|
|
|
+ where signature in %s and project_id = %s
|
|
|
|
+ group by signature
|
|
|
|
+ """ % (tuple(signature), project_id)
|
|
|
|
+ sig_org_df = pd.read_sql(get_data_sql, read_engine)
|
|
|
|
+
|
|
|
|
+ sig_fea_df = pd.DataFrame()
|
|
|
|
+ sig_fea_df['cost'] = sig_org_df['charge'] / sig_org_df['activation']
|
|
|
|
+ sig_fea_df['bclick_aclick_pct'] = sig_org_df['bclick'] / sig_org_df['aclick']
|
|
|
|
+ sig_fea_df['activation_bclick_pct'] = sig_org_df['activation'] / sig_org_df['bclick']
|
|
|
|
+
|
|
|
|
+ # 对特征进行纵向的归一化
|
|
|
|
+ sig_fea_df.index = sig_org_df['signature'].values
|
|
|
|
+ sig_fea_scaler_df = scaler_feature(sig_fea_df, axis=1)
|
|
|
|
+
|
|
|
|
+ return sig_fea_scaler_df
|
|
|
|
+
|
|
|
|
+
|
|
|
|
+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)
|
|
|
|
+
|
|
|
|
+ # 1-1 数据库连接引擎,依据开发环境/生产环境 进行切换
|
|
|
|
+ if os.getenv('LYY_DEV', 'unknown') == 'dev':
|
|
|
|
+ write_engine = get_db_engine(config['devDB'])
|
|
|
|
+ else:
|
|
|
|
+ write_engine = get_db_engine(config['productDB'])
|
|
|
|
+
|
|
|
|
+ read_engine = get_db_engine(config['productDB'])
|
|
|
|
+
|
|
|
|
+ # 2、获取历史所有达标的素材
|
|
|
|
+ project_id = 458
|
|
|
|
+ get_sig_sql = """select signature, sum(activation) activation
|
|
|
|
+ from ctop_kuaishou_audience_report_daily_age_material
|
|
|
|
+ where project_id = %s
|
|
|
|
+ group by signature
|
|
|
|
+ having sum(activation) >= 100
|
|
|
|
+ """ % project_id
|
|
|
|
+ sig_df = pd.read_sql(get_sig_sql, read_engine)
|
|
|
|
+ sig_df = sig_df[~sig_df.signature.isnull()]
|
|
|
|
+ sig_lst = list(sig_df.signature.values)
|
|
|
|
+ print('sig_lst:', len(sig_lst))
|
|
|
|
+
|
|
|
|
+ # TODO for test
|
|
|
|
+ # sig_lst = ['cefd07cf7951ba9674d43c1d9c112f37',
|
|
|
|
+ # '6f11859acaf4f1dd501706f8d50995d8',
|
|
|
|
+ # 'bc8fe6ae97db794acaf050acff4386b9',
|
|
|
|
+ # '59a34e41bfcf321a931a0b204a8609c9',
|
|
|
|
+ # 'c67604889af726d49401f40283865bb0',
|
|
|
|
+ # '75237de4427a9ff6da994976bf516f78',
|
|
|
|
+ # '0ab2a8816b1b34638767862123fc74a6',
|
|
|
|
+ # '177a0f359eb90623b7ecaf1c8d0b9db4',
|
|
|
|
+ # 'd3c9bbd98d07afb7be9fe8b1b40133d3']
|
|
|
|
+
|
|
|
|
+ if sig_lst is None:
|
|
|
|
+ # TODO 加入 logger
|
|
|
|
+ sys.exit(0)
|
|
|
|
+ if len(sig_lst) == 1:
|
|
|
|
+ # TODO 加入 logger
|
|
|
|
+ sys.exit(1)
|
|
|
|
+
|
|
|
|
+ # 2、构造特征
|
|
|
|
+ # 2-1 获取素材整体的特征情况:行为率、激活率、激活成本
|
|
|
|
+ sig_feature_df = get_signature_features(sig_lst, project_id)
|
|
|
|
+
|
|
|
|
+ # 2-2 获取各维度(age,gender)各分段(男、女等)的行为率、激活率、激活成本、激活占比,并进行纵向归一化
|
|
|
|
+ # get_segment_features(table, signature, dim_col, project_id)
|
|
|
|
+ table_dim_tuple = [('ctop_kuaishou_audience_report_daily_age_material', 'age_segment', 'age_'),
|
|
|
|
+ ('ctop_kuaishou_audience_report_daily_gender_material', 'gender', 'gender_')]
|
|
|
|
+
|
|
|
|
+ segment_feature_df = pd.DataFrame()
|
|
|
|
+ for table, dim_col, col_prefix in table_dim_tuple:
|
|
|
|
+ tmp_df = get_segment_features(table, sig_lst, dim_col, project_id, col_prefix)
|
|
|
|
+ segment_feature_df = pd.concat([segment_feature_df, tmp_df], axis=1)
|
|
|
|
+
|
|
|
|
+ # 2-3 素材整体的特征 和 各维度各分段的特征 进行合并,得到最终的特征DataFrame
|
|
|
|
+ final_feature_df = pd.concat([sig_feature_df, segment_feature_df], axis=1)
|
|
|
|
+ # 部分素材在 age 或者 gender 维度上没有数据,特征concat时,会导致空值
|
|
|
|
+ # 去掉这部分的素材,防止在调用 NearestNeighbors 时,报错
|
|
|
|
+ null_df = final_feature_df.isnull().sum(axis=1)
|
|
|
|
+ exist_null_fea_sig_lst = null_df[null_df >= 1].index
|
|
|
|
+ # TODO 添加日志 记录存在数据缺失的素材
|
|
|
|
+ if len(exist_null_fea_sig_lst) > 0:
|
|
|
|
+ print(exist_null_fea_sig_lst)
|
|
|
|
+
|
|
|
|
+ final_feature_df = final_feature_df[~final_feature_df.index.isin(exist_null_fea_sig_lst)]
|
|
|
|
+
|
|
|
|
+ with open('final_feature_df.pkl', 'wb') as f:
|
|
|
|
+ pickle.dump(final_feature_df, f)
|
|
|
|
+
|
|
|
|
+ # 3 Finding the Nearest Neighbors
|
|
|
|
+ k = config['nearestNeighbors']['k']
|
|
|
|
+ distance_threshold = config['nearestNeighbors']['distanceThreshold']
|
|
|
|
+ X = final_feature_df.values
|
|
|
|
+ nbrs = NearestNeighbors(n_neighbors=k, algorithm='ball_tree').fit(X)
|
|
|
|
+ distances, indices = nbrs.kneighbors(X)
|
|
|
|
+
|
|
|
|
+ with open('distances.pkl', 'wb') as f:
|
|
|
|
+ pickle.dump(distances, f)
|
|
|
|
+
|
|
|
|
+ with open('indices.pkl', 'wb') as f:
|
|
|
|
+ pickle.dump(indices, f)
|
|
|
|
+
|
|
|
|
+ # 3-1 两点之间的距离超过阈值时,不作为相邻素材
|
|
|
|
+ # mask 中,为 True 的元素替换为 NaN
|
|
|
|
+ mask = distances > distance_threshold
|
|
|
|
+ indices_mask_df = pd.DataFrame(indices).mask(mask)
|
|
|
|
+ indices_mask_df = indices_mask_df.astype(dtype=pd.Int64Dtype())
|
|
|
|
+
|
|
|
|
+ # 3-2 把 index 替换为具体的 signatures
|
|
|
|
+ sig_lst = final_feature_df.index.values
|
|
|
|
+ indices_mask_df.index = sig_lst
|
|
|
|
+
|
|
|
|
+ indices_mask_df = indices_mask_df.applymap(lambda x: sig_lst[x] if not pd.isnull(x) else x)
|
|
|
|
+ res_lst = []
|
|
|
|
+ for index, row in indices_mask_df.iterrows():
|
|
|
|
+ others = [item for item in row if (not pd.isnull(item)) and (item != index)]
|
|
|
|
+ res_lst.append([index] + others)
|
|
|
|
+
|
|
|
|
+ res_df = pd.DataFrame(res_lst)
|
|
|
|
+ res_df.columns = ['self'] + ['N' + str(i + 1) for i in range(res_df.shape[1] - 1)]
|
|
|
|
+ columns = ['self'] + ['N' + str(i + 1) for i in range(k)]
|
|
|
|
+ res_df = res_df.reindex(columns=columns)
|
|
|
|
+
|
|
|
|
+ with open('res_df.pkl', 'wb') as f:
|
|
|
|
+ pickle.dump(res_df, f)
|
|
|
|
+
|
|
|
|
+ # 4 TODO 结果入库
|
|
|
|
+ pass
|