Merge branch 'master' of git.wanmeizhensuo.com:ML/ffm-baseline

verison 1.0
s Please enter a commit message to explain why this merge is necessary,

eda/ml_tools/rate.csv

-date,answer_imp_all,answer_imp_ios,answer_imp_android,diary_imp_all,diary_imp_ios,diary_imp_android,activate_uid_ctr_all,activate_uid_ctr_ios,activate_uid_ctr_android,activate_uid_ave_imp_all,activate_uid_ave_imp_beijing,click_answer_uid_all,click_answer_uid_ios,click_answer_uid_android,click_diary_uid_all,click_diary_uid_ios,click_diary_uid_android,click_one_uid_all,click_one_uid_ios,click_one_uid_android,question_imp_all,question_imp_ios,question_imp_android,click_question_uid_all,click_question_uid_ios,click_question_uid_android
-20180817,0.0401,0.0569,0.0336,0.7272,0.8801,0.6678,0.0403,0.0624,0.0269,59.93,92.74,0.0189,0.0178,0.02,0.1094,0.1391,0.0852,0.1242,0.1537,0.1
-20180818,0.0383,0.0526,0.0331,0.7134,0.8665,0.658,0.0414,0.065,0.0267,57.73,78.98,0.0153,0.0167,0.0139,0.1052,0.1397,0.0786,0.1227,0.1572,0.0972
-20180819,0.0393,0.0538,0.0337,0.7211,0.8763,0.6605,0.0468,0.0726,0.0293,51.29,73.27,0.0175,0.0212,0.0136,0.1115,0.1442,0.085,0.1283,0.1598,0.1027
-20180820,0.0374,0.0504,0.032,0.7443,0.8829,0.6866,0.0449,0.068,0.0281,55.88,84.81,0.0157,0.0192,0.0118,0.1142,0.149,0.0846,0.1284,0.1641,0.0981
-20180821,0.0376,0.0509,0.0322,0.7392,0.8783,0.6831,0.0429,0.0658,0.0274,58.85,90.43,0.0174,0.0185,0.0162,0.1162,0.1551,0.0846,0.1316,0.1709,0.0998
-20180822,0.028,0.0391,0.0226,0.7481,0.8792,0.6837,0.0426,0.0614,0.0267,59.29,80.53,0.0155,0.0151,0.0162,0.1212,0.1513,0.0899,0.1363,0.1659,0.1056,0.0223,0.0267,0.0201,0.0714,0.1077,0.0459
-20180823,0.0134,0.0244,0.008,0.7531,0.8862,0.6873,0.0439,0.0664,0.0262,56.91,80.93,0.0154,0.0153,0.0156,0.1277,0.1577,0.0963,0.1447,0.175,0.113,0.0368,0.0412,0.0347,0.0709,0.1053,0.0458
-20180824,0.0145,0.0249,0.0092,0.7507,0.8864,0.6816,0.0457,0.0673,0.0285,56.84,92.03,0.0145,0.0147,0.0141,0.1228,0.1477,0.0943,0.1382,0.1624,0.1106,0.0352,0.0371,0.0342,0.0554,0.0718,0.0422
-20180825,0.0145,0.0272,0.0086,0.7412,0.8786,0.6785,0.0458,0.0707,0.0282,58.76,67.86,0.017,0.016,0.0194,0.1216,0.1483,0.0935,0.1374,0.1627,0.1108,0.0345,0.0363,0.0338,0.0491,0.0682,0.0354
-20180826,0.0141,0.0251,0.0084,0.7492,0.8875,0.6772,0.0488,0.0698,0.0296,52.71,72.48,0.016,0.0142,0.0212,0.1214,0.1459,0.0922,0.1386,0.1625,0.1101,0.0342,0.0362,0.0331,0.0736,0.1039,0.0484
-20180827,0.0152,0.0267,0.0096,0.7346,0.8691,0.6696,0.0472,0.0682,0.0293,53.8,85.28,0.0129,0.0134,0.0117,0.1214,0.1493,0.0921,0.1398,0.1684,0.1098,0.0396,0.0463,0.0364,0.0705,0.11,0.043

eda/recommended_indexs/main.py

@@ -128,16 +128,19 @@ def result2file():
 		tplt = "{0:\u3000<6}\t{1:\u3000<15}\t{2:\u3000<15}\t{3:\u3000<15}\n"
 		line = """数据日期：{}
 内容概览：以下所有数据都是昨天一天的首页的
+说明：
+	(1)红色标记的为比较重要的特征
+	(2)[A,+B]格式说明：A表示该特征在当天的数值，+B/-B表示该数值相对于昨天的差值
 1. 比例特征
-	1.0 question曝光占比(=question被曝光数/总cid被曝光数)
-	1.1 answer曝光占比(=answer被曝光数/总cid被曝光数)
-	1.2 diary曝光占比(=diary被曝光数/总cid被曝光数)
-	1.3 活跃用户点击率(=有点击用户点击次数/有点击用户曝光次数)
-	1.4 活跃用户平均每天曝光次数(=活跃用户曝光次数/独立活跃用户数)
-	1.5 点击answer用户占比(=点击answer用户数/曝光answer用户数)
-	1.6 点击question用户占比(=点击question用户数/曝光question用户数)
-	1.7 点击diary用户占比(=点击diary用户数/曝光diary用户数)
-	1.8 有点击用户占比(=有点击用户数/有曝光用户数)
+	1.0 question曝光占比(=question被曝光数/总cid被曝光数) [,]
+	1.1 answer曝光占比(=answer被曝光数/总cid被曝光数) [,]
+	1.2 diary曝光占比(=diary被曝光数/总cid被曝光数) [,]
+	1.3 活跃用户点击率(=有点击用户点击次数/有点击用户曝光次数) [,]
+	1.4 活跃用户平均每天曝光次数(=活跃用户曝光次数/独立活跃用户数) [,]
+	1.5 点击answer用户占比(=点击answer用户数/曝光answer用户数) [,]
+	1.6 点击question用户占比(=点击question用户数/曝光question用户数) [,]
+	1.7 点击diary用户占比(=点击diary用户数/曝光diary用户数) [,]
+	1.8 有点击用户占比(=有点击用户数/有曝光用户数) [,]
 2.Top特征
 	2.1 用户点击次数分布(第一列：用户点击次数；第二列：独立用户数量)
 	2.2 Top 100 diary (sorted by ctr)