1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
# -*- coding:UTF-8 -*-
# @Time : 2020/11/6 10:00
# @File : recommend_strategy_fix.py
# @email : litao@igengmei.com
# @author : litao
import hashlib
import json
import pymysql
import xlwt, datetime
# import redis
# from pyhive import hive
# from maintenance.func_send_email_with_file import send_file_email
# from typing import Dict, List
# from elasticsearch_7 import Elasticsearch
# from elasticsearch_7.helpers import scan
# import sys
import time
from pyspark import SparkConf
from pyspark.sql import SparkSession, DataFrame
# from pyspark.sql.functions import lit
# import pytispark.pytispark as pti
db = pymysql.connect(host='172.16.50.175', port=3306, user='doris', passwd='o5gbA27hXHHm',
db='doris_olap')
cursor = db.cursor()
def con_sql(sql):
# 从数据库的表里获取数据
db = pymysql.connect(host='172.16.50.175', port=3306, user='doris', passwd='o5gbA27hXHHm',
db='doris_olap')
cursor = db.cursor()
cursor.execute(sql)
result = cursor.fetchall()
db.close()
return result
startTime = time.time()
sparkConf = SparkConf()
sparkConf.set("spark.sql.crossJoin.enabled", True)
sparkConf.set("spark.debug.maxToStringFields", "100")
# sparkConf.set("spark.tispark.plan.allow_index_double_read", False)
# sparkConf.set("spark.tispark.plan.allow_index_read", True)
sparkConf.set("spark.hive.mapred.supports.subdirectories", True)
sparkConf.set("spark.hadoop.mapreduce.input.fileinputformat.input.dir.recursive", True)
sparkConf.set("spark.serializer", "org.apache.spark.serializer.KryoSerializer")
# sparkConf.set("mapreduce.output.fileoutputformat.compress", False)
# sparkConf.set("mapreduce.map.output.compress", False)
sparkConf.set("prod.gold.jdbcuri",
"jdbc:mysql://172.16.30.136/doris_prod?user=doris&password=o5gbA27hXHHm&rewriteBatchedStatements=true")
sparkConf.set("prod.mimas.jdbcuri",
"jdbc:mysql://172.16.30.138/mimas_prod?user=mimas&password=GJL3UJe1Ck9ggL6aKnZCq4cRvM&rewriteBatchedStatements=true")
sparkConf.set("prod.gaia.jdbcuri",
"jdbc:mysql://172.16.30.143/zhengxing?user=work&password=BJQaT9VzDcuPBqkd&rewriteBatchedStatements=true")
sparkConf.set("prod.tidb.jdbcuri",
"jdbc:mysql://172.16.40.158:4000/eagle?user=st_user&password=aqpuBLYzEV7tML5RPsN1pntUzFy&rewriteBatchedStatements=true")
# sparkConf.set("prod.jerry.jdbcuri",
# "jdbc:mysql://172.16.40.158:4000/jerry_prod?user=st_user&password=aqpuBLYzEV7tML5RPsN1pntUzFy&rewriteBatchedStatements=true")
# sparkConf.set("prod.tispark.pd.addresses", "172.16.40.158:2379")
# sparkConf.set("prod.tispark.pd.addresses", "172.16.40.170:4000")
# sparkConf.set("prod.tidb.database", "jerry_prod")
spark = (SparkSession.builder.config(conf=sparkConf).appName(
"recommend_strategy_fix").enableHiveSupport().getOrCreate())
spark.sql("ADD JAR hdfs:///user/hive/share/lib/udf/brickhouse-0.7.1-SNAPSHOT.jar")
spark.sql("ADD JAR hdfs:///user/hive/share/lib/udf/hive-udf-1.0-SNAPSHOT.jar")
spark.sql("CREATE TEMPORARY FUNCTION json_map AS 'brickhouse.udf.json.JsonMapUDF'")
spark.sql("CREATE TEMPORARY FUNCTION is_json AS 'com.gmei.hive.common.udf.UDFJsonFormatCheck'")
spark.sql("CREATE TEMPORARY FUNCTION arrayMerge AS 'com.gmei.hive.common.udf.UDFArryMerge'")
for t in range(0, 3):
day_num = 0 - t
now = (datetime.datetime.now() + datetime.timedelta(days=day_num))
last_30_day_str = (now + datetime.timedelta(days=-30)).strftime("%Y%m%d")
today_str = now.strftime("%Y%m%d")
yesterday_str = (now + datetime.timedelta(days=-1)).strftime("%Y%m%d")
one_week_age_str = (now + datetime.timedelta(days=-7)).strftime("%Y%m%d")
ctr_sql = """
SELECT
t1.partition_date as day_id,
t1.device_os_type as device_os_type,
t1.active_type as active_type,
t2.card_content_type as card_content_type,
t2.recommend_type as recommend_type,
NVL(sum(t3.session_pv),0) as card_click,
NVL(sum(t2.session_pv),0) as card_exposure,
NVL(round(sum(page_stay)/count(distinct t4.cl_id)/60,2),0) as avg_page_stay,
NVL(sum(t4_pv.pv),0) as page_pv,
NVL(sum(t4_pv.pv_20),0) as page_pv_20,
NVL(sum(navbar_pv),0) as navbar_search,
NVL(sum(highlight_pv),0) as highlight_word,
NVL(sum(self_wel_pv),0) as self_welfare_card,
NVL(sum(recom_wel_pv),0)-NVL(sum(self_wel_pv),0) as recommend_welfare_card,--需要排除关联的商品卡片点击
NVL(sum(recom_content_pv),0) as recommend_content_card,
NULL as recommend_special_card,
NVL(sum(referral_pv),0) as transfer_card,
NVL(sum(video_pv),0) as video_consultation,
NVL(sum(post_pv),0) as total_post_pv,
NVL(sum(post_click_pv),0) as post_click_pv
FROM
(
SELECT partition_date
,device_os_type
,CASE WHEN active_type = '4' THEN '老活'
WHEN active_type IN ('1','2') THEN '新增' END AS active_type
,device_id
FROM online.ml_device_day_active_status
WHERE partition_date={partition_day}
AND active_type IN ('1','2','4')
AND first_channel_source_type not IN ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei')
AND first_channel_source_type not LIKE 'promotion\_jf\_%'
)t1 JOIN
(--卡片，卡片id和session_id去重
SELECT partition_date,
cl_id
from
( SELECT partition_date,
cl_id,
count(distinct app_session_id) as session_pv0
FROM
(
SELECT partition_date,
cl_id,
case when params['card_content_type'] in ('qa','answer') then 'qa'
when params['card_content_type'] in ('special_pool') then 'special' else params['card_content_type'] end as card_content_type,
CASE when params['transaction_type'] in ('fmctr','samecity_fmctr') then array('fmctr','合计')
when params['transaction_type'] in ('high_quality_fmctr') then array('high_quality_fmctr','合计')
WHEN (params['transaction_type'] like '%ctr' and params['transaction_type'] not in ('high_quality_ctr','high_quality_fmctr','fmctr','samecity_fmctr')) THEN array('ctr预估','合计')
when params['transaction_type'] in ('high_quality_ctr') then array('high_quality_ctr','合计')
WHEN params['transaction_type'] like '%cvr' THEN array('cvr预估','合计')
WHEN params['transaction_type'] in ('-1','smr') THEN array('smr','合计')
when params['transaction_type'] in ('pgc','hotspot') then array('热点卡片')
when params['transaction_type'] in ('newdata') then array('保量卡片')
when params['transaction_type'] in ('hotspot_feed') then array('hotspot_feed','合计')
when params['transaction_type'] in ('aistragegy') then array('新用户AI帖优先','合计')
when params['transaction_type'] in ('excestragegy') then array('新用户精华帖优先','合计')
when params['transaction_type'] in ('FIXEDSTRATEGY') then array('新氧新用户策略一','合计')
when params['transaction_type'] in ('FIXEDSTRATEGY_VIDEO') then array('新氧新用户策略二','合计')
when params['transaction_type'] like 'deeplink%' then array('deeplink策略','合计')
end AS recommend_type,
params['card_id'] as card_id,
app_session_id
from online.bl_hdfs_maidian_updates
WHERE partition_date={partition_day}
AND action='on_click_card'
AND params['page_name'] ='home'
AND params['tab_name'] = '精选'
AND (params['transaction_type'] in ('-1','smr','hotspot','pgc','newdata','hotspot_feed','aistragegy','excestragegy','FIXEDSTRATEGY','FIXEDSTRATEGY_VIDEO')
or params['transaction_type'] like '%ctr' or params['transaction_type'] like '%cvr' or params['transaction_type'] like 'deeplink%')
AND params['card_content_type'] in ('qa','diary','user_post','answer','special_pool')
GROUP BY partition_date,
cl_id,
case when params['card_content_type'] in ('qa','answer') then 'qa'
when params['card_content_type'] in ('special_pool') then 'special' else params['card_content_type'] end,
CASE when params['transaction_type'] in ('fmctr','samecity_fmctr') then array('fmctr','合计')
when params['transaction_type'] in ('high_quality_fmctr') then array('high_quality_fmctr','合计')
WHEN (params['transaction_type'] like '%ctr' and params['transaction_type'] not in ('high_quality_ctr','high_quality_fmctr','fmctr','samecity_fmctr')) THEN array('ctr预估','合计')
when params['transaction_type'] in ('high_quality_ctr') then array('high_quality_ctr','合计')
WHEN params['transaction_type'] like '%cvr' THEN array('cvr预估','合计')
WHEN params['transaction_type'] in ('-1','smr') THEN array('smr','合计')
when params['transaction_type'] in ('pgc','hotspot') then array('热点卡片')
when params['transaction_type'] in ('newdata') then array('保量卡片')
when params['transaction_type'] in ('hotspot_feed') then array('hotspot_feed','合计')
when params['transaction_type'] in ('aistragegy') then array('新用户AI帖优先','合计')
when params['transaction_type'] in ('excestragegy') then array('新用户精华帖优先','合计')
when params['transaction_type'] in ('FIXEDSTRATEGY') then array('新氧新用户策略一','合计')
when params['transaction_type'] in ('FIXEDSTRATEGY_VIDEO') then array('新氧新用户策略二','合计')
when params['transaction_type'] like 'deeplink%' then array('deeplink策略','合计') end,
params['card_id'],
app_session_id
)a
LATERAL VIEW explode (a.recommend_type) v as recommend_type
group by partition_date,card_content_type,cl_id,v.recommend_type,card_id having session_pv0 >0
UNION
SELECT partition_date,
cl_id,
count(distinct card_id) as session_pv0
FROM
(SELECT partition_date,
cl_id,
case when card_content_type in ('qa','answer') then 'qa'
when card_content_type in ('special_pool') then 'special' else card_content_type end as card_content_type,
CASE when transaction_type in ('fmctr','samecity_fmctr') then array('fmctr','合计')
when transaction_type in ('high_quality_fmctr') then array('high_quality_fmctr','合计')
WHEN (transaction_type like '%ctr' and transaction_type not in ('high_quality_ctr','high_quality_fmctr','fmctr','samecity_fmctr') ) THEN array('ctr预估','合计')
when transaction_type in ('high_quality_ctr') then array('high_quality_ctr','合计')
WHEN transaction_type like '%cvr' THEN array('cvr预估','合计')
WHEN transaction_type in ('-1','smr') THEN array('smr','合计')
when transaction_type in ('pgc','hotspot') then array('热点卡片')
when transaction_type in ('newdata') then array('保量卡片')
when transaction_type in ('hotspot_feed') then array('hotspot_feed','合计')
when transaction_type in ('aistragegy') then array('新用户AI帖优先','合计')
when transaction_type in ('excestragegy') then array('新用户精华帖优先','合计')
when transaction_type in ('FIXEDSTRATEGY') then array('新氧新用户策略一','合计')
when transaction_type in ('FIXEDSTRATEGY_VIDEO') then array('新氧新用户策略二','合计')
when transaction_type like 'deeplink%' then array('deeplink策略','合计')
end AS recommend_type,
card_id,
app_session_id
from online.ml_community_precise_exposure_detail
WHERE partition_date={partition_day}
AND action in ('page_precise_exposure','home_choiceness_card_exposure') --7745版本action改为page_precise_exposure
AND is_exposure = '1' ----精准曝光
AND page_name ='home'
AND tab_name = '精选'
AND (transaction_type in ('-1','smr','hotspot','pgc','newdata','hotspot_feed','aistragegy','excestragegy','FIXEDSTRATEGY','FIXEDSTRATEGY_VIDEO')
or transaction_type like '%ctr' or transaction_type like '%cvr' or transaction_type like 'deeplink%')
AND card_content_type in ('qa','diary','user_post','answer','special_pool')
group by partition_date,
case when card_content_type in ('qa','answer') then 'qa'
when card_content_type in ('special_pool') then 'special' else card_content_type end,
cl_id,
CASE when transaction_type in ('fmctr','samecity_fmctr') then array('fmctr','合计')
when transaction_type in ('high_quality_fmctr') then array('high_quality_fmctr','合计')
WHEN (transaction_type like '%ctr' and transaction_type not in ('high_quality_ctr','high_quality_fmctr','fmctr','samecity_fmctr')) THEN array('ctr预估','合计')
when transaction_type in ('high_quality_ctr') then array('high_quality_ctr','合计')
WHEN transaction_type like '%cvr' THEN array('cvr预估','合计')
WHEN transaction_type in ('-1','smr') THEN array('smr','合计')
when transaction_type in ('pgc','hotspot') then array('热点卡片')
when transaction_type in ('newdata') then array('保量卡片')
when transaction_type in ('hotspot_feed') then array('hotspot_feed','合计')
when transaction_type in ('aistragegy') then array('新用户AI帖优先','合计')
when transaction_type in ('excestragegy') then array('新用户精华帖优先','合计')
when transaction_type in ('FIXEDSTRATEGY') then array('新氧新用户策略一','合计')
when transaction_type in ('FIXEDSTRATEGY_VIDEO') then array('新氧新用户策略二','合计')
when transaction_type like 'deeplink%' then array('deeplink策略','合计') end,
card_id,
app_session_id
)a
LATERAL VIEW explode (a.recommend_type) v as recommend_type
group by partition_date,cl_id having session_pv0 >= 4) group by partition_date,cl_id
) t0 on t1.device_id = t0.cl_id
LEFT JOIN
(--精准曝光，卡片id和session_id去重
SELECT partition_date,
card_content_type,
cl_id,
v.recommend_type,
card_id,
count(distinct app_session_id) as session_pv
FROM
(
SELECT partition_date,
cl_id,
case when card_content_type in ('qa','answer') then 'qa'
when card_content_type in ('special_pool') then 'special' else card_content_type end as card_content_type,
CASE when transaction_type in ('fmctr','samecity_fmctr') then array('fmctr','合计')
when transaction_type in ('high_quality_fmctr') then array('high_quality_fmctr','合计')
WHEN (transaction_type like '%ctr' and transaction_type not in ('high_quality_ctr','high_quality_fmctr','fmctr','samecity_fmctr') ) THEN array('ctr预估','合计')
when transaction_type in ('high_quality_ctr') then array('high_quality_ctr','合计')
WHEN transaction_type like '%cvr' THEN array('cvr预估','合计')
WHEN transaction_type in ('-1','smr') THEN array('smr','合计')
when transaction_type in ('pgc','hotspot') then array('热点卡片')
when transaction_type in ('newdata') then array('保量卡片')
when transaction_type in ('hotspot_feed') then array('hotspot_feed','合计')
when transaction_type in ('aistragegy') then array('新用户AI帖优先','合计')
when transaction_type in ('excestragegy') then array('新用户精华帖优先','合计')
when transaction_type in ('FIXEDSTRATEGY') then array('新氧新用户策略一','合计')
when transaction_type in ('FIXEDSTRATEGY_VIDEO') then array('新氧新用户策略二','合计')
when transaction_type like 'deeplink%' then array('deeplink策略','合计')
end AS recommend_type,
card_id,
app_session_id
from online.ml_community_precise_exposure_detail
WHERE partition_date={partition_day}
AND action in ('page_precise_exposure','home_choiceness_card_exposure') --7745版本action改为page_precise_exposure
AND is_exposure = '1' ----精准曝光
AND page_name ='home'
AND tab_name = '精选'
AND (transaction_type in ('-1','smr','hotspot','pgc','newdata','hotspot_feed','aistragegy','excestragegy','FIXEDSTRATEGY','FIXEDSTRATEGY_VIDEO')
or transaction_type like '%ctr' or transaction_type like '%cvr' or transaction_type like 'deeplink%')
AND card_content_type in ('qa','diary','user_post','answer','special_pool')
group by partition_date,
case when card_content_type in ('qa','answer') then 'qa'
when card_content_type in ('special_pool') then 'special' else card_content_type end,
cl_id,
CASE when transaction_type in ('fmctr','samecity_fmctr') then array('fmctr','合计')
when transaction_type in ('high_quality_fmctr') then array('high_quality_fmctr','合计')
WHEN (transaction_type like '%ctr' and transaction_type not in ('high_quality_ctr','high_quality_fmctr','fmctr','samecity_fmctr')) THEN array('ctr预估','合计')
when transaction_type in ('high_quality_ctr') then array('high_quality_ctr','合计')
WHEN transaction_type like '%cvr' THEN array('cvr预估','合计')
WHEN transaction_type in ('-1','smr') THEN array('smr','合计')
when transaction_type in ('pgc','hotspot') then array('热点卡片')
when transaction_type in ('newdata') then array('保量卡片')
when transaction_type in ('hotspot_feed') then array('hotspot_feed','合计')
when transaction_type in ('aistragegy') then array('新用户AI帖优先','合计')
when transaction_type in ('excestragegy') then array('新用户精华帖优先','合计')
when transaction_type in ('FIXEDSTRATEGY') then array('新氧新用户策略一','合计')
when transaction_type in ('FIXEDSTRATEGY_VIDEO') then array('新氧新用户策略二','合计')
when transaction_type like 'deeplink%' then array('deeplink策略','合计') end,
card_id,
app_session_id
)a
LATERAL VIEW explode (a.recommend_type) v as recommend_type
group by partition_date,card_content_type,cl_id,v.recommend_type,card_id
)t2
on t0.cl_id=t2.cl_id and t0.partition_date=t2.partition_date
LEFT JOIN
(--卡片，卡片id和session_id去重
SELECT partition_date,
card_content_type,
cl_id,
v.recommend_type,
card_id,
count(distinct app_session_id) as session_pv
FROM
(
SELECT partition_date,
cl_id,
case when params['card_content_type'] in ('qa','answer') then 'qa'
when params['card_content_type'] in ('special_pool') then 'special' else params['card_content_type'] end as card_content_type,
CASE when params['transaction_type'] in ('fmctr','samecity_fmctr') then array('fmctr','合计')
when params['transaction_type'] in ('high_quality_fmctr') then array('high_quality_fmctr','合计')
WHEN (params['transaction_type'] like '%ctr' and params['transaction_type'] not in ('high_quality_ctr','high_quality_fmctr','fmctr','samecity_fmctr')) THEN array('ctr预估','合计')
when params['transaction_type'] in ('high_quality_ctr') then array('high_quality_ctr','合计')
WHEN params['transaction_type'] like '%cvr' THEN array('cvr预估','合计')
WHEN params['transaction_type'] in ('-1','smr') THEN array('smr','合计')
when params['transaction_type'] in ('pgc','hotspot') then array('热点卡片')
when params['transaction_type'] in ('newdata') then array('保量卡片')
when params['transaction_type'] in ('hotspot_feed') then array('hotspot_feed','合计')
when params['transaction_type'] in ('aistragegy') then array('新用户AI帖优先','合计')
when params['transaction_type'] in ('excestragegy') then array('新用户精华帖优先','合计')
when params['transaction_type'] in ('FIXEDSTRATEGY') then array('新氧新用户策略一','合计')
when params['transaction_type'] in ('FIXEDSTRATEGY_VIDEO') then array('新氧新用户策略二','合计')
when params['transaction_type'] like 'deeplink%' then array('deeplink策略','合计')
end AS recommend_type,
params['card_id'] as card_id,
app_session_id
from online.bl_hdfs_maidian_updates
WHERE partition_date={partition_day}
AND action='on_click_card'
AND params['page_name'] ='home'
AND params['tab_name'] = '精选'
AND (params['transaction_type'] in ('-1','smr','hotspot','pgc','newdata','hotspot_feed','aistragegy','excestragegy','FIXEDSTRATEGY','FIXEDSTRATEGY_VIDEO')
or params['transaction_type'] like '%ctr' or params['transaction_type'] like '%cvr' or params['transaction_type'] like 'deeplink%')
AND params['card_content_type'] in ('qa','diary','user_post','answer','special_pool')
GROUP BY partition_date,
cl_id,
case when params['card_content_type'] in ('qa','answer') then 'qa'
when params['card_content_type'] in ('special_pool') then 'special' else params['card_content_type'] end,
CASE when params['transaction_type'] in ('fmctr','samecity_fmctr') then array('fmctr','合计')
when params['transaction_type'] in ('high_quality_fmctr') then array('high_quality_fmctr','合计')
WHEN (params['transaction_type'] like '%ctr' and params['transaction_type'] not in ('high_quality_ctr','high_quality_fmctr','fmctr','samecity_fmctr')) THEN array('ctr预估','合计')
when params['transaction_type'] in ('high_quality_ctr') then array('high_quality_ctr','合计')
WHEN params['transaction_type'] like '%cvr' THEN array('cvr预估','合计')
WHEN params['transaction_type'] in ('-1','smr') THEN array('smr','合计')
when params['transaction_type'] in ('pgc','hotspot') then array('热点卡片')
when params['transaction_type'] in ('newdata') then array('保量卡片')
when params['transaction_type'] in ('hotspot_feed') then array('hotspot_feed','合计')
when params['transaction_type'] in ('aistragegy') then array('新用户AI帖优先','合计')
when params['transaction_type'] in ('excestragegy') then array('新用户精华帖优先','合计')
when params['transaction_type'] in ('FIXEDSTRATEGY') then array('新氧新用户策略一','合计')
when params['transaction_type'] in ('FIXEDSTRATEGY_VIDEO') then array('新氧新用户策略二','合计')
when params['transaction_type'] like 'deeplink%' then array('deeplink策略','合计') end,
params['card_id'],
app_session_id
)a
LATERAL VIEW explode (a.recommend_type) v as recommend_type
group by partition_date,card_content_type,cl_id,v.recommend_type,card_id
)t3
on t2.partition_date=t3.partition_date
and t2.cl_id=t3.cl_id
and t2.card_id=t3.card_id
and t2.card_content_type=t3.card_content_type
and t2.recommend_type=t3.recommend_type
LEFT JOIN
(--页面浏览时长
select partition_date,cl_id,coalesce(b.id,a.business_id) as business_id,a.page_name
,sum(page_stay) as page_stay
from
(
SELECT partition_date,cl_id,business_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa'
when page_name in ('custom_special') then 'special' else null end as page_name,
page_stay,time_str
FROM online.bl_hdfs_maidian_updates
WHERE partition_date={partition_day}
AND action='page_view'
AND page_name IN ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail','custom_special')
AND referrer='home'
AND page_stay>=0 AND page_stay<1000
GROUP BY partition_date,cl_id,business_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa'
when page_name in ('custom_special') then 'special' else null end,page_stay,time_str
)a
left join
(
select id,visual_page_id,'special' as page_name
from tl.tl_zx_api_special_pool
where partition_day ={partition_day}
group by id,visual_page_id
)b
on a.business_id=b.visual_page_id and a.page_name=b.page_name
group by partition_date,cl_id,coalesce(b.id,a.business_id),a.page_name
)t4
on t4.partition_date=t3.partition_date
and t4.cl_id=t3.cl_id
and t4.business_id=t3.card_id
and t4.page_name=t3.card_content_type
LEFT JOIN
(--页面浏览时长
select partition_date,cl_id,coalesce(b.id,a.business_id) as business_id,a.page_name
,count(1) as pv
,count(case when page_stay>=20 then 1 end) as pv_20
from
(
SELECT partition_date,cl_id,business_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa'
when page_name in ('custom_special') then 'special' else null end as page_name,time_str,page_stay
FROM online.bl_hdfs_maidian_updates
WHERE partition_date={partition_day}
AND action='page_view'
AND page_name IN ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail','custom_special')
AND referrer='home'
GROUP BY partition_date,cl_id,business_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa'
when page_name in ('custom_special') then 'special' else null end,time_str,page_stay
)a
left join
(--在8月份新增了内容专题卡片，需要转换下id
select id,visual_page_id,'special' as page_name
from tl.tl_zx_api_special_pool
where partition_day ={partition_day}
group by id,visual_page_id
)b
on a.business_id=b.visual_page_id and a.page_name=b.page_name
group by partition_date,cl_id,coalesce(b.id,a.business_id),a.page_name
)t4_pv
on t4_pv.partition_date=t3.partition_date
and t4_pv.cl_id=t3.cl_id
and t4_pv.business_id=t3.card_id
and t4_pv.page_name=t3.card_content_type
LEFT JOIN
(--搜索框和点击行为
select partition_date,cl_id,coalesce(b.id,a.business_id) as business_id,a.page_name,navbar_pv
from
(
SELECT partition_date,cl_id,business_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa'
when page_name in ('custom_special') then 'special' else null end as page_name,
count(1) as navbar_pv
FROM online.bl_hdfs_maidian_updates
WHERE partition_date={partition_day}
AND action in ('on_click_navbar_search','do_search')
AND page_name IN ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail','custom_special')
AND (referrer='home' or
(params['referrer_link'] like '%[%' and
json_split(params['referrer_link'])[size(json_split(params['referrer_link']))-1]='home'))
group by partition_date,cl_id,business_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa'
when page_name in ('custom_special') then 'special' else null end
)a
left join
(
select id,visual_page_id,'special' as page_name
from tl.tl_zx_api_special_pool
where partition_day ={partition_day}
group by id,visual_page_id
)b
on a.business_id=b.visual_page_id and a.page_name=b.page_name
)t5
on t5.partition_date=t3.partition_date
and t5.cl_id=t3.cl_id
and t5.business_id=t3.card_id
and t5.page_name=t3.card_content_type
LEFT JOIN
(--点击高亮词
select partition_date,cl_id,coalesce(b.id,a.business_id) as business_id,a.page_name,highlight_pv
from
(
SELECT partition_date,cl_id,business_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa'
when page_name in ('custom_special') then 'special' else null end as page_name,
count(1) as highlight_pv
FROM online.bl_hdfs_maidian_updates
WHERE partition_date={partition_day}
AND action='on_click_card'
and params['card_type']='highlight_word'
AND page_name IN ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail','custom_special')
AND (referrer='home' or
(params['referrer_link'] like '%[%' and
json_split(params['referrer_link'])[size(json_split(params['referrer_link']))-1]='home'))
group by partition_date,cl_id,business_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa'
when page_name in ('custom_special') then 'special' else null end
)a
left join
(
select id,visual_page_id,'special' as page_name
from tl.tl_zx_api_special_pool
where partition_day ={partition_day}
group by id,visual_page_id
)b
on a.business_id=b.visual_page_id and a.page_name=b.page_name
)t6
on t6.partition_date=t3.partition_date
and t6.cl_id=t3.cl_id
and t6.business_id=t3.card_id
and t6.page_name=t3.card_content_type
LEFT JOIN
(--关联的美购卡片
SELECT partition_date,cl_id,coalesce(b.id,a.business_id) as business_id,a.page_name,count(1) as self_wel_pv
FROM
(
SELECT partition_date,cl_id,business_id,app_session_id,params['card_id'] as card_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa'
when page_name in ('custom_special') then 'special' else null end as page_name,
count(1) as pv
FROM online.bl_hdfs_maidian_updates
WHERE partition_date={partition_day}
AND (get_json_object(params['extra_param'], '$.type')='交互栏'
or get_json_object(params['extra_param'], '$.jump_from')='msg_link'
or params['in_page_pos']='top'
or (params['in_page_pos']='bottom' and params['position'] is null and cl_type='android')
or (params['in_page_pos']='bottom' and params['card_but_pos'] is not null and cl_type='ios'))
AND action='on_click_card'
and params['card_content_type']='service'
AND page_name IN ('diary_detail','topic_detail')
AND (referrer='home' or
(params['referrer_link'] like '%[%' and
json_split(params['referrer_link'])[size(json_split(params['referrer_link']))-1]='home'))
group by partition_date,cl_id,business_id,app_session_id,params['card_id'],
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa'
when page_name in ('custom_special') then 'special' else null end
)a
left join
(
select id,visual_page_id,'special' as page_name
from tl.tl_zx_api_special_pool
where partition_day ={partition_day}
group by id,visual_page_id
)b
on a.business_id=b.visual_page_id and a.page_name=b.page_name
group by partition_date,cl_id,coalesce(b.id,a.business_id),a.page_name
)t7
on t7.partition_date=t3.partition_date
and t7.cl_id=t3.cl_id
and t7.business_id=t3.card_id
and t7.page_name=t3.card_content_type
LEFT JOIN
(--推荐的美购卡片(需要排除作者消费的美购)
SELECT partition_date,cl_id,coalesce(b.id,a.business_id) as business_id,a.page_name,count(1) as recom_wel_pv
FROM
(
SELECT partition_date,cl_id,business_id,app_session_id,params['card_id'] as card_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa'
when page_name in ('custom_special') then 'special' else null end as page_name,
count(1) as service_pv
FROM online.bl_hdfs_maidian_updates
WHERE partition_date={partition_day}
AND (action='on_click_card'and params['card_content_type']='service'
or action='on_click_button' and params['button_name']='unfold' and page_name in ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail')
or action='on_click_button' and params['button_name'] = 'more_recommendations')
AND page_name IN ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail','custom_special')
AND (referrer='home' or
(params['referrer_link'] like '%[%' and
json_split(params['referrer_link'])[size(json_split(params['referrer_link']))-1]='home'))
group by partition_date,cl_id,business_id,app_session_id,params['card_id'],
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa'
when page_name in ('custom_special') then 'special' else null end
)a
left join
(
select id,visual_page_id,'special' as page_name
from tl.tl_zx_api_special_pool
where partition_day ={partition_day}
group by id,visual_page_id
)b
on a.business_id=b.visual_page_id and a.page_name=b.page_name
group by partition_date,cl_id,coalesce(b.id,a.business_id),a.page_name
)t8
on t8.partition_date=t3.partition_date
and t8.cl_id=t3.cl_id
and t8.business_id=t3.card_id
and t8.page_name=t3.card_content_type
LEFT JOIN
(--推荐的内容卡片
SELECT partition_date,cl_id,coalesce(b.id,a.business_id) as business_id,a.page_name,count(1) as recom_content_pv
FROM
(
SELECT partition_date,cl_id,business_id,app_session_id,params['card_id'] as card_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa'
when page_name in ('custom_special') then 'special' else null end as page_name,
count(1) as service_pv
FROM online.bl_hdfs_maidian_updates
WHERE partition_date={partition_day}
AND action='on_click_card'
and params['card_content_type'] in ('qa','diary','user_post','answer')
AND page_name IN ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail','custom_special')
AND (referrer='home' or
(params['referrer_link'] like '%[%' and
json_split(params['referrer_link'])[size(json_split(params['referrer_link']))-1]='home'))
group by partition_date,cl_id,business_id,app_session_id,params['card_id'],
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa'
when page_name in ('custom_special') then 'special' else null end
)a
left join
(
select id,visual_page_id,'special' as page_name
from tl.tl_zx_api_special_pool
where partition_day ={partition_day}
group by id,visual_page_id
)b
on a.business_id=b.visual_page_id and a.page_name=b.page_name
group by partition_date,cl_id,coalesce(b.id,a.business_id),a.page_name
)t9
on t9.partition_date=t3.partition_date
and t9.cl_id=t3.cl_id
and t9.business_id=t3.card_id
and t9.page_name=t3.card_content_type
LEFT JOIN
(--视频面诊点击
select partition_date,cl_id,coalesce(b.id,a.business_id) as business_id,a.page_name,video_pv
from
(
SELECT partition_date,cl_id,business_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa'
when page_name in ('custom_special') then 'special' else null end as page_name,
count(1) as video_pv
FROM online.bl_hdfs_maidian_updates
WHERE partition_date={partition_day}
AND action='on_click_button'
and params['button_name']='video_interview'
AND page_name IN ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail','custom_special')
AND (referrer='home' or
(params['referrer_link'] like '%[%' and
json_split(params['referrer_link'])[size(json_split(params['referrer_link']))-1]='home'))
group by partition_date,cl_id,business_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa'
when page_name in ('custom_special') then 'special' else null end
)a
left join
(
select id,visual_page_id,'special' as page_name
from tl.tl_zx_api_special_pool
where partition_day ={partition_day}
group by id,visual_page_id
)b
on a.business_id=b.visual_page_id and a.page_name=b.page_name
)t10
on t10.partition_date=t3.partition_date
and t10.cl_id=t3.cl_id
and t10.business_id=t3.card_id
and t10.page_name=t3.card_content_type
LEFT JOIN
(--转诊按钮点击
select partition_date,cl_id,coalesce(b.id,a.business_id) as business_id,a.page_name,referral_pv
from
(
SELECT partition_date,cl_id,business_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa'
when page_name in ('custom_special') then 'special' else null end as page_name,
count(1) as referral_pv
FROM online.bl_hdfs_maidian_updates
WHERE partition_date={partition_day}
AND action='on_click_button'
and params['button_name']='referral'
AND page_name IN ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail','custom_special')
AND (referrer='home' or
(params['referrer_link'] like '%[%' and
json_split(params['referrer_link'])[size(json_split(params['referrer_link']))-1]='home'))
group by partition_date,cl_id,business_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa'
when page_name in ('custom_special') then 'special' else null end
)a
left join
(
select id,visual_page_id,'special' as page_name
from tl.tl_zx_api_special_pool
where partition_day ={partition_day}
group by id,visual_page_id
)b
on a.business_id=b.visual_page_id and a.page_name=b.page_name
)t11
on t11.partition_date=t3.partition_date
and t11.cl_id=t3.cl_id
and t11.business_id=t3.card_id
and t11.page_name=t3.card_content_type
LEFT JOIN
(--从帖子页到帖子页
SELECT partition_date,cl_id,params['referrer_id'] as business_id,
case when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
else null end as page_name,
count(distinct params['business_id'],app_session_id) as post_pv
FROM online.bl_hdfs_maidian_updates
WHERE partition_date={partition_day}
AND action='page_view'
AND page_name IN ('post_detail','user_post_detail','doctor_post_detail','custom_special')
AND (json_split(params['referrer_link'])[size(json_split(params['referrer_link']))-1]IN ('post_detail','user_post_detail','doctor_post_detail')
and json_split(params['referrer_link'])[size(json_split(params['referrer_link']))-2]='home')
group by partition_date,cl_id,params['referrer_id'],
case when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
else null end
)t12
on t12.partition_date=t3.partition_date
and t12.cl_id=t3.cl_id
and t12.business_id=t3.card_id
and t12.page_name=t3.card_content_type
left join
(--在帖子页点击帖子
SELECT partition_date,cl_id,params['business_id'] as business_id,
case when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
else null end as page_name,
count(distinct params['card_id'],app_session_id) as post_click_pv
FROM online.bl_hdfs_maidian_updates
WHERE partition_date={partition_day}
AND action='on_click_card'
and params['card_content_type'] in ('user_post')
AND page_name IN ('post_detail','user_post_detail','doctor_post_detail')
AND (referrer='home' or
(params['referrer_link'] like '%[%' and
json_split(params['referrer_link'])[size(json_split(params['referrer_link']))-1]='home'))
group by partition_date,cl_id,params['business_id'],
case when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
else null end
)t13
on t13.partition_date=t3.partition_date
and t13.cl_id=t3.cl_id
and t13.business_id=t3.card_id
and t13.page_name=t3.card_content_type
LEFT JOIN
(
select distinct device_id
from ML.ML_D_CT_DV_DEVICECLEAN_DIMEN_D
where PARTITION_DAY = '{partition_day}'
AND is_abnormal_device = 'true'
)dev
on t2.cl_id=dev.device_id
WHERE dev.device_id is null
GROUP BY t1.partition_date,t1.device_os_type,t1.active_type,t2.card_content_type,t2.recommend_type
order by day_id,device_os_type,active_type,card_content_type,recommend_type
""".format(partition_day=today_str)
ctr_df = spark.sql(ctr_sql)
ctr_df.createOrReplaceTempView("temp_ctr")
grey_select_sql = """SELECT *,
NVL(ROUND((navbar_search+highlight_word+self_welfare_card+recommend_welfare_card+recommend_content_card*0.2+transfer_card+video_consultation)/card_exposure,5),0) as recommend_ctr,
NVL(ROUND(card_click/card_exposure,5),0) as click_ctr,
NVL(ROUND((navbar_search+highlight_word+self_welfare_card+recommend_welfare_card+recommend_content_card*0.2+transfer_card+video_consultation)/card_click,5),0) as second_jump_ctr ,
NVL(ROUND(page_pv_20/page_pv,5),0) as page_pv_20_percent
FROM temp_ctr"""
device_df = spark.sql(grey_select_sql)
device_df.show(1, False)
sql_res = device_df.collect()
print("-----------------------------------------------------------------------------")
for res in sql_res:
print(res)
day_id = res.day_id
device_os_type = res.device_os_type
active_type = res.active_type
card_content_type = res.card_content_type
recommend_type = res.recommend_type
card_click = res.card_click
card_exposure = res.card_exposure
avg_page_stay = res.avg_page_stay
navbar_search = res.navbar_search
highlight_word = res.highlight_word
self_welfare_card = res.self_welfare_card
page_pv_20 = res.page_pv_20
page_pv_20_percent = res.page_pv_20_percent
if not card_content_type or not recommend_type:
continue
recommend_welfare_card = res.recommend_welfare_card
recommend_content_card = res.recommend_content_card
if not recommend_content_card:
recommend_content_card = 0
recommend_special_card = res.recommend_special_card
if not recommend_special_card:
recommend_special_card = 0
transfer_card = res.transfer_card
video_consultation = res.video_consultation
partition_day = today_str
recommend_ctr = res.recommend_ctr
second_jump_ctr = res.second_jump_ctr
click_ctr = res.click_ctr
pid = hashlib.md5((day_id + device_os_type + active_type + card_content_type + recommend_type).encode("utf8")).hexdigest()
instert_sql = """replace into recommend_strategy_d_fix(
day_id,device_os_type,active_type,card_content_type,recommend_type,card_click,card_exposure,avg_page_stay,navbar_search,
highlight_word,self_welfare_card,recommend_welfare_card,recommend_content_card,recommend_special_card,transfer_card,video_consultation,
partition_day,pid,recommend_ctr,second_jump_ctr,click_ctr,page_pv_20_percent
) VALUES('{day_id}','{device_os_type}','{active_type}','{card_content_type}','{recommend_type}',{card_click},{card_exposure},
{avg_page_stay},{navbar_search},{highlight_word},{self_welfare_card},{recommend_welfare_card},{recommend_content_card},{recommend_special_card},
{transfer_card},{video_consultation},'{partition_day}','{pid}',{recommend_ctr},{second_jump_ctr},{click_ctr},{page_pv_20_percent});""".format(
day_id=day_id, device_os_type=device_os_type, active_type=active_type, card_content_type=card_content_type,
card_click=card_click, recommend_type=recommend_type, card_exposure=card_exposure, avg_page_stay=avg_page_stay,
navbar_search=navbar_search, self_welfare_card=self_welfare_card, recommend_welfare_card=recommend_welfare_card,
recommend_content_card=recommend_content_card, recommend_special_card=recommend_special_card,page_pv_20_percent=page_pv_20_percent,
transfer_card=transfer_card,
video_consultation=video_consultation, partition_day=partition_day, pid=pid, recommend_ctr=recommend_ctr,
second_jump_ctr=second_jump_ctr, click_ctr=click_ctr,highlight_word=highlight_word
)
print(instert_sql)
# cursor.execute("set names 'UTF8'")
res = cursor.execute(instert_sql)
db.commit()
print(res)
# cursor.executemany()
db.close()