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
# -*- coding:UTF-8 -*-
# @Time : 2020/9/16 17:41
# @File : new_user_has_protratit_rate.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 meta_base_code.utils.func_from_redis_get_portrait import *
# from pyspark.sql.functions import lit
# import pytispark.pytispark as pti
def con_sql(sql):
# 从数据库的表里获取数据
# db = pymysql.connect(host='172.16.40.158', port=4000, user='st_user', passwd='aqpuBLYzEV7tML5RPsN1pntUzFy',
# db='jerry_prod')
db = pymysql.connect(host='172.16.30.136', port=3306, user='doris', passwd='o5gbA27hXHHm',
db='doris_prod')
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")
sparkConf.setAppName("new_user_has_protratit_rate")
spark = (SparkSession.builder.config(conf=sparkConf).config("spark.sql.extensions", "org.apache.spark.sql.TiExtensions")
.config("spark.tispark.pd.addresses", "172.16.40.170:2379").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'")
task_list = []
task_days = 3
for t in range(2, task_days):
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")
tomorrow_str = (datetime.datetime.now() + datetime.timedelta(days=day_num+1)).strftime("%Y%m%d")
today_str = now.strftime("%Y%m%d")
today_str_format = now.strftime("%Y-%m-%d")
yesterday_str = (now + datetime.timedelta(days=-1)).strftime("%Y%m%d")
yesterday_str_format = (now + datetime.timedelta(days=-1)).strftime("%Y-%m-%d")
one_week_age_str = (now + datetime.timedelta(days=-7)).strftime("%Y%m%d")
new_urser_device_id_sql = r"""
select t2.device_id as device_id from
(select device_id from online.ml_device_day_active_status where partition_date = '{today_str}' and active_type in (1,2)) t2
LEFT join (
select first_device from online.ml_user_history_detail where partition_date = '{tomorrow_str}' and last_active_date = '{today_str}'
) on first_device = t2.device_id
LEFT JOIN
(
select distinct device_id
from ml.ml_d_ct_dv_devicespam_d --去除机构刷单设备，即作弊设备（浏览和曝光事件去除）
WHERE partition_day='{today_str}'
union all
select distinct device_id
from dim.dim_device_user_staff --去除内网用户
)spam_pv
on spam_pv.device_id=t2.device_id
LEFT JOIN
(
SELECT partition_date,device_id
FROM
(--找出user_id当天活跃的第一个设备id
SELECT user_id,partition_date,
if(size(device_list) > 0, device_list [ 0 ], '') AS device_id
FROM online.ml_user_updates
WHERE partition_date='{today_str}'
)t1
JOIN
( --医生账号
SELECT distinct user_id
FROM online.tl_hdfs_doctor_view
WHERE partition_date = '{today_str}'
--马甲账号/模特用户
UNION ALL
SELECT user_id
FROM ml.ml_c_ct_ui_user_dimen_d
WHERE partition_day = '{today_str}'
AND (is_puppet = 'true' or is_classifyuser = 'true')
UNION ALL
--公司内网覆盖用户
select distinct user_id
from dim.dim_device_user_staff
UNION ALL
--登陆过医生设备
SELECT distinct t1.user_id
FROM
(
SELECT user_id, v.device_id as device_id
FROM online.ml_user_history_detail
LATERAL VIEW EXPLODE(device_history_list) v AS device_id
WHERE partition_date = '{today_str}'
) t1
JOIN
(
SELECT device_id
FROM online.ml_device_history_detail
WHERE partition_date = '{today_str}'
AND is_login_doctor = '1'
) t2
ON t1.device_id = t2.device_id
)t2
on t1.user_id=t2.user_id
group by partition_date,device_id
)dev
on t2.device_id=dev.device_id
WHERE spam_pv.device_id IS NULL
and dev.device_id is null and first_device is not null
""".format(today_str=today_str, yesterday_str_format=yesterday_str_format, today_str_format=today_str_format,tomorrow_str=tomorrow_str)
print(new_urser_device_id_sql)
new_urser_device_id_df = spark.sql(new_urser_device_id_sql)
new_urser_device_id_df.createOrReplaceTempView("device_id_view")
new_urser_device_id_df.show(1)
sql_res = new_urser_device_id_df.collect()
res_dict = {}
portrait_dict = {
"first_demands": {},
"second_demands": {},
"first_solutions": {},
"second_solutions": {},
"first_positions": {},
"second_positions": {},
"projects": {},
'anecdote_tags':{}
}
no_portrait_device_id_list = []
print("-------------------------------")
count_not_has_portratit = 0
for count_user_count, res in enumerate(sql_res):
# print(count, res)
portratit_res = get_user_portrait_tag3_from_redis(res.device_id)
sql = """select cl_id, projects from kafka_tag3_log
where cl_id = '%s' and event_cn = 'kyc' """ % res.device_id
# print(count_user_count, res, portratit_res)
sql_res_list = con_sql(sql)
kyc_str_list= []
if sql_res_list:
print(sql_res_list,type(sql_res_list))
kyc_str_list = sql_res_list[0][1].split(",")
temp_count = 0
for demand in portratit_res:
if portratit_res[demand]:
try:
for tag in portratit_res[demand][0:3]:
if tag in portrait_dict[demand]:
portrait_dict[demand][tag] += 1
else:
portrait_dict[demand][tag] = 1
if tag in kyc_str_list and demand == "projects":
portrait_dict["projects"][demand] -= 1
except Exception as e:
print("error ", e)
temp_count += 1
if not temp_count:
count_not_has_portratit += 1
no_portrait_device_id_list.append(res.device_id)
print(portrait_dict)
print(count_user_count+1,count_not_has_portratit)
print("-------------------------------")
for protratit_type in portrait_dict["projects"]:
partition_date = today_str
pid = hashlib.md5((partition_date + protratit_type).encode("utf8")).hexdigest()
action_count = portrait_dict["projects"][protratit_type]
instert_sql = """replace into new_user_project_count(
partition_day,pid,protratit_count,protratit_type) VALUES('{partition_day}','{pid}',{protratit_count},'{protratit_type}');""".format(
partition_day=today_str, pid=pid, protratit_count=action_count
, protratit_type=protratit_type
)
print(instert_sql)
# cursor.execute("set names 'UTF8'")
db = pymysql.connect(host='172.16.40.158', port=4000, user='st_user', passwd='aqpuBLYzEV7tML5RPsN1pntUzFy',
db='jerry_prod')
cursor = db.cursor()
res = cursor.execute(instert_sql)
db.commit()
print(res)
# print("-------------------------------")
# for count, res in enumerate(sql_res):
# # print(count, res)
# track = res.track
# if not track:
# continue
# track_list = track.split(",")
# for one_key_word in track_list:
# if one_key_word in res_dict:
# res_dict[one_key_word] += 1
# else:
# res_dict[one_key_word] = 1
# print(res_dict)