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
package com.gmei
import java.io.Serializable
import com.gmei.WeafareStat.{defaultParams, parser}
import org.apache.spark.sql.{SaveMode, TiContext}
import org.apache.log4j.{Level, Logger}
import scopt.OptionParser
import com.gmei.lib.AbstractParams
object temp_count {
Logger.getLogger("org.apache.spark").setLevel(Level.WARN)
Logger.getLogger("org.apache.eclipse.jetty.server").setLevel(Level.OFF)
case class Params(env: String = "dev",
date: String = "2018-08-01"
) extends AbstractParams[Params] with Serializable
val defaultParams = Params()
val parser = new OptionParser[Params]("Feed_EDA") {
head("WeafareStat")
opt[String]("env")
.text(s"the databases environment you used")
.action((x, c) => c.copy(env = x))
opt[String] ("date")
.text(s"the date you used")
.action((x,c) => c.copy(date = x))
note(
"""
|For example, the following command runs this app on a tidb dataset:
|
| spark-submit --class com.gmei.WeafareStat ./target/scala-2.11/feededa-assembly-0.1.jar \
""".stripMargin +
s"| --env ${defaultParams.env}"
)
}
def main(args: Array[String]): Unit = {
parser.parse(args, defaultParams).map { param =>
GmeiConfig.setup(param.env)
val spark_env = GmeiConfig.getSparkSession()
val sc = spark_env._2
val ti = new TiContext(sc)
ti.tidbMapTable(dbName = "jerry_prod", tableName = "diary_video")
ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_click")
ti.tidbMapTable(dbName = "jerry_prod", tableName = "blacklist")
ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_exposure")
ti.tidbMapTable(dbName = "jerry_prod", tableName = "merge_queue_table")
// val stat_date = GmeiConfig.getMinusNDate(1)
val stat_date = param.date
//println(param.date)
val partition_date = stat_date.replace("-","")
val decive_id_oldUser = sc.sql(
s"""
|select distinct(device_id) as device_id
|from online.ml_device_day_active_status
|where active_type = '4'
|and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
| ,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
| ,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
| ,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
| ,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
| ,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
| ,'promotion_shike','promotion_julang_jl03','','unknown')
|and partition_date ='${partition_date}'
""".stripMargin
)
decive_id_oldUser.createOrReplaceTempView("device_id_old")
val clk_count_oldUser = sc.sql(
s"""
|select '${stat_date}' as stat_date, count(jd.cid_id) as clk_count_oldUser
|from data_feed_click jd inner join device_id_old
|on jd.device_id = device_id_old.device_id
|where (jd.cid_type = 'diary' or jd.cid_type = 'diary_video')
|and jd.device_id not in (select device_id from blacklist)
|and jd.city_id in ("huzhou","liuan","zhenjiang","taizhou","jiaxing","weihai","maanshan","changzhou","shantou","nantong","yantai","wuxi","huhehaote","taiyuan","xining","yinchuan")
|and jd.stat_date ='${stat_date}'
""".stripMargin
)
val imp_count_oldUser = sc.sql(
s"""
|select '${stat_date}' as stat_date, count(cid_id) as imp_count_oldUser
|from data_feed_exposure je inner join device_id_old
|on je.device_id = device_id_old.device_id
|where je.cid_type = 'diary'
|and je.device_id not in (select device_id from blacklist)
|and je.city_id in ("huzhou","liuan","zhenjiang","taizhou","jiaxing","weihai","maanshan","changzhou","shantou","nantong","yantai","wuxi","huhehaote","taiyuan","xining","yinchuan")
|and je.stat_date ='${stat_date}'
""".stripMargin
)
val clk_count_all = sc.sql(
s"""
|select '${stat_date}' as stat_date, count(cid_id) as clk_count_all
|from data_feed_click
|where (cid_type = 'diary' or cid_type = 'diary_video')
|and device_id not in (select device_id from blacklist)
|and city_id in ("huzhou","liuan","zhenjiang","taizhou","jiaxing","weihai","maanshan","changzhou","shantou","nantong","yantai","wuxi","huhehaote","taiyuan","xining","yinchuan")
|and stat_date ='${stat_date}'
""".stripMargin
)
val imp_count__all = sc.sql(
s"""
|select '${stat_date}' as stat_date, count(cid_id) as imp_count_all
|from data_feed_exposure
|where cid_type = 'diary'
|and device_id not in (select device_id from blacklist)
|and city_id in ("huzhou","liuan","zhenjiang","taizhou","jiaxing","weihai","maanshan","changzhou","shantou","nantong","yantai","wuxi","huhehaote","taiyuan","xining","yinchuan")
|and stat_date ='${stat_date}'
""".stripMargin
)
val clk_count_oldUser_Contrast = sc.sql(
s"""
|select '${stat_date}' as stat_date, count(cid_id) as clk_count_oldUser_Contrast
|from data_feed_click jd inner join device_id_old
|on jd.device_id = device_id_old.device_id
|where (jd.cid_type = 'diary' or jd.cid_type = 'diary_video')
|and jd.device_id regexp'1$$'
|and jd.device_id not in (select device_id from blacklist)
|and jd.city_id in ("huzhou","liuan","zhenjiang","taizhou","jiaxing","weihai","maanshan","changzhou","shantou","nantong","yantai","wuxi","huhehaote","taiyuan","xining","yinchuan")
|and jd.stat_date ='${stat_date}'
""".stripMargin
)
val imp_count_oldUser_Contrast = sc.sql(
s"""
|select '${stat_date}' as stat_date, count(cid_id) as imp_count_oldUser_Contrast
|from data_feed_exposure je inner join device_id_old
|on je.device_id = device_id_old.device_id
|where je.cid_type = 'diary'
|and je.device_id regexp'1$$'
|and je.device_id not in (select device_id from blacklist)
|and je.city_id in ("huzhou","liuan","zhenjiang","taizhou","jiaxing","weihai","maanshan","changzhou","shantou","nantong","yantai","wuxi","huhehaote","taiyuan","xining","yinchuan")
|and je.stat_date ='${stat_date}'
""".stripMargin
)
val result1 = clk_count_oldUser.join(imp_count_oldUser,"stat_date")
.join(clk_count_all,"stat_date")
.join(imp_count__all,"stat_date")
.join(clk_count_oldUser_Contrast,"stat_date")
.join(imp_count_oldUser_Contrast,"stat_date")
result1.show()
GmeiConfig.writeToJDBCTable(result1, "ffm_diary_ctr", SaveMode.Append)
}
}
}
object Repeated_content_recommendation {
Logger.getLogger("org.apache.spark").setLevel(Level.WARN)
Logger.getLogger("org.apache.eclipse.jetty.server").setLevel(Level.OFF)
case class Params(env: String = "dev",
date: String = "2018-08-01"
) extends AbstractParams[Params] with Serializable
val defaultParams = Params()
val parser = new OptionParser[Params]("Feed_EDA") {
head("WeafareStat")
opt[String]("env")
.text(s"the databases environment you used")
.action((x, c) => c.copy(env = x))
opt[String] ("date")
.text(s"the date you used")
.action((x,c) => c.copy(date = x))
note(
"""
|For example, the following command runs this app on a tidb dataset:
|
| spark-submit --class com.gmei.WeafareStat ./target/scala-2.11/feededa-assembly-0.1.jar \
""".stripMargin +
s"| --env ${defaultParams.env}"
)
}
def main(args: Array[String]): Unit = {
parser.parse(args, defaultParams).map { param =>
GmeiConfig.setup(param.env)
val spark_env = GmeiConfig.getSparkSession()
val sc = spark_env._2
val ti = new TiContext(sc)
ti.tidbMapTable(dbName = "jerry_prod", tableName = "diary_video")
ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_click")
ti.tidbMapTable(dbName = "jerry_prod", tableName = "blacklist")
ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_exposure")
ti.tidbMapTable(dbName = "jerry_prod", tableName = "merge_queue_table")
// val stat_date = GmeiConfig.getMinusNDate(1)
val stat_date = param.date
val partition_date = stat_date.replace("-","")
val exp_diary = sc.sql(
s"""
|select concat_ws(|,device_id,cid_id)
|from data_feed_exposure
|where cid_type = 'diary'
|and device_id not in (select device_id from blacklist)
|and stat_date ='${stat_date}'
""".stripMargin
)
exp_diary.show()
val get_result =exp_diary.rdd.map((_, 1)).reduceByKey(_ + _)
.sortBy(_._2,false)
val temp=get_result.collect()
for (i <- 0 until temp.length ) {
println(temp(i))
}
}
}
}