testt.scala 30 KB
Newer Older
王志伟's avatar
王志伟 committed
1
package com.gmei
王志伟's avatar
王志伟 committed
2 3 4 5

import java.io.Serializable

import com.gmei.WeafareStat.{defaultParams, parser}
王志伟's avatar
王志伟 committed
6 7
//import org.apache.spark.sql.{SaveMode, TiContext}
import org.apache.spark.sql.{SaveMode}
王志伟's avatar
王志伟 committed
8 9 10
import org.apache.log4j.{Level, Logger}
import scopt.OptionParser
import com.gmei.lib.AbstractParams
王志伟's avatar
王志伟 committed
11 12 13

object testt {

王志伟's avatar
王志伟 committed
14 15 16
  Logger.getLogger("org.apache.spark").setLevel(Level.WARN)
  Logger.getLogger("org.apache.eclipse.jetty.server").setLevel(Level.OFF)

王志伟's avatar
王志伟 committed
17 18
  case class Params(env: String = "dev",
                    date: String = "2018-08-01"
王志伟's avatar
王志伟 committed
19
                   ) extends AbstractParams[Params] with Serializable
王志伟's avatar
王志伟 committed
20

王志伟's avatar
王志伟 committed
21
  val defaultParams = Params()
王志伟's avatar
王志伟 committed
22

王志伟's avatar
王志伟 committed
23
  val parser = new OptionParser[Params]("Feed_EDA") {
王志伟's avatar
王志伟 committed
24
    head("WeafareStat")
王志伟's avatar
王志伟 committed
25 26 27
    opt[String]("env")
      .text(s"the databases environment you used")
      .action((x, c) => c.copy(env = x))
王志伟's avatar
王志伟 committed
28 29 30
    opt[String] ("date")
      .text(s"the date you used")
      .action((x,c) => c.copy(date = x))
王志伟's avatar
王志伟 committed
31 32 33 34
    note(
      """
        |For example, the following command runs this app on a tidb dataset:
        |
王志伟's avatar
王志伟 committed
35
        | spark-submit --class com.gmei.WeafareStat ./target/scala-2.11/feededa-assembly-0.1.jar \
王志伟's avatar
王志伟 committed
36 37 38
      """.stripMargin +
        s"|   --env ${defaultParams.env}"
    )
王志伟's avatar
王志伟 committed
39
  }
王志伟's avatar
王志伟 committed
40 41 42 43 44 45 46

  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

王志伟's avatar
王志伟 committed
47 48 49 50 51 52
//      val ti = new TiContext(sc)
      sc.sql("use jerry_prod")
//      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")
王志伟's avatar
王志伟 committed
53

王志伟's avatar
王志伟 committed
54 55
      val stat_date = GmeiConfig.getMinusNDate(1)
//      val stat_date=param.date
王志伟's avatar
王志伟 committed
56
      val partition_date = stat_date.replace("-","")
王志伟's avatar
王志伟 committed
57
      //机构id
王志伟's avatar
王志伟 committed
58
      val blacklist = sc.sql(
王志伟's avatar
王志伟 committed
59 60 61 62
        s"""
           |select device_id from blacklist
         """.stripMargin
      )
王志伟's avatar
王志伟 committed
63
      blacklist.createOrReplaceTempView("blacklist")
王志伟's avatar
王志伟 committed
64

王志伟's avatar
王志伟 committed
65 66


王志伟's avatar
王志伟 committed
67 68 69 70 71
      val agency_id = sc.sql(
        s"""
           |SELECT DISTINCT(cl_id) as device_id
           |FROM online.ml_hospital_spam_pv_day
           |WHERE partition_date >= '20180402'
王志伟's avatar
王志伟 committed
72
           |AND partition_date <= '${partition_date}'
王志伟's avatar
王志伟 committed
73 74 75 76 77
           |AND pv_ratio >= 0.95
           |UNION ALL
           |SELECT DISTINCT(cl_id) as device_id
           |FROM online.ml_hospital_spam_pv_month
           |WHERE partition_date >= '20171101'
王志伟's avatar
王志伟 committed
78
           |AND partition_date <= '${partition_date}'
王志伟's avatar
王志伟 committed
79 80 81
           |AND pv_ratio >= 0.95
         """.stripMargin
      )
王志伟's avatar
王志伟 committed
82
      agency_id.show()
王志伟's avatar
王志伟 committed
83
      agency_id.createOrReplaceTempView("agency_id")
王志伟's avatar
王志伟 committed
84 85 86
//每日新用户
      val device_id_newUser = sc.sql(
        s"""
87
           |select distinct(os.device_id) as device_id
88
           |from online.ml_device_day_active_status os left join blacklist
89
           |on os.device_id=blacklist.device_id
王志伟's avatar
王志伟 committed
90
           |where (os.active_type = '1' or os.active_type='2')
91
           |and os.first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
92 93 94 95 96
           |    ,'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'
王志伟's avatar
王志伟 committed
97
           |    ,'promotion_shike','promotion_julang_jl03','','unknown','promotion_zuimei')
98 99
           |and os.partition_date ='${partition_date}'
           |and blacklist.device_id is null
王志伟's avatar
王志伟 committed
100 101
         """.stripMargin
      )
王志伟's avatar
王志伟 committed
102
      device_id_newUser.show()
王志伟's avatar
王志伟 committed
103 104 105 106 107
      device_id_newUser.createOrReplaceTempView("device_id_new")

      //每日老用户
      val device_id_oldUser = sc.sql(
        s"""
王志伟's avatar
王志伟 committed
108
           |select distinct(os.device_id) as device_id
109 110
           |from online.ml_device_day_active_status os left join blacklist
           |on os.device_id=blacklist.device_id
111 112
           |where os.active_type = '4'
           |and os.first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
113 114 115 116 117
           |    ,'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'
王志伟's avatar
王志伟 committed
118
           |    ,'promotion_shike','promotion_julang_jl03','','unknown','promotion_zuimei')
119
           |and os.partition_date ='${partition_date}'
120
           |and blacklist.device_id is null
王志伟's avatar
王志伟 committed
121 122
         """.stripMargin
      )
王志伟's avatar
王志伟 committed
123
      device_id_oldUser.show()
王志伟's avatar
王志伟 committed
124 125
      device_id_oldUser.createOrReplaceTempView("device_id_old")

王志伟's avatar
王志伟 committed
126 127 128

      //日记本转化美购
      //1.日记本到美购转化数
王志伟's avatar
王志伟 committed
129
      val diary_meigou_temp = sc.sql(
王志伟's avatar
王志伟 committed
130
        s"""
王志伟's avatar
王志伟 committed
131
           |select ou.cl_id as device_id
王志伟's avatar
王志伟 committed
132 133 134 135 136
           |from online.bl_hdfs_page_view_updates ou left join agency_id
           |on ou.cl_id = agency_id.device_id
           |where ou.partition_date = '${partition_date}'
           |and ou.page_name='welfare_detail'
           |and ou.referrer='diary_detail'
王志伟's avatar
王志伟 committed
137
           |and agency_id.device_id is  null
王志伟's avatar
王志伟 committed
138 139 140
         """.stripMargin
      )
      diary_meigou_temp.createOrReplaceTempView("diary_meigou_temp")
王志伟's avatar
王志伟 committed
141 142 143

      diary_meigou_temp.show()

王志伟's avatar
王志伟 committed
144 145
      val diary_meigou_device = sc.sql(
        s"""
王志伟's avatar
王志伟 committed
146
           |select dt.device_id
王志伟's avatar
王志伟 committed
147 148 149
           |from diary_meigou_temp dt left join blacklist
           |on dt.device_id = blacklist.device_id
           |where blacklist.device_id is null
王志伟's avatar
王志伟 committed
150 151
         """.stripMargin
      )
王志伟's avatar
王志伟 committed
152
      diary_meigou_device.createOrReplaceTempView("diary_meigou_device")
王志伟's avatar
王志伟 committed
153 154
      diary_meigou_device.show()

王志伟's avatar
王志伟 committed
155 156 157
//新用户到美购详情页的转化
      val diary_meigou_newUser = sc.sql(
        s"""
王志伟's avatar
王志伟 committed
158
           |select '${stat_date}' as stat_date, count(dd.device_id) as diary_meigou_newUser
王志伟's avatar
王志伟 committed
159 160 161 162 163
           |from diary_meigou_device dd left join device_id_new
           |on dd.device_id = device_id_new.device_id
           |where device_id_new.device_id is not null
         """.stripMargin
      )
王志伟's avatar
王志伟 committed
164
      diary_meigou_newUser.show()
王志伟's avatar
王志伟 committed
165 166 167
      //老用户到美购详情页的转化
      val diary_meigou_oldUser = sc.sql(
        s"""
王志伟's avatar
王志伟 committed
168
           |select '${stat_date}' as stat_date, count(dd.device_id) as diary_meigou_oldUser
王志伟's avatar
王志伟 committed
169 170 171 172 173
           |from diary_meigou_device dd left join device_id_old
           |on dd.device_id = device_id_old.device_id
           |where device_id_old.device_id is not null
         """.stripMargin
      )
王志伟's avatar
王志伟 committed
174 175
      diary_meigou_oldUser.show()

王志伟's avatar
王志伟 committed
176

王志伟's avatar
王志伟 committed
177 178

      //2.日记本点击数
王志伟's avatar
王志伟 committed
179
      val diary_clk_temp = sc.sql(
王志伟's avatar
王志伟 committed
180
        s"""
王志伟's avatar
王志伟 committed
181
           |select ov.cl_id as device_id
王志伟's avatar
王志伟 committed
182 183 184 185 186
           |from online.tl_hdfs_maidian_view ov left join agency_id
           |on ov.cl_id = agency_id.device_id
           |where ov.action = 'on_click_diary_card'
           |and ov.cl_id != "NULL"
           |and ov.partition_date='${partition_date}'
王志伟's avatar
王志伟 committed
187
           |and agency_id.device_id is  null
王志伟's avatar
王志伟 committed
188 189
       """.stripMargin
      )
王志伟's avatar
王志伟 committed
190
      diary_clk_temp.createOrReplaceTempView("diary_clk_temp")
王志伟's avatar
王志伟 committed
191
      diary_clk_temp.show()
王志伟's avatar
王志伟 committed
192 193 194

      val diary_clk_device = sc.sql(
        s"""
王志伟's avatar
王志伟 committed
195
           |select dt.device_id
王志伟's avatar
王志伟 committed
196 197 198 199 200 201
           |from diary_clk_temp dt left join blacklist
           |on dt.device_id = blacklist.device_id
           |where blacklist.device_id is  null
         """.stripMargin
      )

王志伟's avatar
王志伟 committed
202
      diary_clk_device.createOrReplaceTempView("diary_clk_device")
王志伟's avatar
王志伟 committed
203
      diary_clk_device.show()
王志伟's avatar
王志伟 committed
204 205 206 207

      //新用户日记本点击
      val diary_clk_newUser = sc.sql(
        s"""
王志伟's avatar
王志伟 committed
208
           |select '${stat_date}' as stat_date, count(dd.device_id) as diary_clk_newUser
王志伟's avatar
王志伟 committed
209 210 211 212 213
           |from diary_clk_device dd left join device_id_new
           |on dd.device_id = device_id_new.device_id
           |where device_id_new.device_id is not null
         """.stripMargin
      )
王志伟's avatar
王志伟 committed
214
      diary_clk_newUser.show()
王志伟's avatar
王志伟 committed
215 216 217
      //老用户日记本点击
      val diary_clk_oldUser = sc.sql(
        s"""
王志伟's avatar
王志伟 committed
218
           |select '${stat_date}' as stat_date, count(dd.device_id) as diary_clk_oldUser
王志伟's avatar
王志伟 committed
219 220 221 222 223
           |from diary_clk_device dd left join device_id_old
           |on dd.device_id = device_id_old.device_id
           |where device_id_old.device_id is not null
         """.stripMargin
      )
王志伟's avatar
王志伟 committed
224 225
      diary_clk_oldUser.show()

王志伟's avatar
王志伟 committed
226 227

      //3.日记本曝光数
王志伟's avatar
王志伟 committed
228
      val diary_expoure_temp=sc.sql(
王志伟's avatar
王志伟 committed
229
        s"""
王志伟's avatar
王志伟 committed
230
           |select od.cl_id as device_id
王志伟's avatar
王志伟 committed
231 232 233 234 235
           |from online.ml_community_exposure_detail od left join agency_id
           |on od.cl_id = agency_id.device_id
           |where od.business_type = "diary"
           |and od.cl_id != "NULL"
           |and od.partition_date='${partition_date}'
王志伟's avatar
王志伟 committed
236
           |and agency_id.device_id is  null
王志伟's avatar
王志伟 committed
237 238
       """.stripMargin
      )
王志伟's avatar
王志伟 committed
239
      diary_expoure_temp.createOrReplaceTempView("diary_expoure_temp")
王志伟's avatar
王志伟 committed
240
      diary_expoure_temp.show()
王志伟's avatar
王志伟 committed
241 242 243

      val diary_expoure_device = sc.sql(
        s"""
王志伟's avatar
王志伟 committed
244
           |select dt.device_id
王志伟's avatar
王志伟 committed
245 246 247 248 249
           |from diary_expoure_temp dt left join blacklist
           |on dt.device_id = blacklist.device_id
           |where blacklist.device_id is  null
         """.stripMargin
      )
王志伟's avatar
王志伟 committed
250
      diary_expoure_device.show()
王志伟's avatar
王志伟 committed
251

王志伟's avatar
王志伟 committed
252 253 254 255
      diary_expoure_device.createOrReplaceTempView("diary_expoure_device")
      //新用户日记本曝光
      val diary_exp_newUser = sc.sql(
        s"""
王志伟's avatar
王志伟 committed
256
           |select '${stat_date}' as stat_date, count(dd.device_id) as diary_exp_newUser
王志伟's avatar
王志伟 committed
257 258 259 260 261
           |from diary_expoure_device dd left join device_id_new
           |on dd.device_id = device_id_new.device_id
           |where device_id_new.device_id is not null
         """.stripMargin
      )
王志伟's avatar
王志伟 committed
262 263
      diary_exp_newUser.show()

王志伟's avatar
王志伟 committed
264 265 266
      //老用户日记本曝光
      val diary_exp_oldUser = sc.sql(
        s"""
王志伟's avatar
王志伟 committed
267
           |select '${stat_date}' as stat_date, count(dd.device_id) as diary_exp_oldUser
王志伟's avatar
王志伟 committed
268 269 270 271 272
           |from diary_expoure_device dd left join device_id_old
           |on dd.device_id = device_id_old.device_id
           |where device_id_old.device_id is not null
         """.stripMargin
      )
王志伟's avatar
王志伟 committed
273 274
      diary_exp_oldUser.show()

王志伟's avatar
王志伟 committed
275

王志伟's avatar
王志伟 committed
276 277

      //4.搜索次数统计
王志伟's avatar
王志伟 committed
278
      val search_device_temp = sc.sql(
王志伟's avatar
王志伟 committed
279
        s"""
王志伟's avatar
王志伟 committed
280
           |select ov.cl_id as device_id
王志伟's avatar
王志伟 committed
281 282 283 284
           |from online.tl_hdfs_maidian_view ov left join agency_id
           |on ov.cl_id = agency_id.device_id
           |where (ov.action = 'do_search' or ov.action = 'search_result_click_search')
           |and ov.partition_date ='${partition_date}'
王志伟's avatar
王志伟 committed
285
           |and agency_id.device_id is  null
王志伟's avatar
王志伟 committed
286 287 288
         """.stripMargin
      )
      search_device_temp.createOrReplaceTempView("search_device_temp")
王志伟's avatar
王志伟 committed
289
      search_device_temp.show()
王志伟's avatar
王志伟 committed
290 291 292

      val search_device = sc.sql(
        s"""
王志伟's avatar
王志伟 committed
293
           |select dt.device_id
王志伟's avatar
王志伟 committed
294 295
           |from search_device_temp dt left join blacklist
           |on dt.device_id = blacklist.device_id
王志伟's avatar
王志伟 committed
296
           |where blacklist.device_id is null
王志伟's avatar
王志伟 committed
297 298
         """.stripMargin
      )
王志伟's avatar
王志伟 committed
299
      search_device.createOrReplaceTempView("search_device")
王志伟's avatar
王志伟 committed
300
      search_device.show()
王志伟's avatar
王志伟 committed
301 302 303
      //新用户搜索次数
      val search_newUser = sc.sql(
        s"""
王志伟's avatar
王志伟 committed
304
           |select '${stat_date}' as stat_date, count(sd.device_id) as search_newUser
王志伟's avatar
王志伟 committed
305 306 307 308 309
           |from search_device sd left join device_id_new
           |on sd.device_id = device_id_new.device_id
           |where device_id_new.device_id is not null
         """.stripMargin
      )
王志伟's avatar
王志伟 committed
310
      search_newUser.show()
王志伟's avatar
王志伟 committed
311 312 313
      //老用户日搜索次数
      val search_oldUser = sc.sql(
        s"""
王志伟's avatar
王志伟 committed
314
           |select '${stat_date}' as stat_date, count(sd.device_id) as search_oldUser
王志伟's avatar
王志伟 committed
315 316 317 318 319
           |from search_device sd left join device_id_old
           |on sd.device_id = device_id_old.device_id
           |where device_id_old.device_id is not null
         """.stripMargin
      )
王志伟's avatar
王志伟 committed
320
      search_oldUser.show()
王志伟's avatar
王志伟 committed
321 322

      //5.登录人数
王志伟's avatar
王志伟 committed
323
      val log_device_temp = sc.sql(
王志伟's avatar
王志伟 committed
324
        s"""
王志伟's avatar
王志伟 committed
325
           |select distinct(oe.device_id)  as device_id
王志伟's avatar
王志伟 committed
326 327 328
           |from data_feed_exposure oe left join agency_id
           |on oe.device_id = agency_id.device_id
           |and oe.stat_date ='${stat_date}'
王志伟's avatar
王志伟 committed
329
           |and agency_id.device_id is  null
王志伟's avatar
王志伟 committed
330 331
         """.stripMargin
      )
王志伟's avatar
王志伟 committed
332
      log_device_temp.createOrReplaceTempView("log_device_temp")
王志伟's avatar
王志伟 committed
333
      log_device_temp.show()
王志伟's avatar
王志伟 committed
334 335 336

      val log_device = sc.sql(
        s"""
王志伟's avatar
王志伟 committed
337
           |select dt.device_id
王志伟's avatar
王志伟 committed
338 339 340 341 342
           |from log_device_temp dt left join blacklist
           |on dt.device_id = blacklist.device_id
           |where blacklist.device_id is  null
         """.stripMargin
      )
王志伟's avatar
王志伟 committed
343
      log_device.createOrReplaceTempView("log_device")
王志伟's avatar
王志伟 committed
344
      log_device.show()
王志伟's avatar
王志伟 committed
345 346 347 348

      //新用户登录人数
      val log_newUser = sc.sql(
        s"""
王志伟's avatar
王志伟 committed
349
           |select '${stat_date}' as stat_date, count(distinct(ld.device_id)) as log_newUser
王志伟's avatar
王志伟 committed
350 351 352 353 354
           |from log_device ld left join device_id_new
           |on ld.device_id = device_id_new.device_id
           |where device_id_new.device_id is not null
         """.stripMargin
      )
王志伟's avatar
王志伟 committed
355
      log_newUser.show()
王志伟's avatar
王志伟 committed
356 357 358
      //老用户登录人数
      val log_oldUser = sc.sql(
        s"""
王志伟's avatar
王志伟 committed
359
           |select '${stat_date}' as stat_date, count(distinct(ld.device_id)) as log_oldUser
王志伟's avatar
王志伟 committed
360 361 362 363 364
           |from log_device ld left join device_id_old
           |on ld.device_id = device_id_old.device_id
           |where device_id_old.device_id is not null
         """.stripMargin
      )
王志伟's avatar
王志伟 committed
365 366
      log_oldUser.show()

王志伟's avatar
王志伟 committed
367

王志伟's avatar
王志伟 committed
368 369 370 371 372 373 374 375 376
      val result = diary_meigou_newUser.join(diary_meigou_oldUser,"stat_date")
        .join(diary_clk_newUser,"stat_date")
        .join(diary_clk_oldUser,"stat_date")
        .join(diary_exp_newUser,"stat_date")
        .join(diary_exp_oldUser,"stat_date")
        .join(search_newUser,"stat_date")
        .join(search_oldUser,"stat_date")
        .join(log_newUser,"stat_date")
        .join(log_oldUser,"stat_date")
王志伟's avatar
王志伟 committed
377

王志伟's avatar
王志伟 committed
378
//      GmeiConfig.writeToJDBCTable(result, "diary_meigou_crv", SaveMode.Append)
王志伟's avatar
王志伟 committed
379 380 381
//      GmeiConfig.writeToJDBCTable("jdbc:mysql://152.136.44.138:4000/jerry_prod?user=root&password=3SYz54LS9#^9sBvC&rewriteBatchedStatements=true",result, table="diary_meigou_crv",SaveMode.Append)

      println("开始写入")
王志伟's avatar
王志伟 committed
382 383 384
//      GmeiConfig.writeToJDBCTable("jerry.jdbcuri",result, table="diary_meigou_crv",SaveMode.Append)
//      println("写入完成")
      GmeiConfig.writeToJDBCTable("jdbc:mysql://172.16.40.158:4000/jerry_prod?user=root&password=3SYz54LS9#^9sBvC&rewriteBatchedStatements=true",result, table="diary_meigou_crv",SaveMode.Append)
王志伟's avatar
王志伟 committed
385
      println("写入完成")
王志伟's avatar
王志伟 committed
386

王志伟's avatar
王志伟 committed
387

王志伟's avatar
王志伟 committed
388 389

    }
王志伟's avatar
王志伟 committed
390

王志伟's avatar
王志伟 committed
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
object diary_clk_card {

  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

王志伟's avatar
王志伟 committed
440 441 442 443 444 445
//      val ti = new TiContext(sc)
      sc.sql("use jerry_prod")
//      ti.tidbMapTable(dbName = "jerry_prod", tableName = "diary_video")
//      ti.tidbMapTable(dbName = "jerry_prod", tableName = "blacklist")
//      ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_exposure")
//      ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_exposure_precise")
446

王志伟's avatar
王志伟 committed
447 448
      val stat_date = GmeiConfig.getMinusNDate(1)
//      val stat_date=param.date
449 450
      val partition_date = stat_date.replace("-","")
      //机构id
王志伟's avatar
王志伟 committed
451

王志伟's avatar
王志伟 committed
452 453 454 455
//      sc.sql("ADD JAR hdfs:///user/hive/share/lib/udf/brickhouse-0.7.1-SNAPSHOT.jar")
//      sc.sql("ADD JAR hdfs:///user/hive/share/lib/udf/hive-udf-1.0-SNAPSHOT.jar")
//      sc.sql("CREATE TEMPORARY FUNCTION json_map AS 'brickhouse.udf.json.JsonMapUDF'")
//      sc.sql("CREATE TEMPORARY FUNCTION is_json AS 'com.gmei.hive.common.udf.UDFJsonFormatCheck'")
王志伟's avatar
王志伟 committed
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
      val blacklist = sc.sql(
        s"""
           |select device_id from blacklist
         """.stripMargin
      )
      blacklist.createOrReplaceTempView("blacklist")

      val agency_id = sc.sql(
        s"""
           |SELECT DISTINCT(cl_id) as device_id
           |FROM online.ml_hospital_spam_pv_day
           |WHERE partition_date >= '20180402'
           |AND partition_date <= '${partition_date}'
           |AND pv_ratio >= 0.95
           |UNION ALL
           |SELECT DISTINCT(cl_id) as device_id
           |FROM online.ml_hospital_spam_pv_month
           |WHERE partition_date >= '20171101'
           |AND partition_date <= '${partition_date}'
           |AND pv_ratio >= 0.95
         """.stripMargin
      )
      agency_id.createOrReplaceTempView("agency_id")

      val blacklist_all=sc.sql(
        s"""
           |SELECT device_id
           |FROM blacklist
           |UNION ALL
           |SELECT device_id
           |FROM agency_id
         """.stripMargin
      )
      blacklist_all.createOrReplaceTempView("blacklist_all")


      val device_id_oldUser = sc.sql(
        s"""
           |select distinct(om.device_id) as device_id
           |from online.ml_device_day_active_status om left join blacklist_all
           |on om.device_id = blacklist_all.device_id
           |where om.active_type = '4'
           |and om.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 om.partition_date ='${partition_date}'
           |and blacklist_all.device_id is null
         """.stripMargin
      )
      device_id_oldUser.createOrReplaceTempView("device_id_old")
王志伟's avatar
王志伟 committed
511
      device_id_oldUser.show()
512 513 514 515 516 517 518 519 520 521 522


      val clk_count_oldUser_Contrast_a = sc.sql(
        s"""
           |select '${stat_date}' as stat_date, count(ot.cl_id) as clk_count_oldUser_Contrast_a
           |from online.tl_hdfs_maidian_view ot inner join device_id_old
           |on ot.cl_id = device_id_old.device_id
           |where ot.action='on_click_diary_card'
           |and ot.params['tab_name'] = '精选'
           |and ot.params['page_name'] = 'home'
           |and ot.cl_id regexp'1$$'
523
           |and ot.partition_date ='${partition_date}'
524 525
         """.stripMargin
      )
王志伟's avatar
王志伟 committed
526
      clk_count_oldUser_Contrast_a.show()
527 528 529 530 531 532 533 534 535 536

      val clk_count_oldUser_Contrast_b = sc.sql(
        s"""
           |select '${stat_date}' as stat_date, count(ot.cl_id) as clk_count_oldUser_Contrast_b
           |from online.tl_hdfs_maidian_view ot inner join device_id_old
           |on ot.cl_id = device_id_old.device_id
           |where ot.action='full_stack_click_video_card_full_screen_play'
           |and ot.params['tab_name'] = '精选'
           |and ot.params["card_type"]="diary"
           |and ot.cl_id regexp'1$$'
537
           |and ot.partition_date ='${partition_date}'
538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553
         """.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.stat_date ='${stat_date}'
         """.stripMargin
      )

王志伟's avatar
王志伟 committed
554 555 556 557 558 559 560 561 562 563 564 565 566
      val imp_count_oldUser_Contrast_precise = sc.sql(
        s"""
           |select '${stat_date}' as stat_date, count(cid_id) as imp_count_oldUser_Contrast_precise
           |from data_feed_exposure_precise 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.stat_date ='${stat_date}'
         """.stripMargin
      )


567 568
      val clk_count_oldUser_all_a = sc.sql(
        s"""
569
           |select '${stat_date}' as stat_date, count(ot.cl_id) as clk_count_oldUser_all_a
570 571 572 573 574
           |from online.tl_hdfs_maidian_view ot inner join device_id_old
           |on ot.cl_id = device_id_old.device_id
           |where ot.action='on_click_diary_card'
           |and ot.params['tab_name'] = '精选'
           |and ot.params['page_name'] = 'home'
575
           |and ot.partition_date ='${partition_date}'
576 577 578 579 580 581 582 583 584 585 586
         """.stripMargin
      )

      val clk_count_oldUser_all_b = sc.sql(
        s"""
           |select '${stat_date}' as stat_date, count(ot.cl_id) as clk_count_oldUser_all_b
           |from online.tl_hdfs_maidian_view ot inner join device_id_old
           |on ot.cl_id = device_id_old.device_id
           |where ot.action='full_stack_click_video_card_full_screen_play'
           |and ot.params['tab_name'] = '精选'
           |and ot.params["card_type"]="diary"
587
           |and ot.partition_date ='${partition_date}'
588 589 590 591 592 593 594 595 596 597 598 599 600 601 602
         """.stripMargin
      )


      val imp_count_oldUser_all = sc.sql(
        s"""
           |select '${stat_date}' as stat_date, count(cid_id) as imp_count_oldUser_all
           |from data_feed_exposure je inner join device_id_old
           |on je.device_id = device_id_old.device_id
           |where je.cid_type = 'diary'
           |and je.device_id not in (select device_id from blacklist)
           |and je.stat_date ='${stat_date}'
         """.stripMargin
      )

王志伟's avatar
王志伟 committed
603 604 605 606 607 608 609 610 611 612 613
      val imp_count_oldUser_all_precise = sc.sql(
        s"""
           |select '${stat_date}' as stat_date, count(cid_id) as imp_count_oldUser_all_precise
           |from data_feed_exposure_precise je inner join device_id_old
           |on je.device_id = device_id_old.device_id
           |where je.cid_type = 'diary'
           |and je.device_id not in (select device_id from blacklist)
           |and je.stat_date ='${stat_date}'
         """.stripMargin
      )

614 615 616 617 618
//统计新用户ctr
      val device_id_newUser = sc.sql(
        s"""
           |select distinct(device_id) as device_id
           |from online.ml_device_day_active_status
王志伟's avatar
王志伟 committed
619
           |where (active_type = '1' or active_type = '2')
620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641
           |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
      )
      device_id_newUser.createOrReplaceTempView("device_id_new")


      val clk_count_newUser_Contrast_a = sc.sql(
        s"""
           |select '${stat_date}' as stat_date, count(ot.cl_id) as clk_count_newUser_Contrast_a
           |from online.tl_hdfs_maidian_view ot inner join device_id_new
           |on ot.cl_id = device_id_new.device_id
           |where ot.action='on_click_diary_card'
           |and ot.params['tab_name'] = '精选'
           |and ot.params['page_name'] = 'home'
           |and ot.cl_id regexp'1$$'
642
           |and ot.partition_date ='${partition_date}'
643 644 645 646 647 648 649 650 651 652 653 654 655
         """.stripMargin
      )


      val clk_count_newUser_Contrast_b = sc.sql(
        s"""
           |select '${stat_date}' as stat_date, count(ot.cl_id) as clk_count_newUser_Contrast_b
           |from online.tl_hdfs_maidian_view ot inner join device_id_new
           |on ot.cl_id = device_id_new.device_id
           |where ot.action='full_stack_click_video_card_full_screen_play'
           |and ot.params['tab_name'] = '精选'
           |and ot.params["card_type"]="diary"
           |and ot.cl_id regexp'1$$'
656
           |and ot.partition_date ='${partition_date}'
657 658 659 660 661 662
         """.stripMargin
      )


      val imp_count_newUser_Contrast = sc.sql(
        s"""
663
           |select '${stat_date}' as stat_date, count(cid_id) as imp_count_newUser_Contrast
664 665 666 667 668 669 670 671 672
           |from data_feed_exposure je inner join device_id_new
           |on je.device_id = device_id_new.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.stat_date ='${stat_date}'
         """.stripMargin
      )

王志伟's avatar
王志伟 committed
673
      val imp_count_newUser_Contrast_precise = sc.sql(
674
        s"""
王志伟's avatar
王志伟 committed
675 676
           |select '${stat_date}' as stat_date, count(cid_id) as imp_count_newUser_Contrast_precise
           |from data_feed_exposure_precise je inner join device_id_new
677 678
           |on je.device_id = device_id_new.device_id
           |where je.cid_type = 'diary'
王志伟's avatar
王志伟 committed
679 680 681 682 683 684 685
           |and je.device_id regexp'1$$'
           |and je.device_id not in (select device_id from blacklist)
           |and je.stat_date ='${stat_date}'
         """.stripMargin
      )


王志伟's avatar
王志伟 committed
686
      val clk_count_newUser_all_a = sc.sql(
王志伟's avatar
王志伟 committed
687
        s"""
王志伟's avatar
王志伟 committed
688
           |select '${stat_date}' as stat_date, count(ot.cl_id) as clk_count_newUser_all_a
王志伟's avatar
王志伟 committed
689 690 691 692 693 694 695 696 697
           |from online.tl_hdfs_maidian_view ot inner join device_id_new
           |on ot.cl_id = device_id_new.device_id
           |where ot.action='on_click_diary_card'
           |and ot.params['tab_name'] = '精选'
           |and ot.params['page_name'] = 'home'
           |and ot.partition_date ='${partition_date}'
         """.stripMargin
      )

王志伟's avatar
王志伟 committed
698
      val clk_count_newUser_all_b = sc.sql(
王志伟's avatar
王志伟 committed
699
        s"""
王志伟's avatar
王志伟 committed
700
           |select '${stat_date}' as stat_date, count(ot.cl_id) as clk_count_newUser_all_b
王志伟's avatar
王志伟 committed
701 702 703 704 705 706 707 708 709 710
           |from online.tl_hdfs_maidian_view ot inner join device_id_new
           |on ot.cl_id = device_id_new.device_id
           |where ot.action='full_stack_click_video_card_full_screen_play'
           |and ot.params['tab_name'] = '精选'
           |and ot.params["card_type"]="diary"
           |and ot.partition_date ='${partition_date}'
         """.stripMargin
      )


王志伟's avatar
王志伟 committed
711
      val imp_count_newUser_all = sc.sql(
王志伟's avatar
王志伟 committed
712
        s"""
王志伟's avatar
王志伟 committed
713 714
           |select '${stat_date}' as stat_date, count(cid_id) as imp_count_newUser_all
           |from data_feed_exposure je inner join device_id_new
王志伟's avatar
王志伟 committed
715 716 717 718 719 720 721
           |on je.device_id = device_id_new.device_id
           |where je.cid_type = 'diary'
           |and je.device_id not in (select device_id from blacklist)
           |and je.stat_date ='${stat_date}'
         """.stripMargin
      )

王志伟's avatar
王志伟 committed
722
      val imp_count_newUser_all_precise = sc.sql(
王志伟's avatar
王志伟 committed
723
        s"""
王志伟's avatar
王志伟 committed
724
           |select '${stat_date}' as stat_date, count(cid_id) as imp_count_newUser_all_precise
王志伟's avatar
王志伟 committed
725 726 727 728 729 730 731 732
           |from data_feed_exposure_precise je inner join device_id_new
           |on je.device_id = device_id_new.device_id
           |where je.cid_type = 'diary'
           |and je.device_id not in (select device_id from blacklist)
           |and je.stat_date ='${stat_date}'
         """.stripMargin
      )

王志伟's avatar
王志伟 committed
733

王志伟's avatar
王志伟 committed
734 735 736 737 738 739 740 741 742 743 744
      val result1 = clk_count_oldUser_Contrast_a.join(clk_count_oldUser_Contrast_b,"stat_date")
        .join(imp_count_oldUser_Contrast,"stat_date")
        .join(clk_count_oldUser_all_a,"stat_date")
        .join(clk_count_oldUser_all_b,"stat_date")
        .join(imp_count_oldUser_all,"stat_date")
        .join(clk_count_newUser_Contrast_a,"stat_date")
        .join(clk_count_newUser_Contrast_b,"stat_date")
        .join(imp_count_newUser_Contrast,"stat_date")
        .join(clk_count_newUser_all_a,"stat_date")
        .join(clk_count_newUser_all_b,"stat_date")
        .join(imp_count_newUser_all,"stat_date")
王志伟's avatar
王志伟 committed
745 746 747 748
        .join(imp_count_oldUser_Contrast_precise,"stat_date")
        .join(imp_count_oldUser_all_precise,"stat_date")
        .join(imp_count_newUser_Contrast_precise,"stat_date")
        .join(imp_count_newUser_all_precise,"stat_date")
王志伟's avatar
王志伟 committed
749 750
      result1.show()

王志伟's avatar
王志伟 committed
751
//      GmeiConfig.writeToJDBCTable(result1, "on_click_diary_card", SaveMode.Append)
王志伟's avatar
王志伟 committed
752 753 754
//      GmeiConfig.writeToJDBCTable("jdbc:mysql://152.136.44.138:4000/jerry_prod?user=root&password=3SYz54LS9#^9sBvC&rewriteBatchedStatements=true",result1, table="on_click_diary_card",SaveMode.Append)

      println("开始写入")
王志伟's avatar
王志伟 committed
755 756 757 758
//      GmeiConfig.writeToJDBCTable("jerry.jdbcuri",result1, table="on_click_diary_card",SaveMode.Append)
//      println("写入完成")

      GmeiConfig.writeToJDBCTable("jdbc:mysql://172.16.40.158:4000/jerry_prod?user=root&password=3SYz54LS9#^9sBvC&rewriteBatchedStatements=true",result1, table="on_click_diary_card",SaveMode.Append)
王志伟's avatar
王志伟 committed
759 760
      println("写入完成")

王志伟's avatar
王志伟 committed
761

王志伟's avatar
王志伟 committed
762 763 764 765 766 767


    }

  }

768

王志伟's avatar
王志伟 committed
769
}