testt.scala 29.9 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 6 7 8 9

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
王志伟's avatar
王志伟 committed
10
import com.gmei.GmeiConfig.{getMinusNDate, writeToJDBCTable}
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 47 48 49 50 51 52

  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")

53 54
      val stat_date = GmeiConfig.getMinusNDate(1)
//      val stat_date=param.date
王志伟's avatar
王志伟 committed
55
      val partition_date = stat_date.replace("-","")
王志伟's avatar
王志伟 committed
56
      //机构id
王志伟's avatar
王志伟 committed
57
      val blacklist = sc.sql(
王志伟's avatar
王志伟 committed
58 59 60 61
        s"""
           |select device_id from blacklist
         """.stripMargin
      )
王志伟's avatar
王志伟 committed
62
      blacklist.createOrReplaceTempView("blacklist")
王志伟's avatar
王志伟 committed
63

王志伟's avatar
王志伟 committed
64 65 66 67 68
      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
69
           |AND partition_date <= '${partition_date}'
王志伟's avatar
王志伟 committed
70 71 72 73 74
           |AND pv_ratio >= 0.95
           |UNION ALL
           |SELECT DISTINCT(cl_id) as device_id
           |FROM online.ml_hospital_spam_pv_month
           |WHERE partition_date >= '20171101'
王志伟's avatar
王志伟 committed
75
           |AND partition_date <= '${partition_date}'
王志伟's avatar
王志伟 committed
76 77 78
           |AND pv_ratio >= 0.95
         """.stripMargin
      )
79
//      agency_id.show()
王志伟's avatar
王志伟 committed
80
      agency_id.createOrReplaceTempView("agency_id")
王志伟's avatar
王志伟 committed
81 82 83
//每日新用户
      val device_id_newUser = sc.sql(
        s"""
84
           |select distinct(os.device_id) as device_id
85
           |from online.ml_device_day_active_status os left join blacklist
86
           |on os.device_id=blacklist.device_id
87 88
           |where os.active_type != '4'
           |and os.first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
89 90 91 92 93 94
           |    ,'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')
95 96
           |and os.partition_date ='${partition_date}'
           |and blacklist.device_id is null
王志伟's avatar
王志伟 committed
97 98
         """.stripMargin
      )
王志伟's avatar
王志伟 committed
99
      device_id_newUser.show()
王志伟's avatar
王志伟 committed
100 101 102 103 104
      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
105
           |select distinct(os.device_id) as device_id
106 107
           |from online.ml_device_day_active_status os left join blacklist
           |on os.device_id=blacklist.device_id
108 109
           |where os.active_type = '4'
           |and os.first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
110 111 112 113 114 115
           |    ,'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')
116
           |and os.partition_date ='${partition_date}'
117
           |and blacklist.device_id is null
王志伟's avatar
王志伟 committed
118 119
         """.stripMargin
      )
120
//      device_id_oldUser.show()
王志伟's avatar
王志伟 committed
121 122
      device_id_oldUser.createOrReplaceTempView("device_id_old")

王志伟's avatar
王志伟 committed
123 124 125

      //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
126
      val diary_meigou_temp = sc.sql(
王志伟's avatar
王志伟 committed
127
        s"""
王志伟's avatar
王志伟 committed
128
           |select ou.cl_id as device_id
王志伟's avatar
王志伟 committed
129 130 131 132 133
           |from online.bl_hdfs_page_view_updates ou left join agency_id
           |on ou.cl_id = agency_id.device_id
           |where ou.partition_date = '${partition_date}'
           |and ou.page_name='welfare_detail'
           |and ou.referrer='diary_detail'
王志伟's avatar
王志伟 committed
134
           |and agency_id.device_id is  null
王志伟's avatar
王志伟 committed
135 136 137 138 139
         """.stripMargin
      )
      diary_meigou_temp.createOrReplaceTempView("diary_meigou_temp")
      val diary_meigou_device = sc.sql(
        s"""
王志伟's avatar
王志伟 committed
140
           |select dt.device_id
王志伟's avatar
王志伟 committed
141 142 143
           |from diary_meigou_temp dt left join blacklist
           |on dt.device_id = blacklist.device_id
           |where blacklist.device_id is null
王志伟's avatar
王志伟 committed
144 145
         """.stripMargin
      )
王志伟's avatar
王志伟 committed
146 147 148 149
      diary_meigou_device.createOrReplaceTempView("diary_meigou_device")
//新用户到美购详情页的转化
      val diary_meigou_newUser = sc.sql(
        s"""
王志伟's avatar
王志伟 committed
150
           |select '${stat_date}' as stat_date, count(dd.device_id) as diary_meigou_newUser
王志伟's avatar
王志伟 committed
151 152 153 154 155 156 157 158
           |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
      )
      //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
159
           |select '${stat_date}' as stat_date, count(dd.device_id) as diary_meigou_oldUser
王志伟's avatar
王志伟 committed
160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178
           |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
      )

//      val diary_meigou_count = sc.sql(
//        s"""
//           |select '${stat_date}' as stat_date, count(page_name) as diary_meigou_count
//           |from online.bl_hdfs_page_view_updates ou left join agency_id
//           |on ou.cl_id = agency_id.device_id
//           |where ou.partition_date = '${partition_date}'
//           |and ou.page_name='welfare_detail'
//           |and ou.referrer='diary_detail'
//           |and agency_id.device_id is  null
//           |and ou.cl_id not in (select device_id from blacklist)
//         """.stripMargin
//      )
//      diary_meigou_count.show()
王志伟's avatar
王志伟 committed
179 180

      //2.日记本点击数
王志伟's avatar
王志伟 committed
181
      val diary_clk_temp = sc.sql(
王志伟's avatar
王志伟 committed
182
        s"""
王志伟's avatar
王志伟 committed
183
           |select ov.cl_id as device_id
王志伟's avatar
王志伟 committed
184 185 186 187 188
           |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
189
           |and agency_id.device_id is  null
王志伟's avatar
王志伟 committed
190 191
       """.stripMargin
      )
王志伟's avatar
王志伟 committed
192 193 194 195
      diary_clk_temp.createOrReplaceTempView("diary_clk_temp")

      val diary_clk_device = sc.sql(
        s"""
王志伟's avatar
王志伟 committed
196
           |select dt.device_id
王志伟's avatar
王志伟 committed
197 198 199 200 201 202
           |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
203 204 205 206 207
      diary_clk_device.createOrReplaceTempView("diary_clk_device")

      //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 '${stat_date}' as stat_date, count(dd.device_id) as diary_clk_newUser
王志伟's avatar
王志伟 committed
209 210 211 212 213 214 215 216
           |from diary_clk_device dd left join device_id_new
           |on dd.device_id = device_id_new.device_id
           |where device_id_new.device_id is not null
         """.stripMargin
      )
      //老用户日记本点击
      val diary_clk_oldUser = sc.sql(
        s"""
王志伟's avatar
王志伟 committed
217
           |select '${stat_date}' as stat_date, count(dd.device_id) as diary_clk_oldUser
王志伟's avatar
王志伟 committed
218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235
           |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
      )
//      val diary_clk = sc.sql(
//        s"""
//           |select '${stat_date}' as stat_date,count(cl_id) as diary_clk
//           |from online.tl_hdfs_maidian_view ov left join agency_id
//           |on ov.cl_id = agency_id.device_id
//           |where ov.action = 'on_click_diary_card'
//           |and ov.cl_id != "NULL"
//           |and ov.partition_date='${partition_date}'
//           |and agency_id.device_id is  null
//           |and ov.cl_id not in (select device_id from blacklist)
//       """.stripMargin
//      )
//      diary_clk.show()
王志伟's avatar
王志伟 committed
236 237

      //3.日记本曝光数
王志伟's avatar
王志伟 committed
238
      val diary_expoure_temp=sc.sql(
王志伟's avatar
王志伟 committed
239
        s"""
王志伟's avatar
王志伟 committed
240
           |select od.cl_id as device_id
王志伟's avatar
王志伟 committed
241 242 243 244 245
           |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
246
           |and agency_id.device_id is  null
王志伟's avatar
王志伟 committed
247 248
       """.stripMargin
      )
王志伟's avatar
王志伟 committed
249 250 251 252
      diary_expoure_temp.createOrReplaceTempView("diary_expoure_temp")

      val diary_expoure_device = sc.sql(
        s"""
王志伟's avatar
王志伟 committed
253
           |select dt.device_id
王志伟's avatar
王志伟 committed
254 255 256 257 258 259
           |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
260 261 262 263
      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
264
           |select '${stat_date}' as stat_date, count(dd.device_id) as diary_exp_newUser
王志伟's avatar
王志伟 committed
265 266 267 268 269 270 271 272
           |from diary_expoure_device dd left join device_id_new
           |on dd.device_id = device_id_new.device_id
           |where device_id_new.device_id is not null
         """.stripMargin
      )
      //老用户日记本曝光
      val diary_exp_oldUser = sc.sql(
        s"""
王志伟's avatar
王志伟 committed
273
           |select '${stat_date}' as stat_date, count(dd.device_id) as diary_exp_oldUser
王志伟's avatar
王志伟 committed
274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292
           |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
      )

//      val diary_expoure=sc.sql(
//        s"""
//           |select '${stat_date}' as stat_date,count(cl_id) as diary_expoure
//           |from online.ml_community_exposure_detail od left join agency_id
//           |on od.cl_id = agency_id.device_id
//           |where od.business_type = "diary"
//           |and od.cl_id != "NULL"
//           |and od.partition_date='${partition_date}'
//           |and agency_id.device_id is  null
//           |and od.cl_id not in (select device_id from blacklist)
//       """.stripMargin
//      )
//      diary_expoure.show()
王志伟's avatar
王志伟 committed
293 294

      //4.搜索次数统计
王志伟's avatar
王志伟 committed
295
      val search_device_temp = sc.sql(
王志伟's avatar
王志伟 committed
296
        s"""
王志伟's avatar
王志伟 committed
297
           |select ov.cl_id as device_id
王志伟's avatar
王志伟 committed
298 299 300 301
           |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
302
           |and agency_id.device_id is  null
王志伟's avatar
王志伟 committed
303 304 305 306 307 308
         """.stripMargin
      )
      search_device_temp.createOrReplaceTempView("search_device_temp")

      val search_device = sc.sql(
        s"""
王志伟's avatar
王志伟 committed
309
           |select dt.device_id
王志伟's avatar
王志伟 committed
310 311
           |from search_device_temp dt left join blacklist
           |on dt.device_id = blacklist.device_id
王志伟's avatar
王志伟 committed
312
           |where blacklist.device_id is null
王志伟's avatar
王志伟 committed
313 314
         """.stripMargin
      )
王志伟's avatar
王志伟 committed
315 316 317 318
      search_device.createOrReplaceTempView("search_device")
      //新用户搜索次数
      val search_newUser = sc.sql(
        s"""
王志伟's avatar
王志伟 committed
319
           |select '${stat_date}' as stat_date, count(sd.device_id) as search_newUser
王志伟's avatar
王志伟 committed
320 321 322 323 324 325 326 327
           |from search_device sd left join device_id_new
           |on sd.device_id = device_id_new.device_id
           |where device_id_new.device_id is not null
         """.stripMargin
      )
      //老用户日搜索次数
      val search_oldUser = sc.sql(
        s"""
王志伟's avatar
王志伟 committed
328
           |select '${stat_date}' as stat_date, count(sd.device_id) as search_oldUser
王志伟's avatar
王志伟 committed
329 330 331 332 333
           |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
334 335

      //5.登录人数
王志伟's avatar
王志伟 committed
336
      val log_device_temp = sc.sql(
王志伟's avatar
王志伟 committed
337
        s"""
王志伟's avatar
王志伟 committed
338
           |select distinct(oe.device_id)  as device_id
王志伟's avatar
王志伟 committed
339 340 341
           |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
342
           |and agency_id.device_id is  null
王志伟's avatar
王志伟 committed
343 344
         """.stripMargin
      )
王志伟's avatar
王志伟 committed
345 346 347 348
      log_device_temp.createOrReplaceTempView("log_device_temp")

      val log_device = sc.sql(
        s"""
王志伟's avatar
王志伟 committed
349
           |select dt.device_id
王志伟's avatar
王志伟 committed
350 351 352 353 354
           |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
355 356 357 358 359
      log_device.createOrReplaceTempView("log_device")

      //新用户登录人数
      val log_newUser = sc.sql(
        s"""
王志伟's avatar
王志伟 committed
360
           |select '${stat_date}' as stat_date, count(distinct(ld.device_id)) as log_newUser
王志伟's avatar
王志伟 committed
361 362 363 364 365 366 367 368
           |from log_device ld left join device_id_new
           |on ld.device_id = device_id_new.device_id
           |where device_id_new.device_id is not null
         """.stripMargin
      )
      //老用户登录人数
      val log_oldUser = sc.sql(
        s"""
王志伟's avatar
王志伟 committed
369
           |select '${stat_date}' as stat_date, count(distinct(ld.device_id)) as log_oldUser
王志伟's avatar
王志伟 committed
370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385
           |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
      )
//      val log_num = sc.sql(
//        s"""
//           |select '${stat_date}' as stat_date,count(distinct(device_id)) as log_num
//           |from data_feed_exposure oe left join agency_id
//           |on oe.device_id = agency_id.device_id
//           |and oe.stat_date ='${stat_date}'
//           |and agency_id.device_id is  null
//           |and oe.device_id not in (select device_id from blacklist)
//         """.stripMargin
//      )
//      log_num.show()
王志伟's avatar
王志伟 committed
386

王志伟's avatar
王志伟 committed
387 388 389 390 391 392 393 394 395
      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
396

王志伟's avatar
王志伟 committed
397
      GmeiConfig.writeToJDBCTable(result, "diary_meigou_crv", SaveMode.Append)
王志伟's avatar
王志伟 committed
398

王志伟's avatar
王志伟 committed
399

王志伟's avatar
王志伟 committed
400
      }
王志伟's avatar
王志伟 committed
401

王志伟's avatar
王志伟 committed
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
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

      val ti = new TiContext(sc)
      ti.tidbMapTable(dbName = "jerry_prod", tableName = "diary_video")
      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
455
      ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_exposure_precise")
456

王志伟's avatar
王志伟 committed
457 458
      val stat_date = GmeiConfig.getMinusNDate(1)
//      val stat_date=param.date
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
      val partition_date = stat_date.replace("-","")
      //机构id
      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
515
      device_id_oldUser.show()
516 517 518 519 520 521 522 523 524 525 526


      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$$'
527
           |and ot.partition_date ='${partition_date}'
528 529
         """.stripMargin
      )
王志伟's avatar
王志伟 committed
530
      clk_count_oldUser_Contrast_a.show()
531 532 533 534 535 536 537 538 539 540

      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$$'
541
           |and ot.partition_date ='${partition_date}'
542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557
         """.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
558 559 560 561 562 563 564 565 566 567 568 569 570
      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
      )


571 572
      val clk_count_oldUser_all_a = sc.sql(
        s"""
573
           |select '${stat_date}' as stat_date, count(ot.cl_id) as clk_count_oldUser_all_a
574 575 576 577 578
           |from online.tl_hdfs_maidian_view ot inner join device_id_old
           |on ot.cl_id = device_id_old.device_id
           |where ot.action='on_click_diary_card'
           |and ot.params['tab_name'] = '精选'
           |and ot.params['page_name'] = 'home'
579
           |and ot.partition_date ='${partition_date}'
580 581 582 583 584 585 586 587 588 589 590
         """.stripMargin
      )

      val clk_count_oldUser_all_b = sc.sql(
        s"""
           |select '${stat_date}' as stat_date, count(ot.cl_id) as clk_count_oldUser_all_b
           |from online.tl_hdfs_maidian_view ot inner join device_id_old
           |on ot.cl_id = device_id_old.device_id
           |where ot.action='full_stack_click_video_card_full_screen_play'
           |and ot.params['tab_name'] = '精选'
           |and ot.params["card_type"]="diary"
591
           |and ot.partition_date ='${partition_date}'
592 593 594 595 596 597 598 599 600 601 602 603 604 605 606
         """.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
607 608 609 610 611 612 613 614 615 616 617
      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
      )

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
//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
           |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
      )
      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$$'
646
           |and ot.partition_date ='${partition_date}'
647 648 649 650 651 652 653 654 655 656 657 658 659
         """.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$$'
660
           |and ot.partition_date ='${partition_date}'
661 662 663 664 665 666
         """.stripMargin
      )


      val imp_count_newUser_Contrast = sc.sql(
        s"""
667
           |select '${stat_date}' as stat_date, count(cid_id) as imp_count_newUser_Contrast
668 669 670 671 672 673 674 675 676
           |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
677
      val imp_count_newUser_Contrast_precise = sc.sql(
678
        s"""
王志伟's avatar
王志伟 committed
679 680
           |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
681 682
           |on je.device_id = device_id_new.device_id
           |where je.cid_type = 'diary'
王志伟's avatar
王志伟 committed
683 684 685 686 687 688 689
           |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
690
      val clk_count_newUser_all_a = sc.sql(
王志伟's avatar
王志伟 committed
691
        s"""
王志伟's avatar
王志伟 committed
692
           |select '${stat_date}' as stat_date, count(ot.cl_id) as clk_count_newUser_all_a
王志伟's avatar
王志伟 committed
693 694 695 696 697 698 699 700 701
           |from online.tl_hdfs_maidian_view ot inner join device_id_new
           |on ot.cl_id = device_id_new.device_id
           |where ot.action='on_click_diary_card'
           |and ot.params['tab_name'] = '精选'
           |and ot.params['page_name'] = 'home'
           |and ot.partition_date ='${partition_date}'
         """.stripMargin
      )

王志伟's avatar
王志伟 committed
702
      val clk_count_newUser_all_b = sc.sql(
王志伟's avatar
王志伟 committed
703
        s"""
王志伟's avatar
王志伟 committed
704
           |select '${stat_date}' as stat_date, count(ot.cl_id) as clk_count_newUser_all_b
王志伟's avatar
王志伟 committed
705 706 707 708 709 710 711 712 713 714
           |from online.tl_hdfs_maidian_view ot inner join device_id_new
           |on ot.cl_id = device_id_new.device_id
           |where ot.action='full_stack_click_video_card_full_screen_play'
           |and ot.params['tab_name'] = '精选'
           |and ot.params["card_type"]="diary"
           |and ot.partition_date ='${partition_date}'
         """.stripMargin
      )


王志伟's avatar
王志伟 committed
715
      val imp_count_newUser_all = sc.sql(
王志伟's avatar
王志伟 committed
716
        s"""
王志伟's avatar
王志伟 committed
717 718
           |select '${stat_date}' as stat_date, count(cid_id) as imp_count_newUser_all
           |from data_feed_exposure je inner join device_id_new
王志伟's avatar
王志伟 committed
719 720 721 722 723 724 725
           |on je.device_id = device_id_new.device_id
           |where je.cid_type = 'diary'
           |and je.device_id not in (select device_id from blacklist)
           |and je.stat_date ='${stat_date}'
         """.stripMargin
      )

王志伟's avatar
王志伟 committed
726
      val imp_count_newUser_all_precise = sc.sql(
王志伟's avatar
王志伟 committed
727
        s"""
王志伟's avatar
王志伟 committed
728
           |select '${stat_date}' as stat_date, count(cid_id) as imp_count_newUser_all_precise
王志伟's avatar
王志伟 committed
729 730 731 732 733 734 735 736
           |from data_feed_exposure_precise je inner join device_id_new
           |on je.device_id = device_id_new.device_id
           |where je.cid_type = 'diary'
           |and je.device_id not in (select device_id from blacklist)
           |and je.stat_date ='${stat_date}'
         """.stripMargin
      )

王志伟's avatar
王志伟 committed
737

王志伟's avatar
王志伟 committed
738 739 740 741 742 743 744 745 746 747 748
      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
749 750 751 752
        .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
753 754 755
      result1.show()

      GmeiConfig.writeToJDBCTable(result1, "on_click_diary_card", SaveMode.Append)
王志伟's avatar
王志伟 committed
756 757 758 759 760 761


    }

  }

762

王志伟's avatar
王志伟 committed
763
}