1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
package com.gmei
import java.io.Serializable
import org.apache.spark.sql.{SaveMode, TiContext}
import org.apache.log4j.{Level, Logger}
import scopt.OptionParser
import com.gmei.lib.AbstractParams
object WeafareStat {
Logger.getLogger("org.apache.spark").setLevel(Level.WARN)
Logger.getLogger("org.apache.eclipse.jetty.server").setLevel(Level.OFF)
case class Params(env: String = "dev"
) 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))
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 ${defaultParams.env}"
)
}
def main(args: Array[String]): Unit = {
parser.parse(args, defaultParams).map { param =>
GmeiConfig.setup(param.env)
val spark_env = GmeiConfig.getSparkSession()
val sc = spark_env._2
val ti = new TiContext(sc)
ti.tidbMapTable(dbName = "eagle",tableName = "diary_video")
ti.tidbMapTable(dbName = "jerry_prod",tableName = "data_feed_click")
ti.tidbMapTable(dbName = "eagle",tableName = "feed_diary_boost")
import sc.implicits._
val stat_date = GmeiConfig.getMinusNDate(1)
println(stat_date)
val video_cids = sc.sql(
s"""
|select distinct(cid_id) as cid_id
|from data_feed_click
|where cid_type = 'diary'
|and cid_id in (select cid from diary_video where stat_date='${stat_date}')
|and stat_date ='${stat_date}'
""".stripMargin
)
// video_cids.show()
video_cids.createOrReplaceTempView("tmp1")
val txt_cids = sc.sql(
s"""
|select distinct(cid_id) as cid_id
|from data_feed_click
|where cid_type = 'diary'
|and cid_id not in (select cid from diary_video where stat_date='${stat_date}')
|and stat_date ='${stat_date}'
""".stripMargin
)
// txt_cids.show()
txt_cids.createOrReplaceTempView("tmp2")
val partition_date = stat_date.replace("-","")
println(partition_date)
val video_meigou_count = sc.sql(
s"""
|select '${stat_date}' as stat_date, count(page_name) as video_meigou_count
|from online.bl_hdfs_page_view_updates pv inner join tmp1
|on pv.referrer_id = tmp1.cid_id
|where pv.partition_date = '${partition_date}'
|and pv.page_name='welfare_detail'
|and pv.referrer='diary_detail'
""".stripMargin
)
// video_meigou_count.show()
val txt_meigou_count = sc.sql(
s"""
|select '${stat_date}' as stat_date, count(page_name) as txt_meigou_count
|from online.bl_hdfs_page_view_updates pv inner join tmp2
|on pv.referrer_id = tmp2.cid_id
|where pv.partition_date = '${partition_date}'
|and pv.page_name='welfare_detail'
|and pv.referrer='diary_detail'
""".stripMargin
)
// txt_meigou_count.show()
val video_clk_count = sc.sql(
s"""
|select '${stat_date}' as stat_date, count(cid_id) as video_clk_count
|from data_feed_click
|where cid_type = 'diary'
|and cid_id in (select cid from diary_video where stat_date='${stat_date}')
|and stat_date='${stat_date}'
""".stripMargin
)
// video_clk_count.show()
val txt_clk_count = sc.sql(
s"""
|select '${stat_date}' as stat_date, count(cid_id) as txt_clk_count
|from data_feed_click
|where cid_type = 'diary'
|and cid_id not in (select cid from diary_video where stat_date='${stat_date}')
|and stat_date='${stat_date}'
""".stripMargin
)
// txt_clk_count.show()
val video_count = sc.sql(
s"""
|select '${stat_date}' as stat_date,count(distinct(cid)) as video_count
|from diary_video where stat_date='${stat_date}'
""".stripMargin
)
// video_count.show()
val vlog_meigou_clk_count = sc.sql(
s"""
|select '${stat_date}' as stat_date,count(page_name) as vlog_meigou_clk_num
|from online.bl_hdfs_page_view_updates
|where partition_date='${partition_date}'
|and page_name='welfare_detail'
|and referrer='diary_detail'
|and referrer_id in (select distinct(diary_id) from feed_diary_boost)
""".stripMargin
)
// vlog_meigou_clk_count.show()
val vlog_clk_count = sc.sql(
s"""
|select '${stat_date}' as stat_date,count(cid_id) as vlog_clk_num
|from data_feed_click
|where stat_date='${stat_date}'
|and cid_type = 'diary'
|and cid_id in (select distinct(diary_id) from feed_diary_boost)
""".stripMargin
)
// vlog_clk_count.show()
//日记本转化美购
//1.日记本到美购转化数
val diary_meigou_count = sc.sql(
s"""
|select '${stat_date}' as stat_date, count(page_name) as diary_meigou_count
|from online.bl_hdfs_page_view_updates
|where partition_date = '${partition_date}'
|and page_name='welfare_detail'
|and referrer='diary_detail'
""".stripMargin
)
//2.日记本点击数
val diary_clk = sc.sql(
s"""
|select '${stat_date}' as stat_date,count(cl_id) as diary_clk
|from online.tl_hdfs_maidian_view
|where action = 'on_click_diary_card'
|and cl_id != "NULL"
|and partition_date='${partition_date}'
""".stripMargin
)
//3.日记本曝光数
val diary_expoure=sc.sql(
s"""
|select '${stat_date}' as stat_date,count(cl_id) as diary_expoure
|from online.ml_community_exposure_detail
|where business_type = "diary"
|and cl_id != "NULL"
|and partition_date='${partition_date}'
""".stripMargin
)
val result = video_clk_count.join(video_meigou_count,"stat_date")
.join(txt_clk_count,"stat_date")
.join(txt_meigou_count,"stat_date")
.join(video_count,"stat_date")
.join(vlog_meigou_clk_count,"stat_date")
.join(vlog_clk_count,"stat_date")
.join(diary_meigou_count,"stat_date")
.join(diary_clk,"stat_date")
.join(diary_expoure,"stat_date")
val result1 = result.withColumn("video_meigou_rate",result.col("video_meigou_count")/result.col("video_clk_count"))
val result2 = result1.withColumn("txt_meigou_rate",result.col("txt_meigou_count")/result.col("txt_clk_count"))
val result3 = result2.withColumn("vlog_meigou_rate",result.col("vlog_meigou_clk_num")/result.col("vlog_clk_num"))
val result4=result3.withColumn("diary_meigou_rate",result.col("diary_meigou_count")/result.col("diary_clk"))
val result5 =result4.withColumn("diary_expoure_meigou_rate",result.col("diary_meigou_count")/result.col("diary_expoure"))
result5.show()
GmeiConfig.writeToJDBCTable(result5, "diary_meigou_cvr", SaveMode.Append)
sc.stop()
}
}
}
object NdDataInput {
Logger.getLogger("org.apache.spark").setLevel(Level.WARN)
Logger.getLogger("org.apache.eclipse.jetty.server").setLevel(Level.OFF)
case class Params(env: String = "dev"
) 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))
note("winter is coming")
}
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 = "nd_data_meigou_cid")
ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_click")
ti.tidbMapTable(dbName = "eagle", tableName = "feed_diary_boost")
val date8 = GmeiConfig.getMinusNDate(70)
val result00 = sc.sql(
s"""
|SELECT
| split(service_id,'\\\\|')[1] as sid,split(cid,'\\\\|')[1] as cid
|FROM nd_data_meigou_cid
|where stat_date > '${date8}'
""".stripMargin
)
result00.createOrReplaceTempView("tmp1")
result00.show()
println(result00.count())
val yesteday = GmeiConfig.getMinusNDate(1).replace("-","")
val result01 = sc.sql(
s"""
|select a.sid as sid, a.cid as cid, b.tag_id as ctag_id, c.level1_id as clevel1_id
|from tmp1 a
|left join online.tl_hdfs_diary_tags_view b on a.cid=b.diary_id
|left join online.bl_tag_hierarchy_detail c on b.tag_id=c.id
|where b.partition_date='${yesteday}'
|and c.partition_date='${yesteday}'
""".stripMargin
)
result01.createOrReplaceTempView("tmp2")
result01.show()
println(result01.count())
val result02 = sc.sql(
s"""
|select a.sid as sid, a.cid as cid, a.ctag_id as ctag_id, a.clevel1_id as clevel1_id,
| b.tag_id as stag_id, c.level1_id as slevel1_id
|from tmp2 a
|left join online.tl_meigou_servicetag_view b on a.sid=b.service_id
|left join online.bl_tag_hierarchy_detail c on b.tag_id=c.id
|where b.partition_date='${yesteday}'
|and c.partition_date='${yesteday}'
""".stripMargin
)
result02.createOrReplaceTempView("tmp3")
result02.show()
println(result02.count())
val tidb_input = sc.sql(
s"""
|select sid as service_id,cid
|from tmp3
|where clevel1_id = slevel1_id
""".stripMargin
)
tidb_input.show()
println(tidb_input.count())
}
}
}
object ServiceStat {
Logger.getLogger("org.apache.spark").setLevel(Level.WARN)
Logger.getLogger("org.apache.eclipse.jetty.server").setLevel(Level.OFF)
case class Params(env: String = "dev"
) 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))
note("winter is coming")
}
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 = "nd_data_meigou_cid")
ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_click")
ti.tidbMapTable(dbName = "eagle", tableName = "feed_diary_boost")
val result00 = sc.sql(
s"""
|select a.cl_id as device_id,
|COALESCE(a.params['diary_id'], a.params['business_id'], 0) as diary_id,
|c.level1_id as level1_id
|from online.tl_hdfs_maidian_view a
|left join online.tl_hdfs_diary_tags_view b on COALESCE(a.params['diary_id'], a.params['business_id'], 0)=b.diary_id
|left join online.bl_tag_hierarchy_detail c on b.tag_id=c.id
|where a.partition_date > "20181112"
|and a.action="on_click_diary_card"
|and a.params["page_name"]="home"
|and a.cl_id != "NULL"
|and b.partition_date="20181119"
|and c.partition_date="20181119"
""".stripMargin
)
result00.collect.foreach(println)
}
}
}