get tractate data

requirements.txt

@@ -25,7 +25,7 @@ pymysql==0.10.1
 
 gensim==3.8.3
 
-# pyspark==2.3.0
+# pyspark==2.3.3
 pytispark==2.0
 
 ipython

utils/spark.py

@@ -23,8 +23,7 @@ def get_spark(app_name=""):
     return spark
 
 
-# TODO partition_date
-def get_click_data(spark, start, end):
+def get_tracate_click_data(spark, start, end):
     reg = r"""^\\d+$"""
     sql = """
         SELECT DISTINCT t1.partition_date, t1.cl_id, cast(t1.business_id as int) card_id
@@ -33,7 +32,7 @@ def get_click_data(spark, start, end):
           from online.bl_hdfs_maidian_updates
           where action = 'page_view'
             AND partition_date BETWEEN '{}' AND '{}'
-            AND page_name='welfare_detail'
+            AND page_name='user_post_detail'
             AND page_stay>=1
             AND cl_id is not null
             AND cl_id != ''
@@ -124,3 +123,7 @@ def get_click_data(spark, start, end):
     # print("sql", flush=True)
     # print(sql, flush=True)
     return spark.sql(sql)
+
+
+def get_device_click_tractate_ids():
+    pass

word_vector/tests.py

 # from django.test import TestCase
-from datetime import date, timedelta
-
-from pyspark import SparkConf
-from pyspark.sql import SparkSession
-from pytispark import pytispark as pti
-
-# Create your tests here.
-
-
-def get_spark(app_name=""):
-    sparkConf = SparkConf()
-    sparkConf.set("spark.sql.crossJoin.enabled", True)
-    sparkConf.set("spark.debug.maxToStringFields", "100")
-    sparkConf.set("spark.tispark.plan.allow_index_double_read", False)
-    sparkConf.set("spark.tispark.plan.allow_index_read", True)
-    sparkConf.set("spark.hive.mapred.supports.subdirectories", True)
-    sparkConf.set("spark.hadoop.mapreduce.input.fileinputformat.input.dir.recursive", True)
-    sparkConf.set("spark.serializer", "org.apache.spark.serializer.KryoSerializer")
-    sparkConf.set("mapreduce.output.fileoutputformat.compress", False)
-    sparkConf.set("mapreduce.map.output.compress", False)
-    spark = (SparkSession.builder.config(conf=sparkConf).config(
-        "spark.sql.extensions",
-        "org.apache.spark.sql.TiExtensions").config("spark.tispark.pd.addresses",
-                                                    "172.16.40.170:2379").appName(app_name).enableHiveSupport().getOrCreate())
-    ti = pti.TiContext(spark)
-    ti.tidbMapDatabase("jerry_test")
-    return spark
-
-
-def getNDaysBeforeWithFormat(n, format):
-    yesterday = (date.today() + timedelta(days=-n)).strftime(format)
-    return yesterday
-
-
-def getNDaysBeforeNoMinus(n):
-    return getNDaysBeforeWithFormat(n, "%Y%m%d")
-
-
-def getClickDataForLr(spark, start, end):
-    reg = r"""^\\d+$"""
-    positiveSql = """
-        SELECT DISTINCT t1.partition_date, t1.cl_id, cast(t1.business_id as int) card_id
-          FROM
-          (select partition_date,cl_id,business_id,action,page_name,page_stay
-          from online.bl_hdfs_maidian_updates
-          where action = 'page_view'
-            AND partition_date BETWEEN '{}' AND '{}'
-            AND page_name='welfare_detail'
-            AND page_stay>=1
-            AND cl_id is not null
-            AND cl_id != ''
-            AND business_id is not null
-            AND business_id != ''
-            AND business_id rlike '{}'
-            ) AS t1
-          JOIN
-          (select partition_date,active_type,first_channel_source_type,device_id
-          from online.ml_device_day_active_status
-          where partition_date BETWEEN '{}' AND '{}'
-            AND active_type IN ('1', '2', '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','promotion_zuimei')
-            AND first_channel_source_type not LIKE 'promotion\\_jf\\_%') as t2
-          ON t1.cl_id = t2.device_id
-          AND t1.partition_date = t2.partition_date
-      LEFT JOIN
-    (
-        SELECT DISTINCT device_id
-        FROM ml.ml_d_ct_dv_devicespam_d  --去除机构刷单设备，即作弊设备（浏览和曝光事件去除）
-        WHERE partition_day='{}'
-
-        UNION ALL
-        SELECT DISTINCT device_id
-        FROM dim.dim_device_user_staff   --去除内网用户
-    )spam_pv
-    on spam_pv.device_id=t1.cl_id
-        LEFT JOIN
-    (
-        SELECT partition_date,device_id
-        FROM
-        (--找出user_id当天活跃的第一个设备id
-            SELECT user_id,partition_date,
-                    if(size(device_list) > 0, device_list [ 0 ], '') AS device_id
-              FROM online.ml_user_updates
-              WHERE partition_date>='{}' AND partition_date<'{}'
-        )t1
-        JOIN
-        (  --医生账号
-            SELECT distinct user_id
-            FROM online.tl_hdfs_doctor_view
-            WHERE partition_date = '{}'
-
-            --马甲账号/模特用户
-            UNION ALL
-            SELECT user_id
-            FROM ml.ml_c_ct_ui_user_dimen_d
-            WHERE partition_day = '{}'
-            AND (is_puppet = 'true' or is_classifyuser = 'true')
-
-            UNION ALL
-            --公司内网覆盖用户
-            select distinct user_id
-            from dim.dim_device_user_staff
-
-            UNION ALL
-            --登陆过医生设备
-            SELECT distinct t1.user_id
-            FROM
-            (
-                SELECT user_id, v.device_id as device_id
-                FROM online.ml_user_history_detail
-                    LATERAL VIEW EXPLODE(device_history_list) v AS device_id
-                WHERE partition_date = '{}'
-            )t1
-            JOIN
-            (
-                SELECT device_id
-                FROM online.ml_device_history_detail
-                WHERE partition_date = '{}'
-                AND is_login_doctor = '1'
-            )t2
-                ON t1.device_id = t2.device_id
-        )t2
-        on t1.user_id=t2.user_id
-        group by partition_date,device_id
-    )dev
-    on t1.partition_date=dev.partition_date and t1.cl_id=dev.device_id
-    WHERE (spam_pv.device_id IS NULL or spam_pv.device_id ='')
-    and (dev.device_id is null or dev.device_id ='')
-     """.format(start, end, reg, start, end, end, start, end, end, end, end, end)
-    # print('positiveSql',flush=True)
-    # print(positiveSql,flush=True)
-    return spark.sql(positiveSql)
+from utils.date import get_ndays_before_no_minus
+from utils.spark import get_spark, get_tracate_click_data
 
+# create your tests here.
 
 if __name__ == "__main__":
     spark = get_spark("test")
-    yesterday = getNDaysBeforeNoMinus(1)
-    startDay = getNDaysBeforeNoMinus(2)
-    clickData = getClickDataForLr(spark, startDay, yesterday)
-    clickData.show(5, False)
+    click_data = get_tracate_click_data(spark, get_ndays_before_no_minus(2), get_ndays_before_no_minus(1))
+    click_data.show(5, False)
 
 # /opt/spark/bin/spark-submit --master yarn --deploy-mode client --queue root.strategy --driver-memory 16g --executor-memory 1g --executor-cores 1 --num-executors 70 --conf spark.default.parallelism=100 --conf spark.storage.memoryFraction=0.5 --conf spark.shuffle.memoryFraction=0.3 --conf spark.locality.wait=0 --jars /srv/apps/tispark-core-2.1-SNAPSHOT-jar-with-dependencies.jar,/srv/apps/spark-connector_2.11-1.9.0-rc2.jar,/srv/apps/mysql-connector-java-5.1.38.jar /srv/apps/strategy_embedding/word_vector/tests.py