update requirements

requirements.txt

@@ -7,7 +7,6 @@ git+ssh://git@git.wanmeizhensuo.com/system/kafka-python.git@master
 git+ssh://git@git.wanmeizhensuo.com/backend/gm-types.git@master
 
 faiss-cpu==1.6.3
-pandas==1.1.1
 elasticsearch==7.0.0
 opencv-python==4.4.0.42
 pillow==7.2.0
@@ -15,6 +14,7 @@ dlib==19.21.0
 requests==2.24.0
 redis==3.5.3
 numpy
+pandas
 
 django==1.10.6
 django-extensions==1.9.9
@@ -25,5 +25,7 @@ pymysql==0.10.1
 
 gensim==3.8.3
 
-pyspark==2.3.0
+# pyspark==2.3.0
 pytispark==2.0
+
+ipython

utils/date.py

+from datetime import date, timedelta
+
+
+def get_ndays_before_with_format(n, format):
+    yesterday = (date.today() + timedelta(days=-n)).strftime(format)
+    return yesterday
+
+
+def get_ndays_before_no_minus(n):
+    return get_ndays_before_with_format(n, "%Y%m%d")

utils/spark.py

+from pyspark import SparkConf
+from pyspark.sql import SparkSession
+from pytispark import pytispark as pti
+
+
+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
+
+
+# TODO partition_date
+def get_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
+          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("sql", flush=True)
+    # print(sql, flush=True)
+    return spark.sql(sql)

word_vector/tests.py

@@ -8,7 +8,7 @@ from pytispark import pytispark as pti
 # Create your tests here.
 
 
-def get_spark(name=""):
+def get_spark(app_name=""):
     sparkConf = SparkConf()
     sparkConf.set("spark.sql.crossJoin.enabled", True)
     sparkConf.set("spark.debug.maxToStringFields", "100")
@@ -22,7 +22,7 @@ def get_spark(name=""):
     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(name).enableHiveSupport().getOrCreate())
+                                                    "172.16.40.170:2379").appName(app_name).enableHiveSupport().getOrCreate())
     ti = pti.TiContext(spark)
     ti.tidbMapDatabase("jerry_test")
     return spark