修改test文件

tensnsorflow/test.py

 
 import datetime
-from pyspark.sql import HiveContext
-from pyspark.context import SparkContext
-from pyspark.conf import SparkConf
-from pyspark.sql import SQLContext
-from pyspark.sql import SparkSession
-from py4j.java_gateway import java_import
-import pytispark.pytispark as pti
+# from pyspark.sql import HiveContext
+# from pyspark.context import SparkContext
+# from pyspark.conf import SparkConf
+# from pyspark.sql import SQLContext
+# from pyspark.sql import SparkSession
+# from py4j.java_gateway import java_import
+# import pytispark.pytispark as pti
 import pandas as pd
 import pymysql
 
@@ -25,35 +25,35 @@ def con_sql(db,sql):
     return df
 
 
-def test():
-        conf = SparkConf().setAppName("My App").set("spark.io.compression.codec", "lzf")
-        sc = SparkContext(conf = conf)
-        hive_context = HiveContext(sc)
-        hive_context.sql(''' select device["device_type"] from online.tl_hdfs_maidian_view 
-        where partition_date = '20181012' and action = "page_view" 
-        and params["page_name"] = "diary_detail" and params["referrer"] = "home" limit 10 ''').show(6)
+# def test():
+#         conf = SparkConf().setAppName("My App").set("spark.io.compression.codec", "lzf")
+#         sc = SparkContext(conf = conf)
+#         hive_context = HiveContext(sc)
+#         hive_context.sql(''' select device["device_type"] from online.tl_hdfs_maidian_view
+#         where partition_date = '20181012' and action = "page_view"
+#         and params["page_name"] = "diary_detail" and params["referrer"] = "home" limit 10 ''').show(6)
 
 
-def esmm_pre():
-    yesterday = (datetime.date.today() - datetime.timedelta(days=1)).strftime("%Y-%m-%d")
-    print(yesterday)
-
-    spark = SparkSession.builder.enableHiveSupport().getOrCreate()
-    # gw = SparkContext._gateway
-    #
-    # # Import TiExtensions
-    # java_import(gw.jvm, "org.apache.spark.sql.TiContext")
-
-    # Inject TiExtensions, and get a TiContext
-    # ti = gw.jvm.TiExtensions.getInstance(spark._jsparkSession).getOrCreateTiContext(spark._jsparkSession)
-    ti = pti.TiContext(spark)
-
-    ti.tidbMapDatabase("jerry_test")
-
-    # sql("use tpch_test")
-    spark.sql("select count(*) from esmm_pre_data").show(6)
-
-    # conf = SparkConf().setAppName("esmm_pre").set("spark.io.compression.codec", "lzf")
+# def esmm_pre():
+#     yesterday = (datetime.date.today() - datetime.timedelta(days=1)).strftime("%Y-%m-%d")
+#     print(yesterday)
+#
+#     spark = SparkSession.builder.enableHiveSupport().getOrCreate()
+#     # gw = SparkContext._gateway
+#     #
+#     # # Import TiExtensions
+#     # java_import(gw.jvm, "org.apache.spark.sql.TiContext")
+#
+#     # Inject TiExtensions, and get a TiContext
+#     # ti = gw.jvm.TiExtensions.getInstance(spark._jsparkSession).getOrCreateTiContext(spark._jsparkSession)
+#     ti = pti.TiContext(spark)
+#
+#     ti.tidbMapDatabase("jerry_test")
+#
+#     # sql("use tpch_test")
+#     spark.sql("select count(*) from esmm_pre_data").show(6)
+#
+#     # conf = SparkConf().setAppName("esmm_pre").set("spark.io.compression.codec", "lzf")
 #
 #     spark.sql("""
 #     select concat(tmp1.device_id,",",tmp1.city_id) as device_city, tmp1.merge_queue from (select device_id,if(city_id='world','worldwide',city_id) city_id,similarity_cid as merge_queue from nd_device_cid_similarity_matrix