修改test文件

tensnsorflow/multi.py

@@ -2,17 +2,28 @@
 from pyspark.sql import HiveContext
 from pyspark.context import SparkContext
 from pyspark.conf import SparkConf
-import pytispark.pytispark as pti
-from pyspark.sql import SQLContext
+# import pytispark.pytispark as pti
+# from pyspark.sql import SQLContext
 from pyspark.sql import SparkSession
 import datetime
 
 
 def test():
-    spark = SparkSession.builder.enableHiveSupport().getOrCreate()
-    ti = pti.TiContext(spark)
-    ti.tidbMapDatabase("jerry_test")
-    df = spark.sql("select max(stat_date) from esmm_train_data")
+    sparkConf = SparkConf().set("spark.tispark.plan.allow_index_double_read", "false")\
+        .set("spark.tispark.plan.allow_index_read", "true")\
+        .set("spark.hive.mapred.supports.subdirectories", "true")\
+        .set("spark.hadoop.mapreduce.input.fileinputformat.input.dir.recursive", "true")
+    spark = SparkSession.builder.config("spark.sql.extensions", "org.apache.spark.sql.TiExtensions")\
+        .config("spark.tispark.pd.addresses", "172.16.40.158:2379")\
+        .config(sparkConf).enableHiveSupport().getOrCreate()
+    spark.sql("use online")
+    spark.sql("ADD JAR hdfs:///user/hive/share/lib/udf/brickhouse-0.7.1-SNAPSHOT.jar")
+    spark.sql("ADD JAR hdfs:///user/hive/share/lib/udf/hive-udf-1.0-SNAPSHOT.jar")
+    spark.sql("CREATE TEMPORARY FUNCTION json_map AS 'brickhouse.udf.json.JsonMapUDF'")
+    spark.sql("CREATE TEMPORARY FUNCTION is_json AS 'com.gmei.hive.common.udf.UDFJsonFormatCheck'")
+    spark.sparkContext.setLogLevel("WARN")
+
+    df = spark.sql("select max(stat_date) from jerry_test.esmm_train_data")
     df.show()
     t = df.rdd.map(lambda x: str(x[0])).collect()
     print(t.count())