change testflie

tensnsorflow/test.py

@@ -3,6 +3,7 @@ from pyspark.context import SparkContext
 from pyspark.conf import SparkConf
 import pytispark.pytispark as pti
 from pyspark.sql import SparkSession
+import numpy as np
 
 
 def test():
@@ -27,6 +28,11 @@ def test():
         spark.sql(sql).show(6)
 
 
+def some_function(x):
+    # Use the libraries to do work
+    return np.sin(x)**2 + 2
+
+
 if __name__ == '__main__':
         sparkConf = SparkConf().set("spark.hive.mapred.supports.subdirectories", "true") \
                 .set("spark.hadoop.mapreduce.input.fileinputformat.input.dir.recursive", "true") \
@@ -37,16 +43,15 @@ if __name__ == '__main__':
                 .set("spark.driver.maxResultSize", "8g")
 
         spark = SparkSession.builder.config(conf=sparkConf).enableHiveSupport().getOrCreate()
-        ti = pti.TiContext(spark)
-        ti.tidbMapDatabase("jerry_test")
-        spark.sparkContext.setLogLevel("WARN")
-        sql = "select stat_date,cid_id,y,ccity_name from esmm_train_data limit 60"
-        spark.sql(sql).show(6)
+        # ti = pti.TiContext(spark)
+        # ti.tidbMapDatabase("jerry_test")
+        # spark.sparkContext.setLogLevel("WARN")
+        # sql = "select stat_date,cid_id,y,ccity_name from esmm_train_data limit 60"
+        # spark.sql(sql).show(6)
+
+        rdd = (spark.parallelize(range(1000))
+               .map(some_function)
+               .take(10))
+
+        print(rdd)
 
-        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'")
-        sql = "select user_id from online.tl_hdfs_maidian_view where partition_date = '20190412' limit 10"
-        spark.sql(sql).show(6)
\ No newline at end of file