python start sucess

eda/esmm/Model_pipline/dist_predict.py

@@ -176,25 +176,25 @@ def test_map(x):
 
 
 if __name__ == "__main__":
-    # sparkConf = SparkConf().set("spark.hive.mapred.supports.subdirectories", "true") \
-    #     .set("spark.hadoop.mapreduce.input.fileinputformat.input.dir.recursive", "true") \
-    #     .set("spark.tispark.plan.allow_index_double_read", "false") \
-    #     .set("spark.tispark.plan.allow_index_read", "true") \
-    #     .set("spark.sql.extensions", "org.apache.spark.sql.TiExtensions") \
-    #     .set("spark.tispark.pd.addresses", "172.16.40.158:2379").set("spark.io.compression.codec", "lzf")\
-    #     .set("spark.driver.maxResultSize", "8g").set("spark.sql.avro.compression.codec","snappy")
-    # spark = SparkSession.builder.config(conf=sparkConf).enableHiveSupport().getOrCreate()
-    # spark.sparkContext.setLogLevel("WARN")
+    sparkConf = SparkConf().set("spark.hive.mapred.supports.subdirectories", "true") \
+        .set("spark.hadoop.mapreduce.input.fileinputformat.input.dir.recursive", "true") \
+        .set("spark.tispark.plan.allow_index_double_read", "false") \
+        .set("spark.tispark.plan.allow_index_read", "true") \
+        .set("spark.sql.extensions", "org.apache.spark.sql.TiExtensions") \
+        .set("spark.tispark.pd.addresses", "172.16.40.158:2379").set("spark.io.compression.codec", "lzf")\
+        .set("spark.driver.maxResultSize", "8g").set("spark.sql.avro.compression.codec","snappy")
+    spark = SparkSession.builder.config(conf=sparkConf).enableHiveSupport().getOrCreate()
+    spark.sparkContext.setLogLevel("WARN")
 
     path = "hdfs://172.16.32.4:8020/strategy/esmm/"
     # df = spark.read.format("tfrecords").load(path+"nearby/part-r-00000")
     # df.show()
 
-    # name = spark.sparkContext.parallelize([1,2,3,4,5])
-    #
-    # test = name.repartition(5).map(lambda x: test_map(x))
-    # print(test)
-    # print(test.collect())
+    name = spark.sparkContext.parallelize([1,2,3,4,5])
+
+    test = name.repartition(5).map(lambda x: test_map(x))
+    print(test)
+    print(test.collect())
 
     tf.logging.set_verbosity(tf.logging.INFO)
     # te_files = [[path+"nearby/part-r-00000"],[path+"native/part-r-00000"]]