add dist sort

eda/esmm/Model_pipline/dist_sort.py

@@ -98,6 +98,25 @@ def main():
         print(e)
 
 
-if __name__ == '__main__':
+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")
+
+    path = "hdfs://172.16.32.4:8020/strategy/esmm/"
+    # df = spark.read.format("tfrecords").load(path+"nearby/part-r-00000")
+    # df.show()
+
+    uid1 = spark.read.format("csv").options(sep="\t",header=True).load(path+"nearby/nearby.csv")
+    uid1.show()
+    pred1 = spark.read.format("csv").options(sep="\t").load(path+"nearby/pred.txt")
+    pred1.show()
+
     path = "/home/gmuser/esmm"
     main()
\ No newline at end of file