# -*- coding: utf-8 -*- 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(): conf = SparkConf().setAppName("My App").set("spark.io.compression.codec", "lzf") sc = SparkContext(conf = conf) spark = SparkSession.builder.enableHiveSupport().getOrCreate() # ti = pti.TiContext(spark) # ti.tidbMapDatabase("jerry_test") spark = SparkSession.builder.appName("hello test").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'") # hive_context.sql("SET mapreduce.job.queuename=data") # hive_context.sql("SET mapred.input.dir.recursive=true") # hive_context.sql("SET hive.mapred.supports.subdirectories=true") sql = "select user_id from online.tl_hdfs_maidian_view where partition_date = '20190412' limit 10" 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") \ .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") 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)