from pyspark.sql import HiveContext,SparkSession
 
_SPARK_HOST = "spark://spark-master:7077"
_APP_NAME = "test"
spark_session = SparkSession.builder.master(_SPARK_HOST).appName(_APP_NAME).getOrCreate()
 
hive_context= HiveContext(spark_session )
 
# 生成查询的SQL语句，这个跟hive的查询语句一样，所以也可以加where等条件语句
hive_database = "database1"
hive_table = "test"
hive_read = "select * from {}.{}".format(hive_database, hive_table)
 
# 通过SQL语句在hive中查询的数据直接是dataframe的形式
read_df = hive_context.sql(hive_read)

from pyspark.sql import SparkSession, HiveContext
 
_SPARK_HOST = "spark://spark-master:7077"
_APP_NAME = "test"
 
spark = SparkSession.builder.master(_SPARK_HOST).appName(_APP_NAME).getOrCreate()
 
data = [
 (1,"3","145"),
 (1,"4","146"),
 (1,"5","25"),
 (1,"6","26"),
 (2,"32","32"),
 (2,"8","134"),
 (2,"8","134"),
 (2,"9","137")
]
df = spark.createDataFrame(data, ['id', "test_id", 'camera_id'])
 
# method one，default是默认数据库的名字，write_test 是要写到default中数据表的名字
df.registerTempTable('test_hive')
sqlContext.sql("create table default.write_test select * from test_hive")

# method two
 
# "overwrite"是重写表的模式，如果表存在，就覆盖掉原始数据，如果不存在就重新生成一张表
# mode("append")是在原有表的基础上进行添加数据
df.write.format("hive").mode("overwrite").saveAsTable('default.write_test')
 

#/usr/bin/python
#-*- coding:utf-8 –*-
 
from pyspark import SparkContext
from pyspark.sql import SQLContext,HiveContext,SparkSession
from pyspark.sql.types import Row,StringType,StructField,StringType,IntegerType
from pyspark.sql.dataframe import DataFrame
 
sc = SparkContext(appName="pyspark_hbase")
sql_sc = SQLContext(sc)
 
dep = "org.apache.spark.sql.execution.datasources.hbase"
#定义schema
catalog = """{
       "table":{"namespace":"default", "name":"teacher"},
       "rowkey":"key",
       "columns":{
            "id":{"cf":"rowkey", "col":"key", "type":"string"},
            "name":{"cf":"teacherInfo", "col":"name", "type":"string"},
            "age":{"cf":"teacherInfo", "col":"age", "type":"string"},
            "gender":{"cf":"teacherInfo", "col":"gender","type":"string"},
            "cat":{"cf":"teacherInfo", "col":"cat","type":"string"},
            "tag":{"cf":"teacherInfo", "col":"tag", "type":"string"},
            "level":{"cf":"teacherInfo", "col":"level","type":"string"} }
      }"""
 
df = sql_sc.read.options(catalog = catalog).format(dep).load()
 
print ('***************************************************************')
print ('***************************************************************')
print ('***************************************************************')
df.show()
print ('***************************************************************')
print ('***************************************************************')
print ('***************************************************************')
sc.stop()