--driver-memory MEM         Memory for driver (e.g. 1000M, 2G) (Default: 1024M). 

from pyspark import SparkContext
sc = SparkContext(master='yarn')
rdd = sc.parallelize(range(300000000))
# spark-submit --master yarn-client  --driver-memory 512M  driver_oom.py    内存溢出
# spark-submit --master yarn-client  --driver-memory 3G  driver_oom.py  可以执行

rdd = sc.parallelize(range(100))
rdd.flatMap(lambda x: ['%d'%x*50 for _ in range(100000)]).collect()     # 内存溢出

def func(x): print(x)
rdd.flatMap(lambda x: ['%d'%x*50 for _ in range(100000)]).foreach(func) # 分区输出

rdd.flatMap(lambda x: ['%d'%x*50 for _ in range(100000000)]).count()      # 100 * 100000000 个对象，内存溢出
rdd.flatMap(lambda x: len(['%d'%x*50 for _ in range(100000000)])).sum()     # 内存溢出

rdd.repartition(1000000).flatMap(lambda x: ['%d'%x*50 for _ in range(100000000)]).count()   

with table_name as(子查询语句) 其他sql;

with temp as (
    select * from xxx
)
select * from temp;

CREATE VIEW [IF NOT EXISTS] view_name [(column_name [COMMENT column_comment], ...) ]
[COMMENT table_comment]
AS SELECT ...

hive> CREATE VIEW emp_30000 AS
   > SELECT * FROM employee
   > WHERE salary>30000;
   

DROP VIEW view_name

select coalesce(success_cnt,period,1) from tableA

array_contains(array，值)

Cast(字段名 as 转换的类型 )

1 public class classname extends UDF
2 编写evalute

select udf1（col1） from table1

load data [local] inpath ‘/opt/module/datas/student.txt’ [overwrite] | into table tabName [partition (partcol1=val1,…)];

load data inpath '/origin_data/gmall/log/topic_log/2020-06-14' into table ods_log partition(dt='2020-06-14')

1
insert into table student  partition(month='20201022') values(1,'zhangsan');
2 
insert overwrite table student partition(month='20201023')
select id, name from student where month='20201023';

CREATE EXTERNAL TABLE dim_sku_info (
    `id` STRING COMMENT '商品id',
    `price` DECIMAL(16,2) COMMENT '商品价格',
    `sku_name` STRING COMMENT '商品名称',
    `sku_desc` STRING COMMENT '商品描述',
    `weight` DECIMAL(16,2) COMMENT '重量',
    `is_sale` BOOLEAN COMMENT '是否在售',
    `spu_id` STRING COMMENT 'spu编号',
    `spu_name` STRING COMMENT 'spu名称',
    `category3_id` STRING COMMENT '三级分类id',
    `category3_name` STRING COMMENT '三级分类名称',
    `category2_id` STRING COMMENT '二级分类id',
    `category2_name` STRING COMMENT '二级分类名称',
    `category1_id` STRING COMMENT '一级分类id',
    `category1_name` STRING COMMENT '一级分类名称',
    `tm_id` STRING COMMENT '品牌id',
    `tm_name` STRING COMMENT '品牌名称',
    `sku_attr_values` ARRAY<STRUCT<attr_id:STRING,value_id:STRING,attr_name:STRING,value_name:STRING>> COMMENT '平台属性',
    `sku_sale_attr_values` ARRAY<STRUCT<sale_attr_id:STRING,sale_attr_value_id:STRING,sale_attr_name:STRING,sale_attr_value_name:STRING>> COMMENT '销售属性',
    `create_time` STRING COMMENT '创建时间'
) COMMENT '商品维度表'

--建表
DROP TABLE IF EXISTS dwd_display_log;
CREATE EXTERNAL TABLE dwd_display_log(
    `area_code` STRING COMMENT '地区编码',
    `brand` STRING COMMENT '手机品牌',
    `channel` STRING COMMENT '渠道',
    `is_new` STRING COMMENT '是否首次启动',
    `model` STRING COMMENT '手机型号',
    `mid_id` STRING COMMENT '设备id',
    `os` STRING COMMENT '操作系统',
    `user_id` STRING COMMENT '会员id',
    `version_code` STRING COMMENT 'app版本号',
    `during_time` BIGINT COMMENT 'app版本号',
    `page_item` STRING COMMENT '目标id ',
    `page_item_type` STRING COMMENT '目标类型',
    `last_page_id` STRING COMMENT '上页类型',
    `page_id` STRING COMMENT '页面ID ',
    `source_type` STRING COMMENT '来源类型',
    `ts` BIGINT COMMENT 'app版本号',
    `display_type` STRING COMMENT '曝光类型',
    `item` STRING COMMENT '曝光对象id ',
    `item_type` STRING COMMENT 'app版本号',
    `order` BIGINT COMMENT '曝光顺序',
    `pos_id` BIGINT COMMENT '曝光位置'
) COMMENT '曝光日志表'
PARTITIONED BY (`dt` STRING)
STORED AS PARQUET
LOCATION '/warehouse/gmall/dwd/dwd_display_log'
TBLPROPERTIES('parquet.compression'='lzo');
--加载数据
insert overwrite table dwd_display_log partition(dt='2020-06-14')
select
    get_json_object(line,'$.common.ar'),
    get_json_object(line,'$.common.ba'),
    get_json_object(line,'$.common.ch'),
    get_json_object(line,'$.common.is_new'),
    get_json_object(line,'$.common.md'),
    get_json_object(line,'$.common.mid'),
    get_json_object(line,'$.common.os'),
    get_json_object(line,'$.common.uid'),
    get_json_object(line,'$.common.vc'),
    get_json_object(line,'$.page.during_time'),
    get_json_object(line,'$.page.item'),
    get_json_object(line,'$.page.item_type'),
    get_json_object(line,'$.page.last_page_id'),
    get_json_object(line,'$.page.page_id'),
    get_json_object(line,'$.page.source_type'),
    get_json_object(line,'$.ts'),
    get_json_object(display,'$.display_type'),
    get_json_object(display,'$.item'),
    get_json_object(display,'$.item_type'),
    get_json_object(display,'$.order'),
    get_json_object(display,'$.pos_id')
from ods_log lateral view explode_json_array(get_json_object(line,'$.displays')) tmp as display
where dt='2020-06-14'
and get_json_object(line,'$.displays') is not null;

--建表
DROP TABLE IF EXISTS dwd_comment_info;
CREATE EXTERNAL TABLE dwd_comment_info(
    `id` STRING COMMENT '编号',
    `user_id` STRING COMMENT '用户ID',
    `sku_id` STRING COMMENT '商品sku',
    `spu_id` STRING COMMENT '商品spu',
    `order_id` STRING COMMENT '订单ID',
    `appraise` STRING COMMENT '评价(好评、中评、差评、默认评价)',
    `create_time` STRING COMMENT '评价时间'
) COMMENT '评价事实表'
PARTITIONED BY (`dt` STRING)
STORED AS PARQUET
LOCATION '/warehouse/gmall/dwd/dwd_comment_info/'
TBLPROPERTIES ("parquet.compression"="lzo");
--加载数据
insert overwrite table dwd_comment_info partition (dt)
select
    id,
    user_id,
    sku_id,
    spu_id,
    order_id,
    appraise,
    create_time,
    date_format(create_time,'yyyy-MM-dd')
from ods_comment_info
where dt='2020-0

SELECT column_name
INTO newtable
FROM table1;