zoukankan      html  css  js  c++  java
  • pig的limit无效(返回所有记录)sample有效

    pig中,limit可以取样少部分数据,但有很多问题,比如数据不能少于10条,否则返回全部。

    今天又遇到另一个问题:

    group后的数据,limit无效:也就是group后的数据,不能用limit,估计是含group结构不行(没验证)

    相比而言sample比较好,我试了一下是可以的,对group后的数据也能有作用


    测试代码如下:


    origin_cleaned_data = LOAD '$cleanedLog' as 省略;

    STORE  origin_cleaned_data INTO '/user/wizad/tmp/origin_cleaned_data' USING PigStorage(',');
    DESCRIBE origin_cleaned_data;


    test_data = foreach origin_cleaned_data generate $0,$1,$2,$3, $4;
    ts_limit = limit origin_cleaned_data 100;--可以看到返回100条数据
    STORE ts_limit INTO '/user/wizad/tmp/my' USING PigStorage(',');


    g_log = group test_data by ($2,$4);
    DESCRIBE g_log;


    alldata = limit g_log 10;

    dump alldata;--返回了全部数据,limit 无效


    返回的group结构如下

    origin_cleaned_data: 
    {

    wizad_ad_id: chararray,
    guid: chararray,
    android_id: chararray,

    imei: chararray,

    app_category_id: chararray

    }


    g_log: {
    group: (android_id: chararray,app_category_id: chararray),
    test_data: {
    wizad_ad_id: chararray,
    guid: chararray,
    android_id: chararray,

    imei: chararray,

    app_category_id: chararray
    }
    }






    对sample的测试:

    test_data = foreach origin_cleaned_data generate wizad_ad_id,guid,android_id,imei,app_category_id;
    g_log = group test_data by ($2,$4);
    DESCRIBE g_log;

    myts = sample g_log 0.0001;
    STORE myts INTO '/user/wizad/tmp/my' USING PigStorage(',');

    dump myts;
    describe myts;


    结果如下:

    g_log: {
    group: (android_id: chararray,app_category_id: chararray),
    test_data: {wizad_ad_id: chararray,guid: chararray,android_id: chararray,imei: chararray,app_category_id: chararray}
    }

    myts: {
    group: (android_id: chararray,app_category_id: chararray),
    test_data: {wizad_ad_id: chararray,guid: chararray,android_id: chararray,imei: chararray,app_category_id: chararray}
    }

    ((-1,),{(74,9051235c-a391-4dae-ab22-f93d24a12636,-1,-1,),(75,053e9f48-03bf-4b39-9455-ff412a725a3c,-1,-1,),(75,e77c7cd1-c2ae-4fdb-bc07-992235b97b58,-1,-1,),(74,f2752e0b-b5e6-4310-849a-12c5dd10a0c5,-1,-1,),(74,a9072546-3cd9-4215-9d0c-b0632d201505,-1,-1,),(74,68b5a933-f452-4850-8b93-59acd60b0e9a,-1,-1,),(74,8c4d6d1c-644c-4287-9a86-3117bfaf430b,-1,-1,),(74,a4efdcb5-9a2e-42c4-8c8f-d32c0a22e765,-1,-1,),(74,49d6e13e-4080-4739-b0dc-ad3f89e4bdf9,-1,-1,),(74,7982b4b1-d925-4404-91c6-e59d96f2a074,-1,-1,),(74,051d62e1-634e-4a22-abe6-d2653c3165fb,-1,-1,),(74,2e7350b4-450a-4124-9e5b-ed083dcef902,-1,-1,),(74,5a7cf340-4f66-4b43-862e-49acd8beeea3,-1,-1,),(74,e6abe1d5-3070-4e2a-9e86-358b21f0cd6b,-1,-1,),(74,5d6f3f9a-d194-4ccd-b465-25703c8047e0,-1,-1,),(74,76aa0b57-c68c-42f6-ba4b-bbd5a386eb1a,-1,-1,),(74,915ec619-52dd-4bd1-b8d5-2479c9a5467a,-1,-1,),(74,433521f3-e677-4159-80bc-f918ba5bd49c,-1,-1,),(74,51e0b6f3-26a2-4531-9a0f-337f25a4c171,-1,-1,),(74,dfe58439-29d6-4a05-84d1-0dd0ee033dc7,-1,-1,),(74,f46d55c8-5f5f-4f50-a9ef-75d3f25ea21c,-1,-1,),(74,2623d054-dbe1-433e-97c6-5d568d49442f,-1,-1,),(74,86bc62e7-7e96-415a-a5bc-2d8e1483e6db,-1,-1,),(74,68a5a8b7-4b4c-49ce-b323-3baebd9f814f,-1,-1,),(74,5d58bc0e-14a9-45ec-bc2c-9d06780b2d9b,-1,-1,),(74,d896d166-327e-4187-a4c6-4c2fd58876a5,-1,-1,),(74,e214a7f9-2c2c-4875-85ac-011b431296f3,-1,-1,),(74,3743bc6a-09af-4d44-a058-9caf7b2374dd,-1,-1,),(74,777c5eb8-0b12-46fb-968f-9e9679794abf,-1,-1,),(74,550e9982-f62d-4bba-bce9-5fb98ea28e22,-1,-1,),(74,68e96b35-62a4-4160-aa56-b9f7aed4da52,-1,-1,),(74,1b5dc09b-f03c-4fa3-b290-7388afacbea7,-1,-1,),(74,44e4afc0-e439-4853-a004-9467d363dd0a,-1,-1,),(74,05f01d54-2c5c-44c1-a24b-213f1b0a184d,-1,-1,),(74,169f9282-0437-43af-98c4-e078fc360533,-1,-1,),(74,2bb741f9-170f-4fa4-955f-370605f8261d,-1,-1,),(74,9bc1a4dc-0324-4007-8be0-93a4b3286b49,-1,-1,),(74,2e820c47-bce6-45df-a1e6-3751f76b11f5,-1,-1,),(74,e2b26638-c2bb-4375-8498-bc94bf590b18,-1,-1,),(74,a02e372d-6773-4282-9925-44def1d6c564,-1,-1,),(74,b7da49ce-5ba3-41d4-ba18-8eade05c9745,-1,-1,),(74,b44017a5-b5c9-45ba-8903-6a6de996772b,-1,-1,),(74,da0e84c3-78f3-4b19-a695-c00d8f114299,-1,-1,),(74,f935cf93-8867-4496-8315-bd4045b1b6b9,-1,-1,),(74,5827b614-03cc-47a5-bc40-5c6952488617,-1,-1,),(74,8771188e-cc86-43b8-bcc1-ad632dfd56cb,-1,-1,),(74,2619bcf9-bed6-45de-a25e-003cd73a9ffc,-1,-1,),(74,1dd06a98-cf68-4130-9f0f-d2dcf1809085,-1,-1,),(74,b3f2c66a-6988-4ede-8f11-66e34764e93c,-1,-1,),(74,b1ab5c0b-5e1c-4e0f-99eb-07dc7722b7a4,-1,-1,),(74,c0698e6f-6e2e-4456-8bc0-c438276f0b36,-1,-1,),(74,feb44a38-ac42-4fb4-a7f1-30d087709a97,-1,-1,),(74,0387bcf5-04e2-49f9-af3c-65bb6875b09d,-1,-1,),(74,f3711f23-2a34-49af-89f8-130f299eb17d,-1,-1,),(74,85f13431-5be6-4d72-ad97-9873b2c6c2e7,-1,-1,),(74,21ca723c-ec2b-4242-8108-b95436f10e3e,-1,-1,),(74,fec1932a-b0e4-4bf0-b504-8ed8f3c159e7,-1,-1,),(74,d74374ec-8cf4-4c4a-b598-9631f6972cbb,-1,-1,),(74,6780962a-bf75-4c4c-a557-94a7de5a3e36,-1,-1,),(74,14517915-ee3f-4d34-943f-d6f1813afdef,-1,-1,),(74,c5547aca-3b8b-4108-93ba-bf365c106cdd,-1,-1,),(74,e9a986c1-6868-4f7f-baf6-69d8c302583e,-1,-1,),(74,9c1341cf-45b8-48c6-b699-33b1a4215c66,-1,-1,),(74,f16e6222-a84b-4758-ae71-0613c8f34b29,-1,-1,),(74,47cc25ef-05bc-47f4-a32b-3cddaf0ac22b,-1,-1,),(74,d5c1b6b0-38c3-464b-8cb9-70ced875be5f,-1,-1,),(74,6a4f782a-1f5c-45c0-bb3a-4df25c436be3,-1,-1,),(74,23bb2f0c-d629-479d-800e-b86fc3d6e45c,-1,-1,)})
    ((a50a17bde79ac018,),{(74,863010025134441,a50a17bde79ac018,863010025134441,)})
    ((a51779f736cd3f54,),{(74,862949029595753,a51779f736cd3f54,862949029595753,)})
    ((c7ae5867-3b77-4987-b082-ed3867b5c384,),{(74,353627055387065,c7ae5867-3b77-4987-b082-ed3867b5c384,353627055387065,)})



  • 相关阅读:
    吴裕雄--天生自然 R语言开发学习:图形初阶
    吴裕雄--天生自然 R语言开发学习:导入数据
    如何基于阿里云搭建适合初创企业的轻量级架构?
    基于协同过滤算法的推荐
    重磅!阿里巴巴工程师获得 containerd 社区席位,与社区共建云时代容器标准
    完爆 Best Fit,看阿里如何优化 Sigma 在线调度策略节约亿级成本
    阿里云物联网边缘计算加载MQTT驱动
    阿里云物联网平台体验(树莓派+Python篇)
    RAM SSO功能重磅发布 —— 满足客户使用企业本地账号登录阿里云
    阿里云高级技术专家带你全面了解云主机性能评测
  • 原文地址:https://www.cnblogs.com/cl1024cl/p/6205429.html
Copyright © 2011-2022 走看看