创建表命令

Question

只有STRING定义的列在HIVE中加载，即int和double的列为NULL

创建表命令

create table A(
id STRING,
member_id STRING,
loan_amnt DOUBLE,   
funded_amnt DOUBLE,
`funded_amnt_inv` DOUBLE,
`term` STRING,
`int_rate`  STRING, 
`installment` DOUBLE,   
`grade` STRING, 
`sub_grade` STRING, 
`emp_title` STRING, 
`emp_length` STRING,    
`home_ownership` STRING,    
`nnual_inc` INT,
`verification_status` STRING,
`issue_d` STRING,
`loan_status` STRING,
`pymnt_plan`    STRING,
`url`   STRING,
`desc`  STRING,
`purpose`   STRING,
`title` STRING,
`zip_code` STRING,  
`addr_state`    STRING,
`dti`   DOUBLE,
`delinq_2yrs`   INT,
`earliest_cr_line` STRING,  
`inq_last_6mths`    STRING,
`mths_since_last_delinq`    STRING,
`mths_since_last_record`    STRING,
`open_acc`  INT,
`pub_rec`   INT,
`revol_bal` INT,
`revol_util`    STRING,    
`total_acc` INT,    
`initial_list_status`   STRING,    
`out_prncp` DOUBLE,    
`out_prncp_inv` DOUBLE,
`total_pymnt`   DOUBLE,
`total_pymnt_inv`   DOUBLE,
`total_rec_prncp`   DOUBLE,
`total_rec_int` DOUBLE,
`total_rec_late_fee`    DOUBLE,
`recoveries`    DOUBLE,
`collection_recovery_fee`   DOUBLE,
`last_pymnt_d`  STRING,
`last_pymnt_amnt`   DOUBLE,
`next_pymnt_d`  STRING,
`last_credit_pull_d`    STRING,
`collections_12_mths_ex_med`    INT,
`mths_since_last_major_derog`   STRING,
`policy_code`   STRING,
`application_type`  STRING,
`annual_inc_joint`  STRING,
`dti_joint` STRING,
`verification_status_joint` STRING, 
`acc_now_delinq`    STRING,
`tot_coll_amt`  STRING,
`tot_cur_bal`   STRING,
`open_acc_6m`   STRING,
`open_il_6m`    STRING,
`open_il_12m`   STRING,
`open_il_24m`   STRING,
`mths_since_rcnt_il` STRING,    
`total_bal_il`   STRING,
`il_util`    STRING,
`open_rv_12m ` STRING,  
`open_rv_24m`  STRING,  
`max_bal_bc`  STRING,   
`all_util`   STRING,    
`total_credit_rv`   STRING,
`inq_fi`  STRING,   
`total_fi_tl`    STRING,
`inq_last_12m`  STRING
)  

ROW FORMAT delimited
fields terminated by ','

STORED AS TEXTFILE;

将数据加载到表A

load data local inpath '/home/cloudera/Desktop/Project-3/1/LoanStats3a.txt' into table A;

选择数据

hive> SELECT * FROM A LIMIT 1;

输出

＆＃34; 1077501＆＃34; ＆＃34; 1296599＆＃34; NULL NULL NULL＆＃34; 36个月＆＃34; ＆＃34;   10.65％＆＃34; NULL＆＃34; B＆＃34; ＆＃34; B2＆＃34; ＆＃34;＆＃34; ＆＃34; 10年以上＆＃34; ＆＃34;出租＆＃34; NULL＆＃34;已验证＆＃34; ＆＃34; DEC-2011＆＃34; ＆＃34;全   付费和＃34; ＆＃34; N＆＃34; ＆＃34; https://www.lendingclub.com/browse/loanDetail.action?loan_id=1077501＆＃34; ＆＃34;   借款人于12/22/11添加＆gt;我需要升级我的业务   技术
＆＃34。＆＃34; CREDIT_CARD＆＃34; ＆＃34;计算机＆＃34; ＆＃34; 860xx＆＃34; ＆＃34; AZ＆＃34; NULL NULL＆＃34; 1985年1月＆＃34; ＆＃34; 1＆＃34; ＆＃34;＆＃34; ＆＃34;＆＃34; NULL NULL NULL＆＃34; 83.7％＆＃34; NULL＆＃34; f＆＃34; NULL NULL NULL NULL NULL NULL NULL NULL NULL＆＃34; Jan-2015＆＃34; NULL＆＃34;＆＃34; ＆＃34; DEC-2015＆＃34; NULL＆＃34;＆＃34; ＆＃34; 1＆＃34; ＆＃34;个人＆＃34;

＆＃34;＆＃34; ＆＃34;＆＃34; ＆＃34;＆＃34; ＆＃34; 0＆＃34; ＆＃34;＆＃34; ＆＃34;＆＃34; ＆＃34;＆＃34; ＆＃34;＆＃34; ＆＃34;＆＃34; ＆＃34;＆＃34; ＆＃34;＆＃34; ＆＃34;＆＃34; ＆＃34;＆＃34; ＆＃34;＆＃34; ＆＃34;＆＃34; ＆＃34;＆＃34; ＆＃34;＆＃34; ＆＃34;＆＃34; ＆＃34;＆＃34; ＆＃34;＆＃34; ＆＃34;＆＃34;

Answer 1

您的CSV似乎包含各个字段的引号。 HIVE不支持周围的引号，因此它们成为了这些领域的一部分。在字符串字段的情况下，引号成为字符串的一部分。如果是数字字段，引号会使该字段成为无效数字，从而产生NULL。

有关支持CSV文件中引号的服务，请参阅csv-serde 。

Answer 2

我找到了解决方案： -

create table stat2（id String，member_id INT，loan_amnt FLOAT，funding_amnt FLOAT，funding_amnt_inv FLOAT，term String，int_rate String，installment FLOAT，grade String，sub_grade String，emp_title String，emp_length String，home_ownership String，annual_inc FLOAT，verification_status String，issue_d date，loan_status String，pymnt_plan String，url String，descp String，purpose String，title String，zip_code String，addr_state String，dti FLOAT，delinq_2yrs FLOAT，earliest_cr_line String，inq_last_6mths FLOAT，mths_since_last_delinq FLOAT，mths_since_last_record FLOAT，open_acc FLOAT， pub_rec FLOAT，revol_bal FLOAT，revol_util字符串，total_acc FLOAT，initial_list_status字符串，out_prncp FLOAT，out_prncp_inv FLOAT，total_pymnt FLOAT，total_pymnt_inv FLOAT，total_rec_prncp FLOAT，total_rec_int FLOAT，total_rec_late_fee FLOAT，recoveries FLOAT，collection_recovery_fee FLOAT， last_pymnt_d字符串，last_pymnt_amnt FLOAT，next_pymnt_d字符串，last_credit_pull_d字符串，collections_12_mths_ex_med FLOAT，mths_since_last_major_derog FLOAT，policy_code FLOAT，APPLICATION_TYPE字符串，annual_inc_joint FLOAT，dti_joint FLOAT，verification_status_joint字符串，acc_now_delinq FLOAT，tot_coll_amt FLOAT，tot_cur_bal FLOAT，open_acc_6m FLOAT，open_il_6m FLOAT，open_il_12m FLOAT ，open_il_24m FLOAT，mths_since_rcnt_il FLOAT，total_bal_il FLOAT，il_util FLOAT，open_rv_12m FLOAT，open_rv_24m FLOAT，max_bal_bc FLOAT，all_util FLOAT，total_rev_hi_lim FLOAT，inq_fi FLOAT，total_cu_tl FLOAT，inq_last_12m FLOAT）

行格式SERDE＆＃39; org.apache.hadoop.hive.serde2.OpenCSVSerde＆＃39;与serdeproperties（

＆＃34; separatorChar＆＃34; =＆＃34;，＆＃34;，

＆＃34; quoteChar＆＃34; =＆＃34; \＆＃34;＆＃34;
）

存储为TEXTFILE tblproperties（＆＃34; skip.header.line.count＆＃34; =＆＃34; 2＆＃34;，＆＃34; skip.footer.line.count＆＃34; =＆＃34; 4＆＃34）;

只有STRING定义的列在HIVE中加载，即int和double的列为NULL

创建表命令

将数据加载到表A

选择数据

输出

2 个答案: