xgboost的pmml文件轉爲hive udf

1. 將項目拉到本地

git clone [email protected]:jpmml/jpmml-evaluator-hive.git

2. 進到目錄中安裝

mvn clean install

3. 將得到的其中一個runtime的`jar`包放到HDFS上

hdfs dfs -put jpmml-evaluator-hive-runtime-1.0-SNAPSHOT.jar somedir/

4. 在hive中加載

add jar {hdfs_home}/somedir/jpmml-evaluator-hive-runtime-1.0-SNAPSHOT.jar;
CREATE TEMPORARY FUNCTION BuildArchive AS 'org.jpmml.evaluator.hive.ArchiveBuilderUDF';
DESCRIBE FUNCTION BuildArchive;
DESCRIBE FUNCTION EXTENDED BuildArchive;

5. 處理pmml

將pmml文件中Output的`probability(1)`、`probability(0)`, 括號替換掉,否則hive無法識別

6. 生成模型jar

三個參數分別是,包名,pmml本地路徑,輸出jar包的本地路徑

SELECT BuildArchive('com.mycompany.XGBPredictor', '/home/model/xgboost_model.pmml', '/home/model/XGBPredictor.jar');

7. 將jar包放到HDFS

hdfs dfs -put XGBPredictor.jar somedir/

8. 加載包

add jar {hdfs_home}/somedir/XGBPredictor.jar;
CREATE TEMPORARY FUNCTION XGBPredictor AS 'com.mycompany.XGBPredictor';
DESCRIBE FUNCTION ModelPredictor;
DESCRIBE FUNCTION EXTENDED T3ModelPredictor;

9. 更改serialization的傳輸格式,不支持kyro

set hive.plan.serialization.format=javaXML;

10. 測試

select
id,
request_time,
XGBPredictor(named_struct(
    'feature1', nvl(feature1, -1),
    'feature2', nvl(feature2, -1),
    'feature3', nvl(feature3, -1)
)) as proba_struct
from some_table
where id in (22, 23, 24)

得到輸出:

id	request_time proba_struct
22	2020-01-31 11:55:24	{"_target":0,"proba_0":0.93001777,"proba_1":0.069982216}
23	2020-01-31 10:06:35	{"_target":0,"proba_0":0.9754708,"proba_1":0.024529234}
24	2020-01-31 10:39:16	{"_target":0,"proba_0":0.96165186,"proba_1":0.038348127}

遺留問題

對於需要MapReduce的任務,在reduce階段會報錯,暫時未解決,求大神指點

Diagnostic Messages for this Task:
Error: java.lang.RuntimeException: Error in configuring object
        at org.apache.hadoop.util.ReflectionUtils.setJobConf(ReflectionUtils.java:112)
        at org.apache.hadoop.util.ReflectionUtils.setConf(ReflectionUtils.java:78)
        at org.apache.hadoop.util.ReflectionUtils.newInstance(ReflectionUtils.java:136)
        at org.apache.hadoop.mapred.MapTask.runOldMapper(MapTask.java:450)
        at org.apache.hadoop.mapred.MapTask.run(MapTask.java:343)
        at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:164)
        at java.security.AccessController.doPrivileged(Native Method)
        at javax.security.auth.Subject.doAs(Subject.java:422)
        at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1923)
        at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:158)
Caused by: java.lang.reflect.InvocationTargetException
        at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
        at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
        at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
        at java.lang.reflect.Method.invoke(Method.java:498)
        at org.apache.hadoop.util.ReflectionUtils.setJobConf(ReflectionUtils.java:109)
        ... 9 more
Caused by: java.lang.RuntimeException: Error in configuring object
        at org.apache.hadoop.util.ReflectionUtils.setJobConf(ReflectionUtils.java:112)
        at org.apache.hadoop.util.ReflectionUtils.setConf(ReflectionUtils.java:78)
        at org.apache.hadoop.util.ReflectionUtils.newInstance(ReflectionUtils.java:136)
        at org.apache.hadoop.mapred.MapRunner.configure(MapRunner.java:38)
        ... 14 more
Caused by: java.lang.reflect.InvocationTargetException
        at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
        at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
        at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
        at java.lang.reflect.Method.invoke(Method.java:498)
        at org.apache.hadoop.util.ReflectionUtils.setJobConf(ReflectionUtils.java:109)
        ... 17 more
Caused by: java.lang.RuntimeException: Map operator initialization failed
        at org.apache.hadoop.hive.ql.exec.mr.ExecMapper.configure(ExecMapper.java:140)
        ... 22 more
Caused by: java.lang.NullPointerException
        at org.apache.hadoop.hive.ql.udf.generic.GenericUDFBaseArithmetic.initialize(GenericUDFBaseArithmetic.java:53)
        at org.apache.hadoop.hive.ql.udf.generic.GenericUDF.initializeAndFoldConstants(GenericUDF.java:139)
        at org.apache.hadoop.hive.ql.exec.ExprNodeGenericFuncEvaluator.initialize(ExprNodeGenericFuncEvaluator.java:145)
        at org.apache.hadoop.hive.ql.exec.ExprNodeGenericFuncEvaluator.initialize(ExprNodeGenericFuncEvaluator.java:139)
        at org.apache.hadoop.hive.ql.exec.ExprNodeGenericFuncEvaluator.initialize(ExprNodeGenericFuncEvaluator.java:139)
        at org.apache.hadoop.hive.ql.exec.ExprNodeGenericFuncEvaluator.initialize(ExprNodeGenericFuncEvaluator.java:139)
        at org.apache.hadoop.hive.ql.exec.ExprNodeGenericFuncEvaluator.initialize(ExprNodeGenericFuncEvaluator.java:139)
        at org.apache.hadoop.hive.ql.exec.ExprNodeGenericFuncEvaluator.initialize(ExprNodeGenericFuncEvaluator.java:139)
        at org.apache.hadoop.hive.ql.exec.ExprNodeGenericFuncEvaluator.initialize(ExprNodeGenericFuncEvaluator.java:139)
        at org.apache.hadoop.hive.ql.exec.ExprNodeGenericFuncEvaluator.initialize(ExprNodeGenericFuncEvaluator.java:139)
        at org.apache.hadoop.hive.ql.exec.ExprNodeGenericFuncEvaluator.initialize(ExprNodeGenericFuncEvaluator.java:139)
        at org.apache.hadoop.hive.ql.exec.ExprNodeGenericFuncEvaluator.initialize(ExprNodeGenericFuncEvaluator.java:139)
        at org.apache.hadoop.hive.ql.exec.ExprNodeGenericFuncEvaluator.initialize(ExprNodeGenericFuncEvaluator.java:139)
        at org.apache.hadoop.hive.ql.exec.ExprNodeGenericFuncEvaluator.initialize(ExprNodeGenericFuncEvaluator.java:139)
        at org.apache.hadoop.hive.ql.exec.ExprNodeGenericFuncEvaluator.initialize(ExprNodeGenericFuncEvaluator.java:139)
        at org.apache.hadoop.hive.ql.exec.ExprNodeGenericFuncEvaluator.initialize(ExprNodeGenericFuncEvaluator.java:139)
        at org.apache.hadoop.hive.ql.exec.ExprNodeGenericFuncEvaluator.initialize(ExprNodeGenericFuncEvaluator.java:139)
        at org.apache.hadoop.hive.ql.exec.ExprNodeEvaluatorHead.initialize(ExprNodeEvaluatorHead.java:39)
        at org.apache.hadoop.hive.ql.exec.Operator.initEvaluators(Operator.java:979)
        at org.apache.hadoop.hive.ql.exec.Operator.initEvaluatorsAndReturnStruct(Operator.java:1005)
        at org.apache.hadoop.hive.ql.exec.SelectOperator.initializeOp(SelectOperator.java:67)
        at org.apache.hadoop.hive.ql.exec.Operator.initialize(Operator.java:363)
        at org.apache.hadoop.hive.ql.exec.Operator.initialize(Operator.java:482)
        at org.apache.hadoop.hive.ql.exec.Operator.initializeChildren(Operator.java:439)
        at org.apache.hadoop.hive.ql.exec.Operator.initialize(Operator.java:376)
        at org.apache.hadoop.hive.ql.exec.MapOperator.initializeMapOperator(MapOperator.java:469)
at org.apache.hadoop.hive.ql.exec.mr.ExecMapper.configure(ExecMapper.java:119)
        ... 22 more

 

發表評論
所有評論
還沒有人評論,想成為第一個評論的人麼? 請在上方評論欄輸入並且點擊發布.
相關文章