bat*_*man 37 java hadoop hive user-defined-functions
有没有办法将重复项保存在Hive中的收集集中,或者模拟Hive使用其他方法提供的聚合集合的类型?我想将列中具有相同键的所有项聚合到一个数组中,并重复.
IE:
hash_id | num_of_cats
=====================
ad3jkfk 4
ad3jkfk 4
ad3jkfk 2
fkjh43f 1
fkjh43f 8
fkjh43f 8
rjkhd93 7
rjkhd93 4
rjkhd93 7
Run Code Online (Sandbox Code Playgroud)
应该返回:
hash_agg | cats_aggregate
===========================
ad3jkfk Array<int>(4,4,2)
fkjh43f Array<int>(1,8,8)
rjkhd93 Array<int>(7,4,7)
Run Code Online (Sandbox Code Playgroud)
Mar*_*n W 29
尝试在Hive 0.13.0之后使用COLLECT_LIST(col)
SELECT
hash_id, COLLECT_LIST(num_of_cats) AS aggr_set
FROM
tablename
WHERE
blablabla
GROUP BY
hash_id
;
Run Code Online (Sandbox Code Playgroud)
Jef*_* Mc 22
内置任何东西,但创建用户定义的功能,包括聚合,并没有那么糟糕.唯一粗略的部分是尝试使它们类型为通用,但这里是一个收集示例.
package com.example;
import java.util.ArrayList;
import org.apache.hadoop.hive.ql.exec.UDFArgumentTypeException;
import org.apache.hadoop.hive.ql.metadata.HiveException;
import org.apache.hadoop.hive.ql.parse.SemanticException;
import org.apache.hadoop.hive.ql.udf.generic.AbstractGenericUDAFResolver;
import org.apache.hadoop.hive.ql.udf.generic.GenericUDAFEvaluator;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorFactory;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorUtils;
import org.apache.hadoop.hive.serde2.objectinspector.PrimitiveObjectInspector;
import org.apache.hadoop.hive.serde2.objectinspector.StandardListObjectInspector;
import org.apache.hadoop.hive.serde2.typeinfo.TypeInfo;
public class CollectAll extends AbstractGenericUDAFResolver
{
@Override
public GenericUDAFEvaluator getEvaluator(TypeInfo[] tis)
throws SemanticException
{
if (tis.length != 1)
{
throw new UDFArgumentTypeException(tis.length - 1, "Exactly one argument is expected.");
}
if (tis[0].getCategory() != ObjectInspector.Category.PRIMITIVE)
{
throw new UDFArgumentTypeException(0, "Only primitive type arguments are accepted but " + tis[0].getTypeName() + " was passed as parameter 1.");
}
return new CollectAllEvaluator();
}
public static class CollectAllEvaluator extends GenericUDAFEvaluator
{
private PrimitiveObjectInspector inputOI;
private StandardListObjectInspector loi;
private StandardListObjectInspector internalMergeOI;
@Override
public ObjectInspector init(Mode m, ObjectInspector[] parameters)
throws HiveException
{
super.init(m, parameters);
if (m == Mode.PARTIAL1)
{
inputOI = (PrimitiveObjectInspector) parameters[0];
return ObjectInspectorFactory
.getStandardListObjectInspector((PrimitiveObjectInspector) ObjectInspectorUtils
.getStandardObjectInspector(inputOI));
}
else
{
if (!(parameters[0] instanceof StandardListObjectInspector))
{
inputOI = (PrimitiveObjectInspector) ObjectInspectorUtils
.getStandardObjectInspector(parameters[0]);
return (StandardListObjectInspector) ObjectInspectorFactory
.getStandardListObjectInspector(inputOI);
}
else
{
internalMergeOI = (StandardListObjectInspector) parameters[0];
inputOI = (PrimitiveObjectInspector) internalMergeOI.getListElementObjectInspector();
loi = (StandardListObjectInspector) ObjectInspectorUtils.getStandardObjectInspector(internalMergeOI);
return loi;
}
}
}
static class ArrayAggregationBuffer implements AggregationBuffer
{
ArrayList<Object> container;
}
@Override
public void reset(AggregationBuffer ab)
throws HiveException
{
((ArrayAggregationBuffer) ab).container = new ArrayList<Object>();
}
@Override
public AggregationBuffer getNewAggregationBuffer()
throws HiveException
{
ArrayAggregationBuffer ret = new ArrayAggregationBuffer();
reset(ret);
return ret;
}
@Override
public void iterate(AggregationBuffer ab, Object[] parameters)
throws HiveException
{
assert (parameters.length == 1);
Object p = parameters[0];
if (p != null)
{
ArrayAggregationBuffer agg = (ArrayAggregationBuffer) ab;
agg.container.add(ObjectInspectorUtils.copyToStandardObject(p, this.inputOI));
}
}
@Override
public Object terminatePartial(AggregationBuffer ab)
throws HiveException
{
ArrayAggregationBuffer agg = (ArrayAggregationBuffer) ab;
ArrayList<Object> ret = new ArrayList<Object>(agg.container.size());
ret.addAll(agg.container);
return ret;
}
@Override
public void merge(AggregationBuffer ab, Object o)
throws HiveException
{
ArrayAggregationBuffer agg = (ArrayAggregationBuffer) ab;
ArrayList<Object> partial = (ArrayList<Object>)internalMergeOI.getList(o);
for(Object i : partial)
{
agg.container.add(ObjectInspectorUtils.copyToStandardObject(i, this.inputOI));
}
}
@Override
public Object terminate(AggregationBuffer ab)
throws HiveException
{
ArrayAggregationBuffer agg = (ArrayAggregationBuffer) ab;
ArrayList<Object> ret = new ArrayList<Object>(agg.container.size());
ret.addAll(agg.container);
return ret;
}
}
}
Run Code Online (Sandbox Code Playgroud)
然后在hive中,只是问题add jar Whatever.jar;,CREATE TEMPORARY FUNCTION collect_all AS 'com.example.CollectAll';
你应该能够按预期使用它.
hive> SELECT hash_id, collect_all(num_of_cats) FROM test GROUP BY hash_id;
OK
ad3jkfk [4,4,2]
fkjh43f [1,8,8]
rjkhd93 [7,4,7]
Run Code Online (Sandbox Code Playgroud)
值得注意的是元素的顺序应该被认为是未定义的,因此如果您打算使用它来将信息提供给n_grams,您可能需要对其进行扩展以根据需要对数据进行排序.
nep*_*tes 12
修改了Jeff Mc的代码来删除输入必须是原始类型的限制(可能是从collect_set继承).此版本可以收集结构,地图和数组以及基元.
package com.example;
import java.util.ArrayList;
import org.apache.hadoop.hive.ql.exec.UDFArgumentTypeException;
import org.apache.hadoop.hive.ql.metadata.HiveException;
import org.apache.hadoop.hive.ql.parse.SemanticException;
import org.apache.hadoop.hive.ql.udf.generic.AbstractGenericUDAFResolver;
import org.apache.hadoop.hive.ql.udf.generic.GenericUDAFEvaluator;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorFactory;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorUtils;
import org.apache.hadoop.hive.serde2.objectinspector.StandardListObjectInspector;
import org.apache.hadoop.hive.serde2.typeinfo.TypeInfo;
public class CollectAll extends AbstractGenericUDAFResolver
{
@Override
public GenericUDAFEvaluator getEvaluator(TypeInfo[] tis)
throws SemanticException
{
if (tis.length != 1)
{
throw new UDFArgumentTypeException(tis.length - 1, "Exactly one argument is expected.");
}
return new CollectAllEvaluator();
}
public static class CollectAllEvaluator extends GenericUDAFEvaluator
{
private ObjectInspector inputOI;
private StandardListObjectInspector loi;
private StandardListObjectInspector internalMergeOI;
@Override
public ObjectInspector init(Mode m, ObjectInspector[] parameters)
throws HiveException
{
super.init(m, parameters);
if (m == Mode.PARTIAL1)
{
inputOI = parameters[0];
return ObjectInspectorFactory
.getStandardListObjectInspector(ObjectInspectorUtils
.getStandardObjectInspector(inputOI));
}
else
{
if (!(parameters[0] instanceof StandardListObjectInspector))
{
inputOI = ObjectInspectorUtils
.getStandardObjectInspector(parameters[0]);
return (StandardListObjectInspector) ObjectInspectorFactory
.getStandardListObjectInspector(inputOI);
}
else
{
internalMergeOI = (StandardListObjectInspector) parameters[0];
inputOI = internalMergeOI.getListElementObjectInspector();
loi = (StandardListObjectInspector) ObjectInspectorUtils.getStandardObjectInspector(internalMergeOI);
return loi;
}
}
}
static class ArrayAggregationBuffer implements AggregationBuffer
{
ArrayList<Object> container;
}
@Override
public void reset(AggregationBuffer ab)
throws HiveException
{
((ArrayAggregationBuffer) ab).container = new ArrayList<Object>();
}
@Override
public AggregationBuffer getNewAggregationBuffer()
throws HiveException
{
ArrayAggregationBuffer ret = new ArrayAggregationBuffer();
reset(ret);
return ret;
}
@Override
public void iterate(AggregationBuffer ab, Object[] parameters)
throws HiveException
{
assert (parameters.length == 1);
Object p = parameters[0];
if (p != null)
{
ArrayAggregationBuffer agg = (ArrayAggregationBuffer) ab;
agg.container.add(ObjectInspectorUtils.copyToStandardObject(p, this.inputOI));
}
}
@Override
public Object terminatePartial(AggregationBuffer ab)
throws HiveException
{
ArrayAggregationBuffer agg = (ArrayAggregationBuffer) ab;
ArrayList<Object> ret = new ArrayList<Object>(agg.container.size());
ret.addAll(agg.container);
return ret;
}
@Override
public void merge(AggregationBuffer ab, Object o)
throws HiveException
{
ArrayAggregationBuffer agg = (ArrayAggregationBuffer) ab;
ArrayList<Object> partial = (ArrayList<Object>)internalMergeOI.getList(o);
for(Object i : partial)
{
agg.container.add(ObjectInspectorUtils.copyToStandardObject(i, this.inputOI));
}
}
@Override
public Object terminate(AggregationBuffer ab)
throws HiveException
{
ArrayAggregationBuffer agg = (ArrayAggregationBuffer) ab;
ArrayList<Object> ret = new ArrayList<Object>(agg.container.size());
ret.addAll(agg.container);
return ret;
}
}
}
Run Code Online (Sandbox Code Playgroud)
| 归档时间: |
|
| 查看次数: |
49746 次 |
| 最近记录: |