1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
|
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.spark.sql.hive;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import org.junit.After;
import org.junit.Assert;
import org.junit.Before;
import org.junit.Test;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.sql.*;
import org.apache.spark.sql.expressions.Window;
import org.apache.spark.sql.expressions.UserDefinedAggregateFunction;
import static org.apache.spark.sql.functions.*;
import org.apache.spark.sql.hive.test.TestHive$;
import org.apache.spark.sql.hive.aggregate.MyDoubleSum;
public class JavaDataFrameSuite {
private transient JavaSparkContext sc;
private transient SQLContext hc;
Dataset<Row> df;
private static void checkAnswer(Dataset<Row> actual, List<Row> expected) {
String errorMessage = QueryTest$.MODULE$.checkAnswer(actual, expected);
if (errorMessage != null) {
Assert.fail(errorMessage);
}
}
@Before
public void setUp() throws IOException {
hc = TestHive$.MODULE$;
sc = new JavaSparkContext(hc.sparkContext());
List<String> jsonObjects = new ArrayList<>(10);
for (int i = 0; i < 10; i++) {
jsonObjects.add("{\"key\":" + i + ", \"value\":\"str" + i + "\"}");
}
df = hc.read().json(sc.parallelize(jsonObjects));
df.registerTempTable("window_table");
}
@After
public void tearDown() throws IOException {
// Clean up tables.
if (hc != null) {
hc.sql("DROP TABLE IF EXISTS window_table");
}
}
@Test
public void saveTableAndQueryIt() {
checkAnswer(
df.select(avg("key").over(
Window.partitionBy("value").orderBy("key").rowsBetween(-1, 1))),
hc.sql("SELECT avg(key) " +
"OVER (PARTITION BY value " +
" ORDER BY key " +
" ROWS BETWEEN 1 preceding and 1 following) " +
"FROM window_table").collectAsList());
}
@Test
public void testUDAF() {
Dataset<Row> df = hc.range(0, 100).union(hc.range(0, 100)).select(col("id").as("value"));
UserDefinedAggregateFunction udaf = new MyDoubleSum();
UserDefinedAggregateFunction registeredUDAF = hc.udf().register("mydoublesum", udaf);
// Create Columns for the UDAF. For now, callUDF does not take an argument to specific if
// we want to use distinct aggregation.
Dataset<Row> aggregatedDF =
df.groupBy()
.agg(
udaf.distinct(col("value")),
udaf.apply(col("value")),
registeredUDAF.apply(col("value")),
callUDF("mydoublesum", col("value")));
List<Row> expectedResult = new ArrayList<>();
expectedResult.add(RowFactory.create(4950.0, 9900.0, 9900.0, 9900.0));
checkAnswer(
aggregatedDF,
expectedResult);
}
}
|