package com.thinkbiganalytics.spark.dataprofiler.testcases;
/*-
* #%L
* thinkbig-spark-job-profiler-app
* %%
* Copyright (C) 2017 ThinkBig Analytics
* %%
* Licensed 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.
* #L%
*/
import com.thinkbiganalytics.spark.dataprofiler.columns.BooleanColumnStatistics;
import com.thinkbiganalytics.spark.dataprofiler.columns.StandardColumnStatistics;
import com.thinkbiganalytics.spark.dataprofiler.core.ProfilerTest;
import com.thinkbiganalytics.spark.dataprofiler.topn.TopNDataItem;
import com.thinkbiganalytics.spark.dataprofiler.topn.TopNDataList;
import org.junit.AfterClass;
import org.junit.Assert;
import org.junit.Before;
import org.junit.Test;
import java.util.Iterator;
import java.util.TreeSet;
import static org.junit.Assert.assertEquals;
/**
* Boolean Column Statistics Test Case
*/
public class BooleanColumnCase1Test extends ProfilerTest {
private static StandardColumnStatistics columnStats;
private static long nullCount;
private static long totalCount;
private static long uniqueCount;
private static double percNullValues;
private static double percUniqueValues;
private static double percDuplicateValues;
private static TopNDataList topNValues;
private static long trueCount;
private static long falseCount;
@AfterClass
public static void tearDownClass() {
System.out.println("\t*** Completed run for BooleanColumnCase1Test ***");
}
@Before
public void setUp() {
super.setUp();
columnStats = columnStatsMap.get(7); //lifemember
nullCount = 2L;
totalCount = 10L;
uniqueCount = 3L;
percNullValues = 20.0d;
percUniqueValues = 30.0d;
percDuplicateValues = 70.0d;
topNValues = columnStats.getTopNValues();
trueCount = 5L;
falseCount = 3L;
}
@Test
public void testBooleanNullCount() {
Assert.assertEquals(nullCount, columnStats.getNullCount());
}
@Test
public void testBooleanTotalCount() {
Assert.assertEquals(totalCount, columnStats.getTotalCount());
}
@Test
public void testBooleanUniqueCount() {
Assert.assertEquals(uniqueCount, columnStats.getUniqueCount());
}
@Test
public void testBooleanPercNullValues() {
assertEquals(percNullValues, columnStats.getPercNullValues(), epsilon);
}
@Test
public void testBooleanPercUniqueValues() {
assertEquals(percUniqueValues, columnStats.getPercUniqueValues(), epsilon);
}
@Test
public void testBooleanPercDuplicateValues() {
assertEquals(percDuplicateValues, columnStats.getPercDuplicateValues(), epsilon);
}
@Test
public void testBooleanTopNValues() {
TreeSet<TopNDataItem> items = topNValues.getTopNDataItemsForColumn();
Iterator<TopNDataItem> iterator = items.descendingIterator();
//Verify that there are 3 items
Assert.assertEquals(3, items.size());
//Verify the top 3 item counts
int index = 1;
while (iterator.hasNext()) {
TopNDataItem item = iterator.next();
if (index == 1) {
Assert.assertEquals(Boolean.TRUE, item.getValue());
Assert.assertEquals(Long.valueOf(5L), item.getCount());
} else if (index == 2) {
Assert.assertEquals(Boolean.FALSE, item.getValue());
Assert.assertEquals(Long.valueOf(3L), item.getCount());
} else if (index == 3) {
Assert.assertEquals(null, item.getValue());
Assert.assertEquals(Long.valueOf(2L), item.getCount());
}
index++;
}
}
@Test
public void testBooleanTrueCount() {
Assert.assertEquals(trueCount, ((BooleanColumnStatistics) columnStats).getTrueCount());
}
@Test
public void testBooleanFalseCount() {
Assert.assertEquals(falseCount, ((BooleanColumnStatistics) columnStats).getFalseCount());
}
}