@Test
public void testBloomFilter() {
DataFrame df = context.range(1000);
BloomFilter filter1 = df.stat().bloomFilter("id", 1000, 0.03);
Assert.assertTrue(filter1.expectedFpp() - 0.03 < 1e-3);
for (int i = 0; i < 1000; i++) {
Assert.assertTrue(filter1.mightContain(i));
}
BloomFilter filter2 = df.stat().bloomFilter(col("id").multiply(3), 1000, 0.03);
Assert.assertTrue(filter2.expectedFpp() - 0.03 < 1e-3);
for (int i = 0; i < 1000; i++) {
Assert.assertTrue(filter2.mightContain(i * 3));
}
BloomFilter filter3 = df.stat().bloomFilter("id", 1000, 64 * 5);
Assert.assertTrue(filter3.bitSize() == 64 * 5);
for (int i = 0; i < 1000; i++) {
Assert.assertTrue(filter3.mightContain(i));
}
BloomFilter filter4 = df.stat().bloomFilter(col("id").multiply(3), 1000, 64 * 5);
Assert.assertTrue(filter4.bitSize() == 64 * 5);
for (int i = 0; i < 1000; i++) {
Assert.assertTrue(filter4.mightContain(i * 3));
}
}
@Test
public void testFrequentItems() {
DataFrame df = context.table("testData2");
String[] cols = {"a"};
DataFrame results = df.stat().freqItems(cols, 0.2);
Assert.assertTrue(results.collect()[0].getSeq(0).contains(1));
}
@Test
public void testSampleBy() {
DataFrame df = context.range(0, 100, 1, 2).select(col("id").mod(3).as("key"));
DataFrame sampled = df.stat().<Integer>sampleBy("key", ImmutableMap.of(0, 0.1, 1, 0.2), 0L);
Row[] actual = sampled.groupBy("key").count().orderBy("key").collect();
Row[] expected = {RowFactory.create(0, 5), RowFactory.create(1, 8)};
Assert.assertArrayEquals(expected, actual);
}
@Test
public void testSampleBy() {
DataFrame df = context.range(0, 100, 1, 2).select(col("id").mod(3).as("key"));
DataFrame sampled = df.stat().<Integer>sampleBy("key", ImmutableMap.of(0, 0.1, 1, 0.2), 0L);
Row[] actual = sampled.groupBy("key").count().orderBy("key").collect();
Assert.assertEquals(0, actual[0].getLong(0));
Assert.assertTrue(0 <= actual[0].getLong(1) && actual[0].getLong(1) <= 8);
Assert.assertEquals(1, actual[1].getLong(0));
Assert.assertTrue(2 <= actual[1].getLong(1) && actual[1].getLong(1) <= 13);
}
@Test
public void testCountMinSketch() {
DataFrame df = context.range(1000);
CountMinSketch sketch1 = df.stat().countMinSketch("id", 10, 20, 42);
Assert.assertEquals(sketch1.totalCount(), 1000);
Assert.assertEquals(sketch1.depth(), 10);
Assert.assertEquals(sketch1.width(), 20);
CountMinSketch sketch2 = df.stat().countMinSketch(col("id"), 10, 20, 42);
Assert.assertEquals(sketch2.totalCount(), 1000);
Assert.assertEquals(sketch2.depth(), 10);
Assert.assertEquals(sketch2.width(), 20);
CountMinSketch sketch3 = df.stat().countMinSketch("id", 0.001, 0.99, 42);
Assert.assertEquals(sketch3.totalCount(), 1000);
Assert.assertEquals(sketch3.relativeError(), 0.001, 1e-4);
Assert.assertEquals(sketch3.confidence(), 0.99, 5e-3);
CountMinSketch sketch4 = df.stat().countMinSketch(col("id"), 0.001, 0.99, 42);
Assert.assertEquals(sketch4.totalCount(), 1000);
Assert.assertEquals(sketch4.relativeError(), 0.001, 1e-4);
Assert.assertEquals(sketch4.confidence(), 0.99, 5e-3);
}
@Test
public void testCrosstab() {
DataFrame df = context.table("testData2");
DataFrame crosstab = df.stat().crosstab("a", "b");
String[] columnNames = crosstab.schema().fieldNames();
Assert.assertEquals("a_b", columnNames[0]);
Assert.assertEquals("2", columnNames[1]);
Assert.assertEquals("1", columnNames[2]);
Row[] rows = crosstab.collect();
Arrays.sort(rows, crosstabRowComparator);
Integer count = 1;
for (Row row : rows) {
Assert.assertEquals(row.get(0).toString(), count.toString());
Assert.assertEquals(1L, row.getLong(1));
Assert.assertEquals(1L, row.getLong(2));
count++;
}
}
@Test
public void testCovariance() {
DataFrame df = context.table("testData2");
Double result = df.stat().cov("a", "b");
Assert.assertTrue(Math.abs(result) < 1.0e-6);
}
@Test
public void testCorrelation() {
DataFrame df = context.table("testData2");
Double pearsonCorr = df.stat().corr("a", "b", "pearson");
Assert.assertTrue(Math.abs(pearsonCorr) < 1.0e-6);
}