@Test
public void testAsString() {
Locale.setDefault(Locale.ENGLISH);
FeatureVectorEncoder enc = new TextValueEncoder("text");
assertEquals(
"[text:test1:1.0000, text:and:1.0000, text:more:1.0000]", enc.asString("test1 and more"));
}
// public Vector encode(String type, List<String> data, String label) throws IOException
public static org.apache.mahout.math.Vector encode(String label, List<String> data)
throws IOException {
FeatureVectorEncoder content_encoder = new AdaptiveWordValueEncoder("content");
content_encoder.setProbes(2);
org.apache.mahout.math.Vector v = new RandomAccessSparseVector(100);
for (String word : data) {
content_encoder.addToVector(word, v);
}
return new NamedVector(v, label);
}
@Test
public void testAddToVector() {
FeatureVectorEncoder enc = new ContinuousValueEncoder("foo");
Vector v1 = new DenseVector(20);
enc.addToVector("-123", v1);
Assert.assertEquals(-123, v1.minValue(), 0);
Assert.assertEquals(0, v1.maxValue(), 0);
Assert.assertEquals(123, v1.norm(1), 0);
v1 = new DenseVector(20);
enc.addToVector("123", v1);
Assert.assertEquals(123, v1.maxValue(), 0);
Assert.assertEquals(0, v1.minValue(), 0);
Assert.assertEquals(123, v1.norm(1), 0);
Vector v2 = new DenseVector(20);
enc.setProbes(2);
enc.addToVector("123", v2);
Assert.assertEquals(123, v2.maxValue(), 0);
Assert.assertEquals(2 * 123, v2.norm(1), 0);
v1 = v2.minus(v1);
Assert.assertEquals(123, v1.maxValue(), 0);
Assert.assertEquals(123, v1.norm(1), 0);
Vector v3 = new DenseVector(20);
enc.setProbes(2);
enc.addToVector("100", v3);
v1 = v2.minus(v3);
Assert.assertEquals(23, v1.maxValue(), 0);
Assert.assertEquals(2 * 23, v1.norm(1), 0);
enc.addToVector("7", v1);
Assert.assertEquals(30, v1.maxValue(), 0);
Assert.assertEquals(2 * 30, v1.norm(1), 0);
Assert.assertEquals(30, v1.get(10), 0);
Assert.assertEquals(30, v1.get(18), 0);
try {
enc.addToVector("foobar", v1);
Assert.fail("Should have noticed bad numeric format");
} catch (NumberFormatException e) {
Assert.assertEquals("For input string: \"foobar\"", e.getMessage());
}
}
