/*
* The constructor establishes the RuntimeContract between
* the SQL-MR function and Aster Database. During query planning,
* the function will constructed on a single node. During
* query execution, it will be constructed and run on one or more nodes.
*/
public ChiSquareTest(RuntimeContract contract) {
// Read argument clauses into appropriate member variables.
observedArgumentIdx =
contract
.getInputInfo()
.getColumnIndex(contract.useArgumentClause("observed").getSingleValue());
expectedArgumentIdx =
contract
.getInputInfo()
.getColumnIndex(contract.useArgumentClause("expected").getSingleValue());
accumulator = new Accumulator(contract);
errorHandler =
new ErrorHandler(
this.getClass().getName(),
Utils.getSingleBooleanFromParameter(contract, "stoponerror", false),
Utils.getSingleIntFromParameter(contract, "log", Integer.MAX_VALUE));
// Initialize the service
chiSquareTest = new org.apache.commons.math3.stat.inference.ChiSquareTest();
// Verify that the function accepts the given input schema.
if (!SqlType.integer().equals(contract.getInputInfo().getColumnType(observedArgumentIdx))) {
throw new IllegalUsageException(
"\""
+ contract.useArgumentClause("observed").getSingleValue()
+ "\" must be of type 'integer'");
}
if (!SqlType.doublePrecision()
.equals(contract.getInputInfo().getColumnType(expectedArgumentIdx))) {
throw new IllegalUsageException(
"\""
+ contract.useArgumentClause("expected").getSingleValue()
+ "\" must be a numeric type");
}
// Construct the output schema
List<ColumnDefinition> outputColumns = new ArrayList<ColumnDefinition>();
accumulator.constructOutputSchema(contract, outputColumns);
outputColumns.add(new ColumnDefinition("pValue", SqlType.getType("double")));
contract.setOutputInfo(new OutputInfo(outputColumns));
// Complete the contract
contract.complete();
}
public void operateOnPartition(
PartitionDefinition definition, RowIterator inputIterator, RowEmitter outputEmitter) {
errorHandler.enterOperateOnPartition(definition, inputIterator, outputEmitter);
try {
// Collect input rows for observed and expected values
ArrayList<Double> expectedList = new ArrayList<Double>();
ArrayList<Long> observedList = new ArrayList<Long>();
while (inputIterator.advanceToNextRow()) {
errorHandler.enterOperateOnRow(inputIterator, outputEmitter);
if (inputIterator.isNullAt(observedArgumentIdx)
|| inputIterator.isNullAt(expectedArgumentIdx))
throw new IllegalArgumentException("observed and expected values cannot be null");
expectedList.add(inputIterator.getDoubleAt(expectedArgumentIdx));
observedList.add(inputIterator.getLongAt(observedArgumentIdx));
errorHandler.exitOperateOnRow();
}
double[] expected = new double[expectedList.size()];
for (int i = 0; i < expected.length; i++) expected[i] = expectedList.get(i);
long[] observed = new long[observedList.size()];
for (int i = 0; i < observed.length; i++) observed[i] = observedList.get(i);
// Run test
double pValue = chiSquareTest.chiSquareTest(expected, observed);
// Emit result
accumulator.emit(inputIterator, outputEmitter);
outputEmitter.addDouble(pValue);
outputEmitter.emitRow();
} catch (IllegalArgumentException e) {
errorHandler.catchException(e);
return; // End this partition and go to next if stopOnError is set to false (otherwise
// exception is thrown)
}
errorHandler.exitOperateOnPartition();
}