@Override
protected void _transform(Dataset data, boolean trainingMode) {
// handle non-numeric types, extract columns to dummy variables
Map<Object, Dataset.ColumnType> newColumns = new HashMap<>();
int n = data.size();
Iterator<Map.Entry<Object, Dataset.ColumnType>> it = data.getColumns().entrySet().iterator();
while (it.hasNext()) {
Map.Entry<Object, Dataset.ColumnType> entry = it.next();
Object column = entry.getKey();
Dataset.ColumnType columnType = entry.getValue();
if (columnType == Dataset.ColumnType.CATEGORICAL
|| columnType
== Dataset.ColumnType
.ORDINAL) { // ordinal and categorical are converted into dummyvars
// Remove the old column from the column map
it.remove();
// create dummy variables for all the levels
for (Record r : data) {
if (!r.getX().containsKey(column)) {
continue; // does not contain column
}
Object value = r.getX().get(column);
// remove the column from data
r.getX().remove(column);
List<Object> newColumn = Arrays.<Object>asList(column, value);
// add a new boolean feature with combination of column and value
r.getX().put(newColumn, true);
// add the new column in the list for insertion
newColumns.put(newColumn, Dataset.ColumnType.DUMMYVAR);
}
}
}
// add the new columns in the dataset column map
if (!newColumns.isEmpty()) {
data.getColumns().putAll(newColumns);
}
}
