use of org.apache.ignite.ml.math.exceptions.knn.EmptyFileException in project ignite by apache.
the class LabeledDatasetLoader method loadFromTxtFile.
/**
* Datafile should keep class labels in the first column.
*
* @param pathToFile Path to file.
* @param separator Element to tokenize row on separate tokens.
* @param isDistributed Generates distributed dataset if true.
* @param isFallOnBadData Fall on incorrect data if true.
* @return Labeled Dataset parsed from file.
*/
public static LabeledDataset loadFromTxtFile(Path pathToFile, String separator, boolean isDistributed, boolean isFallOnBadData) throws IOException {
Stream<String> stream = Files.lines(pathToFile);
List<String> list = new ArrayList<>();
stream.forEach(list::add);
final int rowSize = list.size();
List<Double> labels = new ArrayList<>();
List<Vector> vectors = new ArrayList<>();
if (rowSize > 0) {
final int colSize = getColumnSize(separator, list) - 1;
if (colSize > 0) {
for (int i = 0; i < rowSize; i++) {
Double clsLb;
String[] rowData = list.get(i).split(separator);
try {
clsLb = Double.parseDouble(rowData[0]);
Vector vec = parseFeatures(pathToFile, isDistributed, isFallOnBadData, colSize, i, rowData);
labels.add(clsLb);
vectors.add(vec);
} catch (NumberFormatException e) {
if (isFallOnBadData)
throw new FileParsingException(rowData[0], i, pathToFile);
}
}
LabeledVector[] data = new LabeledVector[vectors.size()];
for (int i = 0; i < vectors.size(); i++) data[i] = new LabeledVector(vectors.get(i), labels.get(i));
return new LabeledDataset(data, colSize);
} else
throw new NoDataException("File should contain first row with data");
} else
throw new EmptyFileException(pathToFile.toString());
}
Aggregations