Examples with ColumnType org.opensearch.ml.common.dataframe.ColumnType used on opensource projects

Example 1 with ColumnType

use of org.opensearch.ml.common.dataframe.ColumnType in project ml-commons by opensearch-project.

the class FixedInTimeRandomCutForest method process.

private List<Map<String, Object>> process(DataFrame dataFrame, ThresholdedRandomCutForest forest) {
    List<Double> pointList = new ArrayList<>();
    ColumnMeta[] columnMetas = dataFrame.columnMetas();
    List<Map<String, Object>> predictResult = new ArrayList<>();
    for (int rowNum = 0; rowNum < dataFrame.size(); rowNum++) {
        Row row = dataFrame.getRow(rowNum);
        long timestamp = -1;
        for (int i = 0; i < columnMetas.length; i++) {
            ColumnMeta columnMeta = columnMetas[i];
            ColumnValue value = row.getValue(i);
            // TODO: sort dataframe by time field with asc order. Currently consider the date already sorted by time.
            if (timeField != null && timeField.equals(columnMeta.getName())) {
                ColumnType columnType = columnMeta.getColumnType();
                if (columnType == ColumnType.LONG) {
                    timestamp = value.longValue();
                } else if (columnType == ColumnType.STRING) {
                    try {
                        timestamp = simpleDateFormat.parse(value.stringValue()).getTime();
                    } catch (ParseException e) {
                        log.error("Failed to parse timestamp " + value.stringValue(), e);
                        throw new MLValidationException("Failed to parse timestamp " + value.stringValue());
                    }
                } else {
                    throw new MLValidationException("Wrong data type of time field. Should use LONG or STRING, but got " + columnType);
                }
            } else {
                pointList.add(value.doubleValue());
            }
        }
        double[] point = pointList.stream().mapToDouble(d -> d).toArray();
        pointList.clear();
        Map<String, Object> result = new HashMap<>();
        AnomalyDescriptor process = forest.process(point, timestamp);
        result.put(timeField, timestamp);
        result.put("score", process.getRCFScore());
        result.put("anomaly_grade", process.getAnomalyGrade());
        predictResult.add(result);
    }
    return predictResult;
}