anomaly

The official instructions say to use joblib for pickling PyOD models.

This fails for AutoEncoders, or any other TensorFlow-backed model as far as I can tell. The error is:

>>> dump(model, 'model.joblib')
...
TypeError: can't pickle _thread.RLock objects

Note that it's not sufficient to save the underlying Keras S

tf.keras.Sequential is an instance of tf.keras.Model so could be left out across types in alibi-detect.

In the following code

    @Override
    public DetectorDocument findByUuid(String uuid) {
        val queryBuilder = QueryBuilders.termQuery("uuid", uuid);
        val searchSourceBuilder = elasticsearchUtil.getSourceBuilder(queryBuilder).size(DEFAULT_ES_RESULTS_SIZE);
        val searchRequest = elasticsearchUtil.getSearchRequest(searchSourceBuilder, DETECTOR_INDEX, DETECTOR_DOC_TYPE)

Create a docker compose file for:

• logdata-anomaly-miner
• aminer-aelastic
• aminer-akafka