Search Results
https://dev.mysql.com/doc/heatwave/en/mys-hw-lakehouse-incremental-load.html
A call to Auto Parallel Load might contain both loaded and unloaded tables. Available as of MySQL 9.0.0, Lakehouse Incremental Load allows you to refresh the data in an external table. This topic contains the following sections: Before You Begin ...
https://dev.mysql.com/doc/heatwave/en/mys-hw-metadata-queries-secondary-engine.html
If the CREATE_OPTIONS column contains both SECONDARY_ENGINE=RAPID and SECONDARY_LOAD=1, the table is offloaded and loaded into the MySQL HeatWave Cluster Before You Begin Ensure that the enable_secondary_engine_statistics system variables is set to ... To identify tables in the DB System that are defined with a secondary engine, query the CREATE_OPTIONS column in the INFORMATION_SCHEMA.TABLES ...
https://dev.mysql.com/doc/heatwave/en/mys-hwaml-anomaly-detection-logs.html
You can set either embedding_model or keyword_model to NULL, but you cannot set both to NULL. MySQL 9.2.2 introduces the ability to detect anomalies in log data. To perform anomaly detection on logs, log data is cleaned, segemented, and encoded ...
https://dev.mysql.com/doc/heatwave/en/mys-hwaml-automl.html
Scalable design: The Oracle AutoML pipeline is able to exploit both MySQL HeatWave internode and intranode parallelism, which improves scalability and reduces runtime. The MySQL HeatWave AutoML ML_TRAIN routine leverages Oracle AutoML technology to ...
https://dev.mysql.com/doc/heatwave/en/mys-hwaml-data-drift-detection.html
mean and variance indicate the quality of the trained drift detector, and both values should be low. MySQL HeatWave AutoML includes data drift detection for the following models: Classification Regression Anomaly detection (as of MySQL 9.3.2) ...
https://dev.mysql.com/doc/heatwave/en/mys-hwaml-ml-metrics.html
Both of these options define a metric that must be compatible with the task type and the target data. The ML_TRAIN routine includes the optimization_metric option, and the ML_SCORE routine includes the metric option. precision_k: An Oracle ...
https://dev.mysql.com/doc/heatwave/en/mys-hwaml-ml-model-metadata.html
The model_metadata column in the model catalog allows you to view detailed information on trained models. For example, you can view the algorithm used to train the model, the columns in the training table, and values for the model explanation. When ...
https://dev.mysql.com/doc/heatwave/en/mys-hwaml-onnx-metadata.html
To learn more about model metadata in the model catalog, see Model Metadata. ONNX Inputs Info Use the data_types_map to map the data type of each column to an ONNX model data type. For example, to convert inputs of the type tensor(float) to ...
https://dev.mysql.com/doc/heatwave/en/mys-hwaml-scoring-a-recommendation-model.html
A recommendation task and ranking metrics can use both threshold and topk. After generating predicted ratings/rankings and recommendations, you can score the model to assess its reliability. For a list of scoring metrics you can use with ...
https://dev.mysql.com/doc/heatwave/en/mys-hwaml-using-a-recommendation-model-ratings-rankings.html
The steps below are the same for both types of recommendation models. This topic describes how to generate recommendations for either ratings (recommendation model with explicit feedback) or rankings (recommendation model with implicit feedback).