Search Results
https://dev.mysql.com/doc/heatwave/en/mys-hw-lakehouse-data-recovery.html
In the event of a problem where query processing stops or the MySQL HeatWave Cluster stops, the external tables are recovered when the Cluster resumes and begins processing queries again using the MySQL HeatWave recovery process. See the following ...
https://dev.mysql.com/doc/heatwave/en/mys-hw-rpd-exec-stats-table.html
The rpd_exec_stats table stores query execution statistics produced by MySQL HeatWave nodes in JSON format. For MySQL HeatWave AutoML routines that include multiple sub-queries, such as ML_TRAIN, a new record is used for each query. The counter ...
https://dev.mysql.com/doc/heatwave/en/mys-hw-window-functions.html
For optimal performance, window functions in MySQL HeatWave utilize a massively parallel, partitioning-based algorithm. For general information about window functions, see Window Functions, in the MySQL Reference Manual. MySQL HeatWave window ...The ...
https://dev.mysql.com/doc/heatwave/en/mys-hw-workload-optimization-olap.html
Apply these optimizations manually, or use MySQL HeatWave Autopilot Advisor, which includes the following: Auto Encoding recommends string column encodings that minimize the required cluster size and improve query performance. Unload Advisor ...
https://dev.mysql.com/doc/heatwave/en/mys-hwaml-anomaly-detection-logs.html
MySQL 9.2.2 introduces the ability to detect anomalies in log data. As of MySQL 9.4.1, at least one column must act as the primary key to establish the temporal order of logs. In addition to the anomaly scores included in the output table, you have ...To perform anomaly detection on logs, log data is cleaned, segemented, and encoded before running anomaly ...
https://dev.mysql.com/doc/heatwave/en/mys-hwaml-classification-generate-explanation.html
mysql> CALL sys.ML_MODEL_LOAD(@model, NULL); The following example uses the model handle. mysql> CALL sys.ML_MODEL_LOAD('classification_use_case', NULL); Use the ML_EXPLAIN_TABLE routine to generate explanations for predictions made in the test ...
https://dev.mysql.com/doc/heatwave/en/mys-hwaml-ml-explain-row.html
A table can include extra columns, and still use the MySQL HeatWave AutoML model. ML_EXPLAIN_ROW Syntax Required ML_EXPLAIN_ROW Parameters ML_EXPLAIN_ROW Options Syntax Examples See Also ML_EXPLAIN_ROW Syntax mysql> SELECT ... The ML_EXPLAIN_ROW ...
https://dev.mysql.com/doc/heatwave/en/mys-hwaml-ml-model-metadata.html
format: string The model can be in one of the following formats (MySQL 9.0.0 and later): HWMLv1.0 HWMLv2.0 ONNXv1.0 ONNXv2.0 For MySQL 8.4.0 and earlier, MySQL HeatWave AutoML models are in HWMLv1.0 format, and ONNX models are in ONNX format. This ... The model_metadata column in the model catalog allows you to view detailed information on trained ...
https://dev.mysql.com/doc/heatwave/en/mys-hwaml-regression-explanations.html
mysql> SELECT JSON_PRETTY(model_explanation) FROM ML_SCHEMA_user1.MODEL_CATALOG WHERE model_handle='regression_use_case'; +------------------------------------------------------------------------------------------------------------------------+ | ...
https://dev.mysql.com/doc/heatwave/en/mys-hwaml-topic-modeling-train.html
Unsupported Topic Modeling Options When MySQL HeatWave AutoML runs topic modeling, the operation is based on a single algorithm that does not require the tuning of hyperparameters. mysql> SET @variable = 'model_handle'; Replace @variable and ...