3.19 HeatWave AutoML Limitations

The following limitations apply to HeatWave AutoML. For HeatWave limitations, see: Section 2.18, “HeatWave MySQL Limitations”.

• The ML_TRAIN routine does not support MySQL user names that contain a period; for example, a user named 'joe.smith'@'%' cannot run the ML_TRAIN routine. The model catalog schema created by the ML_TRAIN procedure incorporates the user name in the schema name (e.g., ML_SCHEMA_joesmith), and a period is not a permitted schema name character.

• The table used to train a model cannot exceed 10 GB, 100 million rows, or 1017 columns.

• As of MySQL 9.0.0, the maximum model size is only limited by the amount of memory defined by the shape. ML_TRAIN will fail to execute and will raise an error if it attempts to train a model larger than this. Before MySQL 9.0.0, the limit was 900 MB.

  All active users and models share this memory, and it might be necessary to schedule users. See: ML_MODEL_ACTIVE.

• To avoid taking up too much space in memory, the number of loaded models should be limited to three.

• “Bring your own model” is not supported. Use of non-HeatWave AutoML models or manually modified HeatWave AutoML models can cause undefined behavior.

• There is currently no way to monitor HeatWave AutoML query progress. ML_TRAIN is typically the most time consuming routine. The time required to train a model depends on the number of rows and columns in the dataset and the specified ML_TRAIN parameters and options.

  ML_EXPLAIN_TABLE and ML_PREDICT_TABLE are compute intensive processes, with ML_EXPLAIN_TABLE being the most compute intensive. Limiting operations to batches of 10 to 100 rows by splitting large tables into smaller tables is recommended. Use batch processing with the batch_size option. See: Section 3.15, “Progress tracking”.

• Only ML_TRAIN, ML_EXPLAIN_ROW, and ML_EXPLAIN_TABLE support Ctrl+C interruption.

• ML_EXPLAIN, ML_EXPLAIN_ROW, and ML_EXPLAIN_TABLE routines limit explanations to the 100 most relevant features.

• The ML_PREDICT_TABLE ml_results column contains the prediction results and the data. This combination must be less than 65,532 characters.

• HeatWave AutoML only supports datasets in the English language.

• HeatWave AutoML does not support text columns with NULL values.

• HeatWave AutoML does not support a text target column.

• HeatWave AutoML does not support recommendation tasks with a text column.

• For the forecasting task, endogenous_variables cannot be text.

• Concurrent HeatWave analytics and HeatWave AutoML queries are not supported. A HeatWave AutoML query must wait for HeatWave analytics queries to finish, and vice versa. HeatWave analytics queries are given priority over HeatWave AutoML queries.

• HeatWave on AWS only supports HeatWave AutoML with the HeatWave.256GB node shape. To use HeatWave machine learning functionality, select that shape when creating a HeatWave Cluster.