3.7.1 Row Predictions

ML_PREDICT_ROW generates predictions for one or more rows of data specified in JSON format. It is invoked using a SELECT statement. For ML_PREDICT_ROW parameter descriptions, see Section 3.16.5, “ML_PREDICT_ROW”.

Before running ML_PREDICT_ROW, ensure that the model you want to use is loaded; for example:

Press CTRL+C to copy
 
mysql> CALL sys.ML_MODEL_LOAD(@census_model, NULL);

For more information about loading models, see Section 3.14.3, “Loading Models”.

The following example runs ML_PREDICT_ROW on a single row of unlabeled data, which is assigned to a @row_input session variable:

Press CTRL+C to copy
 
mysql> SET @row_input = JSON_OBJECT( 
          "age", 25, 
          "workclass", "Private", 
          "fnlwgt", 226802, 
          "education", "11th", 
          "education-num", 7, 
          "marital-status", "Never-married", 
          "occupation", "Machine-op-inspct", 
          "relationship", "Own-child", 
          "race", "Black", 
          "sex", "Male", 
          "capital-gain", 0, 
          "capital-loss", 0, 
          "hours-per-week", 40, 
          "native-country", "United-States"); 

mysql> SELECT sys.ML_PREDICT_ROW(@row_input, @census_model, NULL);

where:

• @row_input is a session variable containing a row of unlabeled data. The data is specified in JSON key-value format. The column names must match the feature column names in the training dataset.

• @census_model is the session variable that contains the model handle.

ML_PREDICT_ROW returns a JSON object containing a Prediction key with the predicted value and the features values used to make the prediction.

You can also run ML_PREDICT_ROW on multiple rows of data selected from a table. For an example, refer to the syntax examples in Section 3.16.5, “ML_PREDICT_ROW”.