Skip to content

Query the model from Microsoft SQL Server

This section assumes that you have trained a new model using SQL client or MindsDB Studio.

Prerequisite

Don't forget to install the prerequisites as explained in connect your data section.

To query the model, you will need to SELECT from the model table:

exec('SELECT <target_variable> AS predicted,
             <target_variable_confidence> AS confidence,
             <target_variable_explain> AS info 
      FROM mindsdb.<model_name>
      WHERE <feature value>') AT mindsdb;

Query the model from other databases

Note that even if you have trained the model from the Microsoft SQL Server, you will be able to query it from other databases too.

Query example

The following example shows you how to query the model from a mssql client. The table used for training the model is the Medical insurance dataset. MindsDB will predict the charges based on the values added in when_data.

exec('SELECT charges AS predicted,
             charges_confidence AS confidence,
             charges_explain AS info 
      FROM mindsdb.insurance_model
      WHERE age=30') AT mindsdb;
You should get a response from MindsDB similar to:

predicted confidence info
7571.147 0.9 Check JSON below
info: {
  "predicted_value": 7571.147932782108, 
  "confidence": 0.9, 
  "prediction_quality": "very confident", 
  "important_missing_information": ["smoker", "bmi"]

Model predictions

Comments