Score the Predictive Model with APPLY Table Operator | Scoring with a model file | Open Analytics Framework - Scoring the Predictive Model with APPLY Table Operator

Use the Apply class to create a teradataml Apply class object with the characteristics you want to consider for the call to the APPLY Table Operator.

In this example, specify the following:

The data argument, so you can specify the input teradataml DataFrame that points to the test data table.
The files_local_path argument with the path_to_files variable defined earlier.
The apply_command argument to call the Python 3 interpreter in your user environment and execute your script.
The returns argument with the list of output variables and types returned by your script.
The env_name argument to specify your user environment handler.

Assume your Python script returns scored rows that contain the following variables:

An integer variable Cust_ID with a customer ID.
A float variable Prob_0 with the probability that a customer will not open a new credit card account.
A float variable Prob_1 with the probability that a customer will open a new credit card account.
A float variable Actual with the actual outcome for the specific customer.

Call to the Apply class.

apply_obj = Apply(data = scoringData,
                  apply_command = 'python3 scoring.py',
                  returns = {'Cust_ID': VARCHAR(20), 'Prob_0': VARCHAR(10), 
                             'Prob_1': VARCHAR(10), 'Actual': VARCHAR(10)},
                  env_name = demo_env,
                 )

You can request to view SQL queries submitted by teradataml in the background with the following statement:

display.print_sqlmr_query = True

Run the Python script inside the user environment with the execute_script method of the Apply class object.

Observe that after running the Python statement, the system prints for you the corresponding SQL query as requested before producing the results.

apply_obj.execute_script().head(n=5)

Out:

SELECT * FROM Apply(
        ON "VCLUSTER"."scoringData" AS "input"
        PARTITION BY ANY
        returns(Cust_ID VARCHAR(20), Prob_0 VARCHAR(10), Prob_1 VARCHAR(10), Actual VARCHAR(10))
        USING
        APPLY_COMMAND('python3 scoring.py')
        ENVIRONMENT('opaf_my_scoring_env')
        STYLE('csv')
        delimiter(',') 
) as sqlmr

Cust_ID      Prob_0   Prob_1  Actual
13624840         0.0         1.0         1
13624870         0.0         1.0         1
13624850         0.0         1.0         1
13624810         1.0         0.0         0
13624800         0.0         1.0         1

Score the Predictive Model with APPLY Table Operator | Scoring with a model file | Open Analytics Framework - Scoring the Predictive Model with APPLY Table Operator - Teradata Vantage

Teradata® VantageCloud Lake