Platform For AI:PMML processor

Step 1: Deploy a model service

{
  "name": "eas_lr_example",
  "processor": "pmml",
  "model_path": "http://examplebucket.oss-cn-shanghai.aliyuncs.com/models/lr.pmml",
  "metadata": {
    "instance": 1,
    "cpu": 1
  }
}

You can also deploy PMML model services in the Platform for AI (PAI) console. For more information, see Model service deployment by using the PAI console.

Step 2: Call the model service

You can perform the following operations to call the model service.

1. After you deploy the PMML model service, obtain the endpoints of the service and the token used for service authentication. To obtain the information, perform the following operations: On the EAS-Online Model Services page, find the service that you want to call and click Call Inform in the Service Type column.

2. Create a service request.

   Both the input and output of a PMML model service are JSON arrays. You can include multiple samples in a request. Each sample contains data that is presented by using key-value pairs. Example:

   [
       {
           "address": 12,
           "age": 22,
           "ed": 4,
           "marital": 3.0,
           "region": 2.0,
           "tenure": 4.0
       },
       {
           "address": 2,
           "age": 34,
           "ed": 6,
           "marital": 1.3,
           "region": 2.1,
           "tenure": 4.2
       }
   ]

   Note

   When you send the service request, you must delete the line breaks and space characters from the JSON file to speed up data transmission and improve service performance.

3. Send a service request.

   The following methods are supported:

   Important

   If you run the curl command to send the request, the authentication token is specified in the HTTP header and is transmitted in plaintext over the Internet. If you use EAS SDK for Python to send the request, the token is used to sign the request, which improves security.

   • Run the curl command to send the request.

     PMML services support HTTP access. When you send a request, the authentication token can be directly specified in the HTTP header. Example:

     // Send the request. 
     curl -v 18284888792***.cn-shanghai.pai-eas.aliyuncs.com/api/predict/pmml_test \
           -H 'Authorization: YmE3NDkyMzdiMzNmMGM3ZmE4ZmNjZDk0M2NiMDA***' \
           -d '[{"region": 2.0, "marital":3.0,"tenure":4.0, "age":22,"address":12,"ed":4},{"region": 2.1, "marital":1.3,"tenure":4.2, "age":34,"address":2,"ed":6}]'

     Parameters:

     • 18284888792***.cn-shanghai.pai-eas.aliyuncs.com/api/predict/pmml_test: Replace the value with the endpoint that you obtained in Step 1.

     • Authorization: Configure the token that you obtained in Step 1 for service authentication.

     The following result is returned:

     [{"p_0":0.2856724025030001,"p_1":0.7143275974969999},{"p_0":0.18324957921381624,"p_1":0.8167504207861838}]

   • Use EAS SDK for Python to send the request. For more information, see SDK for Python.

     Sample code:

     #!/usr/bin/env python
     
     from eas_prediction import PredictClient
     from eas_prediction import StringRequest
     
     if __name__ == '__main__':
         # Replace the value with the endpoint and service name that you obtained in Step 1. 
         client = PredictClient('1828488879222***.cn-shanghai.pai-eas.aliyuncs.com', 'pmml_test')
         # Replace the value with the token that you obtained in Step 1 for service authentication. 
         client.set_token('YmE3NDkyMzdiMzNmMGM3ZmE4ZmNjZDk0M2NiMDA***')
         client.init()
     
     
         req = StringRequest('[{"region": 2.0, "marital":3.0,"tenure":4.0, "age":22,"address":12,"ed":4},{"region": 2.1, "marital":1.3,"tenure":4.2, "age":34,"address":2,"ed":6}]')
         for x in range(100):
             resp = client.predict(req)
             print(resp)
     

     For more information about how to use EAS SDKs for other languages, see SDKs.