SEVERE: Failed to evaluate org.jpmml.evaluator.InvalidResultException

[gopinathankm]

Hello
My scenario is as follows:
Using Linear Regression I trying to predict power generated based on the values of temperature, vacuum, pressure and humidity which is inspired and Adapted from "http://datascience-enthusiast.com" and applying model to real time data from Kafka topic. Properly generated pickled .pkl.z file and converts to PMML using JPMML as suggested https://github.com/jpmml/jpmml-sklearn.

1. Kafka Producer, a Python program (kafka_producer.py) randomly generates data within some ranges as float and converts string and sending to Kafka topic as bytes.

2. Kafka Consumer, a python program(kafka_consumer) which act as Openscoring python client, reads the data from Kafka topic, converts byte string to string and finally to a dictionary which form the arguments like arguments = {"AT" : 9.2, "V" : 39.82, "AP" : 1013.19, "RH" : 91.25} for result = os.evaluate("CCPP", arguments) statement.

3. It works well and predict power, but after showing the result correctly for 4 to 10 records,
   Openscoring server throws SEVERE: INFO:
   Received EvaluationRequest{id=null, arguments={AT=12.12, V=41.35, AP=1031.67, RH=66.32}}
   Nov 20, 2017 6:39:16 AM org.openscoring.service.ModelResource evaluate
   INFO: Returned EvaluationResponse{id=null, result={PE=472.152110955029}}
   Nov 20, 2017 6:39:17 AM org.openscoring.service.ModelResource evaluate
   INFO: Received EvaluationRequest{id=null, arguments={AT=34.06, V=51.53, AP=1016.22, RH=91.7}}
   Nov 20, 2017 6:39:17 AM org.openscoring.service.ModelResource evaluate
   INFO: Returned EvaluationResponse{id=null, result={PE=444.9147880324237}}
   Nov 20, 2017 6:39:18 AM org.openscoring.service.ModelResource evaluate
   INFO: Received EvaluationRequest{id=null, arguments={AT=20.41, V=50.33, AP=1018.19, RH=100.18}}
   Nov 20, 2017 6:39:18 AM org.openscoring.service.ModelResource doEvaluate
   SEVERE: Failed to evaluate
   org.jpmml.evaluator.InvalidResultException (at or around line 130)
   at org.jpmml.evaluator.FieldValueUtil.performInvalidValueTreatment(FieldValueUtil.java:178)
   at org.jpmml.evaluator.FieldValueUtil.prepareInputValue(FieldValueUtil.java:90)
   at org.jpmml.evaluator.InputField.prepare(InputField.java:64)

4. Kafka Consumer stops and show: raise Exception(self.message)
   Exception: Bad Request

kafka_producer.py
import random
import time
from kafka import KafkaProducer
from kafka.errors import KafkaError
producer = KafkaProducer(bootstrap_servers='localhost:9092')
topic = "power"
for i in range(1000):
AT = "19.651231"
V = "54.305804"
AP = "1013.259078"
RH = "73.308978"
def getAT():
return str(round(random.uniform(2.0, 38.0),2))
def getV():
return str(round(random.uniform(26.0, 81.5),2))
def getAP():
return str(round(random.uniform(993.0, 1033.0),2))
def getRH():
return str(round(random.uniform(26.0, 101.0),2))
# arguments = {"AT" :9.2, "V" : 39.82, "AP" : 1013.19, "RH" : 91.25}
message = "{"AT" : " + getAT() + "," + ""V" : " +getV() + "," + ""AP" : " +getAP() + "," + ""RH" : " + getRH() + "}"
producer.send(topic, key=str.encode('key_{}'.format(i)), value=(message.encode('utf-8')))
time.sleep(1)
producer.close()

kafka_consumer.py
import ast
from kafka import KafkaConsumer
import openscoring
import os
os = openscoring.Openscoring("http://localhost:8080/openscoring")
kwargs = {"auth" : ("admin", "adminadmin")}
os.deploy("CCPP", "/home/gopinathankm/jpmml-sklearn-master/ccpp.pmml", **kwargs)
consumer = KafkaConsumer('power', bootstrap_servers='localhost:9092')
for message in consumer:
arguments =message.value
argsdict = arguments.decode("utf-8")
dict = ast.literal_eval(argsdict)
print(dict)
result = os.evaluate("CCPP", dict)
print(result)

For some data generated it is not working, I really don't know how bad request is generated.
Any assistance will be highly appreciated.
Regards
Gopinathan K.M

[vruusmann]

Exception type InvalidResultException means that the evaluation of a model could not be completed successfully, because one or more input field values are outside of their declared range.

def getAT():
return str(round(random.uniform(2.0, 38.0),2))
def getV():
return str(round(random.uniform(26.0, 81.5),2))
def getAP():
return str(round(random.uniform(993.0, 1033.0),2))
def getRH():
return str(round(random.uniform(26.0, 101.0),2))

The value ranges of your PMML document and Python script do not match. Either delete PMML document value ranges (so that all input values are considered to be valid), or contract Python script value ranges.

[gopinathankm]

I will try both.
Many Thanks.

[gopinathankm]

I will try both and see.
Many thanks.

Gopinathan K.M

[gopinathankm]

Mr.Villu Ruusmann I do really thanking you for your prompt response, really appreciate. With Regards Gopinathan K.M

…

On Mon, Nov 20, 2017 at 11:07 AM, Villu Ruusmann ***@***.***> wrote: Closed #84 <#84>. — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub <#84 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AGTPT2-16-uVSScwMfU2Y8_J-ef9nmsTks5s4RAWgaJpZM4Qjqbo> .

-- Until next time, you can tell everybody this is your song….................... Gopinathan K.M