azureml-ai-monitoring

Microsoft Azure Machine Learning Data Collection SDK v2 for model monitoring

The azureml-ai-monitoring package provides an SDK to enable Model Data Collector (MDC) for custom logging allows customers to collect data at arbitrary points in their data pre-processing pipeline. Customers can leverage SDK in score.py to log data to desired sink before, during, and after any data transformations.

Quickstart

Start by importing the azureml-ai-monitoring package in score.py

import pandas as pd
import json
from azureml.ai.monitoring import Collector

def init():
  global inputs_collector, outputs_collector

  # instantiate collectors with appropriate names, make sure align with deployment spec
  inputs_collector = Collector(name='model_inputs')                    
  outputs_collector = Collector(name='model_outputs')

def run(data): 
  # json data: { "data" : {  "col1": [1,2,3], "col2": [2,3,4] } }
  pdf_data = preprocess(json.loads(data))
  
  # tabular data: {  "col1": [1,2,3], "col2": [2,3,4] }
  input_df = pd.DataFrame(pdf_data)

  # collect inputs data, store correlation_context
  context = inputs_collector.collect(input_df)

  # perform scoring with pandas Dataframe, return value is also pandas Dataframe
  output_df = predict(input_df) 

  # collect outputs data, pass in correlation_context so inputs and outputs data can be correlated later
  outputs_collector.collect(output_df, context)
  
  return output_df.to_dict()
  
def preprocess(json_data):
  # preprocess the payload to ensure it can be converted to pandas DataFrame
  return json_data["data"]

def predict(input_df):
  # process input and return with outputs
  ...
  
  return output_df

Create environment with base image mcr.microsoft.com/azureml/openmpi4.1.0-ubuntu20.04 and conda dependencies, then build the environment.

channels:
  - conda-forge
dependencies:
  - python=3.8
  - pip=22.3.1
  - pip:
      - azureml-defaults==1.38.0
      - azureml-ai-monitoring
name: model-env

Create deployment with custom logging enabled (model_inputs and model_outputs are enabled) and the environment you just built, please update the yaml according to your scenario.

#source ../configs/model-data-collector/data-storage-basic-OnlineDeployment.YAML
$schema: http://azureml/sdk-2-0/OnlineDeployment.json

endpoint_name: my_endpoint #unchanged
name: blue #unchanged
model: azureml:my-model-m1:1 #azureml:models/<name>:<version> #unchanged
environment: azureml:custom-logging-env@latest #unchanged
data_collector:
  collections:
    model_inputs:
      enabled: 'True'
    model_outputs:
      enabled: 'True'

Configurable error handler

By default, we'll raise the exception when there is unexpected behavior (like custom logging is not enabled, collection is not enabled, not supported data type), if you want a configurable on_error, you can do it with

collector = Collector(name="inputs", on_error=lambda e: logging.info("ex:{}".format(e)))

Change Log

v1.0.0 (2024.4.25)

Announcement

• Publish official version v1.0.0.

v0.1.0b4 (2023.8.21)

Improvements

• improve error msg when queue is full.
• Increase msg queue to handle more requests.

v0.1.0b3 (2023.5.15)

Improvements

• fix install_requires
• fix classifiers
• fix README

v0.1.0b2 (2023.5.9)

New Features

• Support local capture

v0.1.0b1 (2023.4.25)

New Features

• Support model data collection for pandas Dataframe.