HemachandranD

# This Azure Pipeline validates and deploys bundle config (ML resource config and more)
# defined under my_mlops_stacks/resources/*
# and my_mlops_stacks/databricks.yml.
# The bundle is validated (CI) upon making a PR against the main_mlops_stack branch.
# Bundle resources defined for staging are deployed when a PR is merged into the main_mlops_stack branch.
# Bundle resources defined for prod are deployed when a PR is merged into the release_mlops_stack branch.

trigger:
  branches:
    include:

HemachandranD

my_mlops_stacks        <- Root directory. Both monorepo and polyrepo are supported.
│
├── my_mlops_stacks       <- Contains python code, notebooks and ML resources related to one ML project. 
│   │
│   ├── requirements.txt        <- Specifies Python dependencies for ML code (for example: model training, batch inference).
│   │
│   ├── databricks.yml          <- databricks.yml is the root bundle file for the ML project that can be loaded by databricks CLI bundles. It defines the bundle name, workspace URL and resource config component to be included.
│   │
│   ├── training                <- Training folder contains Notebook that trains and registers the model with feature store support.
│   │

HemachandranD

# Databricks notebook source
# MAGIC %load_ext autoreload
# MAGIC %autoreload 2

# COMMAND ----------

import os

notebook_path =  '/Workspace/' + os.path.dirname(dbutils.notebook.entry_point.getDbutils().notebook().getContext().notebookPath().get())
%cd $notebook_path

HemachandranD

# Databricks notebook source
import os
import sys
import requests
import json
notebook_path =  '/Workspace/' + os.path.dirname(dbutils.notebook.entry_point.getDbutils().notebook().getContext().notebookPath().get())

# COMMAND ----------

# Set the name of the MLflow endpoint

HemachandranD

# Log the trained model with MLflow and package it with feature lookup information.
# fs.log_model(
#     model,
#     artifact_path="model_packaged",
#     flavor=mlflow.lightgbm,
#     training_set=training_set,
#     registered_model_name=model_name,
# )
# Log the trained model with MLflow.
autolog_run = mlflow.last_active_run()

HemachandranD

# The name of the bundle. run `databricks bundle schema` to see the full bundle settings schema.
bundle:
  name: my_mlops_stacks

variables:
  experiment_name:
    description: Experiment name for the model training.
    default: /Users/${workspace.current_user.userName}/${bundle.target}-my_mlops_stacks-experiment
  model_name:
    description: Model name for the model training.