ray_proj/setup_mlflow_example.py

import os
import tempfile
import time

import mlflow

from ray import air, tune
from ray.air import session
from ray.air.integrations.mlflow import MLflowLoggerCallback, setup_mlflow

def evaluation_fn(step, width, height):
    return (0.1 + width * step / 100) ** (-1) + height * 0.1


def train_function(config):
    width, height = config["width"], config["height"]

    for step in range(config.get("steps", 100)):
        # Iterative training function - can be any arbitrary training procedure
        intermediate_score = evaluation_fn(step, width, height)
        # Feed the score back to Tune.
        session.report({"iterations": step, "mean_loss": intermediate_score})
        time.sleep(0.1)

def train_function_mlflow(config):
    setup_mlflow(config)
    
    # Hyperparameters
    width, height = config["width"], config["height"]

    for step in range(config.get("steps", 100)):
        # Iterative training function - can be any arbitrary training procedure
        intermediate_score = evaluation_fn(step, width, height)
        # Log the metrics to mlflow
        mlflow.log_metrics(dict(mean_loss=intermediate_score), step=step)
        # Feed the score back to Tune.
        session.report({"iterations": step, "mean_loss": intermediate_score})
        time.sleep(0.1)

def tune_with_setup(mlflow_tracking_uri, finish_fast=False):
    # Set the experiment, or create a new one if does not exist yet.
    mlflow.set_tracking_uri(mlflow_tracking_uri)
    mlflow.set_experiment(experiment_name="mixin_example")
    
    tuner = tune.Tuner(
        train_function_mlflow,
        tune_config=tune.TuneConfig(
            num_samples=5
        ),
        run_config=air.RunConfig(
            name="mlflow",
        ),
        param_space={
            "width": tune.randint(10, 100),
            "height": tune.randint(0, 100),
            "steps": 5 if finish_fast else 100,
            "mlflow": {
                "experiment_name": "mixin_example",
                "tracking_uri": mlflow.get_tracking_uri(),
            },
        },
    )
    results = tuner.fit()

smoke_test = True

mlflow_tracking_uri = os.path.join(tempfile.gettempdir(), "mlruns")
tune_with_setup(mlflow_tracking_uri, finish_fast=smoke_test)