

Sklearn

Training

"""
Example taken from https://github.com/mlflow/mlflow/blob/master/examples/sklearn_elasticnet_wine/train.py
"""
import warnings
import sys

import pandas as pd
import numpy as np
from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score
from sklearn.model_selection import train_test_split
from sklearn.linear_model import ElasticNet

import mlflow
import mlflow.sklearn

import logging

logging.basicConfig(level=logging.WARN)
logger = logging.getLogger(__name__)


def eval_metrics(actual, pred):
    rmse = np.sqrt(mean_squared_error(actual, pred))
    mae = mean_absolute_error(actual, pred)
    r2 = r2_score(actual, pred)
    return rmse, mae, r2


if __name__ == "__main__":
    mlflow.set_tracking_uri("http://localhost:5000")
    warnings.filterwarnings("ignore")
    np.random.seed(40)

    # Read the wine-quality csv file from the URL
    csv_url = "http://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-red.csv"
    try:
        data = pd.read_csv(csv_url, sep=";")
    except Exception as e:
        logger.exception(
            "Unable to download training & test CSV, check your internet connection. Error: %s",
            e,
        )

    # Split the data into training and test sets. (0.75, 0.25) split.
    train, test = train_test_split(data)

    # The predicted column is "quality" which is a scalar from [3, 9]
    train_x = train.drop(["quality"], axis=1)
    test_x = test.drop(["quality"], axis=1)
    train_y = train[["quality"]]
    test_y = test[["quality"]]

    alpha = float(sys.argv[1]) if len(sys.argv) > 1 else 0.5
    l1_ratio = float(sys.argv[2]) if len(sys.argv) > 2 else 0.5

    experiment_name = "test_sklearn"
    if mlflow.get_experiment_by_name(experiment_name) is None:
        mlflow.create_experiment(experiment_name)

    with mlflow.start_run(experiment_id=1):
        lr = ElasticNet(alpha=alpha, l1_ratio=l1_ratio, random_state=42)
        lr.fit(train_x, train_y)

        predicted_qualities = lr.predict(test_x)

        (rmse, mae, r2) = eval_metrics(test_y, predicted_qualities)

        print("Elasticnet model (alpha=%f, l1_ratio=%f):" % (alpha, l1_ratio))
        print("  RMSE: %s" % rmse)
        print("  MAE: %s" % mae)
        print("  R2: %s" % r2)

        mlflow.log_param("alpha", alpha)
        mlflow.log_param("l1_ratio", l1_ratio)
        mlflow.log_metric("rmse", rmse)
        mlflow.log_metric("r2", r2)
        mlflow.log_metric("mae", mae)

        mlflow.sklearn.log_model(
            lr, "model", registered_model_name="sklearn_model"
        )

To run it :

python3 -m examples.training.sklearn

Serving

from serveml.api import ApiBuilder
from serveml.inputs import BasicInput
from serveml.loader import load_mlflow_model
from serveml.predictions import GenericPrediction


# load model
model = load_mlflow_model(
    # MlFlow model path
    "models:/sklearn_model/1",
    # MlFlow Tracking URI
    "http://localhost:5000",
)


# Implement deserializer for input data
class WineComposition(BasicInput):
    alcohol: float
    chlorides: float
    citric_acid: float
    density: float
    fixed_acidity: float
    free_sulfur_dioxide: int
    pH: float
    residual_sugar: float
    sulphates: float
    total_sulfur_dioxide: int
    volatile_acidity: int


# implement application
app = ApiBuilder(GenericPrediction(model), WineComposition).build_api()

To run it :

uvicorn examples.serving.sklearn:app --host 0.0.0.0