Add MLFlow Compatibility needed for MVP

The code below (adapted from https://github.com/mlflow/mlflow-example) should work by changing the tracking URI to gitlab experiment tracking base url (https://gitlab.com/<my-project>/-/ml/experiments).

The endpoints we need to implement:

Prefix: /experiments/api/2.0/mlfow

• MR: Add MLFlow Rest API with 3 endpoints (!95689 - merged)
  • GET /experiments/get
  • GET /experiments/get-by-name
  • POST /experiments/create
• MR: Adds Run endpoints for MLFlow Integration (!97003 - merged)
  • POST /runs/create
  • GET /runs/get
  • POST /runs/update
• MR: Add LogMetric endpoint (!97394 - merged)
  • POST /runs/log-metric
• MR: Adds LogParam and LogBatch endpoints to MLFlow (!97815 - merged)
  • POST /runs/log-parameter
  • POST /runs/log-batch
• MR: Adds remaining endpoints for MLFlow API compati... (!98106 - merged)
  • Remaining needed endpoints to make the script work, except log_model

Note: log-model will not be implemented right for MVP

import os
import warnings

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

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__":
    warnings.filterwarnings("ignore")
    np.random.seed(40)

    # Read the wine-quality csv file (make sure you're running this from the root of MLflow!)
    wine_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), "wine-quality.csv")
    data = pd.read_csv(wine_path)

    # 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
    
    mlflow.set_experiment(experiment_name="yet_another_experiment_3")
    mlflow.set_tracking_uri("http://127.0.0.1:5001/")

    for alpha in range(1, 3):
        for l1_ratio in [0.05,  0.1, 0.2]:
            with mlflow.start_run():
                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 / 10.0, l1_ratio))
                print("  RMSE: %s" % rmse)
                print("  MAE: %s" % mae)
                print("  R2: %s" % r2)

                mlflow.log_param("alpha", alpha / 10.0)
                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")