From be0e247d2f0d11fe9b94ddb59e2e580e398cbc05 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Tomasz=20Zi=C4=99tkiewicz?= <tomasz.zietkiewicz@amu.edu.pl>
Date: Wed, 26 May 2021 21:26:06 +0200
Subject: [PATCH] MLflow in Docker on Jenkins

---
 Dockerfile  |  5 +++
 Jenkinsfile | 17 +++++++++
 train.py    | 99 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 121 insertions(+)
 create mode 100644 Dockerfile
 create mode 100644 Jenkinsfile
 create mode 100644 train.py

diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000..db6e42f
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,5 @@
+FROM ubuntu:20.04
+
+RUN apt update
+RUN apt install -y python3 python3-pip
+RUN pip install mlflow 
diff --git a/Jenkinsfile b/Jenkinsfile
new file mode 100644
index 0000000..b09102c
--- /dev/null
+++ b/Jenkinsfile
@@ -0,0 +1,17 @@
+node {
+    def img
+    stage('Preparation') { // for display purposes
+        img = docker.build('ium-helloworld')
+    }
+    stage('Train') {
+            img.inside('-v /tmp/mlruns:/tmp/mlruns -v /mlruns:/mlruns ') {
+                sh 'ls -l /tmp/mlruns'
+                sh 'ls -l /mlruns'
+		sh './train.py'
+                sh 'ls -l /tmp/mlruns'
+                sh 'ls -l /mlruns'
+            }
+    }
+
+}
+
diff --git a/train.py b/train.py
new file mode 100644
index 0000000..673fed3
--- /dev/null
+++ b/train.py
@@ -0,0 +1,99 @@
+# The data set used in this example is from http://archive.ics.uci.edu/ml/datasets/Wine+Quality
+# P. Cortez, A. Cerdeira, F. Almeida, T. Matos and J. Reis.
+# Modeling wine preferences by data mining from physicochemical properties. In Decision Support Systems, Elsevier, 47(4):547-553, 2009.
+
+import os
+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
+from urllib.parse import urlparse
+import mlflow
+import mlflow.sklearn
+
+import logging
+
+logging.basicConfig(level=logging.WARN)
+logger = logging.getLogger(__name__)
+
+mlflow.set_tracking_uri("http://localhost:5001")
+mlflow.set_experiment("s123456")
+
+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 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
+    #alpha = 0.5
+    l1_ratio = float(sys.argv[2]) if len(sys.argv) > 2 else 0.5
+    #l1_ratio = 0.5
+
+    with mlflow.start_run() as run:
+        print("MLflow run experiment_id: {0}".format(run.info.experiment_id))
+        print("MLflow run artifact_uri: {0}".format(run.info.artifact_uri))
+
+        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)
+        
+        # Infer model signature to log it
+        signature = mlflow.models.signature.infer_signature(train_x, lr.predict(train_x))
+
+        tracking_url_type_store = urlparse(mlflow.get_tracking_uri()).scheme
+
+        # Model registry does not work with file store
+        if tracking_url_type_store != "file":
+
+            # Register the model
+            # There are other ways to use the Model Registry, which depends on the use case,
+            # please refer to the doc for more information:
+            # https://mlflow.org/docs/latest/model-registry.html#api-workflow
+            mlflow.sklearn.log_model(lr, "wines-model", registered_model_name="ElasticnetWineModel", signature=signature)
+        else:
+            mlflow.sklearn.log_model(lr, "model", signature=signature)