Jenkins training script

Dockerfile

@@ -23,8 +23,4 @@ RUN chmod +x /load_data.sh
 RUN /load_data.sh
 
 RUN chmod +x /grab_avocado.py 
-RUN python3 /grab_avocado.py
+RUN python3 /grab_avocado.py
-
-# Run the model and train it
-RUN chmod +x /model.py
-RUN python3 /model.py

jenkins/training.Jenkinsfile

@@ -0,0 +1,61 @@
+pipeline {
+    agent {
+        dockerfile true
+    }
+    parameters {
+        string(
+            defaultValue: '5',
+            description: 'epochs number',
+            name: 'epochs'
+        ),
+        string {
+            defaultValue: '--save',
+            description: 'save model after training',
+            name: 'save_model'
+        }
+    }
+    stages {
+        stage('Checkout') {
+            steps {
+                checkout([$class: 'GitSCM', branches: [[name: '*/develop']], extensions: [], userRemoteConfigs: [
+                    [url: 'https://git.wmi.amu.edu.pl/s478841/ium_478841.git']]])
+            }
+        }
+        stage('Copy Artifacts') {
+            steps {
+                copyArtifacts filter: '*.csv', fingerprintArtifacts: true, projectName: 's478841-create-dataset', selector: lastSuccessful()
+            }
+        }
+        stage('Model training') {
+            steps {
+                sh "chmod +x -R ${env.WORKSPACE}"
+                sh 'python model.py -e $epochs $save_model'
+            }
+        }
+        stage('Archive artifacts') {
+            steps {
+
+                archiveArtifacts artifacts: '*data/predictions.csv', onlyIfSuccessful: true
+                archiveArtifacts artifacts: '*data/model_scripted*', onlyIfSuccessful: true
+            }
+        }
+    }
+
+    post {
+        success {
+            emailtext body: 'SUCCESS', subject: "s478841-training", to: 'e19191c5.uam.onmicrosoft.com@emea.teams.ms'
+        }
+        
+        failure {
+            emailtext body: 'FAILURE', subject: "s478841-training", to: 'e19191c5.uam.onmicrosoft.com@emea.teams.ms'
+        }
+
+        unstable {
+            emailtext body: 'UNSTABLE', subject: "s478841-training", to: 'e19191c5.uam.onmicrosoft.com@emea.teams.ms'
+        }
+
+        changed {
+            emailtext body: 'CHANGED', subject: "s478841-training", to: 'e19191c5.uam.onmicrosoft.com@emea.teams.ms'
+        }
+    }
+}

scripts/model.py

@@ -1,3 +1,5 @@
+import argparse
+
 import pandas as pd
 import numpy as np
 from sklearn.metrics import mean_squared_error
@@ -111,6 +113,21 @@ def predict(row, model):
 
 if __name__ == '__main__':
 
+    # * Model parameters
+    parser = argparse.ArgumentParser(description="Script performing logistic regression model training",
+                                     formatter_class=argparse.ArgumentDefaultsHelpFormatter)
+    parser.add_argument(
+        "-e", "--epochs", default=100, help="Number of epochs the model will be trained for")
+    parser.add_argument("--save", action="store_true",
+                        help="Save trained model to file 'trained_model.h5'")
+
+    args = vars(parser.parse_args())
+
+    epochs = args['epochs']
+    save_model = args['save']
+    print(
+        f"Your model will be trained for {epochs} epochs. Trained model will {'not ' if save_model else ''}be saved.")
+
     # * Paths to data
     avocado_train = './data/avocado.data.train'
     avocado_valid = './data/avocado.data.valid'
@@ -135,7 +152,7 @@ if __name__ == '__main__':
 
     # * Train model
     print("Let's start the training, mate!")
-    train_model(train_dl, model)
+    train_model(train_dl, model, int(epochs))
 
     # * Evaluate model
     mse = evaluate_model(validate_dl, model)
@@ -144,5 +161,12 @@ if __name__ == '__main__':
     # * Prediction
     predictions = [(predict(row, model)[0], row[1].item()) for row in test_dl]
     preds_df = pd.DataFrame(predictions, columns=["Prediction", "Target"])
-    print("\nNow predictions - hey ho, let's go!\n", preds_df.head())
+    print("\nNow predictions - hey ho, let's go!\n",
+          preds_df.head(), "\n\n...let's save them\ndum...\ndum...\ndum dum dum...\n\tDUM\n")
     preds_df.to_csv("./data/predictions.csv", index=False)
+
+    # * Save the trained model
+    if save_model:
+        print("Your model has been saved - have a nice day!")
+        scripted_model = torch.jit.script(model)
+        scripted_model.save('./data/model_scripted.pt')