From 0fce6cd355c38fa279b30e8dedc51f341fa129c9 Mon Sep 17 00:00:00 2001
From: Wojciech Jarmosz <wojciech@jarmosz.com>
Date: Thu, 13 May 2021 22:20:25 +0200
Subject: [PATCH] LAB 6 - 1, Add pipeline for training

---
 Jenkinsfile_train | 29 +++++++++++++++++++++++++++++
 training.py       | 43 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 72 insertions(+)
 create mode 100644 Jenkinsfile_train
 create mode 100644 training.py

diff --git a/Jenkinsfile_train b/Jenkinsfile_train
new file mode 100644
index 0000000..6952ed2
--- /dev/null
+++ b/Jenkinsfile_train
@@ -0,0 +1,29 @@
+pipeline {
+    agent {
+        docker { image 'jarmosz/ium:1.1' }
+    }
+    parameters {
+        string(name: 'optioms', description: 'Trainig script options')
+        buildSelector(defaultSelector: lastSuccessful(), description: 'Use latest build', name: 'BUILD_SELECTOR')
+    }
+    stages {
+        stage("Copy artifacts"){
+            steps {
+                copyArtifacts fingerprintArtifacts: true, projectName: 's434704-create-dataset', selector: buildParameter('BUILD_SELECTOR')
+            }
+        }
+        stage("Run training"){
+            sh "python3 training.py ${params.options}"
+        }
+        stage('Save trained model files') {
+			steps{
+				archiveArtifacts 'linear_regression/**'
+			}
+		}
+    }
+    post {
+        always {
+            mail body: ${currentBuild.currentResult}, subject: 's434704', to: '26ab8f35.uam.onmicrosoft.com@emea.teams.ms'
+        }
+    }
+}
\ No newline at end of file
diff --git a/training.py b/training.py
new file mode 100644
index 0000000..cddf32b
--- /dev/null
+++ b/training.py
@@ -0,0 +1,43 @@
+import pandas as pd
+import numpy as np
+import tensorflow as tf
+import os.path
+
+from tensorflow import keras
+from tensorflow.keras import layers
+from tensorflow.keras.layers.experimental import preprocessing
+
+pd.set_option("display.max_columns", None)
+
+# Wczytanie danych
+train_data = pd.read_csv("./train.csv")
+test_data = pd.read_csv("./test.csv")
+
+# Stworzenie modelu 
+columns_to_use = ['Year', 'Runtime', 'Netflix']
+train_X = tf.convert_to_tensor(train_data[columns_to_use])
+train_Y = tf.convert_to_tensor(train_data[["IMDb"]])
+test_X = tf.convert_to_tensor(test_data[columns_to_use])
+test_Y = tf.convert_to_tensor(test_data[["IMDb"]])
+
+normalizer = preprocessing.Normalization(input_shape=[3,])
+normalizer.adapt(train_X)
+
+if os.path.isdir('linear_regression'):
+    model = keras.models.load_model('linear_regression')
+else:
+    model = keras.Sequential([
+        keras.Input(shape=(len(columns_to_use),)),
+        normalizer,
+        layers.Dense(30, activation='relu'),
+        layers.Dense(10, activation='relu'),
+        layers.Dense(25, activation='relu'),
+        layers.Dense(1)
+    ])
+
+    model.compile(loss='mean_absolute_error',
+                    optimizer=tf.keras.optimizers.Adam(0.001))
+
+    model.fit(train_X, train_Y, verbose=0, epochs=100)
+
+    model.save('linear_regression')
\ No newline at end of file