Update Dockerfile

Dockerfile

@@ -2,4 +2,4 @@ FROM ubuntu:latest
 
 RUN apt update && apt install -y python3-pip
 
-RUN pip install pandas numpy scikit-learn tensorflow
+RUN pip install pandas numpy scikit-learn tensorflow --break-system-packages

Jenkinsfile

@@ -1,54 +1,45 @@
 pipeline {
-  agent any
+  agent { 
+    dockerfile true 
+  }
+
+  triggers {
+    upstream(upstreamProjects: 'z-s464913-create-dataset', threshold: hudson.model.Result.SUCCESS)
+  }
   
   parameters {
-    string (
-      defaultValue: 'vskyper',
-      description: 'Kaggle username',
-      name: 'KAGGLE_USERNAME',
-      trim: false
-    )
-    password (
-      defaultValue: '',
-      description: 'Kaggle API key',
-      name: 'KAGGLE_KEY',
+    buildSelector(
+      defaultSelector: lastSuccessful(),
+      description: 'Which build to use for copying artifacts',
+      name: 'BUILD_SELECTOR'
     )
+    string(name: 'LEARNING_RATE', defaultValue: '0.001', description: 'Learning rate')
+    string(name: 'EPOCHS', defaultValue: '5', description: 'Number of epochs')
   }
 
   stages {
     stage('Clone Repository') {
       steps {
-        git branch: 'main', url: 'https://git.wmi.amu.edu.pl/s464913/ium_464913.git'
+        git branch: 'training', url: 'https://git.wmi.amu.edu.pl/s464913/ium_464913.git'
       }
     }
 
-    stage('Download dataset') {
+    stage('Copy Artifacts') {
       steps {
-        withEnv(["KAGGLE_USERNAME=${params.KAGGLE_USERNAME}", "KAGGLE_KEY=${params.KAGGLE_KEY}"]) {
-          sh 'pip install kaggle'
-          sh 'kaggle datasets download -d mlg-ulb/creditcardfraud'
-          sh 'unzip -o creditcardfraud.zip'
-          sh 'rm creditcardfraud.zip'
-        }
-      }
-    }
-
-    stage('Run create-dataset script') {
-        agent {
-          dockerfile {
-            reuseNode true
+        copyArtifacts filter: 'data/*', projectName: 'z-s464913-create-dataset', selector: buildParameter('BUILD_SELECTOR')
       }
     }
 
+    stage('Run train_model script') {
       steps {
-        sh 'chmod +x create-dataset.py'
-        sh 'python3 ./create-dataset.py'
+        sh 'chmod +x train_model.py'
+        sh "python3 ./train_model.py ${params.LEARNING_RATE} ${params.EPOCHS}"
       }
     }
 
     stage('Archive Artifacts') {
       steps {
-        archiveArtifacts artifacts: 'data/*', onlyIfSuccessful: true
+        archiveArtifacts artifacts: 'model/*', onlyIfSuccessful: true
       }
     }
   }

train_model.py

@@ -6,6 +6,7 @@ from keras.models import Sequential
 from keras.layers import BatchNormalization, Dropout, Dense, Flatten, Conv1D
 from keras.optimizers import Adam
 import pandas as pd
+import sys
 
 
 def main():
@@ -22,6 +23,9 @@ def main():
     X_train = X_train.reshape(X_train.shape[0], X_train.shape[1], 1)
     X_val = X_val.reshape(X_val.shape[0], X_val.shape[1], 1)
 
+    learning_rate = float(sys.argv[1])
+    epochs = int(sys.argv[2])
+
     model = Sequential(
         [
             Conv1D(32, 2, activation="relu", input_shape=X_train[0].shape),
@@ -38,7 +42,7 @@ def main():
     )
 
     model.compile(
-        optimizer=Adam(learning_rate=1e-3),
+        optimizer=Adam(learning_rate=learning_rate),
         loss="binary_crossentropy",
         metrics=["accuracy"],
     )
@@ -47,7 +51,7 @@ def main():
         X_train,
         y_train,
         validation_data=(X_val, y_val),
-        epochs=5,
+        epochs=epochs,
         verbose=1,
     )