Update Jenkinsfile

Dockerfile

@@ -4,7 +4,7 @@ RUN apt update && apt install -y python3-pip
 RUN apt install unzip
 RUN apt install bc
 
-RUN pip3 install kaggle pandas scikit-learn torch
+RUN pip3 install kaggle pandas scikit-learn torch matplotlib
 
 WORKDIR /app
 

Jenkinsfile

@@ -1,49 +1,59 @@
 pipeline {
     agent any
     parameters {
-    string(name: 'KAGGLE_USERNAME', defaultValue: 'alicjaszulecka', description: 'Kaggle username')
+            buildSelector (
-    password(name: 'KAGGLE_KEY', defaultValue:'', description: 'Kaggle Key')
+                defaultSelector: lastSuccessful(),
-    string(name: 'CUTOFF', defaultValue: '100', description: 'cut off number')
+                description: 'Build for copying artifacts',
-    }
+                name: 'BUILD_SELECTOR'
+            )
+            gitParameter branchFilter: 'origin/(.*)', defaultValue: 'model', name: 'BRANCH', type: 'PT_BRANCH'
+        }
+        triggers {
+            upstream(upstreamProjects: 's464914-training/' + params.BRANCH + '/', threshold: hudson.model.Result.SUCCESS)
+        }
     stages {
         stage('Git Checkout') {
             steps {
                checkout scm
             }
         }
-         stage('Download dataset') {
+     stage('Copy Artifacts') {
-      steps {
+            steps {
-        withEnv(["KAGGLE_USERNAME=${params.KAGGLE_USERNAME}", "KAGGLE_KEY=${params.KAGGLE_KEY}"]) {
+               copyArtifacts fingerprintArtifacts: true, projectName: 'z-s464914-create-dataset', selector: buildParameter('BUILD_SELECTOR')
-          sh 'pip install kaggle'
+               copyArtifacts filter: '*', projectName: 's464914-training/' + params.BRANCH + '/', selector: buildParameter('BUILD_SELECTOR')
-          sh 'kaggle datasets download -d uciml/forest-cover-type-dataset'
+               copyArtifacts filter: '*', projectName: 's464914-evaluation/evaluation/', selector: buildParameter('BUILD_SELECTOR'), optional: true
-          sh 'unzip -o forest-cover-type-dataset.zip'
+            }
-          sh 'rm forest-cover-type-dataset.zip'
         }
-      }
+         stage('Prediction') {
-    }
-     stage('Build') {
-         steps {
-            script {
-                 withEnv(["KAGGLE_USERNAME=${params.KAGGLE_USERNAME}",
-                          "KAGGLE_KEY=${params.KAGGLE_KEY}" ]) {
-                    def customImage = docker.build("custom-image")
-                    customImage.inside {
-                        sh 'python3 ./IUM_2.py'
-                        archiveArtifacts artifacts: 'covtype.csv, forest_train.csv, forest_test.csv, forest_val.csv', onlyIfSuccessful: true
-                    }
-                 }
-             }
-         }
-         }
-
-         stage('Train and Predict') {
             steps {
               script {
                def customImage = docker.build("custom-image")
                     customImage.inside {
-                        sh 'python3 ./model.py'
                         sh 'python3 ./prediction.py'
-                        archiveArtifacts artifacts: 'model.pth, predictions.txt', onlyIfSuccessful: true
+                        archiveArtifacts artifacts: 'predictions.txt', onlyIfSuccessful: true
+                    }
+              }
+            }
+        }
+        stage('Metrics') {
+            steps {
+              script {
+               def customImage = docker.build("custom-image")
+                    customImage.inside {
+                        sh 'python3 ./metrics.py'
+                        archiveArtifacts artifacts: 'metrics.txt', onlyIfSuccessful: true
+                    }
+              }
+            }
+        }
+
+        stage('Plot Accuracy') {
+            steps {
+              script {
+               def customImage = docker.build("custom-image")
+                    customImage.inside {
+                        sh 'python3 ./plot.py'
+                        archiveArtifacts artifacts: 'accuracy.png', onlyIfSuccessful: true
                     }
               }
             }

metrics.py

@@ -0,0 +1,24 @@
+from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, mean_squared_error
+import numpy as np
+
+true_labels = []
+predicted_labels = []
+
+f = open("predictions.txt", "r")
+for line in f:
+  parts = line.strip().split(' ')
+  true_labels.append(int(parts[3]))
+  predicted_labels.append(int(parts[1]))
+
+accuracy = accuracy_score(true_labels, predicted_labels)
+precision_micro = precision_score(true_labels, predicted_labels, average='micro')
+recall_micro = recall_score(true_labels, predicted_labels, average='micro')
+f1_micro = f1_score(true_labels, predicted_labels, average='micro')
+rmse = np.sqrt(mean_squared_error(true_labels, predicted_labels))
+
+with open(r'metrics.txt', 'a') as fp:
+    fp.write(f"Accuracy: {accuracy}\n")
+    fp.write(f"Precision: {precision_micro}\n")
+    fp.write(f"Recall: {recall_micro}\n")
+    fp.write(f"F1-score: {f1_micro}\n")
+    fp.write(f"RMSE: {rmse}\n")

model.py

@@ -6,6 +6,7 @@ import pandas as pd
 from sklearn.model_selection import train_test_split
 from sklearn.preprocessing import LabelEncoder
 import torch.nn.functional as F
+import sys
  
 
 device = (
@@ -30,6 +31,9 @@ class Model(nn.Module):
         return x
 
 def main():
+    epochs = int(sys.argv[1])
+    print(epochs)
+
     forest_train = pd.read_csv('forest_train.csv')
     forest_val = pd.read_csv('forest_val.csv')
 
@@ -59,7 +63,6 @@ def main():
     val_loader = DataLoader(list(zip(X_val, y_val)), batch_size=64)
 
     # Training loop
-    epochs = 10
     for epoch in range(epochs):
         model.train()  # Set model to training mode
         running_loss = 0.0

plot.py

@@ -0,0 +1,21 @@
+import matplotlib.pyplot as plt
+import numpy as np
+
+accuracy = [] 
+
+f = open("metrics.txt", "r")
+for line in f:
+  parts = line.strip().split(' ')
+  if(parts[0] == 'Accuracy:'):
+    accuracy.append(float(parts[1]))
+
+build_numbers = np.arange(1, len(accuracy) + 1)
+
+plt.plot(build_numbers, accuracy,  marker='o', linestyle='-', color='b')
+plt.xlabel('Build Number')
+plt.ylabel('Accuracy')
+plt.title('Accuracy Plot')
+plt.grid(True)
+plt.show()
+
+plt.savefig('accuracy.png')

prediction.py

@@ -6,6 +6,8 @@ import pandas as pd
 from sklearn.model_selection import train_test_split
 from sklearn.preprocessing import LabelEncoder
 import torch.nn.functional as F
+from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, mean_squared_error
+import numpy as np
 
 device = (
     "cuda"
@@ -41,7 +43,6 @@ def predict(model, input_data):
     
     return predicted_class.item()  # Return the predicted class label
 
-
 def main():
     forest_test = pd.read_csv('forest_test.csv')
 
@@ -55,15 +56,23 @@ def main():
     load_model(model, model_path)
 
     predictions = []
-    for input_data in X_test:
+    correct = 0
-        predicted_class = predict(model, input_data)
+    total = 0
-        predictions.append(predicted_class)
+    with torch.no_grad():
+        for input_data, target in zip(X_test, y_test):
+            output = model(input_data)
+            _, predicted_class = torch.max(output, 0)
+            prediction_entry = f"predicted: {predicted_class.item()} true_label: {target}"
+            predictions.append(prediction_entry)
+            total += 1
+            if predicted_class.item() == target:
+                correct += 1
+
 
     with open(r'predictions.txt', 'w') as fp:
         for item in predictions:
             # write each item on a new line
             fp.write("%s\n" % item)
 
-
 if __name__ == "__main__":
     main()