From d679916066c18903cff558a0b058bef5264b577b Mon Sep 17 00:00:00 2001
From: wojciechbatruszewicz <wojtek.baltruszewicz@gmail.com>
Date: Tue, 27 Jun 2023 15:34:59 +0200
Subject: [PATCH] evaluate

---
 JenkinsfileEvaluate | 48 +++++++++++++++++++++++++++
 JenkinsfileTrain    | 10 +++---
 evaluate.py         | 80 +++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 133 insertions(+), 5 deletions(-)
 create mode 100644 JenkinsfileEvaluate
 create mode 100644 evaluate.py

diff --git a/JenkinsfileEvaluate b/JenkinsfileEvaluate
new file mode 100644
index 0000000..52888e3
--- /dev/null
+++ b/JenkinsfileEvaluate
@@ -0,0 +1,48 @@
+pipeline {
+    agent any
+    parameters {
+        buildSelector(
+            name: 'BUILD_SELECTOR',
+            defaultSelector: lastSuccessful(),
+            description: 'A build to take the artifacts from'
+        )
+        string(
+            name: 'EPOCHS',
+            description: 'Number of epochs',
+            defaultValue: '10'
+        )
+    }
+    stages {
+        stage('Copy artifacts') {
+            steps {
+                script {
+                    copyArtifacts(
+                        projectName: 'z-s487179-training/main',
+                        selector: buildParameter('BUILD_SELECTOR'),
+                        target: './MLEvaluate'
+                    )
+                    copyArtifacts(
+                        projectName: 'z-s487179-create-dataset',
+                        selector: buildParameter('BUILD_SELECTOR'),
+                        target: './MLEvaluate'
+                    )
+                }
+            }
+        }
+        stage('Run training and save model') {
+            steps {
+                    script {
+                    sh 'ls -l'
+                    docker.image('docker-image').inside {
+                        dir('./MLEvaluate') {
+                            sh 'ls -l'
+                            sh 'python3 ./model_test.py'
+                            archiveArtifacts 'plot.png'
+                            archiveArtifacts 'result.csv'
+                        }
+                    }
+                }
+            }
+        }
+    }
+}
\ No newline at end of file
diff --git a/JenkinsfileTrain b/JenkinsfileTrain
index 7fac944..d486d52 100644
--- a/JenkinsfileTrain
+++ b/JenkinsfileTrain
@@ -37,9 +37,9 @@ pipeline {
             }
         }
     }
-    // post {
-    //     success {
-    //         build job: 'x1-evaluation.eg/main', wait: false
-    //     }
-    // }
+    post {
+        success {
+            build job: 'x1-evaluation.eg/main', wait: false
+        }
+    }
 }
\ No newline at end of file
diff --git a/evaluate.py b/evaluate.py
new file mode 100644
index 0000000..38c2fff
--- /dev/null
+++ b/evaluate.py
@@ -0,0 +1,80 @@
+import torch
+from train import MyNeuralNetwork, load_data
+from torch.utils.data import DataLoader
+import csv
+import os
+import matplotlib.pyplot as plt
+from typing import Tuple, List
+
+def evaluate_model() -> Tuple[List[float], float]:
+    model = MyNeuralNetwork()
+    model.load_state_dict(torch.load('model.pt'))
+    model.eval()
+    test_dataset = load_data("gender_classification_test.csv")
+    batch_size: int = 32
+    test_dataloader: DataLoader = DataLoader(test_dataset, batch_size=batch_size)
+    predictions = []
+    labels = []
+    get_label = lambda pred: 1 if pred >= 0.5 else 0
+    total = 0
+    correct = 0
+    with torch.no_grad():
+        for batch_data, batch_labels in test_dataloader:
+            batch_predictions = model(batch_data)
+            predicted_batch_labels = [get_label(prediction) for prediction in batch_predictions]
+            total += len(predicted_batch_labels)
+            batch_labels_list = list(map(int,batch_labels.tolist()))
+            correct += sum(x == y for x, y in zip(predicted_batch_labels, batch_labels_list))
+            predictions.extend(batch_predictions)
+            labels.extend(batch_labels)
+    accuracy = correct/total
+    return predictions, accuracy
+
+def save_predictions(predictions: list[float]) -> None:
+    filename = "results.csv"
+    column_name = "predict"
+    with open(filename, 'w', newline='') as file:
+        writer = csv.writer(file)
+        writer.writerow([column_name])
+        for result in predictions:
+            loan_decision = 1 if result.item() > 0.5 else 0
+            writer.writerow([loan_decision])
+
+def save_accuracy(accuracy):
+    filename = 'results.csv'
+    if os.path.exists(filename):
+        with open(filename, 'a') as file:
+            writer = csv.writer(file)
+            writer.writerow([accuracy])
+    else:
+        with open(filename, 'w') as file:
+            writer = csv.writer(file)
+            writer.writerow(['accuracy'])
+            writer.writerow([accuracy])
+        
+def plot_accuracy():
+    filename = 'results.csv'
+    accuracy_results = []
+    if os.path.exists(filename):
+        with open(filename, 'r') as file:
+            reader =  csv.reader(file)
+            for idx, row in enumerate(reader):
+                if idx == 0:
+                    continue
+                accuracy_results.append(float(row[0]))
+    iterations = list(map(str,range(1, len(accuracy_results)+1)))
+    plt.plot(iterations, accuracy_results)
+    plt.xlabel('build')
+    plt.ylabel('accuracy')
+    plt.title("Accuracies over builds.")
+    plt.savefig("plot.png")
+                
+def main():
+    predictions, accuracy = evaluate_model()
+    save_predictions(predictions)
+    save_accuracy(accuracy)
+    plot_accuracy()
+    
+    
+if __name__ == "__main__":
+    main()
\ No newline at end of file