From 3c88cb0131767a9629169e3b80702d5143f5d536 Mon Sep 17 00:00:00 2001
From: Kamil Guttmann <kamgut@st.amu.edu.pl>
Date: Tue, 3 May 2022 19:47:36 +0200
Subject: [PATCH] Evaluation

---
 Dockerfile       |  2 +-
 Jenkinsfile.eval | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
 evaluate.py      | 22 ++++++++++++++++++++++
 3 files changed, 71 insertions(+), 1 deletion(-)
 create mode 100644 Jenkinsfile.eval
 create mode 100644 evaluate.py

diff --git a/Dockerfile b/Dockerfile
index bbf0e3a..2359717 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -15,6 +15,6 @@ RUN apt-get update && apt-get install -y python3-pip unzip && rm -rf /var/lib/ap
 
 RUN export PATH="$PATH:/root/.local/bin"
 
-RUN pip3 install kaggle pandas scikit-learn tensorflow keras
+RUN pip3 install kaggle pandas scikit-learn tensorflow keras matplotlib numpy
 
 RUN mkdir /.kaggle && chmod o+w /.kaggle
diff --git a/Jenkinsfile.eval b/Jenkinsfile.eval
new file mode 100644
index 0000000..3e00827
--- /dev/null
+++ b/Jenkinsfile.eval
@@ -0,0 +1,48 @@
+pipeline {
+    agent {
+		docker { image 'kamilguttmann/ium:eval' }
+	}
+    parameters {
+        gitParameter branchFilter: 'origin/(.*)', defaultValue: 'master', name: 'BRANCH', type: 'PT_BRANCH'
+        buildSelector(
+            defaultSelector: lastSuccessful(),
+            description: 'Which build to use for copying dataset artifacts',
+            name: 'DATASET_BUILD_SELECTOR'
+        )
+        buildSelector(
+            defaultSelector: lastSuccessful(),
+            description: 'Which build to use for copying train artifacts',
+            name: 'TRAIN_BUILD_SELECTOR'
+        )
+    }
+    stages {
+        stage('Copy artifacts') {
+            steps {
+                copyArtifacts fingerprintArtifacts: true, projectName: 's444380-create-dataset', selector: buildParameter('DATASET_BUILD_SELECTOR')
+                copyArtifacts fingerprintArtifacts: true, projectName: 's444380-training/${BRANCH}', selector: buildParameter('TRAIN_BUILD_SELECTOR')
+                copyArtifacts filter: "eval_results.csv", projectName: 's444380-evaluation/${BRANCH}', optional: true
+            }
+        }
+        stage("Checkout git") {
+            steps {
+	        checkout([$class: 'GitSCM', branches: [[name: '*/master']], extensions: [], userRemoteConfigs: [[credentialsId: 's444380', url: 'https://git.wmi.amu.edu.pl/s444380/ium_444380.git']]])
+            }
+        }
+        stage("Evaluation") {
+            steps {
+                sh "chmod u+x ./evaluate.py"
+                sh "python3 ./evaluate.py"
+                archiveArtifacts artifacts: "eval_results.csv, plot.png", onlyIfSuccessful: true
+            }
+        }
+    }
+    post {
+        success {
+            emailext body: "SUCCESS", subject: "s444380-evaluation", to: "e19191c5.uam.onmicrosoft.com@emea.teams.ms"
+        }
+
+        failure {
+            emailext body: "FAILURE", subject: "s444380-evaluation", to: "e19191c5.uam.onmicrosoft.com@emea.teams.ms"
+        }
+    }
+}
diff --git a/evaluate.py b/evaluate.py
new file mode 100644
index 0000000..b5b425b
--- /dev/null
+++ b/evaluate.py
@@ -0,0 +1,22 @@
+from sklearn.metrics import accuracy_score
+import pandas as pd
+from matplotlib import pyplot as plt
+import numpy as np
+
+test_data = pd.read_csv("out.csv")
+
+y_true = test_data["OFFENSE_CODE_GROUP"]
+y_pred = test_data["PREDICTED"]
+
+
+accuracy = accuracy_score(y_true, y_pred)
+
+with open("eval_results.csv", "a", encoding="utf-8") as f:
+    f.write(f"{accuracy}\n")
+
+eval_results = pd.read_csv("eval_results.csv", header=None).values
+
+plt.plot(np.arange(len(eval_results)), eval_results)
+plt.xlabel("Build")
+plt.ylabel("Accuracy")
+plt.savefig("plot.png")