From 5dd7412a27a39c4a2369c42d14709d8afdf057dd Mon Sep 17 00:00:00 2001
From: s464953 <micgul1@st.amu.edu.pl>
Date: Mon, 25 Mar 2024 21:46:01 +0100
Subject: [PATCH] added stats scipt

---
 Jenkinsfile-stats | 42 ++++++++++++++++++++++++++++++++++++++++++
 dataset_stats.sh  | 13 +++++++++++++
 2 files changed, 55 insertions(+)
 create mode 100644 Jenkinsfile-stats
 create mode 100644 dataset_stats.sh

diff --git a/Jenkinsfile-stats b/Jenkinsfile-stats
new file mode 100644
index 0000000..08db9ce
--- /dev/null
+++ b/Jenkinsfile-stats
@@ -0,0 +1,42 @@
+pipeline {
+    agent any
+
+    parameters {
+        buildSelector( defaultSelector: lastSuccessful(), description: 'Build for copying artifacts', name: 'BUILD_SELECTOR')
+    }
+
+    stages {
+        stage('Clone Repository') {
+            steps {
+                git 'https://git.wmi.amu.edu.pl/s464953/ium_464953.git'
+            }
+        }
+        stage('Cleanup Artifacts') {
+            steps {
+                script {
+                    sh 'rm -rf artifacts'
+                }
+            }
+        }
+        stage('Copy Artifact') {
+           steps {
+                withEnv([
+                "BUILD_SELECTOR=${params.BUILD_SELECTOR}" 
+                ]) {
+                copyArtifacts fingerprintArtifacts: true, projectName: 'z-s464953-create-dataset', selector: buildParameter('$BUILD_SELECTOR')}
+            }
+        }
+         stage('Execute Shell Script') {
+            steps {
+                script {
+                    sh "bash ./dataset_stats.sh"
+                }
+            }
+        }
+        stage('Archive Results') {
+            steps {
+                archiveArtifacts artifacts: 'artifacts/*', onlyIfSuccessful: true
+            }
+        }
+    }
+}
\ No newline at end of file
diff --git a/dataset_stats.sh b/dataset_stats.sh
new file mode 100644
index 0000000..d138dcb
--- /dev/null
+++ b/dataset_stats.sh
@@ -0,0 +1,13 @@
+#!/bin/bash
+
+echo "------------------ Train dataset stats ------------------"
+wc -l artifacts/train.csv > stats_train.txt
+
+echo "------------------ Validation dataset stats ------------------"
+wc -l artifacts/validation.csv > stats_validation.txt
+
+echo "------------------ Test dataset stats ------------------"
+wc -l artifacts/test.csv > stats_test.txt
+
+mkdir -p data
+mv stats_train.txt stats_validation.txt stats_test.txt artifacts/
\ No newline at end of file