From 495eed614fe014fcf7290332aff9f327754c32f4 Mon Sep 17 00:00:00 2001
From: s434695 <tomgrz3@st.amu.edu.pl>
Date: Sun, 28 Mar 2021 22:32:17 +0200
Subject: [PATCH] zadanie 8

---
 dataset_stats/Jenkinsfile | 27 +++++++++++++++++++++++++++
 dataset_stats/stats.sh    |  5 +++++
 skrypt.sh                 | 28 ++++++++++++++--------------
 3 files changed, 46 insertions(+), 14 deletions(-)
 create mode 100644 dataset_stats/Jenkinsfile
 create mode 100644 dataset_stats/stats.sh

diff --git a/dataset_stats/Jenkinsfile b/dataset_stats/Jenkinsfile
new file mode 100644
index 0000000..87157c7
--- /dev/null
+++ b/dataset_stats/Jenkinsfile
@@ -0,0 +1,27 @@
+pipeline {
+    agent any
+    parameters {
+        buildSelector(defaultSelector: 
+        lastSuccessful(), 
+        description: 'Which build to use for copying artifacts', 
+        name: 'BUILD_SELECTOR')
+    }
+    stages {
+        stage("copyArtifacts"){
+            steps {
+                copyArtifacts fingerprintArtifacts: true, 
+                projectName: 's434695-create-dataset', 
+                selector: buildParameter('BUILD_SELECTOR')
+                sh "chmod +x ./stats.sh"
+                sh "./stats.sh"
+                archiveArtifacts "stats.txt"
+            }
+        }
+    }
+        stage('archiveArtifacts') {
+            steps {
+                archiveArtifacts 'stats.txt'
+        }
+    }
+
+}
\ No newline at end of file
diff --git a/dataset_stats/stats.sh b/dataset_stats/stats.sh
new file mode 100644
index 0000000..ac1b2e2
--- /dev/null
+++ b/dataset_stats/stats.sh
@@ -0,0 +1,5 @@
+wc -l healthcare-dataset-stroke-data.csv >> stats.txt
+wc -l test.csv >> stats.txt
+wc -l dev.csv >> stats.txt
+wc -l train.csv >> stats.txt
+wc -l obcietedane.csv >> stats.txt
\ No newline at end of file
diff --git a/skrypt.sh b/skrypt.sh
index 34d5815..ef29548 100644
--- a/skrypt.sh
+++ b/skrypt.sh
@@ -1,19 +1,19 @@
-    #Pobranie pliku .csv
-    curl -OL https://git.wmi.amu.edu.pl/s434695/ium_434695/raw/branch/master/vgsales.csv
+#Pobranie pliku .csv
+curl -OL https://git.wmi.amu.edu.pl/s434695/ium_434695/raw/branch/master/vgsales.csv
 
 
-    #Podzielenie pliku csv na test/dev/train
-    head -n 1 vgsales.csv > header.csv
-    tail -n +2 vgsales.csv | shuf > data.shuffled
+#Podzielenie pliku csv na test/dev/train
+head -n 1 vgsales.csv > header.csv
+tail -n +2 vgsales.csv | shuf > data.shuffled
 
-    head -n 3320 data.shuffled > games.data.test
-    head -n 6640 data.shuffled | tail -n 3320 > games.data.dev
-    tail -n +6641 data.shuffled > games.data.train
+head -n 3320 data.shuffled > games.data.test
+head -n 6640 data.shuffled | tail -n 3320 > games.data.dev
+tail -n +6641 data.shuffled > games.data.train
 
-    cat header.csv games.data.test > test.csv
-    cat header.csv games.data.dev > dev.csv
-    cat header.csv games.data.train > train.csv
+cat header.csv games.data.test > test.csv
+cat header.csv games.data.dev > dev.csv
+cat header.csv games.data.train > train.csv
 
-    #Obcinanie danych
-    head -n $1 data.shuffled > obcietedane.data
-    cat header.csv obcietedane.data > obcietedane.csv
+#Obcinanie danych
+head -n $1 data.shuffled > obcietedane.data
+cat header.csv obcietedane.data > obcietedane.csv