From ebef6c12ccf94b0c11f07fbe295372e0ba89dfc7 Mon Sep 17 00:00:00 2001
From: Alicja Szulecka <73056579+AliSzu@users.noreply.github.com>
Date: Tue, 2 Apr 2024 22:35:43 +0200
Subject: [PATCH] add stats

---
 get_stats.py      | 19 +++++++++++++++++++
 stats/Jenkinsfile |  8 ++++++--
 2 files changed, 25 insertions(+), 2 deletions(-)
 create mode 100644 get_stats.py

diff --git a/get_stats.py b/get_stats.py
new file mode 100644
index 0000000..b2e7c67
--- /dev/null
+++ b/get_stats.py
@@ -0,0 +1,19 @@
+import pandas as pd 
+
+meteorite_train = pd.read_csv('meteorite_train.csv')
+meteorite_test = pd.read_csv('meteorite_test.csv')
+meteorite_val = pd.read_csv('meteorite_val.csv')
+
+with open('stats.txt', 'w') as f:
+    f.write(f"Wielkość treningowego zbioru:\n {meteorite_train.shape}\n")
+    f.write(f"Wielkość testowego zbioru:\n {meteorite_test.shape}\n")
+    f.write(f"Wielkość walidacyjnego zbioru:\n {meteorite_val.shape}\n")
+
+    f.write(f"\nZbiór Treningowy:\n")
+    f.write(f"{meteorite_train.describe()}\n")
+
+    f.write(f"\nZbiór Testowy:\n")
+    f.write(f"{meteorite_test.describe()}\n")
+
+    f.write(f"\nZbiór walidacyjny:\n")
+    f.write(f"{meteorite_val.describe()}\n")
\ No newline at end of file
diff --git a/stats/Jenkinsfile b/stats/Jenkinsfile
index 144f59a..4cf6262 100644
--- a/stats/Jenkinsfile
+++ b/stats/Jenkinsfile
@@ -1,5 +1,9 @@
 pipeline {
-    agent any
+    agent {
+            docker {
+                image 'aliszu1/ium:1.0'
+            }
+    }
         parameters {
             buildSelector (
                 defaultSelector: lastSuccessful(),
@@ -15,7 +19,7 @@ pipeline {
         }
      stage('Build') {
          steps {
-                 sh "bash ./stats/stats_dataset.sh"
+                 sh "python ./get_stats.py"
                  archiveArtifacts artifacts: 'artifacts/*', onlyIfSuccessful: true
              }
          }