From 919f446857e6b65f0b721d6511228626e059174e Mon Sep 17 00:00:00 2001
From: s487179 <wojbal2@st.amu.edu.pl>
Date: Thu, 20 Apr 2023 19:37:30 +0200
Subject: [PATCH] dockerscript

---
 createDataset/Jenkinsfile      | 30 ++++++++++++++++++++----------
 createDataset/createDataset.py | 22 ++++++++++++++++++++++
 2 files changed, 42 insertions(+), 10 deletions(-)
 create mode 100644 createDataset/createDataset.py

diff --git a/createDataset/Jenkinsfile b/createDataset/Jenkinsfile
index f3b9169..af1cffc 100644
--- a/createDataset/Jenkinsfile
+++ b/createDataset/Jenkinsfile
@@ -20,25 +20,35 @@ pipeline {
          )
    }
    stages {
-      stage('Run sh file') {
+      stage('Download dataset') {
          steps {
             checkout scm
             dir ('./createDataset') {
                sh 'ls -l'
                withEnv(["KAGGLE_USERNAME=${params.KAGGLE_USERNAME}",
                   "KAGGLE_KEY=${params.KAGGLE_KEY}" ]) {
-                  sh 'chmod +x ./datasetScript.sh'
-                  sh './datasetScript.sh'
+                  // sh 'chmod +x ./datasetScript.sh'
+                  // sh './datasetScript.sh'
+                  sh 'kaggle datasets download -d rishikeshkonapure/home-loan-approval'
+                  sh 'unzip -o home-loan-approval.zip'
                }
             }
          }
       }
-      stage('Archive file') {
-         steps {
-            dir ('./createDataset') {
-               archiveArtifacts artifacts: 'loan_sanction_shuffled.csv', fingerprint: true\
-            }
-         }
-      }              
+      stage('Docker') {
+        steps {
+               def dockerImage = docker.build("docker-iamge", "./docker")
+               dockerImage.inside {
+                  sh 'ls -l'
+               }
+        }
+      }
+      // stage('Archive file') {
+      //    steps {
+      //       dir ('./createDataset') {
+      //          archiveArtifacts artifacts: 'loan_sanction_shuffled.csv', fingerprint: true\
+      //       }
+      //    }
+      // }              
    }
 }
diff --git a/createDataset/createDataset.py b/createDataset/createDataset.py
new file mode 100644
index 0000000..3963850
--- /dev/null
+++ b/createDataset/createDataset.py
@@ -0,0 +1,22 @@
+import pandas as pd
+from sklearn.preprocessing import MinMaxScaler
+from sklearn.model_selection import train_test_split
+home_loan_train = pd.read_csv('loan_sanction_train.csv')
+home_loan_test = pd.read_csv('loan_sanction_test.csv')
+
+home_loan_val_final, home_loan_test_final = train_test_split(home_loan_test, test_size=0.5, random_state=1)
+home_loan_train_final = home_loan_train
+
+numeric_cols_train = home_loan_train_final.select_dtypes(include='number').columns
+numeric_cols_test = home_loan_test_final.select_dtypes(include='number').columns
+numeric_cols_val = home_loan_val_final.select_dtypes(include='number').columns
+
+scaler = MinMaxScaler()
+
+home_loan_train_final[numeric_cols_train] = scaler.fit_transform(home_loan_train_final[numeric_cols_train])
+home_loan_test_final[numeric_cols_test] = scaler.fit_transform(home_loan_test_final[numeric_cols_test])
+home_loan_val_final[numeric_cols_val] = scaler.fit_transform(home_loan_val_final[numeric_cols_val])
+
+home_loan_train_final.to_csv('home_loan_train.csv', index=False)
+home_loan_test_final.to_csv('home_loan_test.csv', index=False)
+home_loan_val_final.to_csv('home_loan_val.csv', index=False)
\ No newline at end of file