s487179/ium_z487179
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

dockerscript

Browse Source
This commit is contained in:
s487179 2023-04-20 19:37:30 +02:00
parent e8a8a07d8d
commit 919f446857
2 changed files with 42 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
createDataset/Jenkinsfile vendored
View File

@ -20,25 +20,35 @@ pipeline {
) )
} }
stages { stages {
stage('Run sh file') { stage('Download dataset') {
steps { steps {
checkout scm checkout scm
dir ('./createDataset') { dir ('./createDataset') {
sh 'ls -l' sh 'ls -l'
withEnv(["KAGGLE_USERNAME=${params.KAGGLE_USERNAME}", withEnv(["KAGGLE_USERNAME=${params.KAGGLE_USERNAME}",
"KAGGLE_KEY=${params.KAGGLE_KEY}" ]) { "KAGGLE_KEY=${params.KAGGLE_KEY}" ]) {
sh 'chmod +x ./datasetScript.sh' // sh 'chmod +x ./datasetScript.sh'
sh './datasetScript.sh' // sh './datasetScript.sh'
sh 'kaggle datasets download -d rishikeshkonapure/home-loan-approval'
sh 'unzip -o home-loan-approval.zip'
} }
} }
} }
} }
stage('Archive file') { stage('Docker') {
steps { steps {
dir ('./createDataset') { def dockerImage = docker.build("docker-iamge", "./docker")
archiveArtifacts artifacts: 'loan_sanction_shuffled.csv', fingerprint: true\ dockerImage.inside {
} sh 'ls -l'
} }
} }
}
// stage('Archive file') {
// steps {
// dir ('./createDataset') {
// archiveArtifacts artifacts: 'loan_sanction_shuffled.csv', fingerprint: true\
// }
// }
// }
} }
} }

22
createDataset/createDataset.py Normal file
View File

@ -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)