Added new jenkinsfile and kuggle download script
This commit is contained in:
parent
de92a2cf3b
commit
4a08061465
8
.idea/.gitignore
vendored
Normal file
8
.idea/.gitignore
vendored
Normal file
@ -0,0 +1,8 @@
|
||||
# Default ignored files
|
||||
/shelf/
|
||||
/workspace.xml
|
||||
# Editor-based HTTP Client requests
|
||||
/httpRequests/
|
||||
# Datasource local storage ignored files
|
||||
/dataSources/
|
||||
/dataSources.local.xml
|
6
.idea/inspectionProfiles/profiles_settings.xml
Normal file
6
.idea/inspectionProfiles/profiles_settings.xml
Normal file
@ -0,0 +1,6 @@
|
||||
<component name="InspectionProjectProfileManager">
|
||||
<settings>
|
||||
<option name="USE_PROJECT_PROFILE" value="false" />
|
||||
<version value="1.0" />
|
||||
</settings>
|
||||
</component>
|
8
.idea/ium_464979.iml
Normal file
8
.idea/ium_464979.iml
Normal file
@ -0,0 +1,8 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<module type="PYTHON_MODULE" version="4">
|
||||
<component name="NewModuleRootManager">
|
||||
<content url="file://$MODULE_DIR$" />
|
||||
<orderEntry type="inheritedJdk" />
|
||||
<orderEntry type="sourceFolder" forTests="false" />
|
||||
</component>
|
||||
</module>
|
4
.idea/misc.xml
Normal file
4
.idea/misc.xml
Normal file
@ -0,0 +1,4 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<project version="4">
|
||||
<component name="ProjectRootManager" version="2" project-jdk-name="Python 3.10" project-jdk-type="Python SDK" />
|
||||
</project>
|
8
.idea/modules.xml
Normal file
8
.idea/modules.xml
Normal file
@ -0,0 +1,8 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<project version="4">
|
||||
<component name="ProjectModuleManager">
|
||||
<modules>
|
||||
<module fileurl="file://$PROJECT_DIR$/.idea/ium_464979.iml" filepath="$PROJECT_DIR$/.idea/ium_464979.iml" />
|
||||
</modules>
|
||||
</component>
|
||||
</project>
|
6
.idea/vcs.xml
Normal file
6
.idea/vcs.xml
Normal file
@ -0,0 +1,6 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<project version="4">
|
||||
<component name="VcsDirectoryMappings">
|
||||
<mapping directory="" vcs="Git" />
|
||||
</component>
|
||||
</project>
|
58
Jenkinsfile
vendored
58
Jenkinsfile
vendored
@ -1,29 +1,33 @@
|
||||
pipeline {
|
||||
agent any
|
||||
//Definijuemy parametry, kt<6B>re b<>dzie mo<6D>na poda<64> podczas wywo<77>ywania zadania
|
||||
parameters {
|
||||
string (
|
||||
defaultValue: 'Hello World!',
|
||||
description: 'Tekst, kt<6B>rym chcesz przywita<74> <20>wiat',
|
||||
name: 'INPUT_TEXT',
|
||||
trim: false
|
||||
)
|
||||
}
|
||||
stages {
|
||||
stage('Hello') {
|
||||
steps {
|
||||
//Wypisz warto<74><6F> parametru w konsoli (To nie jest polecenie bash, tylko groovy!)
|
||||
echo "INPUT_TEXT: promoscan"
|
||||
//Wywo<77>aj w konsoli komend<6E> "figlet", kt<6B>ra generuje ASCI-art
|
||||
sh "figlet \"promoscan\" | tee output.txt"
|
||||
}
|
||||
}
|
||||
stage('Goodbye!') {
|
||||
steps {
|
||||
echo 'Goodbye!'
|
||||
//Zarchiwizuj wynik
|
||||
archiveArtifacts 'output.txt'
|
||||
}
|
||||
}
|
||||
}
|
||||
agent any
|
||||
|
||||
parameters {
|
||||
properties([
|
||||
parameters([
|
||||
string(name: 'KAGGLE_DATASET_ID', defaultValue: '', description: 'Kaggle dataset'),
|
||||
string(name: 'REPO_URL', defaultValue: '', description: 'Git Url'),
|
||||
string(name: 'CUTOFF', defaultValue: '10000', description: 'Liczba wierszy do obcięcia ze zbioru danych')
|
||||
])
|
||||
])
|
||||
}
|
||||
|
||||
stages {
|
||||
stage('Clone Repository') {
|
||||
steps {
|
||||
git url: "${params.REPO_URL}"
|
||||
}
|
||||
}
|
||||
|
||||
stage('Download, Process, and Split Dataset') {
|
||||
steps {
|
||||
withEnv([
|
||||
"KAGGLE_USERNAME=${env.KAGGLE_USERNAME}",
|
||||
"KAGGLE_KEY=${env.KAGGLE_KEY}"
|
||||
]) {
|
||||
sh "bash ./kuggle_download.sh ${params.KAGGLE_DATASET_ID} ${params.CUTOFF}"
|
||||
sh './kuggle_download.sh'
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
27
kuggle_download.sh
Normal file
27
kuggle_download.sh
Normal file
@ -0,0 +1,27 @@
|
||||
#!/bin/bash
|
||||
|
||||
pip install kaggle
|
||||
|
||||
kaggle datasets download -d $DATASET_ID
|
||||
|
||||
unzip -o $DATASET_FILE
|
||||
|
||||
shuf $DATASET_FILE > shuffled_dataset.csv
|
||||
|
||||
split -l 80000 shuffled_dataset.csv train.csv
|
||||
split -l 10000 train.csv dev.csv
|
||||
mv shuffled_dataset.csv test.csv
|
||||
|
||||
head -n 1000 train.csv > train_head.csv
|
||||
tail -n 1000 train.csv > train_tail.csv
|
||||
|
||||
if [ -n "$CUTOFF" ]; then
|
||||
head -n "$CUTOFF" train.csv > train_cutoff.csv
|
||||
fi
|
||||
|
||||
tar -czf artifacts.tar.gz train.csv dev.csv test.csv train_head.csv train_tail.csv train_cutoff.csv
|
||||
|
||||
rm $DATASET_FILE shuffled_dataset.csv
|
||||
|
||||
echo "artifacts.tar.gz"
|
||||
|
Loading…
Reference in New Issue
Block a user