diff --git a/Jenkinsfile b/Jenkinsfile index a8825ec..c9adffe 100644 --- a/Jenkinsfile +++ b/Jenkinsfile @@ -27,6 +27,12 @@ node { "KAGGLE_KEY=${params.KAGGLE_KEY}" ]) { sh 'echo KAGGLE_USERNAME: $KAGGLE_USERNAME' sh 'chmod u+x ./download_dataset.sh' + sh ''' kaggle datasets download -d sohier/crime-in-baltimore +unzip crime-in-baltimore.zip + +head -n 8000 BPD_Part_1_Victim_Based_Crime_Data.csv > baltimore_train.csv +tail -n 2000 BPD_Part_1_Victim_Based_Crime_Data.csv > baltimore_test.csv +head -n 2000 baltimore_train.csv > baltimore_dev.csv''' archiveArtifacts artifacts: 'baltimore_train.csv, baltimore_test.csv, baltimore_dev.csv' } } diff --git a/download_dataset.sh b/download_dataset.sh index b1c66f1..f9e0abb 100644 --- a/download_dataset.sh +++ b/download_dataset.sh @@ -1,8 +1,6 @@ #!/bin/bash -echo "Mes" kaggle datasets download -d sohier/crime-in-baltimore unzip crime-in-baltimore.zip -less BPD_Part_1_Victim_Based_Crime_Data.csv head -n 8000 BPD_Part_1_Victim_Based_Crime_Data.csv > baltimore_train.csv tail -n 2000 BPD_Part_1_Victim_Based_Crime_Data.csv > baltimore_test.csv