generate subsets as artifacts in Jenkinsfile
This commit is contained in:
parent
b38a9b9333
commit
b846942ec3
6
Jenkinsfile
vendored
6
Jenkinsfile
vendored
@ -34,4 +34,10 @@ pipeline {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
post {
|
||||||
|
always {
|
||||||
|
archiveArtifacts artifacts: '*atp*.csv', onlyIfSuccessful: true
|
||||||
|
}
|
||||||
|
//df_atp.csv atp_train.csv atp_test.csv atp_dev.csv
|
||||||
|
}
|
||||||
}
|
}
|
||||||
|
@ -1,2 +1,15 @@
|
|||||||
echo 'test'
|
echo 'test'
|
||||||
|
|
||||||
|
# delete old files
|
||||||
|
rm -r df_atp.csv atp_train.csv atp_test.csv atp_dev.csv
|
||||||
|
|
||||||
|
# download dataset
|
||||||
kaggle datasets download -d hakeem/atp-and-wta-tennis-data
|
kaggle datasets download -d hakeem/atp-and-wta-tennis-data
|
||||||
|
unzip -o atp-and-wta-tennis-data.zip
|
||||||
|
|
||||||
|
# split dataset to train, dev and test subsets
|
||||||
|
head -n 8000 df_atp.csv > atp_train.csv
|
||||||
|
tail -n 2000 df_atp.csv > atp_test.csv
|
||||||
|
head -n 2000 atp_train.csv > atp_dev.csv
|
||||||
|
tail -n 6000 atp_train.csv > x.csv
|
||||||
|
tail -n 6000 x.csv > atp_train.csv
|
||||||
|
Loading…
Reference in New Issue
Block a user