s444510/ium_z444510
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

4.3.1 v11

Browse Source
This commit is contained in:
piotrwrzodak 2023-05-11 23:07:00 +02:00
parent 45d6ba5016
commit 1607852ff9
3 changed files with 6 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
Dockerfile
View File

@ -4,10 +4,3 @@ RUN apt-get update && \
apt-get install -y python3 python3-pip apt-get install -y python3 python3-pip
RUN pip3 install pandas numpy RUN pip3 install pandas numpy
WORKDIR /app
COPY create-dataset.py /app
COPY barcelona_weekends.csv /app
CMD ["python3", "create-dataset.py"]

3
Jenkinsfile-create-dataset-docker
View File

@ -44,7 +44,8 @@ pipeline {
dockerfile true dockerfile true
} }
steps { steps {
archiveArtifacts artifacts: 'barcelona_weekends.train.csv, barcelona_weekends.dev.csv, barcelona_weekends.test.csv', fingerprint: true sh 'python3 create-dataset.py'
archiveArtifacts artifacts: 'data/barcelona_weekends.train.csv, data/barcelona_weekends.dev.csv, data/barcelona_weekends.test.csv', fingerprint: true
} }
} }
} }

8
create-dataset.py
View File

@ -5,16 +5,16 @@ import numpy as np
cutoff = 10 cutoff = 10
data = pd.read_csv('./barcelona_weekends.csv') data = pd.read_csv('./data/barcelona_weekends.csv')
data = data.sample(cutoff) data = data.sample(cutoff)
data = data.iloc[:, 1:] data = data.iloc[:, 1:]
train_set, dev_set, test_set = np.split(data.sample(frac=1, random_state=42), train_set, dev_set, test_set = np.split(data.sample(frac=1, random_state=42),
[int(.6 * len(data)), int(.8 * len(data))]) [int(.6 * len(data)), int(.8 * len(data))])
train_set.to_csv('barcelona_weekends.train.csv', index=False) train_set.to_csv('data/barcelona_weekends.train.csv', index=False)
dev_set.to_csv('barcelona_weekends.dev.csv', index=False) dev_set.to_csv('data/barcelona_weekends.dev.csv', index=False)
test_set.to_csv('barcelona_weekends.test.csv', index=False) test_set.to_csv('data/barcelona_weekends.test.csv', index=False)
check = pd.read_csv('./train.csv') check = pd.read_csv('./train.csv')