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

add dockerfile

Browse Source
This commit is contained in:
piotrwrzodak 2023-05-11 21:11:50 +02:00
parent 456a0198a1
commit 6e73cdf650
2 changed files with 19 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
Dockerfile Normal file
View File

@ -0,0 +1,13 @@
FROM ubuntu:latest
RUN apt-get update && \
apt-get install -y python3 python3-pip
RUN pip3 install pandas scikit-learn kaggle
WORKDIR /app
COPY create-dataset.py /app
COPY data/barcelona_weekends.csv /app
CMD ["python3", "create-dataset.py"]

8
create-dataset.py
View File

@ -3,9 +3,9 @@ import os
import numpy as np import numpy as np
cutoff = int(os.environ['CUTOFF']) cutoff = 10
data = pd.read_csv('./ium_z444510/barcelona_weekends.csv') data = pd.read_csv('./barcelona_weekends.csv')
data = data.sample(cutoff) data = data.sample(cutoff)
data = data.iloc[:, 1:] data = data.iloc[:, 1:]
@ -15,3 +15,7 @@ train_set, dev_set, test_set = np.split(data.sample(frac=1, random_state=42),
train_set.to_csv('train.csv', index=False) train_set.to_csv('train.csv', index=False)
dev_set.to_csv('dev.csv', index=False) dev_set.to_csv('dev.csv', index=False)
test_set.to_csv('test.csv', index=False) test_set.to_csv('test.csv', index=False)
check = pd.read_csv('./train.csv')
print(check.head())