zadanie doker
This commit is contained in:
parent
3dbda7a2cd
commit
5a29b56c27
22
Dockerfile
22
Dockerfile
@ -1,14 +1,8 @@
|
||||
FROM python:3.9
|
||||
|
||||
|
||||
RUN pip install --user kaggle
|
||||
RUN pip install --user pandas
|
||||
|
||||
ADD . .
|
||||
ARG KAGGLE_USERNAME
|
||||
ARG KAGGLE_KEY
|
||||
|
||||
RUN chmod a+x *.sh
|
||||
RUN ./dataset_download.sh
|
||||
|
||||
CMD python kagle.py
|
||||
FROM ubuntu:latest
|
||||
WORKDIR /ium
|
||||
RUN apt update && apt install -y python3-pip
|
||||
RUN pip3 install pandas
|
||||
RUN pip3 install numpy
|
||||
RUN pip3 install sklearn
|
||||
COPY ./Steam-200k.csv ./
|
||||
COPY ./kagle.py ./
|
27
Jenkinsfile
vendored
27
Jenkinsfile
vendored
@ -1,33 +1,12 @@
|
||||
pipeline {
|
||||
parameters {
|
||||
string(
|
||||
defaultValue: 'szymonjadczak',
|
||||
description: 'Kaggle username',
|
||||
name: 'KAGGLE_USERNAME',
|
||||
trim: false
|
||||
)
|
||||
password(
|
||||
defaultValue: '',
|
||||
description: 'Kaggle token taken from kaggle.json file, as described in https://github.com/Kaggle/kaggle-api#api-credentials',
|
||||
name: 'KAGGLE_KEY'
|
||||
)
|
||||
}
|
||||
agent {
|
||||
dockerfile {
|
||||
additionalBuildArgs "--build-arg KAGGLE_USERNAME=${params.KAGGLE_USERNAME} --build-arg KAGGLE_KEY=${params.KAGGLE_KEY} -t s444386-create-dataset"
|
||||
}
|
||||
}
|
||||
environment {
|
||||
KAGGLE_USERNAME="$params.KAGGLE_USERNAME"
|
||||
KAGGLE_KEY="$params.KAGGLE_KEY"
|
||||
CUTOFF="$params.CUTOFF"
|
||||
dockerfile true
|
||||
}
|
||||
stages {
|
||||
stage('Stage 1') {
|
||||
steps {
|
||||
echo 'Hello world!!!'
|
||||
checkout([$class: 'GitSCM', branches: [[name: '*/master']], extensions: [], userRemoteConfigs: [[url: 'https://git.wmi.amu.edu.pl/s444386/ium_444386']]])
|
||||
archiveArtifacts 'Steam-200k.csv'
|
||||
sh 'chmod u+x ./kagle.py'
|
||||
sh 'python3 kagle.py'
|
||||
}
|
||||
}
|
||||
}
|
||||
|
4
kagle.py
4
kagle.py
@ -2,8 +2,8 @@ import os
|
||||
import pandas as pd
|
||||
from sklearn.model_selection import train_test_split
|
||||
|
||||
os.system("kaggle datasets download -d tamber/steam-video-games")
|
||||
os.system("unzip -o steam-video-games.zip")
|
||||
#os.system("kaggle datasets download -d tamber/steam-video-games")
|
||||
#os.system("unzip -o steam-video-games.zip")
|
||||
|
||||
steam=pd.read_csv('Steam-200k.csv',usecols=[0,1,2,3],names=['userId','game','behavior','hoursPlayed'])
|
||||
steam.isnull().values.any()
|
||||
|
Loading…
Reference in New Issue
Block a user