Compare commits

..

No commits in common. "31ffbd656cedcbc6fa647574a80ca56f0387c08e" and "8eb731b53f24a1b93481f2b4b9e0b5c570d7c89d" have entirely different histories.

2 changed files with 6 additions and 49 deletions

38
Jenkinsfile vendored
View File

@ -1,36 +1,10 @@
pipeline {
agent any
parameters{
string(
defaultValue: 'piotrwrzodak',
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'
)
string(
defaultValue: '1000',
description: 'CUTOFF',
name: 'CUTOFF',
trim: false
)
}
agent any
stages {
stage('Build') {
steps {
sh 'git clone https://git.wmi.amu.edu.pl/s444510/ium_z444510.git'
withEnv(["KAGGLE_USERNAME=${params.KAGGLE_USERNAME}", "KAGGLE_KEY=${params.KAGGLE_KEY}" ]) {
sh 'kaggle datasets download -d thedevastator/airbnb-prices-in-european-cities'
sh 'unzip airbnb-prices-in-european-cities.zip -d ./ium_z444510'
sh 'rm airbnb-prices-in-european-cities.zip'
sh 'ls -a'
sh 'ls -a ./ium_z444510'
stage('Stage 1') {
steps {
echo 'Hello world!'
}
}
}
}
}
}
}

View File

@ -1,17 +0,0 @@
import pandas as pd
import os
import numpy as np
cutoff = int(os.environ['CUTOFF'])
data = pd.read_csv('./ium_z444510/barcelona_weekends.csv')
data = data.sample(cutoff)
data = data.iloc[:, 1:]
train_set, dev_set, test_set = np.split(data.sample(frac=1, random_state=42),
[int(.6 * len(data)), int(.8 * len(data))])
train_set.to_csv('train.csv', index=False)
dev_set.to_csv('dev.csv', index=False)
test_set.to_csv('test.csv', index=False)