split fetching data and displaying stats

This commit is contained in:
Karolina Oparczyk 2021-04-14 21:22:48 +02:00
parent 146b96312b
commit 7831500e7a
3 changed files with 10 additions and 9 deletions

View File

@ -15,7 +15,7 @@ node {
docker.image("karopa/ium:03").inside {
stage('Test') {
checkout([$class: 'GitSCM', branches: [[name: '*/stats']], doGenerateSubmoduleConfigurations: false, extensions: [], submoduleCfg: [], userRemoteConfigs: [[url: 'https://git.wmi.amu.edu.pl/s434765/ium_434765']]])
copyArtifacts filter: 'data_shuf', fingerprintArtifacts: true, projectName: 's434765-create-dataset', selector: buildParameter("BUILD_SELECTOR")
copyArtifacts fingerprintArtifacts: true, projectName: 's434765-create-dataset', selector: buildParameter("BUILD_SELECTOR")
sh '''
#!/usr/bin/env bash
chmod 777 get_stats_simple.sh

View File

@ -8,13 +8,5 @@ if kaggle datasets download -d sgonkaggle/youtube-trend-with-subscriber && unzip
head -n 544 "data_shuf" > "data_test"
head -n 1088 "data_shuf" | tail -n 544 > "data_dev"
head -n +1089 "data_shuf" > "data_train"
echo "Shuffled dataset"
wc -l "data_shuf"
echo "Test dataset"
wc -l "data_test"
echo "Dev dataset"
wc -l "data_dev"
echo "Train dataset"
wc -l "data_train"
python3 main.py USvideos_modified.csv
fi

9
get_stats.sh Normal file
View File

@ -0,0 +1,9 @@
#!/bin/bash
echo "Shuffled dataset"
wc -l "data_shuf"
echo "Test dataset"
wc -l "data_test"
echo "Dev dataset"
wc -l "data_dev"
echo "Train dataset"
wc -l "data_train"