From 7831500e7a40204f6802dc1eabc5c80d53f3f944 Mon Sep 17 00:00:00 2001 From: Karolina Oparczyk Date: Wed, 14 Apr 2021 21:22:48 +0200 Subject: [PATCH] split fetching data and displaying stats --- JenkinsfileStats | 2 +- get_data.sh | 8 -------- get_stats.sh | 9 +++++++++ 3 files changed, 10 insertions(+), 9 deletions(-) create mode 100644 get_stats.sh diff --git a/JenkinsfileStats b/JenkinsfileStats index b19db0f..1b2c744 100644 --- a/JenkinsfileStats +++ b/JenkinsfileStats @@ -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 diff --git a/get_data.sh b/get_data.sh index 53d0b62..ee225e2 100644 --- a/get_data.sh +++ b/get_data.sh @@ -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 \ No newline at end of file diff --git a/get_stats.sh b/get_stats.sh new file mode 100644 index 0000000..fde5473 --- /dev/null +++ b/get_stats.sh @@ -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" \ No newline at end of file