stats on new set

This commit is contained in:
Filip Izydorczyk 2021-05-25 18:44:03 +02:00
parent 8a3280a07b
commit 347d01adf9
6 changed files with 6 additions and 7800 deletions

View File

@ -1,5 +0,0 @@
wget https://git.wmi.amu.edu.pl/s434700/ium_s434700/raw/branch/master/netflix_titles.csv
head -n 256 netflix_titles.csv > top.csv

File diff suppressed because it is too large Load Diff

View File

View File

@ -1,2 +0,0 @@
wc -l test/netflix_titles.csv > stat.txt
wc -l test/top.csv >> stat.txt

6
stats/Jenkinsfile vendored
View File

@ -9,7 +9,7 @@ pipeline {
step ([$class: 'CopyArtifact', step ([$class: 'CopyArtifact',
projectName: 's434700-create-dataset', projectName: 's434700-create-dataset',
filter: '*.csv', filter: '*.csv',
target: 'test']) target: 'datasets'])
} }
} }
} }
@ -20,8 +20,8 @@ pipeline {
} }
stage('sh: Shell Script') { stage('sh: Shell Script') {
steps { steps {
sh 'chmod +x stats.sh' sh 'chmod +x ./stats/stats.sh'
sh './stats.sh' sh './stats/stats.sh'
} }
} }
stage('archiveArtifacts') { stage('archiveArtifacts') {

3
stats/stats.sh Normal file
View File

@ -0,0 +1,3 @@
wc -l datasets/train_set.csv > train_set_stats.txt
wc -l datasets/dev_set.csv >> dev_set_stats.txt
wc -l datasets/test_set.csv >> test_set_stats.txt