s464914/ium_464914
1
0
Fork 1
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix script

Browse Source
This commit is contained in:
Alicja Szulecka 2024-04-13 18:55:49 +02:00
parent 82b655ce2f
commit 00f443439e
3 changed files with 16 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
Jenkinsfile vendored
View File

@ -15,9 +15,9 @@ pipeline {
steps { steps {
withEnv(["KAGGLE_USERNAME=${params.KAGGLE_USERNAME}", "KAGGLE_KEY=${params.KAGGLE_KEY}"]) { withEnv(["KAGGLE_USERNAME=${params.KAGGLE_USERNAME}", "KAGGLE_KEY=${params.KAGGLE_KEY}"]) {
sh 'pip install kaggle' sh 'pip install kaggle'
sh 'kaggle datasets download -d nasa/meteorite-landings' sh 'kaggle datasets download -d uciml/forest-cover-type-dataset'
sh 'unzip -o meteorite-landings.zip' sh 'unzip -o forest-cover-type-dataset.zip'
sh 'rm meteorite-landings.zip' sh 'rm forest-cover-type-dataset.zip'
} }
} }
} }
@ -29,7 +29,7 @@ pipeline {
def customImage = docker.build("custom-image") def customImage = docker.build("custom-image")
customImage.inside { customImage.inside {
sh 'python3 ./IUM_2.py' sh 'python3 ./IUM_2.py'
archiveArtifacts artifacts: 'meteorite-landings.csv, meteorite_train.csv, meteorite_test.csv, meteorite_val.csv', onlyIfSuccessful: true archiveArtifacts artifacts: 'covtype.csv, forest_train.csv, forest_test.csv, forest_val.csv', onlyIfSuccessful: true
} }
} }
} }

18
get_dataset.sh
View File

@ -1,7 +1,7 @@
#!/bin/bash #!/bin/bash
kaggle datasets download -d nasa/meteorite-landings kaggle datasets download -d uciml/forest-cover-type-dataset
unzip -o meteorite-landings.zip unzip -o forest-cover-type-dataset.zip
###Zmienne### ###Zmienne###
@ -10,12 +10,12 @@ test_val_ratio=0.5
##Przetwrazanie pliku## ##Przetwrazanie pliku##
shuf meteorite-landings.csv -o shuffled-meteorite-landings.csv shuf covtype.csv -o forest.csv
##Cut off $1 rows## ##Cut off $1 rows##
head -n $1 shuffled-meteorite-landings.csv > shuffled-meteorite-landings.csv head -n $1 forest.csv > forest.csv
total_lines=$(wc -l < shuffled-meteorite-landings.csv) total_lines=$(wc -l < forest.csv)
train_lines=$(echo $total_lines*$train_ratio| bc) train_lines=$(echo $total_lines*$train_ratio| bc)
train_lines=$(echo "($train_lines+0.5)/1" | bc ) train_lines=$(echo "($train_lines+0.5)/1" | bc )
@ -24,9 +24,9 @@ test_lines=$(echo "($test_lines+0.5)/1" | bc )
validation_lines=$(echo $total_lines-$train_lines-$test_lines | bc) validation_lines=$(echo $total_lines-$train_lines-$test_lines | bc)
head -n "$train_lines" shuffled-meteorite-landings.csv > "meteorite_train.csv" head -n "$train_lines" forest.csv > "forest_train.csv"
tail -n $((test_lines+validation_lines)) shuffled-meteorite-landings.csv | head -n "$test_lines" > "meteorite_test.csv" tail -n $((test_lines+validation_lines)) forest.csv | head -n "$test_lines" > "forest_test.csv"
tail -n "$validation_lines" shuffled-meteorite-landings.csv > "meteorite_validation.csv" tail -n "$validation_lines" forest.csv > "forest_validation.csv"
mkdir -p artifacts mkdir -p artifacts
mv meteorite-landings.csv shuffled-meteorite-landings.csv meteorite_test.csv meteorite_train.csv meteorite_validation.csv artifacts/ mv covtype.csv forest.csv forest_test.csv forest_train.csv forest_validation.csv artifacts/

6
stats/stats_dataset.sh
View File

@ -1,9 +1,9 @@
#!/bin/bash #!/bin/bash
wc -l artifacts/meteorite_train.csv > stats_train.txt wc -l artifacts/forest_train.csv > stats_train.txt
wc -l artifacts/meteorite_test.csv > stats_test.txt wc -l artifacts/forest_test.csv > stats_test.txt
wc -l artifacts/meteorite_validation.csv > stats_validation.txt wc -l artifacts/forest_validation.csv > stats_validation.txt
mv stats_train.txt stats_test.txt stats_validation.txt artifacts/ mv stats_train.txt stats_test.txt stats_validation.txt artifacts/