fix script

Jenkinsfile

@@ -15,9 +15,9 @@ pipeline {
       steps {
         withEnv(["KAGGLE_USERNAME=${params.KAGGLE_USERNAME}", "KAGGLE_KEY=${params.KAGGLE_KEY}"]) {
           sh 'pip install kaggle'
-          sh 'kaggle datasets download -d nasa/meteorite-landings'
-          sh 'unzip -o meteorite-landings.zip'
-          sh 'rm meteorite-landings.zip'
+          sh 'kaggle datasets download -d uciml/forest-cover-type-dataset'
+          sh 'unzip -o forest-cover-type-dataset.zip'
+          sh 'rm forest-cover-type-dataset.zip'
         }
       }
     }
@@ -29,7 +29,7 @@ pipeline {
                     def customImage = docker.build("custom-image")
                     customImage.inside {
                         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
                     }
                  }
              }

get_dataset.sh

@@ -1,7 +1,7 @@
 #!/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###
 
@@ -10,12 +10,12 @@ test_val_ratio=0.5
 
 ##Przetwrazanie pliku##
 
-shuf meteorite-landings.csv -o shuffled-meteorite-landings.csv
+shuf covtype.csv -o forest.csv
 
 ##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=$(echo "($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)
 
-head -n "$train_lines" shuffled-meteorite-landings.csv > "meteorite_train.csv"
-tail -n $((test_lines+validation_lines)) shuffled-meteorite-landings.csv | head -n "$test_lines" > "meteorite_test.csv"
-tail -n "$validation_lines" shuffled-meteorite-landings.csv > "meteorite_validation.csv"
+head -n "$train_lines" forest.csv > "forest_train.csv"
+tail -n $((test_lines+validation_lines)) forest.csv | head -n "$test_lines" > "forest_test.csv"
+tail -n "$validation_lines" forest.csv > "forest_validation.csv"
 
 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/

stats/stats_dataset.sh

@@ -1,9 +1,9 @@
 #!/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/