Use cutoff

create-dataset/Jenkinsfile

@@ -10,7 +10,7 @@ pipeline {
                     properties([
                         parameters([
                             string(
-                              defaultValue: '1000',
+                              defaultValue: '0',
                               description: 'Maximum number of rows',
                               name: 'CUTOFF',
                               trim: false

create-dataset/main.py

@@ -8,21 +8,21 @@ from datasets import load_dataset
 from sklearn.preprocessing import MinMaxScaler
 
 
-# Read CUTOFF
-
-cutoff = int(sys.argv[1])
-print(cutoff)
-
-
 # Load dataset
 
 data = load_dataset('mstz/spambase')
 data = pd.DataFrame(data['train'])
 
 
+# Read CUTOFF
+
+cutoff = int(sys.argv[1])
+cutoff = cutoff if cutoff > 0 else len(data)
+
+
 # Shuffle data
 
-data = data.sample(frac=1)
+data = data.sample(frac=1).head(cutoff)
 
 
 # Split data