docker task 2 try_4

Jenkinsfile

@@ -25,10 +25,10 @@ pipeline {
 
         stage('Get data save artifacts') {
             steps {
-                sh 'chmod +x -R ./data_prep.sh'
                 withEnv(["KAGGLE_USERNAME=${params.KAGGLE_USERNAME}",
                 "KAGGLE_KEY=${params.KAGGLE_KEY}"]) {
                     sh 'echo KAGGLE_USERNAME: $KAGGLE_USERNAME'
+                    archiveArtifacts artifacts: 'apps_train.csv, apps_test.csv, apps_validate.csv'
                 }
             }
         }

data_expl.py

@@ -32,4 +32,16 @@ data["Installs"] = (data["Installs"] - min_value) / (max_value - min_value)
 # splitting into sets
 np.random.seed(123)
 train, validate, test = np.split(data.sample(frac=1, random_state=42), [int(.6*len(data)), int(.8*len(data))])
-print(f"Data shape: {data.shape}\nTrain shape: {train.shape}\nTest shape: {test.shape}\nValidation shape:{validate.shape}")
+print(f"Data shape: {data.shape}\nTrain shape: {train.shape}\nTest shape: {test.shape}\nValidation shape:{validate.shape}")
+
+f = open("apps_train.csv", "w")
+f.write(train)
+f.close()
+
+f = open("apps_test.csv", "w")
+f.write(test)
+f.close()
+
+f = open("apps_validate.csv", "w")
+f.write(validate)
+f.close()