tweaks(ium_04) Update Jenkinsfile and add Jenkinsfile-stats.

Jenkinsfile

@@ -1,5 +1,7 @@
 pipeline{
-    agent any
+    agent {
+        docker { image 'ubuntu:latest' }
+    }
     stages{
         stage('checkout: Check out from version control'){
             steps{
@@ -8,14 +10,7 @@ pipeline{
         }
         stage('sh: Shell Script'){
             steps{
-                sh '''#!/bin/bash
+                sh './script.sh'
-                      wget -c https://git.wmi.amu.edu.pl/s434780/ium_434780/src/branch/master/data.csv
-                      head -n -1 data.csv | shuf > data.csv.shuf
-                      wc -l data.csv
-                      head -n 500 data.csv.shuf > test.csv
-                      head -n 500 data.csv.shuf | tail -n 500 > dev.csv
-                      tail -n +501 data.csv.shuf > train.csv
-                      wc -l *.csv '''
             }
         }
         stage('Archive artifacts'){

Jenkinsfile-stats

@@ -0,0 +1,25 @@
+pipeline{
+    agent any
+    stages{
+        stage('checkout: Check out from version control'){
+            steps{
+                checkout([$class: 'GitSCM', branches: [[name: '*/master']], doGenerateSubmoduleConfigurations: false, extensions: [], submoduleCfg: [], userRemoteConfigs: [[credentialsId: '321737ab-1c4d-475f-9667-513cf19ba596', url: 'https://git.wmi.amu.edu.pl/s434780/ium_434780.git']]])
+            }
+        }
+        stage('Copy artifacts'){
+            steps{
+                copyArtifacts fingerprintArtifacts: true, projectName: 's434780-create-dataset', selector: buildParameter('BUILD_SELECTOR')
+            }
+        }
+        stage('sh: Shell Script'){
+            steps{
+                sh './stats.sh'
+            }
+        }
+        stage('Archive artifacts'){
+            steps{
+                archiveArtifacts 'stats.txt'
+            }
+        }
+    }
+}

main.py

@@ -3,10 +3,10 @@ from sklearn.model_selection import train_test_split
 
 
 def main():
-    data = pd.read_csv('resources/Amazon_Consumer_Reviews.csv', header=0, sep=',')
+    data = pd.read_csv('Amazon_Consumer_Reviews.csv', header=0, sep=',')
 
     columns = ['reviews.date', 'reviews.numHelpful', 'reviews.rating', 'reviews.doRecommend']
-    string_columns = ['name', 'brand', 'categories', 'primaryCategories', 'keys', 'manufacturer', 'reviews.title',
+    string_columns = ['name', 'categories', 'primaryCategories', 'manufacturer', 'reviews.title',
                       'reviews.username', 'reviews.text']
 
     data = data[string_columns + columns]
@@ -14,17 +14,19 @@ def main():
     for c in string_columns:
         data[c] = data[c].str.lower()
 
-    print("Empty rows summary:")
+    # print("Empty rows summary:")
-    print(data.isnull().sum())
+    # print(data.isnull().sum())
-    data.dropna()
+    # data["reviews.title"].fillna("No title", inplace = True)
+    # print(data.isnull().sum())
 
-    data.to_csv('resources/data.csv')
+    data.to_csv('data.csv')
 
     train, test = train_test_split(data, train_size=0.6, random_state=1)
     test, dev = train_test_split(test, test_size=0.5, random_state=1)
-    test.to_csv('resources/test.csv')
+
-    train.to_csv('resources/train.csv')
+    test.to_csv('test.csv')
-    dev.to_csv('resources/dev.csv')
+    train.to_csv('train.csv')
+    dev.to_csv('dev.csv')
 
     print("\n\nMean reviews rating for each primary category: ")
     print(data[["primaryCategories", "reviews.rating"]].groupby("primaryCategories").mean())

stats.sh

@@ -0,0 +1,2 @@
+#!/bin/bash
+wc -l *.csv > stats.txt