add IUM-05

README.md

@@ -12,4 +12,12 @@ and prints a short summary of the dataset as well as its subsets.
 ### Zadanie 2
 add Jenkinsfiles and mock data preprocessing
 
+### Zadanie 5
+added lab4 file with new python script and updated Dockerfile.
+The container downloads the dataset and installs software needed,
+then trains and evaluates model on the dataset.
+Loss and accuracy are saved to test_eval.txt file.
+
+
 ium01.ipynb is a notebook used to develop previously mentioned scripts.
+

lab2/Jenkinsfile_create_dataset

@@ -14,7 +14,9 @@ pipeline {
         }
         stage('docker') {
             agent {
-                dockerfile true
+                docker {
+                    image 'kubakonieczny/ium:v1.0'
+                }
             }
             stages {
                 stage('script') {

lab2/Jenkinsfile_dataset_stats

@@ -1,11 +1,37 @@
-node {
-    docker.image('kubakonieczny/ium:v1.0').withRun("-t -e KAGGLE_USERNAME=kubakonieczny -e KAGGLE_KEY=${params.KAGGLE_KEY}") { c ->
-        docker.image('kubakonieczny/ium:v1.0').inside {
-            stage('Test') {
-                sh 'cat /etc/issue'
-                sh 'ls -lah'
+pipeline {
+    agent none
+    stages {
+        stage('copy files') {
+            agent any
+                steps {
+                    sh '''
+                        cp ./lab3/script.sh .
+                        cp ./lab3/python_script.py .
+                        cp ./lab3/Dockerfile .
+                        cp ./lab3/requirements.txt .
+                        '''
+                }
+        }
+        stage('docker') {
+            agent {
+                docker {
+                    image 'kubakonieczny/ium:v1.0'
+                }
+            }
+            stages {
+                stage('script') {
+                    steps {
+                    sh '''
+                    chmod +x script.sh
+                    ./script.sh > stats.txt'''
+                    }
+                }
+                stage('archive artifact') {
+                    steps {
+                        archiveArtifacts 'stats.txt'
+                    }
+                }
             }
         }
     }
-    sh 'docker logs ${c.id}'
 }

lab4/Dockerfile

@@ -0,0 +1,19 @@
+FROM ubuntu:latest
+
+RUN apt update >>/dev/null
+RUN apt install -y apt-utils >>/dev/null
+RUN apt install -y python3.8 >>/dev/null
+RUN apt install -y python3-pip >>/dev/null
+RUN apt install -y unzip >>/dev/null
+
+WORKDIR /app
+
+COPY ./test_eval.py ./
+COPY ./script.sh ./
+RUN chmod +x script.sh
+
+COPY ./requirements.txt ./
+
+RUN pip3 install -r requirements.txt >>/dev/null
+
+CMD ./script.sh

lab4/requirements.txt

@@ -0,0 +1,5 @@
+kaggle
+numpy~=1.19.2
+pandas
+sklearn
+tensorflow

lab4/script.sh

@@ -0,0 +1,6 @@
+#!/bin/bash
+
+kaggle datasets download -d 'pcbreviglieri/smart-grid-stability'
+unzip smart-grid-stability.zip >>/dev/null 2>&1
+
+python3 test_eval.py

lab4/test_eval.py

@@ -0,0 +1,61 @@
+import numpy as np
+import pandas as pd
+import tensorflow as tf
+
+from sklearn import preprocessing
+from sklearn.model_selection import train_test_split
+from tensorflow.keras import layers
+
+
+def onezero(label):
+  return 0 if label == 'unstable' else 1
+
+
+df = pd.read_csv('smart_grid_stability_augmented.csv')
+
+scaler = preprocessing.StandardScaler().fit(df.iloc[:, 0:-1])
+df_norm_array = scaler.transform(df.iloc[:, 0:-1])
+df_norm = pd.DataFrame(data=df_norm_array,
+                       columns=df.columns[:-1])
+df_norm['stabf'] = df['stabf']
+
+df_norm_data = df_norm.copy()
+df_norm_data = df_norm_data.drop('stab', axis=1)
+df_norm_labels = df_norm_data.pop('stabf')
+
+X_train, X_testAndValid, Y_train, Y_testAndValid = train_test_split(
+    df_norm_data,
+    df_norm_labels,
+    test_size=0.2,
+    random_state=42)
+
+X_test, X_valid, Y_test, Y_valid = train_test_split(
+    X_testAndValid,
+    Y_testAndValid,
+    test_size=0.5,
+    random_state=42)
+
+model = tf.keras.Sequential([
+            layers.Input(shape=(12,)),
+            layers.Dense(32),
+            layers.Dense(16),
+            layers.Dense(2, activation='softmax')
+        ])
+
+model.compile(
+    loss=tf.losses.BinaryCrossentropy(),
+    optimizer=tf.optimizers.Adam(),
+    metrics=[tf.keras.metrics.BinaryAccuracy()])
+
+Y_train_one_zero = [onezero(x) for x in Y_train]
+Y_train_onehot = np.eye(2)[Y_train_one_zero]
+
+Y_test_one_zero = [onezero(x) for x in Y_test]
+Y_test_onehot = np.eye(2)[Y_test_one_zero]
+
+history = model.fit(tf.convert_to_tensor(X_train, np.float32), Y_train_onehot, epochs=5)
+
+results = model.evaluate(X_test, Y_test_onehot, batch_size=64)
+f = open('model_eval.txt', 'w')
+f.write('test loss: ' + str(results[0]) + '\n' + 'test acc: ' + str(results[1]))
+f.close()