cleanup + jenkinsfile update

Dockerfile

@@ -16,9 +16,11 @@ ENV LC_ALL en_US.UTF-8
 ENV LANG en_US.UTF-8
 ENV LANGUAGE en_US.UTF-8
 
-RUN python3 -m pip --version
 RUN python3 -m pip install kaggle
 RUN python3 -m pip install pandas
+RUN python3 -m pip install wheel --no-deps -U
+RUN python3 -m pip install torch
+RUN python3 -m pip install sklearn
 RUN python3 -m pip freeze
 
 ENV PATH="/root/.local/bin:${PATH}"
@@ -32,3 +34,4 @@ RUN chmod a+x ./script-stats.py
 
 # RUN ./download.sh 117928
 RUN python3 ./script-download.py
+# RUN python3 ./lab05_deepLearning.py

Jenkinsfile

@@ -1,44 +0,0 @@
-pipeline {
-   agent any
-   parameters {
-      string(
-         defaultValue: 'heatedboss2',
-         description: 'Kaggle username',
-         name: 'KAGGLE_USERNAME',
-         trim: false
-      )
-      password(
-         defaultValue: '',
-         description: 'Kaggle token',
-         name: 'KAGGLE_KEY'
-      )
-      string(
-         defaultValue: '1',
-         description: 'Cutoff',
-         name: 'CUTOFF',
-         trim: false
-      )
-   }
-   stages {
-      stage('Checkout') {
-         steps {
-            checkout([$class: 'GitSCM', branches: [
-               [name: '*/master']
-            ], extensions: [], userRemoteConfigs: [
-               [credentialsId: '8b8d54ee-f03c-4980-90b1-959faa97082b', url: 'https://git.wmi.amu.edu.pl/s444507/ium_444507.git']
-            ]])
-         }
-      }
-      stage('Script') {
-         steps {
-            script {
-               withEnv(["KAGGLE_USERNAME=${params.KAGGLE_USERNAME}", "KAGGLE_KEY=${params.KAGGLE_KEY}", "CUTOFF=${params.CUTOFF}"]) {
-                  sh 'echo KAGGLE_USERNAME: $KAGGLE_USERNAME'
-                  sh './download.sh $CUTOFF > ./script_logs.txt'
-                  archiveArtifacts artifacts: 'car_prices.csv.dev, car_prices.csv.test, car_prices.csv.train, script_logs.txt', followSymlinks: false
-               }
-            }
-         }
-      }
-   }
-}

Jenkinsfile2

@@ -1,19 +0,0 @@
-pipeline {
-    agent any
-    parameters {
-        buildSelector(
-            defaultSelector: lastSuccessful(),
-            name: 'BUILD_SELECTOR',
-            description: 'Which build to use for copying artifacts'
-        )
-    }
-    stages {
-        stage("Script") {
-            steps {
-                copyArtifacts fingerprintArtifacts: true, projectName: 's444507-create-dataset', selector: buildParameter('BUILD_SELECTOR')
-                sh './stats.sh'
-                archiveArtifacts artifacts: 'stats.txt'
-            }
-        }
-    }
-}

Jenkinsfile_stats

@@ -11,7 +11,13 @@ pipeline {
         stage('Show stats') {
             steps {
                 sh "python3 ./script-stats.py"
+                sh "python3 ./lab05_deepLearning.py"
             }
         }
     }
+    post {
+        success {
+            archiveArtifacts artifacts: 'Car_Prices_Poland_Kaggle*', followSymlinks: false
+        }
+    }
 }

figlet-loop.sh

@@ -1,4 +0,0 @@
-#!/bin/bash
-while read line; do
-    figlet "$line"
-done

lab05_deepLearning.py

@@ -8,16 +8,15 @@ from sklearn.metrics import accuracy_score
 import torch.nn.functional as F
 import pandas as pd
 from sklearn import preprocessing
-import matplotlib.pyplot as plt
+# import matplotlib.pyplot as plt
 
 
 class Model(nn.Module):
     def __init__(self, input_dim):
         super(Model, self).__init__()
-        self.layer1 = nn.Linear(input_dim, 160)
-        # self.layer2 = nn.Linear(320, 160)
-        self.layer2 = nn.Linear(160, 80)
-        self.layer3 = nn.Linear(80, 5)
+        self.layer1 = nn.Linear(input_dim, 100)
+        self.layer2 = nn.Linear(100, 60)
+        self.layer3 = nn.Linear(60, 5)
 
     def forward(self, x):
         x = F.relu(self.layer1(x))
@@ -61,6 +60,12 @@ def prepare_dataset_raw(dataset):
     return lab, feat
 
 
+# def draw_plot(lbl):
+# need to import matplotlib to work
+#     plt.hist(lbl, bins=[i for i in range(len(set(lbl)))], edgecolor="black")
+#     plt.xticks(np.arange(0, len(set(lbl)), 1))
+#     plt.show()
+
 # Prepare dataset
 print("Loading dataset...")
 dataset = load_dataset_raw()
@@ -71,16 +76,14 @@ dataset = remove_rows(dataset)
 labels, features = prepare_dataset_raw(dataset)
 print("Dataset prepared")
 
-plot = plt.hist(labels, bins=[i for i in range(len(set(labels)))], edgecolor="black")
-plt.xticks(np.arange(0, len(set(labels)), 1))
-plt.show()
+
 features_train, features_test, labels_train, labels_test = train_test_split(features, labels, random_state=42,
                                                                             shuffle=True)
 # Training
 model = Model(features_train.shape[1])
 optimizer = torch.optim.Adam(model.parameters(), lr=0.01)
 loss_fn = nn.CrossEntropyLoss()
-epochs = 100
+epochs = 1000
 
 print("Starting model training...")
 x_train, y_train = Variable(torch.from_numpy(features_train)).float(), Variable(torch.from_numpy(labels_train)).long()

script-download.py

@@ -14,6 +14,7 @@ def unzip_package():
     os.system('rm ./car-prices-poland.zip')
     print('Zip file removed')
 
+
 def download_dataset():
     """Download kaggle dataset."""
     print('Downloading dataset...')