evaluation

evaluation/Jenkinsfile

@@ -0,0 +1,34 @@
+pipeline {
+    agent {
+        dockerfile true
+    }
+    stages {
+        stage('Copy Archive') {
+            steps {
+                script {
+                    step ([$class: 'CopyArtifact',
+                    projectName: 's434700-training',
+                    filter: 'model.pt',
+                    target: 'model'])
+                }
+            }
+        }
+        stage('checkout: Check out from version control') {
+            steps {
+                git 'https://git.wmi.amu.edu.pl/s434700/ium_s434700.git'
+            }
+        }
+        stage('evaluation') {
+            steps {
+                sh 'python ./evaluation/eval.py'
+                sh 'python ./evaluation/plot.py'
+            }
+        }
+        stage('archiveArtifacts') {
+            steps {
+                archiveArtifacts 'model_results.csv'
+                archiveArtifacts 'model_results.png'
+            }
+        }
+    }
+}

evaluation/eval.py

@@ -0,0 +1,59 @@
+import torch
+import torch.nn as nn
+import numpy as np
+import pandas as pd
+import seaborn as sns
+import torch
+import datetime
+from torch.autograd import Variable
+import csv
+
+INPUT_DIM = 1
+OUTPUT_DIM = 1
+LEARNING_RATE = 0.01
+EPOCHS = 100
+
+
+dataset = pd.read_csv('train_set.csv')
+
+# create dummy data for training
+x_values = [datetime.datetime.strptime(
+    item, "%Y-%m-%d").month for item in dataset['date'].values]
+x_train = np.array(x_values, dtype=np.float32)
+x_train = x_train.reshape(-1, 1)
+
+y_values = [min(dataset['result_1'].values[i]/dataset['result_2'].values[i], dataset['result_2'].values[i] /
+                dataset['result_1'].values[i]) for i in range(len(dataset['result_1'].values))]
+y_train = np.array(y_values, dtype=np.float32)
+y_train = y_train.reshape(-1, 1)
+
+
+class LinearRegression(torch.nn.Module):
+    def __init__(self, inputSize, outputSize):
+        super(LinearRegression, self).__init__()
+        self.linear = torch.nn.Linear(inputSize, outputSize)
+
+    def forward(self, x):
+        out = self.linear(x)
+        return out
+
+
+model = LinearRegression(INPUT_DIM, OUTPUT_DIM)
+
+model.load_state_dict(torch.load("model/model.pt"), strict=False)
+
+
+# testing data
+
+with torch.no_grad():  # we don't need gradients in the testing phase
+    predicted = model(Variable(torch.from_numpy(x_train))).data.numpy()
+
+
+with open('model_results.csv', mode='w') as filee:
+    writer = csv.writer(filee, delimiter=',', quotechar='"',
+                        quoting=csv.QUOTE_MINIMAL)
+
+    writer.writerow(['x', 'y', 'predicted_y'])
+
+    for i in range(len(x_train)):
+        writer.writerow([x_train[i][0], y_train[i][0], predicted[i][0]])

evaluation/plot.py

@@ -0,0 +1,14 @@
+import matplotlib.pyplot as plt
+import pandas as pd
+
+results = pd.read_csv('model_results.csv')
+
+x_train = results['x']
+y_train = results['y']
+predicted = results['predicted_y']
+
+plt.clf()
+plt.plot(x_train, y_train, 'go', label='True data', alpha=0.5)
+plt.plot(x_train, predicted, '--', label='Predictions', alpha=0.5)
+plt.legend(loc='best')
+plt.savefig('model_results.png')