add pytorch exercise

Dockerfile

@@ -6,11 +6,13 @@ RUN apt update && apt install python3-pip -y
 RUN pip3 install kaggle && pip3 install pandas && pip3 install scikit-learn && pip3 install matplotlib
 RUN apt install -y curl
 RUN pip3 install --user wget
+RUN pip3 install torch torchvision torchaudio
 
 WORKDIR /app
 
 COPY ./init.py ./
 COPY ./stats.py ./
+COPY ./pytorch-example.py ./
 
 RUN mkdir /.kaggle
 RUN chmod -R 777 /.kaggle

Jenkinsfile

@@ -22,13 +22,20 @@ node {
                 "KAGGLE_KEY=${params.KAGGLE_KEY}", "CUTOFF=${params.CUTOFF}" ]) {
 					checkout([$class: 'GitSCM', branches: [[name: '*/master']], doGenerateSubmoduleConfigurations: false, extensions: [], submoduleCfg: [], userRemoteConfigs: [[url: 'https://git.wmi.amu.edu.pl/s440058/ium_440058']]])
 
+                    checkout scm
+
+					def image = docker.build("s440058/ium")
+					image.inside {
+					sh 'python3 ./pytorch-example.py > model.txt'
+					sh 'python3 ./init.py > model.txt'
                     sh "chmod 777 ./bash.sh"
                     sh "./bash.sh"
 
                     archiveArtifacts "courses.data.dev"
                     archiveArtifacts "courses.data.test"
                     archiveArtifacts "courses.data.train"
-
+                    archiveArtifacts 'model.txt'
+                    }
             }
         }
     }

pytorch-example.py

@@ -0,0 +1,66 @@
+from sklearn.model_selection import train_test_split
+import torch
+import torch.nn as nn
+import pandas as pd
+import numpy as np
+import torch.nn.functional as F
+from torch.utils.data import DataLoader, TensorDataset, random_split
+from sklearn import preprocessing
+
+class LogisticRegressionModel(torch.nn.Module):
+    def __init__(self, input_dim, output_dim):
+        super(LogisticRegressionModel, self).__init__()
+        self.linear = nn.Linear(input_dim, output_dim)
+        self.sigmoid = nn.Sigmoid()
+    def forward(self, x):
+        out = self.linear(x)
+        return self.sigmoid(out)
+
+results = pd.read_csv('diabetes2.csv')
+
+results.dropna()
+
+data_train, data_valid, data_test = np.split(results.sample(frac=1), [int(.6*len(results)), int(.8*len(results))])
+columns_to_train   =  ['Glucose', 'BloodPressure', 'Insulin', 'Age']
+
+x_train = data_train[columns_to_train].astype(np.float32)
+y_train = data_train['Outcome'].astype(np.float32)
+
+x_test = data_test[columns_to_train].astype(np.float32)
+y_test = data_test['Outcome'].astype(np.float32)
+
+fTrain = torch.from_numpy(x_train.values)
+tTrain = torch.from_numpy(y_train.values.reshape(460,1))
+
+fTest= torch.from_numpy(x_test.values)
+tTest = torch.from_numpy(y_test.values)
+
+batch_size = 95
+n_iters = 900
+num_epochs = int(n_iters / (len(x_train) / batch_size))
+learning_rate = 0.005
+input_dim = 4
+output_dim = 1
+
+model = LogisticRegressionModel(input_dim, output_dim)
+
+criterion = torch.nn.BCELoss(reduction='mean')
+optimizer = torch.optim.SGD(model.parameters(), lr = learning_rate)
+
+for epoch in range(num_epochs):
+    print ("Epoch #",epoch)
+    model.train()
+    optimizer.zero_grad()
+    # Forward pass
+    y_pred = model(fTrain)
+    # Compute Loss
+    loss = criterion(y_pred, tTrain)
+    print(loss.item())
+    # Backward pass
+    loss.backward()
+    optimizer.step()
+
+
+y_pred = model(fTest)
+
+torch.save(model, 'diabetes.pkl')