LAB 5 FRAMEWORK PYTORCH

Dockerfile

@@ -1,10 +1,10 @@
 FROM ubuntu:latest
 
-RUN apt update && apt install -y python3-pip && pip3 install setuptools && pip3 install numpy && pip3 install pandas && pip3 install wget && pip3 install scikit-learn && rm -rf /var/lib/apt/lists/*
+RUN apt update && apt install -y python3-pip && pip3 install setuptools && pip3 install numpy && pip3 install pandas && pip3 install wget && pip3 install scikit-learn &&  pip3 install torch==1.8.1+cu102 torchvision==0.9.1+cu102 torchaudio===0.8.1 -f https://download.pytorch.org/whl/torch_stable.html &&rm -rf /var/lib/apt/lists/*
 
 WORKDIR /app
 
 COPY ./create.py ./
 COPY ./stats.py ./
-
+COPY ./stroke-pytorch.py ./
 

Jenkinsfile

@@ -14,6 +14,7 @@ pipeline {
       stage('Docker'){
          steps{
             sh 'python3 ./create.py'
+            sh 'python3 "./stroke-pytorch.py" > model.txt'
          }
       }
       stage('checkout: Check out from version control') {
@@ -23,6 +24,7 @@ pipeline {
       }
       stage('archiveArtifacts') {
          steps {
+            archiveArtifacts 'model.txt'
             archiveArtifacts 'data_val.csv'
             archiveArtifacts 'data_test.csv'
             archiveArtifacts 'data_train.csv'

stroke-pytorch.py

@@ -0,0 +1,69 @@
+import torch
+import torch.nn.functional as F
+from torch import nn
+from torch.autograd import Variable
+import torchvision.transforms as transforms
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import MinMaxScaler
+from sklearn.metrics import accuracy_score
+import numpy as np
+import pandas as pd
+
+class LogisticRegressionModel(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)
+
+data_train = pd.read_csv("data_train.csv")
+data_test  = pd.read_csv("data_test.csv")
+data_val   = pd.read_csv("data_val.csv")
+FEATURES   =  ['age','hypertension','heart_disease','ever_married', 'avg_glucose_level', 'bmi']
+
+x_train = data_train[FEATURES].astype(np.float32)
+y_train = data_train['stroke'].astype(np.float32)
+
+x_test = data_test[FEATURES].astype(np.float32)
+y_test = data_test['stroke'].astype(np.float32)
+
+fTrain = torch.from_numpy(x_train.values)
+tTrain = torch.from_numpy(y_train.values.reshape(2945,1))
+
+fTest= torch.from_numpy(x_test.values)
+tTest = torch.from_numpy(y_test.values)
+
+batch_size = 95
+n_iters = 1000
+num_epochs = int(n_iters / (len(x_train) / batch_size))
+learning_rate = 0.001
+input_dim = 6
+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)
+print("predicted Y value: ", y_pred.data)
+
+print ("The accuracy is", accuracy_score(tTest, np.argmax(y_pred.detach().numpy(), axis=1)))
+
+torch.save(model, 'stroke.pkl')