From 8e88f6e6f03cc686ec739714b4b7d975aa22836c Mon Sep 17 00:00:00 2001
From: Agata <agakul1@st.amu.edu.pl>
Date: Fri, 6 May 2022 09:53:37 +0200
Subject: [PATCH] Update files (sacred)

---
 Dockerfile           |   2 +
 training.Jenkinsfile |   9 ++--
 training_sacred.py   | 113 +++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 121 insertions(+), 3 deletions(-)
 create mode 100755 training_sacred.py

diff --git a/Dockerfile b/Dockerfile
index a8b8966..975977b 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -6,8 +6,10 @@ RUN pip3 install seaborn
 RUN pip3 install ipython
 RUN pip3 install torch
 RUN pip3 install numpy
+RUN pip3 install sacred
 
 WORKDIR /app
 
 COPY ./training.py ./
+COPY ./training_sacred.py ./
 COPY ./evaluation.py ./
diff --git a/training.Jenkinsfile b/training.Jenkinsfile
index 00cf386..7d228b5 100644
--- a/training.Jenkinsfile
+++ b/training.Jenkinsfile
@@ -26,8 +26,12 @@ pipeline {
         stage('Script') {
             steps {
             	copyArtifacts filter: '*', projectName:'s444421-create-dataset', selector: buildParameter('BUILD_SELECTOR')
-            	sh 'ipython ./training.py $EPOCHS'
-            	archiveArtifacts artifacts: 'model.pth'
+            	sh 'ipython ./training_sacred.py with "epochs=$EPOCHS"'
+            	sh 'cp my_runs/1/config.json config.json'
+            	sh 'cp my_runs/1/model.pth model.pth'
+            	sh 'cp my_runs/_sources/training* training_sacred.py'
+            	sh 'cp my_runs/1/info.json info.json'
+            	archiveArtifacts artifacts: 'config.json, model.pth, training_sacred.py, info.json'
             }
         }
     }
@@ -45,5 +49,4 @@ pipeline {
       	changed {
       		emailext body: 'CHANGED', subject: 's444421-training status', to: 'e19191c5.uam.onmicrosoft.com@emea.teams.ms'
       	}
-    }
 }
diff --git a/training_sacred.py b/training_sacred.py
new file mode 100755
index 0000000..8095d1a
--- /dev/null
+++ b/training_sacred.py
@@ -0,0 +1,113 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# In[ ]:
+
+
+import numpy as np
+import pandas as pd
+from sklearn.metrics import accuracy_score
+import torch
+from torch import nn, optim
+import torch.nn.functional as F
+import sys
+from sacred import Experiment
+from sacred.observers import FileStorageObserver
+
+
+# In[ ]:
+
+
+ex = Experiment("file_observer")
+ex.observers.append(FileStorageObserver('my_runs'))
+
+@ex.config
+def my_config():
+    epochs = 400
+
+
+# In[ ]:
+
+
+def prepare_data():
+    X_train = pd.read_csv('X_train.csv')
+    y_train = pd.read_csv('y_train.csv')
+    X_train = torch.from_numpy(np.array(X_train)).float()
+    y_train = torch.squeeze(torch.from_numpy(y_train.values).float())
+    return X_train, y_train
+
+
+# In[ ]:
+
+
+class Net(nn.Module):
+    def __init__(self, n_features):
+        super(Net, self).__init__()
+        self.fc1 = nn.Linear(n_features, 5)
+        self.fc2 = nn.Linear(5, 3)
+        self.fc3 = nn.Linear(3, 1)
+    def forward(self, x):
+        x = F.relu(self.fc1(x))
+        x = F.relu(self.fc2(x))
+        return torch.sigmoid(self.fc3(x))
+
+
+# In[ ]:
+
+
+def calculate_accuracy(y_true, y_pred):
+    predicted = y_pred.ge(.5).view(-1)
+    return (y_true == predicted).sum().float() / len(y_true)
+
+
+# In[ ]:
+
+
+def round_tensor(t, decimal_places=3):
+    return round(t.item(), decimal_places)
+
+# In[ ]:
+
+
+def train_model(X_train, y_train, device, epochs):
+    net = Net(X_train.shape[1])
+    criterion = nn.BCELoss()
+    optimizer = optim.Adam(net.parameters(), lr=0.001)
+    
+    X_train = X_train.to(device)
+    y_train = y_train.to(device)
+    
+    net = net.to(device)
+    criterion = criterion.to(device)
+
+    for epoch in range(epochs):
+        y_pred = net(X_train)
+        y_pred = torch.squeeze(y_pred)
+        train_loss = criterion(y_pred, y_train)
+        if epoch % 100 == 0:
+            train_acc = calculate_accuracy(y_train, y_pred)
+            print(
+                f'''epoch {epoch}
+                Train set - loss: {round_tensor(train_loss)}, accuracy: {round_tensor(train_acc)}
+                ''')
+    optimizer.zero_grad()
+    train_loss.backward()
+    optimizer.step()
+    return net, round_tensor(train_loss)
+
+
+# In[ ]:
+
+
+@ex.automain
+def my_main(epochs, _run):
+    X_train, y_train = prepare_data()
+    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+    
+    model, loss = train_model(X_train, y_train, device, epochs)
+    torch.save(model, 'model.pth')
+    ex.add_artifact('model.pth')
+    
+    _run.info["epochs"] = epochs
+    _run.info["loss"] = loss
+