From 3fef5dda7620590a87e8c1f5fe684d6e97bc7eee Mon Sep 17 00:00:00 2001
From: eugene <eugene.polyakow@gmail.com>
Date: Wed, 7 Jun 2023 00:34:30 +0200
Subject: [PATCH] update

---
 Dockerfile       |   2 +
 Jenkinsfile-lab7 |  55 ++++++++++++++++++++++++++
 script7.py       | 101 +++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 158 insertions(+)
 create mode 100644 Jenkinsfile-lab7
 create mode 100644 script7.py

diff --git a/Dockerfile b/Dockerfile
index 002b674..3b0913b 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -11,6 +11,8 @@ RUN pip3 install tensorflow==2.12.*
 RUN pip3 install torch torchvision
 #RUN pip install torch==1.8.0+cpu torchvision==0.9.0+cpu torchaudio==0.8.0 -f https://download.pytorch.org/whl/torch_stable.html
 RUN pip3 install pickle5
+RUN pip3 install sacred
+RUN pip3 install pymongo
 
 #RUN apt install python3.10-venv -y
 #RUN python3 -m venv docker_ium
diff --git a/Jenkinsfile-lab7 b/Jenkinsfile-lab7
new file mode 100644
index 0000000..61589b2
--- /dev/null
+++ b/Jenkinsfile-lab7
@@ -0,0 +1,55 @@
+pipeline {
+    agent {
+        dockerfile true 
+    }
+    stages {
+        stage('do nothing')
+        {
+            steps {
+                echo ("do nothing")
+                /*echo ("set up venv")
+
+                sh "python3 -m venv docker_ium"
+                sh "source docker_ium/bin/activate"
+                sh "pip3 install kaggle"
+                sh "pip3 install pandas"
+                sh "pip3 install -U scikit-learn"*/
+
+            }
+        }
+        stage('Run Script') {
+            steps {
+                //echo ("checkout: check out from version control")
+                //git "https://git.wmi.amu.edu.pl/s151636/ium_151636.git"
+
+                //echo ("sh: Shell Script")
+                //sh "python3 script2.py"
+
+                //echo ("copyArtifacts")
+
+
+                //echo("archiveArtifacts")
+
+                //echo ("run dockerfile")
+                //sh docker
+
+
+                echo("run data script")
+                //sh "source docker_ium/bin/activate"
+                sh "ls -a"
+                sh "chmod u+x script7.py"
+                //sh "pip3 show pandas"
+                //sh "python3 script5_3.py | tee output.txt | tar -czf output.tar.gz output.txt"
+                sh "python3 script7.py | tee metrics.txt"
+            }
+        }
+        stages {  
+      stage('Archive Output') {
+         steps {
+            archiveArtifacts 'experiments/**/*.*'
+         }
+      }
+   }
+        
+    }
+}
diff --git a/script7.py b/script7.py
new file mode 100644
index 0000000..5cde5c4
--- /dev/null
+++ b/script7.py
@@ -0,0 +1,101 @@
+import pandas as pd
+import torch
+import torch.nn as nn
+import torch.optim as optim
+from torch.utils.data import DataLoader, Dataset
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import LabelEncoder
+import pickle
+from sacred import Experiment
+from sacred.observers import FileStorageObserver, MongoObserver
+
+ex = Experiment("s151636", interactive=True, save_git_info=False)
+ex.observers.append(FileStorageObserver('experiments'))
+ex.observers.append(MongoObserver(url='mongodb://admin:IUM_2021@172.17.0.1:27017', db_name='sacred'))
+
+# Define the neural network model
+class Model(nn.Module):
+    def __init__(self):
+        super(Model, self).__init__()
+        self.fc1 = nn.Linear(1, 64)
+        self.fc2 = nn.Linear(64, 1)
+        self.relu = nn.ReLU()
+
+    def forward(self, x):
+        x = self.fc1(x)
+        x = self.relu(x)
+        x = self.fc2(x)
+        return x
+
+# Define a custom dataset
+class CustomDataset(Dataset):
+    def __init__(self, X, y):
+        self.X = torch.FloatTensor(X.values.reshape(-1, 1))
+        self.y = torch.FloatTensor(y.values.reshape(-1, 1))
+
+    def __len__(self):
+        return len(self.X)
+
+    def __getitem__(self, idx):
+        return self.X[idx], self.y[idx]
+
+@ex.main
+def train_model():
+    # Load the dataset
+    df = pd.read_csv('data.csv')
+
+    # Select the relevant columns (e.g., 'Rating' and 'Writer')
+    data = df[['Rating', 'Writer']]
+
+    # Drop rows with missing values
+    data = data.dropna()
+
+    # Convert the 'Writer' column to numeric using label encoding
+    encoder = LabelEncoder()
+    data['Writer'] = encoder.fit_transform(data['Writer'])
+
+    # Split the data into training and testing sets
+    X = data['Writer']
+    y = data['Rating']
+
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+    # Create the model instance
+    model = Model()
+
+    # Define the loss function and optimizer
+    criterion = nn.MSELoss()
+    optimizer = optim.Adam(model.parameters())
+
+    # Create dataloaders for training and testing
+    train_dataset = CustomDataset(X_train, y_train)
+    test_dataset = CustomDataset(X_test, y_test)
+    train_dataloader = DataLoader(train_dataset, batch_size=64, shuffle=True)
+    test_dataloader = DataLoader(test_dataset, batch_size=64)
+
+    # Train the model
+    for epoch in range(10):
+        model.train()
+        for inputs, targets in train_dataloader:
+            optimizer.zero_grad()
+            outputs = model(inputs)
+            loss = criterion(outputs, targets)
+            loss.backward()
+            optimizer.step()
+
+    # Save the model to a file
+    torch.save(model.state_dict(), 'model.pth')
+
+    # Save the encoder to a file
+    with open('encoder.pkl', 'wb') as f:
+        pickle.dump(encoder, f)
+
+    # Make predictions on new data
+    new_writer = 'Jim Cash'
+    new_writer_encoded = torch.tensor(encoder.transform([new_writer])).float()
+
+    model.eval()
+    rating_prediction = model(new_writer_encoded)
+    print("Predicted rating for the writer 'Jim Cash':", rating_prediction.item())
+
+ex.run()