From 4efd9d91206c3f6ec62569050b13f91907506135 Mon Sep 17 00:00:00 2001
From: piotr6789 <piotr.ulanicki4@gmail.com>
Date: Mon, 24 May 2021 15:43:42 +0200
Subject: [PATCH] add mongo observer

---
 Dockerfile                                    |  2 +-
 lab06/jenkinsfile-train                       |  2 +-
 ...-example-file.py => sacred-example-file.py |  0
 sacred-example-mongo.py                       | 98 +++++++++++++++++++
 4 files changed, 100 insertions(+), 2 deletions(-)
 rename scared-example-file.py => sacred-example-file.py (100%)
 create mode 100644 sacred-example-mongo.py

diff --git a/Dockerfile b/Dockerfile
index 44e7cef..1259540 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -14,7 +14,7 @@ WORKDIR /app
 COPY ./init.py ./
 COPY ./stats.py ./
 COPY ./pytorch-example.py ./
-COPY ./scared-example-file.py ./
+COPY ./sacred-example-file.py ./
 
 RUN mkdir /.kaggle
 RUN chmod -R 777 /.kaggle
\ No newline at end of file
diff --git a/lab06/jenkinsfile-train b/lab06/jenkinsfile-train
index 68e8193..48cc1c7 100644
--- a/lab06/jenkinsfile-train
+++ b/lab06/jenkinsfile-train
@@ -29,7 +29,7 @@ pipeline {
       stage('Docker'){
          steps{
             sh 'python3 "./pytorch-example.py" ${BATCH_SIZE} ${EPOCHS} > model.txt'
-            sh 'python3 "./scared-example-file.py"'
+            sh 'python3 "./sacredd-example-file.py"'
          }
       }
       stage('archiveArtifacts') {
diff --git a/scared-example-file.py b/sacred-example-file.py
similarity index 100%
rename from scared-example-file.py
rename to sacred-example-file.py
diff --git a/sacred-example-mongo.py b/sacred-example-mongo.py
new file mode 100644
index 0000000..69ada91
--- /dev/null
+++ b/sacred-example-mongo.py
@@ -0,0 +1,98 @@
+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
+import sys
+from sacred import Experiment
+from sacred.observers import MongoObserver
+from sklearn.metrics import accuracy_score
+from sklearn.metrics import f1_score
+from sklearn.metrics import mean_squared_error
+
+np.set_printoptions(suppress=False)
+
+ex = Experiment("ium_s440058", interactive=False, save_git_info=False)
+ex.observers.append(MongoObserver(url='mongodb://mongo_user:mongo_password_IUM_2021@172.17.0.1:27017',
+                                  db_name='s440058'))
+
+@ex.config
+def my_config():
+    num_epochs = 10
+    batch_size = 20
+
+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)
+
+@ex.capture
+def script(num_epochs, batch_size, _run):
+    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)
+
+    _run.log_scalar("Batch", str(batch_size))
+    _run.log_scalar("epoch",  str(num_epochs))
+    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()
+
+    _run.log_scalar("Lost", str(loss.item()))
+
+
+    torch.save(model.state_dict(), 'diabetes.pth')
+    pred = model(fTest)
+    accuracy = accuracy_score(tTest, np.argmax(pred.detach().numpy(), axis = 1))
+    f1 = f1_score(tTest, np.argmax(pred.detach().numpy(), axis = 1), average = None)
+    rmse = mean_squared_error(tTest, pred.detach().numpy())
+    _run.log_scalar("accuracy", accuracy)
+    _run.log_scalar("f1", f1)
+    _run.log_scalar("rmse", rmse)
+
+@ex.automain
+def my_main(num_epochs, batch_size, _run):
+    script()
+
+ex.run()
+ex.add_artifact('diabetes_model/diabetes.pth')
\ No newline at end of file