Add mlflow files

Dockerfile

@@ -6,12 +6,10 @@ RUN pip3 install seaborn
 RUN pip3 install ipython
 RUN pip3 install torch
 RUN pip3 install numpy
-RUN pip3 install sacred
+RUN pip3 install mlflow
-RUN pip3 install GitPython
-RUN pip3 install pymongo
 
 WORKDIR /app
 
 COPY ./training.py ./
-COPY ./training_sacred.py ./
+COPY ./training_mlflow.py ./
 COPY ./evaluation.py ./

MLproject

@@ -0,0 +1,12 @@
+name: s444421
+    
+docker_env:
+  image: agakul/ium:mlflow
+
+entry_points:
+  main:
+    parameters:
+      epochs: {type: float, default: 1000}
+    command: "python training_mlflow.py {epochs}"
+  test:
+    command: "python evaluation.py"

training_mlflow.py

@@ -0,0 +1,131 @@
+#!/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
+import mlflow
+from urllib.parse import urlparse
+
+
+# In[ ]:
+
+
+mlflow.set_experiment("s444421")
+
+
+# In[ ]:
+
+
+epochs = int(sys.argv[1])
+
+
+# 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[ ]:
+
+def my_main(epochs):
+    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')
+    mlflow.log_param("epochs", epochs)
+    mlflow.log_metric("loss", loss)
+    
+    X_test = pd.read_csv('X_test.csv')
+    X_test = torch.from_numpy(np.array(X_test)).float()
+    X_test = X_test.to(device)
+    y_pred = model(X_test)
+    y_pred = y_pred.ge(.5).view(-1).cpu()
+    
+    signature = mlflow.models.signature.infer_signature(X_train.numpy(), np.array(y_pred))
+    tracking_url_type_store = urlparse(mlflow.get_tracking_uri()).scheme
+    
+    if tracking_url_type_store != "file":
+        mlflow.sklearn.log_model(model, "s444421", registered_model_name="s444421", signature=signature)
+    else:
+        mlflow.sklearn.log_model(model, "s444421", signature=signature)
+
+
+# In[ ]:
+
+with mlflow.start_run() as run:
+    print("MLflow run experiment_id: {0}".format(run.info.experiment_id))
+    print("MLflow run artifact_uri: {0}".format(run.info.artifact_uri))
+    my_main(epochs)