IUM_08 - add scripts for MLflow tracking params and metrics, add MLproject file with train_test_evaluate command, add conda.yaml, update requirements.txt, fix minor issues

create_model.py

@@ -4,10 +4,7 @@ import torch
 import torch.nn as nn
 import torch.optim as optim
 
-import pathlib
-
 import os
-import sys
 
 from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score
 

mlflow/breast_cancer_pytorch/MLproject

@@ -0,0 +1,11 @@
+name: s464863
+
+conda_env: conda.yaml
+
+entry_points:
+  main:
+    parameters:
+        learning_rate: {type: float, default: 0.001}
+        weight_decay: {type: float, default: 0.001}
+        num_epochs: {type: int, default: 1000}
+    command: "python ../create_model.py {learning_rate} {weight_decay} {num_epochs}"

mlflow/breast_cancer_pytorch/conda.yaml

@@ -0,0 +1,14 @@
+name: breast_cancer_pytorch
+channels:
+  - defaults
+dependencies:
+  - python=3.10
+  - pip
+  - pip:
+    - mlflow
+    - torch
+    - pandas
+    - numpy
+    - scikit-learn
+    - matplotlib
+    - seaborn

mlflow/create_model.py

@@ -0,0 +1,235 @@
+import numpy as np
+import pandas as pd
+import torch
+import torch.nn as nn
+import torch.optim as optim
+
+import mlflow
+
+import os
+import sys
+import inspect
+
+from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score
+
+currentdir = os.path.dirname(os.path.abspath(inspect.getfile(inspect.currentframe())))
+parentdir = os.path.dirname(currentdir)
+sys.path.insert(0, parentdir)
+
+from NeuralNetwork import NeuralNetwork
+
+# MLflow tracking URI
+mlflow.set_tracking_uri("http://localhost:5000")
+
+# Create mlflow experiment if not exists
+experiment = mlflow.get_experiment_by_name("s464863")
+
+if experiment is None:
+    mlflow.create_experiment("s464863")
+
+# Set active mlflow experiment
+mlflow.set_experiment("s464863")
+
+# MLflow experiment
+client = mlflow.tracking.MlflowClient()
+run = client.create_run(experiment_id=experiment.experiment_id)
+run = mlflow.start_run(run_id=run.info.run_id)
+
+# Seed for reproducibility
+torch.manual_seed(1234)
+
+# Get absolute path
+currentdir = os.path.dirname(os.path.abspath(inspect.getfile(inspect.currentframe())))
+parentdir = os.path.dirname(currentdir)
+train_path = os.path.join(parentdir, 'datasets/train.csv')
+test_path = os.path.join(parentdir, 'datasets/test.csv')
+
+# Load data
+train_data = pd.read_csv(train_path)
+test_data = pd.read_csv(test_path)
+
+# Split data
+X_train = train_data.drop(columns=['id', 'diagnosis']).values
+y_train = train_data['diagnosis'].values
+
+X_test = test_data.drop(columns=['id', 'diagnosis']).values
+y_test = test_data['diagnosis'].values
+
+# Convert data to PyTorch tensors
+X_train = torch.FloatTensor(X_train)
+y_train = torch.FloatTensor(y_train).view(-1, 1)
+
+X_test = torch.FloatTensor(X_test)
+y_test = torch.FloatTensor(y_test).view(-1, 1)
+
+# Parameters
+input_size = X_train.shape[1]
+hidden_size = 128
+
+# Learning parameters
+learning_rate = float(sys.argv[1]) if len(sys.argv) > 1 else 0.001
+weight_decay = float(sys.argv[2]) if len(sys.argv) > 2 else 0.001
+num_epochs = int(sys.argv[3]) if len(sys.argv) > 3 else 1000
+
+# Log parameters to mlflow
+mlflow.log_param("hidden_size", hidden_size)
+mlflow.log_param("learning_rate", learning_rate)
+mlflow.log_param("weight_decay", weight_decay)
+mlflow.log_param("num_epochs", num_epochs)
+
+# Model initialization
+model = NeuralNetwork(input_size, hidden_size)
+
+# Loss function and optimizer
+criterion = nn.BCELoss()
+optimizer = optim.Adam(model.parameters(), lr=learning_rate, weight_decay=weight_decay)
+
+# Training loop
+model.train()
+
+for epoch in range(num_epochs):
+    # Zero the gradients
+    optimizer.zero_grad()
+
+    # Forward pass
+    outputs = model(X_train)
+
+    # Compute loss
+    loss = criterion(outputs, y_train)
+
+    # Backward pass
+    loss.backward()
+
+    # Update weights
+    optimizer.step()
+
+    # Print loss
+    if (epoch + 1) % 100 == 0:
+        print(f'Epoch [{epoch + 1}/{num_epochs}], Loss: {loss.item()}')
+
+# Test the model
+model.eval()
+
+with torch.no_grad():
+
+    # Make predictions
+    y_pred = model(X_test)
+    y_pred = np.where(y_pred > 0.5, 1, 0)
+
+    # Calculate metrics
+    accuracy = accuracy_score(y_test, y_pred)
+    precision = precision_score(y_test, y_pred)
+    recall = recall_score(y_test, y_pred)
+    f1 = f1_score(y_test, y_pred)
+
+    # Log metrics to mlflow
+    mlflow.log_metric("accuracy", accuracy)
+    mlflow.log_metric("precision", precision)
+    mlflow.log_metric("recall", recall)
+    mlflow.log_metric("f1", f1)
+
+# If directory models does not exist, create it
+if not os.path.exists('./models'):
+    os.makedirs('./models')
+
+# Save the model
+torch.save(model, './models/model.pth')
+
+# End mlflow run
+mlflow.end_run()
+
+# # MLflow experiment
+# with mlflow.start_run() as run:
+#     # Seed for reproducibility
+#     torch.manual_seed(1234)
+#
+#     # Load data
+#     train_data = pd.read_csv('../datasets/train.csv')
+#     test_data = pd.read_csv('../datasets/test.csv')
+#
+#     # Split data
+#     X_train = train_data.drop(columns=['id', 'diagnosis']).values
+#     y_train = train_data['diagnosis'].values
+#
+#     X_test = test_data.drop(columns=['id', 'diagnosis']).values
+#     y_test = test_data['diagnosis'].values
+#
+#     # Convert data to PyTorch tensors
+#     X_train = torch.FloatTensor(X_train)
+#     y_train = torch.FloatTensor(y_train).view(-1, 1)
+#
+#     X_test = torch.FloatTensor(X_test)
+#     y_test = torch.FloatTensor(y_test).view(-1, 1)
+#
+#     # Parameters
+#     input_size = X_train.shape[1]
+#     hidden_size = 128
+#
+#     # Learning parameters
+#     learning_rate = float(sys.argv[1]) if len(sys.argv) > 1 else 0.001
+#     weight_decay = float(sys.argv[2]) if len(sys.argv) > 2 else 0.001
+#     num_epochs = int(sys.argv[3]) if len(sys.argv) > 3 else 1000
+#
+#     # Log parameters to mlflow
+#     mlflow.log_param("hidden_size", hidden_size)
+#     mlflow.log_param("learning_rate", learning_rate)
+#     mlflow.log_param("weight_decay", weight_decay)
+#     mlflow.log_param("num_epochs", num_epochs)
+#
+#     # Model initialization
+#     model = NeuralNetwork(input_size, hidden_size)
+#
+#     # Loss function and optimizer
+#     criterion = nn.BCELoss()
+#     optimizer = optim.Adam(model.parameters(), lr=learning_rate, weight_decay=weight_decay)
+#
+#     # Training loop
+#     model.train()
+#
+#     for epoch in range(num_epochs):
+#         # Zero the gradients
+#         optimizer.zero_grad()
+#
+#         # Forward pass
+#         outputs = model(X_train)
+#
+#         # Compute loss
+#         loss = criterion(outputs, y_train)
+#
+#         # Backward pass
+#         loss.backward()
+#
+#         # Update weights
+#         optimizer.step()
+#
+#         # Print loss
+#         if (epoch + 1) % 100 == 0:
+#             print(f'Epoch [{epoch + 1}/{num_epochs}], Loss: {loss.item()}')
+#
+#     # Test the model
+#     model.eval()
+#
+#     with torch.no_grad():
+#
+#         # Make predictions
+#         y_pred = model(X_test)
+#         y_pred = np.where(y_pred > 0.5, 1, 0)
+#
+#         # Calculate metrics
+#         accuracy = accuracy_score(y_test, y_pred)
+#         precision = precision_score(y_test, y_pred)
+#         recall = recall_score(y_test, y_pred)
+#         f1 = f1_score(y_test, y_pred)
+#
+#         # Log metrics to mlflow
+#         mlflow.log_metric("accuracy", accuracy)
+#         mlflow.log_metric("precision", precision)
+#         mlflow.log_metric("recall", recall)
+#         mlflow.log_metric("f1", f1)
+#
+#     # If directory models does not exist, create it
+#     if not os.path.exists('./models'):
+#         os.makedirs('./models')
+#
+#     # Save the model
+#     torch.save(model, './models/model.pth')