secrets and mlflow should now work

.gitea/workflows/mlops-pipeline.yml

@@ -11,22 +11,27 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v3
-      
+
       - name: Setup Python
         uses: actions/setup-python@v4
         with:
           python-version: '3.12'
-      
+
       - name: Install dependencies
         run: |
           pip install poetry
           poetry install
-      
+
+      - name: Setup DVC
+        run: |
+          poetry run dvc remote list
+          poetry run dvc pull || echo "DVC pull failed, continuing..."
+
       - name: Start API server
         run: |
           poetry run uvicorn src.api.main:app --host 0.0.0.0 --port 8000 &
           sleep 10
-      
+
       - name: Run unit tests
         run: poetry run pytest tests/ --cov=src --cov-report=xml
 
@@ -36,41 +41,49 @@ jobs:
     if: github.ref == 'refs/heads/main'
     steps:
       - uses: actions/checkout@v3
-      
+
       - name: Setup Python
         uses: actions/setup-python@v4
         with:
           python-version: '3.12'
-      
+
       - name: Install dependencies
         run: |
           pip install poetry
           poetry install
-      
+
       - name: Setup DVC
-        run: poetry run dvc pull
+        run: |
-      
+          poetry run dvc remote list
-      - name: Train model
+          poetry run dvc pull || echo "DVC pull failed, continuing..."
-        run: poetry run python src/models/train.py
+
+      - name: Run DVC pipeline
+        run: poetry run dvc repro
         env:
-          MLFLOW_TRACKING_URI: ${{ secrets.MLFLOW_URI }}
+          MLFLOW_TRACKING_URI: ${{ secrets.MLFLOW_TRACKING_URI }}
-          MLFLOW_TRACKING_USERNAME: ${{ secrets.CSGO }}
+          MLFLOW_TRACKING_USERNAME: ${{ secrets.MLFLOW_TRACKING_USERNAME }}
-          MLFLOW_TRACKING_PASSWORD: ${{ secrets.MLOPSEPITALYON }}
+          MLFLOW_TRACKING_PASSWORD: ${{ secrets.MLFLOW_TRACKING_PASSWORD }}
+
+      - name: Push DVC changes
+        run: |
+          poetry run dvc push || echo "DVC push failed, continuing..."
 
   deploy:
     needs: train
     runs-on: ubuntu-latest
     if: github.ref == 'refs/heads/main'
     steps:
+      - uses: actions/checkout@v3
+
       - name: Build Docker image
         run: |
           docker build -t csgo-mlops:${{ github.sha }} .
           docker tag csgo-mlops:${{ github.sha }} csgo-mlops:latest
-      
+
       - name: Push to registry
         run: |
           docker push csgo-mlops:${{ github.sha }}
           docker push csgo-mlops:latest
-      
+
       - name: Deploy to Kubernetes
-        run: kubectl apply -f kubernetes/deployment.yml
+        run: kubectl apply -f kubernetes/deployment.yml

models/metrics.json

@@ -0,0 +1,7 @@
+{
+  "accuracy": 1.0,
+  "precision": 1.0,
+  "recall": 1.0,
+  "f1_score": 1.0,
+  "roc_auc": 1.0
+}

pyproject.toml

@@ -21,7 +21,8 @@ dependencies = [
     "pytest (>=7.0.0,<8.0.0)",
     "pytest-cov (>=4.0.0,<5.0.0)",
     "uvicorn (>=0.24.0,<1.0.0)",
-    "pandas (>=2.0.0,<3.0.0)"
+    "pandas (>=2.0.0,<3.0.0)",
+    "pyyaml (>=6.0.0,<7.0.0)"
 ]
 
 

src/models/train.py

@@ -7,14 +7,23 @@ import mlflow.sklearn
 import yaml
 import json
 import pickle
+import os
 from pathlib import Path
 from sklearn.ensemble import RandomForestClassifier
 from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, roc_auc_score
 import pandas as pd
 
 # Configure MLflow
-mlflow.set_tracking_uri("https://mlflow.sortifal.dev")
+mlflow.set_tracking_uri(os.getenv("MLFLOW_TRACKING_URI", "https://mlflow.sortifal.dev"))
-mlflow.set_experiment("csgo-match-prediction")
+
+# Try to set experiment, but handle auth errors gracefully
+USE_MLFLOW = True
+try:
+    mlflow.set_experiment("csgo-match-prediction")
+except Exception as e:
+    print(f"Warning: Could not connect to MLflow: {e}")
+    print("Training will continue without MLflow tracking.")
+    USE_MLFLOW = False
 
 def load_params():
     """Load training parameters from params.yaml"""
@@ -92,38 +101,64 @@ def main():
     print(f"  Test samples: {len(X_test)}")
     print(f"  Features: {X_train.shape[1]}")
 
-    # Start MLflow run
+    if USE_MLFLOW:
-    with mlflow.start_run(run_name="random-forest-csgo"):
+        # Start MLflow run
-        # Log parameters
+        with mlflow.start_run(run_name="random-forest-csgo"):
-        mlflow.log_params(params)
+            # Log parameters
-        mlflow.log_param("n_features", X_train.shape[1])
+            mlflow.log_params(params)
-        mlflow.log_param("n_train_samples", len(X_train))
+            mlflow.log_param("n_features", X_train.shape[1])
-        mlflow.log_param("n_test_samples", len(X_test))
+            mlflow.log_param("n_train_samples", len(X_train))
+            mlflow.log_param("n_test_samples", len(X_test))
 
-        # Train model
+            # Train model
+            model = train_model(X_train, y_train, params)
+
+            # Evaluate model
+            metrics = evaluate_model(model, X_test, y_test)
+
+            # Log metrics to MLflow
+            mlflow.log_metrics(metrics)
+
+            # Log feature importance
+            feature_importance = dict(zip(X_train.columns, model.feature_importances_))
+            top_features = sorted(feature_importance.items(), key=lambda x: x[1], reverse=True)[:5]
+            print("\nTop 5 most important features:")
+            for feat, importance in top_features:
+                print(f"  {feat}: {importance:.4f}")
+                mlflow.log_metric(f"importance_{feat}", importance)
+
+            # Try to log model to MLflow (if permissions allow)
+            try:
+                mlflow.sklearn.log_model(model, "model")
+                print("\nModel logged to MLflow successfully!")
+            except Exception as e:
+                print(f"\nWarning: Could not log model to MLflow: {e}")
+                print("Model will only be saved locally.")
+
+            # Save model and metrics locally
+            save_model(model, metrics)
+
+            # Print results
+            print("\n" + "=" * 60)
+            print("Training Results:")
+            print("=" * 60)
+            for metric, value in metrics.items():
+                print(f"  {metric}: {value:.4f}")
+            print("=" * 60)
+
+            print(f"\nMLflow run ID: {mlflow.active_run().info.run_id}")
+            print(f"View run at: {mlflow.get_tracking_uri()}")
+    else:
+        # Train without MLflow
         model = train_model(X_train, y_train, params)
-
-        # Evaluate model
         metrics = evaluate_model(model, X_test, y_test)
 
-        # Log metrics to MLflow
-        mlflow.log_metrics(metrics)
-
         # Log feature importance
         feature_importance = dict(zip(X_train.columns, model.feature_importances_))
         top_features = sorted(feature_importance.items(), key=lambda x: x[1], reverse=True)[:5]
         print("\nTop 5 most important features:")
         for feat, importance in top_features:
             print(f"  {feat}: {importance:.4f}")
-            mlflow.log_metric(f"importance_{feat}", importance)
-
-        # Try to log model to MLflow (if permissions allow)
-        try:
-            mlflow.sklearn.log_model(model, "model")
-            print("\nModel logged to MLflow successfully!")
-        except Exception as e:
-            print(f"\nWarning: Could not log model to MLflow: {e}")
-            print("Model will only be saved locally.")
 
         # Save model and metrics locally
         save_model(model, metrics)
@@ -136,9 +171,6 @@ def main():
             print(f"  {metric}: {value:.4f}")
         print("=" * 60)
 
-        print(f"\nMLflow run ID: {mlflow.active_run().info.run_id}")
-        print(f"View run at: {mlflow.get_tracking_uri()}")
-
     print("\nTraining pipeline completed successfully!")
 
 if __name__ == "__main__":