Spaces:
Sleeping
Sleeping
Download src/mlflow_tracking.py from vettri06/emailspamclassifier: direct link, hf CLI and curl.
- Browser
- Download file 4.5 kB
-
https://huggingface.co/spaces/vettri06/emailspamclassifier/resolve/main/src/mlflow_tracking.py
- Command line
-
hf download hf://spaces/vettri06/emailspamclassifier/src/mlflow_tracking.py
-
curl -L -o mlflow_tracking.py https://huggingface.co/spaces/vettri06/emailspamclassifier/resolve/main/src/mlflow_tracking.py
4.5 kB
| """ | |
| MLflow experiment tracking module: | |
| Handles run initialization, hyperparameter logging, multi-class evaluation metrics, | |
| confusion matrix artifacts, and model pipeline tracking. | |
| """ | |
| import os | |
| import mlflow | |
| import mlflow.sklearn | |
| from typing import Dict, Any | |
| EXPERIMENT_NAME = "Email_Threat_Classification_SOC" | |
| # Environment configuration | |
| os.environ["MLFLOW_ALLOW_FILE_STORE"] = "true" | |
| os.environ["MLFLOW_DISABLE_AGENT_HINT"] = "1" | |
| def setup_mlflow(tracking_dir: str = None) -> str: | |
| """ | |
| Configures MLflow tracking with an SQLite database backend and artifact store. | |
| """ | |
| if tracking_dir is None: | |
| tracking_dir = os.path.abspath(os.path.join(os.path.dirname(__file__), "..", "mlruns")) | |
| os.makedirs(tracking_dir, exist_ok=True) | |
| db_file = os.path.join(tracking_dir, "mlflow.db") | |
| db_path = db_file.replace("\\", "/") | |
| uri = f"sqlite:///{db_path}" | |
| # Ensure existing experiment and run artifact locations match the local environment | |
| if os.path.exists(db_file): | |
| try: | |
| import sqlite3 | |
| conn = sqlite3.connect(db_file) | |
| cur = conn.cursor() | |
| current_exp1_dir = os.path.join(tracking_dir, "1").replace("\\", "/") | |
| current_exp0_dir = os.path.join(tracking_dir, "0").replace("\\", "/") | |
| cur.execute("UPDATE experiments SET artifact_location = ? WHERE experiment_id IN ('1', 1)", (f"file:{current_exp1_dir}",)) | |
| cur.execute("UPDATE experiments SET artifact_location = ? WHERE experiment_id IN ('0', 0)", (f"file:{current_exp0_dir}",)) | |
| for row in cur.execute("SELECT run_uuid, artifact_uri FROM runs").fetchall(): | |
| r_uuid, art_uri = row | |
| if art_uri and "mlruns/1/" in art_uri: | |
| new_uri = f"file:{current_exp1_dir}/{r_uuid}/artifacts" | |
| cur.execute("UPDATE runs SET artifact_uri = ? WHERE run_uuid = ?", (new_uri, r_uuid)) | |
| conn.commit() | |
| conn.close() | |
| except Exception: | |
| pass | |
| mlflow.set_tracking_uri(uri) | |
| mlflow.set_experiment(EXPERIMENT_NAME) | |
| return uri | |
| def log_experiment_run( | |
| run_name: str, | |
| model_type: str, | |
| params: Dict[str, Any], | |
| metrics: Dict[str, float], | |
| artifacts: Dict[str, str] = None, | |
| pipeline=None, | |
| tags: Dict[str, str] = None | |
| ) -> str: | |
| """ | |
| Logs an atomic experiment run with parameters, metrics, figures, and models. | |
| """ | |
| with mlflow.start_run(run_name=run_name) as run: | |
| # Standard cyber defense tags | |
| default_tags = { | |
| "model_type": model_type, | |
| "domain": "Cybersecurity / Email Threat Intelligence", | |
| "framework": "scikit-learn / xgboost", | |
| "classes": "Legitimate, Spam, Suspicious" | |
| } | |
| if tags: | |
| default_tags.update(tags) | |
| mlflow.set_tags(default_tags) | |
| # Log parameters | |
| flat_params = {} | |
| for k, v in params.items(): | |
| flat_params[k] = str(v) | |
| flat_params["model_algorithm"] = model_type | |
| mlflow.log_params(flat_params) | |
| # Log metrics | |
| for metric_name, metric_val in metrics.items(): | |
| if isinstance(metric_val, (int, float)): | |
| mlflow.log_metric(metric_name, float(metric_val)) | |
| # Log artifact files (confusion matrix images, reports) | |
| if artifacts: | |
| for art_name, art_path in artifacts.items(): | |
| if os.path.exists(art_path): | |
| mlflow.log_artifact(art_path, artifact_path="evaluation_artifacts") | |
| # Log model pipeline artifact cleanly | |
| if pipeline is not None: | |
| try: | |
| import tempfile | |
| import joblib | |
| with tempfile.TemporaryDirectory() as tmp_dir: | |
| model_path = os.path.join(tmp_dir, "model_pipeline.joblib") | |
| joblib.dump(pipeline, model_path) | |
| mlflow.log_artifact(model_path, artifact_path="model_pipeline") | |
| except Exception as e: | |
| print(f"[Notice] Model artifact logging notice: {e}") | |
| run_id = run.info.run_id | |
| return run_id | |
| def get_experiment_summary() -> list: | |
| """ | |
| Retrieves summary table of all logged runs in the experiment. | |
| """ | |
| experiment = mlflow.get_experiment_by_name(EXPERIMENT_NAME) | |
| if not experiment: | |
| return [] | |
| runs = mlflow.search_runs(experiment_ids=[experiment.experiment_id]) | |
| return runs.to_dict(orient="records") | |