Editing AI Infrastructure and MLOps (section)

== <span style="color: #FFFFFF;">Applying</span> ==
'''End-to-end ML pipeline with MLflow and FastAPI:'''

<syntaxhighlight lang="python">
import mlflow
import mlflow.sklearn
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.metrics import accuracy_score, roc_auc_score
from sklearn.model_selection import train_test_split
import pandas as pd

# === EXPERIMENT TRACKING ===
mlflow.set_experiment("customer-churn-prediction")

with mlflow.start_run(run_name="GBM-v3"):
    # Log parameters
    params = {"n_estimators": 200, "max_depth": 5, "learning_rate": 0.1}
    mlflow.log_params(params)

    # Train model
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
    model = GradientBoostingClassifier(**params)
    model.fit(X_train, y_train)

    # Log metrics
    y_pred = model.predict(X_test)
    y_prob = model.predict_proba(X_test)[:, 1]
    mlflow.log_metric("accuracy", accuracy_score(y_test, y_pred))
    mlflow.log_metric("roc_auc", roc_auc_score(y_test, y_prob))

    # Log model artifact
    mlflow.sklearn.log_model(model, "model",
                              registered_model_name="churn-predictor")
    print(f"Run ID: {mlflow.active_run().info.run_id}")

# === MODEL SERVING with FastAPI ===
from fastapi import FastAPI
import mlflow.pyfunc

app = FastAPI()
model = mlflow.pyfunc.load_model("models:/churn-predictor/Production")

@app.post("/predict")
async def predict(features: dict):
    df = pd.DataFrame([features])
    prediction = model.predict(df)
    return {"churn_probability": float(prediction[0]),
            "will_churn": bool(prediction[0] > 0.5)}
</syntaxhighlight>

; MLOps tool ecosystem
: '''Experiment tracking''' → MLflow, Weights & Biases, Neptune, CometML
: '''Pipeline orchestration''' → Apache Airflow, Prefect, Kubeflow Pipelines, ZenML
: '''Feature store''' → Feast, Tecton, Hopsworks, Databricks Feature Store
: '''Model registry''' → MLflow Model Registry, Hugging Face Hub, W&B Model Registry
: '''Model serving (traditional)''' → BentoML, Seldon, TorchServe, MLflow Serving
: '''LLM serving''' → vLLM, Text Generation Inference (TGI), Triton Inference Server
: '''Monitoring''' → Evidently AI, WhyLabs, Arize, Fiddler
: '''GPU training infrastructure''' → SLURM + GPUs, AWS SageMaker, Azure ML, Google Vertex AI
</div>

<div style="background-color: #8B4500; color: #FFFFFF; padding: 20px; border-radius: 8px; margin-bottom: 15px;">