ML engineering pipelines
Feature prep, batch inference, model-serving hooks, and production ML workflow glue.
How to Mock a Feature Store Online Lookup in Python
This code simulates an online feature store with single and batch retrieval methods, using a dict-backed cache and timestamps.
import random
import time
class OnlineFeatureStore:
def __init__(self):
self.features = {}
def put(self, entity_id: str, feature_name: str, value):
key = (entity_id, feature_name)
self.features[key] = (value, time.time())
def get(self, entity_id: str, feature_name: str):
…How to Mock a Kubeflow Pipeline in Python
Build a minimal in-memory mock of a Kubeflow pipeline DAG using dataclasses and OrderedDict to chain component functions.
from typing import Dict, Any
from dataclasses import dataclass, field
from collections import OrderedDict
@dataclass
class KubeflowPipelineMock:
"""A minimal mock of a Kubeflow pipeline DAG."""
name: str
components: OrderedDict[str, callable] = field(default_factory=OrderedDict)
def add_component(se…How to Mock train_test_split in Python for Unit Testing
Build a lightweight mock of sklearn's train_test_split to unit test ML pipeline code without needing the full library or deterministic random state.
import numpy as np
from sklearn.model_selection import train_test_split
from unittest.mock import patch
def mock_train_test_split(X, y, test_size=0.25, random_state=None, **kwargs):
"""A simple mock implementation of train_test_split."""
n_samples = len(X)
n_test = int(n_samples * test_size)
n_train =…How to Run Batch Predictions with a Mock Model in Python
Build a lightweight mock model class and run predictions across a batch of samples, returning results as a plain Python list.
import numpy as np
class MockModel:
def __init__(self, weights):
self.weights = np.array(weights)
def predict(self, X):
return X @ self.weights
def predict_batch(model, batch):
"""Run predictions for a batch of samples and return results as a list."""
return model.predict(np.array(ba…How to Save and Load a Mock Model with Pickle and joblib in Python
Serialize a custom machine learning model to a .joblib file with joblib.dump, reload it, and run a prediction with joblib.load.
import joblib
from pathlib import Path
class MockModel:
def __init__(self, weights):
self.weights = weights
def predict(self, features):
return sum(w * f for w, f in zip(self.weights, features))
def save_model_pickle(model, filepath):
with open(filepath, "wb") as f:
joblib.dump(…How to Simulate an Airflow ML Pipeline in Python
Mock an Airflow ML pipeline in plain Python by defining steps, simulating their execution with delays, and returning a success summary.
from datetime import datetime, timedelta
import time
class MLPipeline:
def __init__(self, pipeline_name):
self.pipeline_name = pipeline_name
self.steps = []
def add_step(self, step_name, duration_seconds):
self.steps.append({"name": step_name, "duration": duration_seconds})
def …How to Stage ML Model Workflows with Python Classes
Defines a Stage class to model ML pipeline stages with variants and mocks, printing grammar for Model, Staging, and Production stages.
class Stage:
def __init__(self, name):
self.name = name
self.mocks = []
self.variants = []
def add_mock(self, mock_name):
self.mocks.append(mock_name)
def add_variant(self, variant_name, productions=()):
self.variants.append((variant_name, list(productions)))
…How to Trigger Model Retraining on Drift in Python
Automatically detects accuracy drift in a mock ML model and triggers retraining when performance falls below a threshold.
import random
import time
class MockModel:
def __init__(self, name):
self.name = name
self.accuracy = 0.85
self.version = 1
def train(self, data_size):
# Simulate training time and accuracy improvement
time.sleep(0.1)
drift = random.uniform(-0.02, 0.02)
…How to implement a canary traffic split in Python
Route incoming traffic between stable and canary model or service versions using a weight-based random split with deterministic testing.
import random
def canary_route(service_name: str, canary_weight: float = 0.2) -> str:
"""Route traffic between stable and canary versions based on weight."""
rng = random.Random(42) # deterministic for reproducible demo
if rng.random() < canary_weight:
return f"{service_name}-canary"
return …How to mock an artifact store with local paths in Python for ML pipelines
Create a temporary local artifact store with dummy files and metadata to test ML pipeline code without real storage.
import tempfile
from pathlib import Path
import json
def create_artifact_store_mock(base_path: Path = None):
"""Create a local artifact store mock directory structure."""
if base_path is None:
base_path = Path(tempfile.mkdtemp())
store_layout = {
"artifacts": [
{"name": "mode…K-Fold Cross Validation in Python: A Simple Implementation
Implements k-fold cross validation from scratch, splitting data into folds and computing MSE scores for a baseline mean-predictor model.
import random
from statistics import mean
def cross_validation_scores(data, labels, k=5, seed=42):
random.seed(seed)
indices = list(range(len(data)))
random.shuffle(indices)
fold_size = len(indices) // k
folds = []
for i in range(k):
if i == k - 1:
folds.append(indices[i *…Load CSV Training Data Without Pandas in Python
This code loads a CSV file into a list of dictionaries using only the standard library, ideal for small ML training data without heavy dependencies.
import csv
from pathlib import Path
def load_csv(path):
"""Load CSV file into list of dicts without pandas."""
rows = []
with open(path, newline='', encoding='utf-8') as f:
reader = csv.DictReader(f)
for row in reader:
rows.append(dict(row))
return rows
if __name__ == "__m…Mock a Flyte ML workflow in Python
Build a lightweight mock of a Flyte ML pipeline with dataclasses and a simple execution loop that passes outputs between tasks.
from dataclasses import dataclass, field
from typing import List, Dict, Optional
import time
@dataclass
class FlyteTask:
name: str
inputs: Dict = field(default_factory=dict)
outputs: Dict = field(default_factory=dict)
def run(self) -> Dict:
time.sleep(0.1) # simulate work
return sel…Model registry version mock in Python
A simple in-memory model registry that stores model versions with metadata and supports version listing and latest retrieval.
class ModelRegistry:
def __init__(self):
self.models = {}
def register(self, name, version, model_type, metrics=None):
if name not in self.models:
self.models[name] = []
entry = {
"version": version,
"model_type": model_type,
"metrics": m…One Hot Encode Categories in Python
Convert a list of categorical strings into one-hot encoded numeric vectors using pure Python and NumPy.
import numpy as np
categories = ["red", "green", "blue", "red", "blue", "green", "red"]
unique = sorted(set(categories))
lookup = {cat: i for i, cat in enumerate(unique)}
one_hot = []
for cat in categories:
row = [0] * len(unique)
row[lookup[cat]] = 1
one_hot.append(row)
print("Categories:", categories…Training Pipeline Orchestration Mock DAG in Python
Build a mock DAG orchestrator that runs ML pipeline stages in dependency order using topological sorting (Kahn's algorithm).
from collections import deque
from dataclasses import dataclass, field
@dataclass
class DAGNode:
name: str
task: callable
dependencies: list[str] = field(default_factory=list)
class MockDAG:
def __init__(self, nodes: list[DAGNode]):
self.nodes = {n.name: n for n in nodes}
self.execu…Browse by section
Each section groups closely related Python snippets.
ML engineering pipelines — Python code examples
What you will find here
This page collects ml engineering pipelines snippets — short, copy-ready Python you can paste into our free online IDE and run without installing anything. Each sample includes a plain-English explanation and the full source code.
Samples vs tutorials and challenges
Samples are quick reference — one concept per page. For step-by-step teaching, use our Python tutorials. To test yourself, try quizzes or coding challenges. Clean up style with the Python formatter.