ML engineering pipelines
Feature prep, batch inference, model-serving hooks, and production ML workflow glue.
Build a Mock Random Forest Classifier in Python
Create a simple random-forest-like classifier with random majority voting between trees, including fit, predict, and predict_proba methods.
import random
class MockRandomForest:
def __init__(self, n_trees=10, random_state=42):
self.n_trees = n_trees
self.random_state = random_state
self.classes_ = None
self._class_counts = None
random.seed(random_state)
def fit(self, X, y):
self.classes_ = sorted(…How to Build a Data Validation Schema in Python
Create a lightweight validation schema using dataclasses and lambda validators to check fields in a dictionary.
import re
from dataclasses import dataclass, field
from typing import Any, Callable
@dataclass
class Field:
name: str
validator: Callable[[Any], bool]
required: bool = True
def validate(self, value: Any) -> bool:
if not self.required and value is None:
return True
return …How to Build a Mock Offline Feature Store in Python
Build an in-memory mock of an offline feature store with a dict-based FeatureStore class for storing and retrieving ML features by entity ID.
from datetime import datetime
from collections import defaultdict
class FeatureStore:
"""Simple in-memory mock of an offline feature store."""
def __init__(self):
self._features = defaultdict(dict)
def ingest(self, entity_id, feature_name, value, timestamp=None):
ts = timestamp or datet…How to Compute a Confusion Matrix in Python
Compute a multi-class confusion matrix from true and predicted labels using pure Python dictionaries and nested lists, then format it for readable output.
from collections import defaultdict
def compute_confusion_matrix(y_true, y_pred, labels):
"""Compute confusion matrix using Python dicts and nested lists."""
label_index = {label: i for i, label in enumerate(labels)}
matrix = [[0] * len(labels) for _ in range(len(labels))]
for true, pred in zip(y…How to Define Dagster ML Assets in Python
Define a chain of Dagster software-defined assets that compute raw features, normalized features, and predictions for an ML pipeline.
from dagster import asset
@asset
def raw_features():
return {"sepal_length": [5.1, 4.9, 6.2], "sepal_width": [3.5, 3.0, 3.4]}
@asset
def normalized_features(raw_features):
values = raw_features["sepal_length"]
mean = sum(values) / len(values)
std = (sum((x - mean) ** 2 for x in values) / len(values…How to Load CSV Training Data in Python Without Pandas
Load CSV training data using Python's standard library and mock it with io.StringIO for testing, returning headers and rows as dictionaries.
import csv
from pathlib import Path
def load_csv_training_data(file_path: str | Path) -> tuple[list[str], list[dict[str, str]]]:
"""Load CSV training data and return headers plus rows as dictionaries."""
with open(file_path, mode="r", newline="", encoding="utf-8") as csv_file:
reader = csv.DictReader…How to Load, Save, and Split JSON Data in Python
Provides helper functions to load, save, and split JSON dictionary data for simple ML pipeline preprocessing.
import json
from pathlib import Path
def load_json_data(file_path):
"""Load JSON data from a file, returning an empty dict if missing."""
path = Path(file_path)
if path.exists():
with path.open("r", encoding="utf-8") as f:
return json.load(f)
return {}
def save_json_data(data, f…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 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 PyTorch Model State Dict in Python
This code demonstrates how to save a PyTorch model's state dict to a file and load it back into a new model instance, verifying weights match.
import torch
import torch.nn as nn
class SimpleNet(nn.Module):
def __init__(self):
super().__init__()
self.fc1 = nn.Linear(4, 8)
self.fc2 = nn.Linear(8, 2)
def forward(self, x):
x = torch.relu(self.fc1(x))
return self.fc2(x)
if __name__ == "__main__":
model = Simp…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(…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…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.