Python Code
Samples
Easy snippets you can copy, study, and run in the browser editor.
Compare Model A vs Model B Metrics in Python
A script that simulates and compares metrics between two ML models, showing a formatted diff table for quick insight.
import random
def compare_a_b(samples=5):
"""Mock comparison of model A vs model B predictions."""
metrics = ["accuracy", "precision", "recall", "f1"]
print(f"{'Metric':<12}{'Model A':>10}{'Model B':>10}{'Diff':>10}")
print("-" * 42)
random.seed(42)
for metric in metrics:
a = round(r…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 Build a Mock TFX Pipeline in Python
Simulate a TFX-style ML pipeline with simple Python functions to understand component orchestration, data flow, and artifact passing.
# Mock TFX pipeline to illustrate component orchestration
def CsvExampleGen(data_path):
"""Mock component: Simulates reading CSV data."""
print(f"ExampleGen: Reading from {data_path}")
return {"records": 100, "name": "examples"}
def StatisticsGen(example_artifact):
"""Mock component: Simulates genera…How to Build a Simple ML Pipeline with ZenML in Python
Build a mock machine learning pipeline with ZenML steps for data loading, training, and evaluation, and run it to print the final accuracy.
from zenml import pipeline, step
@step
def load_data() -> dict:
"""Simulate loading data from a source."""
return {"accuracy": 0.0, "loss": 1.0}
@step
def train_model(data: dict) -> dict:
"""Simulate training a model."""
data["accuracy"] = 0.95
data["loss"] = 0.1
return data
@step
def eva…How to Create a Mock Metaflow Flow in Python
Build a minimal Metaflow flow with two sequential steps that pass data between them using instance attributes.
from metaflow import FlowSpec, step, current
class MockFlow(FlowSpec):
"""A minimal Metaflow flow to demonstrate basic steps and branching."""
@step
def start(self):
self.category = "mock"
print(f"Start step for {self.category} flow")
self.next(self.process)
@step
def pr…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 Generate Experiment Tracking Run IDs in Python
Generate unique experiment run IDs with timestamps and random suffixes for tracking ML pipeline executions.
import random
import string
import time
def generate_run_id(prefix="exp"):
timestamp = time.strftime("%Y%m%d_%H%M%S")
suffix = "".join(random.choices(string.ascii_lowercase + string.digits, k=6))
return f"{prefix}_{timestamp}_{suffix}"
if __name__ == "__main__":
# Simulate tracking three experiment r…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 Shadow Mode Inference in Python
Simulates running multiple candidate models in shadow mode by adding randomized delays and returning their outputs alongside a primary model's output.
import random
import time
def shadow_mode_inference(candidates, mock_delay=0.1):
"""
Simulates running multiple candidate models in 'shadow mode'
by adding tiny randomized delays and returning their outputs
alongside the primary model's output.
"""
primary_output = "primary: answer"
shado…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 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 …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…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…Bonferroni Correction in Python
Applies the Bonferroni correction to a list of p-values to control the family-wise error rate when performing multiple comparisons.
import numpy as np
def bonferroni_correction(p_values, alpha=0.05):
"""Apply Bonferroni correction to a list of p-values."""
n = len(p_values)
corrected_alpha = alpha / n
significant = [p < corrected_alpha for p in p_values]
return corrected_alpha, significant
if __name__ == "__main__":
# Moc…How to Calculate Minimum Sample Size for a T-Test in Python
Compute the minimum sample size per group for a two-sample t-test using effect size, significance level, and statistical power.
import math
from scipy.stats import norm
def min_sample_size(effect_size, alpha=0.05, power=0.8):
"""
Calculate minimum sample size for a two-sample t-test (equal groups).
Args:
effect_size: Cohen's d (standardized mean difference)
alpha: significance level (Type I error)
power: …How to Create a Sticky Consistent Mock with unittest.mock in Python
Shows how to use unittest.mock.patch.object to mock a method consistently across multiple calls, returning a sticky value every time.
from unittest.mock import patch
class Database:
def fetch(self, key):
return f"real value for {key}"
def get_value(db, key):
return db.fetch(key)
if __name__ == "__main__":
db = Database()
with patch.object(db, "fetch", return_value="sticky value") as mock_fetch:
result1 = get_value(…How to Generate Multivariate JSON Mock Data in Python
This script generates mock multivariate JSON-compatible data with measurements and boolean flags for testing and experimentation pipelines.
import json
def multivariate_mock(row_count: int = 3) -> list:
"""Generate mock multivariate data as list of JSON-compatible dicts."""
records = []
for i in range(row_count):
record = {
"id": i + 1,
"measurements": {
"temperature": 20.5 + i * 1.5,
…How to Validate Data Before Scaling in Python
A reusable Python helper that validates required fields and constraint checks on data rows before entering a database pipeline, improving data quality and throughput.
def validate_data(data, required_fields, constraints=None):
"""
Basic validation helper demonstrating data-quality workflows
before scaling (catches bad rows early, improves throughput).
"""
constraints = constraints or {}
errors = []
for field in required_fields:
if field not in d…How to Check Negotiated Cipher Suite in Python
Connect to a TLS server with Python's ssl module and print the negotiated protocol version and cipher suite details.
import ssl
import socket
def get_cipher_suites(hostname, port=443):
context = ssl.create_default_context()
context.set_ciphers("DEFAULT:@SECLEVEL=2")
with socket.create_connection((hostname, port), timeout=5) as sock:
with context.wrap_socket(sock, server_hostname=hostname) as ssock:
…How to Generate PKCE Code Challenge in Python
This Python script generates a PKCE code verifier and its corresponding S256 code challenge for secure OAuth2 authorization flows.
import base64
import hashlib
import os
import secrets
import string
def generate_code_verifier(length=64):
alphabet = string.ascii_letters + string.digits + "-._~"
return "".join(secrets.choice(alphabet) for _ in range(length))
def generate_code_challenge(code_verifier, method="S256"):
if method == "S256…How to Build a Mock Trivy Image Scan Gate in Python
Simulate a Trivy image scan and enforce a security gate that fails the pipeline when vulnerabilities meet or exceed a severity threshold.
import json
import sys
def mock_trivy_scan(image_name, severity_threshold="HIGH"):
"""Simulate a Trivy image scan result."""
mock_vulnerabilities = [
{"ID": "CVE-2023-1234", "Severity": "HIGH", "Package": "openssl", "FixedVersion": "3.0.9"},
{"ID": "CVE-2024-5678", "Severity": "CRITICAL", "Pa…Browse by section
Each section groups closely related Python snippets.
Guide: free Python code samples library
Copy-ready Python snippets for learners and developers
PythonSkillset code samples are short, focused examples organised by topic and difficulty. Every snippet is server-rendered HTML — readable by search engines and easy to copy. Open any sample, read the notes, copy the code, then press Try in editor to run it in the browser with Pyodide.
How to use this library
- Pick a topic section — strings, lists, files, functions, and more
- Open a sample, read How it works, and copy the code block
- Run it in the IDE, tweak values, then take a related quiz or tutorial lesson
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.