Python Code
Samples
Easy snippets you can copy, study, and run in the browser editor.
How to Chunk a Long Document for RAG Retrieval in Python
Split text into overlapping chunks at sentence boundaries using a custom Python function suitable for RAG retrieval pipelines.
import re
from pathlib import Path
def chunk_document(text, chunk_size=500, overlap=100):
"""Split text into overlapping chunks suitable for RAG retrieval."""
# Normalize whitespace
text = re.sub(r'\s+', ' ', text).strip()
chunks = []
start = 0
while start < len(text):
end = min(s…Create Mock Watermarked Image Bytes in Python Without PIL
Builds a mock image-like byte stream with an embedded watermark using only stdlib modules, for testing pipelines without PIL.
from io import BytesIO
import zlib
import struct
def create_watermarked_bytes(width: int, height: int, watermark: bytes) -> bytes:
"""Create a mock image-like byte stream with a watermark (no PIL)."""
header = struct.pack("<2I", width, height)
payload = watermark * max(1, (width * height // max(1, len(wa…Create Data Helper Functions in Python for Beginners
Build reusable Python helper functions to load, filter, sort, summarize, and save JSON data — a beginner-friendly starting point for small data pipelines.
import json
from pathlib import Path
from typing import Any, Dict, List
def load_json_file(filepath: str) -> Dict[str, Any]:
"""Load JSON data from a file."""
with Path(filepath).open("r", encoding="utf-8") as file:
return json.load(file)
def filter_by_key(
data: List[Dict[str, Any]], key: str,…Enrich Events with Geo IP Data in Python
Returns a copy of each event dictionary, enriched with a geo-location dict from a mock IP-to-geo lookup table, with a fallback for unknown IPs.
import ipaddress
GEO_IP_DB = {
"192.168.1.10": {"country": "US", "city": "New York", "lat": 40.7128, "lon": -74.0060},
"10.0.0.5": {"country": "DE", "city": "Berlin", "lat": 52.5200, "lon": 13.4050},
"172.16.0.8": {"country": "JP", "city": "Tokyo", "lat": 35.6762, "lon": 139.6503},
}
EVENTS = [
{"id…Fan Out Records to Multiple Sinks in Python
Distribute the same records across multiple target sinks (database, API, queue, etc.) using a defaultdict-based fan-out pattern.
import json
from collections import defaultdict
SINKS = ["database", "api", "message_queue", "data_lake", "monitoring"]
def fan_out(records, *sinks):
dist = defaultdict(list)
for record in records:
for sink in sinks:
dist[sink].append(record)
return dict(dist)
if __name__ == "__main_…Filter Records by Required Fields in Python
Filter a list of dictionaries, keeping only records where every required field is present and not None.
def filter_records(records, required_fields):
"""Return only records that have all required fields non-null."""
return [
record for record in records
if all(record.get(field) is not None for field in required_fields)
]
if __name__ == "__main__":
sample_records = [
{"name": "Al…Generate a Mock CDC Changelog in Python
Simulate a CDC changelog with INSERT, UPDATE, and DELETE operations, timestamps, and record snapshots for testing data pipelines.
import json
from datetime import datetime, timedelta
def generate_mock_changelog(records, operations=("INSERT", "UPDATE", "DELETE")):
"""Simulate a CDC changelog from a list of record snapshots."""
base_time = datetime(2025, 1, 1, 8, 0, 0)
changelog = []
for idx, record in enumerate(records):
…How to Clean and Format Data in Python
This code loads JSON data, cleans records by removing empty fields and normalizing text, then summarizes the results with counts and unique keys.
import json
from pathlib import Path
def load_data(filepath: str) -> dict:
"""Load JSON data from a file."""
with Path(filepath).open("r", encoding="utf-8") as f:
return json.load(f)
def clean_records(records: list[dict]) -> list[dict]:
"""Remove empty fields and normalize text to lowercase."""…How to Group Data by Key in Python
Group a list of dictionaries by a specified key using a defaultdict and compute per-group averages.
from collections import defaultdict
def group_by_key(data, key):
grouped = defaultdict(list)
for item in data:
grouped[item[key]].append(item)
return dict(grouped)
if __name__ == "__main__":
records = [
{"name": "Alice", "dept": "Engineering", "score": 85},
{"name": "Bob", "de…How to List Failed Records in a Dead Letter Queue Mock in Python
A mock Dead Letter Queue stores failed processing records with error details and timestamps, lists them, and exports to JSON.
import json
from datetime import datetime, timedelta
import random
class DeadLetterQueue:
def __init__(self):
self.failed_records = []
def add_failed_record(self, record_id, payload, error_message):
self.failed_records.append({
"record_id": record_id,
"payload": paylo…How to Merge Multiple Data Sources in Python
A beginner-friendly helper that merges lists of dictionaries from multiple sources into one combined list using key filtering.
import json
def merge_pipeline_data(*data_sources, keys=()):
"""Merge multiple data sources (list of dicts) into a single list of merged dicts.
Args:
*data_sources: One or more lists of dictionaries.
keys: Tuple of keys to include from each source (empty means all keys).
Returns:
…How to Sort a List of Dictionaries by Key in Python
A reusable helper function that sorts a list of dictionaries by a specified key, with optional descending order support.
from typing import List
def sort_records(records: List[dict], key: str, descending: bool = False) -> List[dict]:
"""Sort a list of dictionaries by a specified key."""
return sorted(records, key=lambda record: record[key], reverse=descending)
def demonstrate_sorting() -> None:
users = [
{"name": …How to Validate Data in a Python Pipeline
A helper module to validate common record types — email, positive integer, and non-empty string list — before processing data in a pipeline.
from typing import Any, Iterable
def is_valid_email(email: str) -> bool:
"""Basic email check: one '@', no spaces, dot after '@'."""
if "@" not in email or " " in email:
return False
local, _, domain = email.partition("@")
return bool(local) and "." in domain
def is_positive_int(value: Any)…How to create a dated snapshot path for a dataset in Python
Generate a versioned directory path combining a base directory, dataset name, and today's date, ready for creating snapshots in data pipelines.
import datetime
import os
from pathlib import Path
def snapshot_path(base_dir: str, dataset_name: str) -> Path:
"""Return a dated snapshot path for a dataset under a base directory."""
today = datetime.date.today().isoformat()
return Path(base_dir) / dataset_name / today
if __name__ == "__main__":
…How to route late-arriving data to a side output in Python
Separate late-arriving events from a streaming data batch into a dead-letter side output list using a timestamp threshold.
from collections import defaultdict
def late_arriving_side_output(events, late_threshold_ts):
"""
Mock a streaming pipeline that separates late-arriving data events
into a side output list (e.g., for dead-letter analysis).
events: list of (timestamp, data) tuples, timestamps as ints.
late_thresho…Idempotent Pipeline Dedupe by Record ID Set in Python
Filters records against a persistent set of seen IDs, returning only new ones and the updated set for idempotent pipeline processing.
def dedupe_records(records, seen_ids=None):
"""Return records whose id has not been seen before."""
if seen_ids is None:
seen_ids = set()
unique = []
for record in records:
record_id = record.get("id")
if record_id not in seen_ids:
seen_ids.add(record_id)
…Test a Python Pipeline with Fixture Sample Rows
Test pipeline functions with sample rows provided by a pytest fixture, verifying required keys and value constraints.
import pytest
def get_value(data: dict, key: str):
return data.get(key)
def sample_rows():
return [
{"name": "Alice", "age": 30, "city": "London"},
{"name": "Bob", "age": 25, "city": "Paris"},
{"name": "Charlie", "age": 35, "city": "Berlin"},
]
@pytest.fixture
def sample_data(…Dead Letter Queue Failed Messages List Mock in Python
Implements a simple in-memory dead letter queue to collect, list, and retry failed messages, with JSON serialization for inspection in streaming pipelines.
import json
from collections import deque
class Message:
def __init__(self, message_id, payload, attempts=0):
self.message_id = message_id
self.payload = payload
self.attempts = attempts
def __repr__(self):
return f"Message(id={self.message_id}, attempts={self.attempts})"
c…How to Build a Mock Change Data Capture Event Stream in Python
Generate a deterministic list of mock CDC events with event IDs, stream positions, payloads, and timestamps for testing streaming pipelines.
from itertools import count
from random import choice, randint, seed
from datetime import datetime, timedelta
seed(42) # Make output deterministic
event_types = ["INSERT", "UPDATE", "DELETE"]
table_names = ["users", "orders", "products", "payments"]
counter = count(1)
def mock_cdc_event(stream_index: int) -> dict:
…How to Truncate Lineage Back to a Checkpoint in Python
Walks a linked list of lineage nodes upward to find the nearest checkpoint and returns that node, truncating the lineage.
class LineageNode:
def __init__(self, name, parent=None, checkpoint=None):
self.name = name
self.parent = parent
self.checkpoint = checkpoint
def truncate_at_checkpoint(self):
"""Truncate lineage back to the last checkpoint."""
current = self
while current.check…Build a Data Helper Class in Python for ML Pipelines
A beginner-friendly Python class that summarizes, filters, and exports ML dataset rows as JSON.
from typing import List, Dict, Any
import json
class DataHelper:
"""Beginner-friendly helpers for ML data pipelines."""
def __init__(self, data: List[Dict[str, Any]]):
self.data = data
self.keys = list(data[0].keys()) if data else []
def summary(self) -> Dict[str, Any]:
"…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 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 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…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.