Database scaling & optimization
Indexing, connection pooling, read replicas, query tuning, and throughput-aware SQL.
B-Tree Insert and In-Order Traversal in Python
Simulates a B-tree (order 2) with insert and split logic, then prints keys in sorted order via in-order traversal.
class BTreeNode:
def __init__(self, leaf=False):
self.leaf = leaf
self.keys = []
self.children = []
def is_full(self, t):
return len(self.keys) == 2 * t - 1
class BTree:
def __init__(self, t=2):
self.t = t
self.root = BTreeNode(leaf=True)
def insert(s…Build a Full Text Search Index in Python
Create a simple inverted index for full-text search with the standard library, supporting multi-word AND queries across documents.
import re
from collections import defaultdict
class SimpleTextIndex:
def __init__(self):
self.index = defaultdict(list)
self.documents = {}
def add_document(self, doc_id, text):
self.documents[doc_id] = text
words = set(re.findall(r'\w+', text.lower()))
for word in wo…Build a Partial Index Mock in Python for Database Filtering
Simulate a partial database index by filtering keys with a predicate, then return a limited mock lookup dictionary.
data = [
"alpha", "beta", "gamma", "delta", "epsilon",
"zeta", "eta", "theta", "iota", "kappa"
]
filtered_keys = [item for item in data if len(item) >= 5]
def mock_partial_index(keys, filter_func, limit=3):
result = {}
for key in keys:
if not filter_func(key):
continue
res…Composite index leftmost prefix in Python
Simulate a composite index in SQLite and check whether query columns match the leftmost prefix rule for index usage.
import sqlite3
def get_indexed_columns(table_name):
"""Simulate a composite index by reading column names that start with 'idx_'."""
conn = sqlite3.connect(":memory:")
conn.execute(f"CREATE TABLE {table_name} (id INTEGER, idx_col1 TEXT, idx_col2 INTEGER, other TEXT)")
conn.execute(f"CREATE INDEX idx_…Database Helper in Python with SQLite Scaling Optimization
Build a beginner-friendly SQLite database helper class with WAL, indexed queries, and efficient batch inserts for scaling.
import sqlite3
from contextlib import contextmanager
class DatabaseHelper:
"""Beginner-friendly helper for SQLite database operations with scaling tips."""
def __init__(self, db_path):
self.db_path = db_path
@contextmanager
def connection(self):
"""Context manager for automatic comm…Database indexing and query timing optimization in Python
Create SQLite indexes and time query performance to measure speedup for large table lookups in Python.
import sqlite3
import time
def time_query(db_path, query, params=()):
conn = sqlite3.connect(db_path)
conn.execute("PRAGMA journal_mode = WAL")
start = time.perf_counter()
result = conn.execute(query, params).fetchall()
elapsed = time.perf_counter() - start
conn.close()
return result, ela…Hash index equality mock concept in Python
A simple hash index class in Python that stores key-value pairs in buckets and demonstrates basic equality-based lookup.
class HashIndex:
def __init__(self):
self._buckets = {}
def insert(self, key, value):
"""Insert a key-value pair into the hash index."""
index = hash(key) % 10
if index not in self._buckets:
self._buckets[index] = []
self._buckets[index].append((key, value))…How to Create a Covering Index with INCLUDE Columns in Python
Create a covering index with INCLUDE columns in SQLite from Python and inspect the query plan to confirm the index covers the query.
import sqlite3
def create_covering_index_mock():
conn = sqlite3.connect(":memory:")
cursor = conn.cursor()
cursor.execute("""
CREATE TABLE employees (
id INTEGER PRIMARY KEY,
name TEXT,
department TEXT,
salary INTEGER
)
""")
employe…How to Create a Database Helper Class for Beginners in Python
Build a beginner-friendly SQLite helper class with indexing and batch inserts to optimize database queries in Python.
import sqlite3
class DatabaseHelper:
def __init__(self, db_path):
self.connection = sqlite3.connect(db_path)
self.cursor = self.connection.cursor()
def create_table_with_index(self, table_name, columns, indexed_column):
columns_sql = ", ".join(f"{name} {dtype}" for name, dtype in col…How to Explain SQLite Query Plans in Python
Build a Python function that runs EXPLAIN QUERY PLAN on SQLite in-memory tables and prints the optimizer's execution plan for any SELECT statement.
import sqlite3
def explain_query(sql: str) -> str:
"""Return the SQLite query plan for the given SQL statement."""
conn = sqlite3.connect(":memory:")
cursor = conn.cursor()
# Create sample data for a realistic plan
cursor.execute("CREATE TABLE users (id INTEGER PRIMARY KEY, name TEXT)")
c…How to Optimize SQLite Database Performance in Python
A Python helper that creates an index, enables WAL mode, and tunes synchronous settings to optimize SQLite database performance.
import sqlite3
DATABASE_PATH = "beginners.db"
UNOPTIMIZED_TABLE_SCHEMA = """
CREATE TABLE IF NOT EXISTS users (
id INTEGER PRIMARY KEY,
name TEXT NOT NULL,
email TEXT NOT NULL
)
"""
def optimize_database(db_path: str = DATABASE_PATH) -> dict:
with sqlite3.connect(db_path) as connection:
curs…How to Shard Data by User ID Hash in Python
Deterministically map user IDs to shard indexes using an MD5 hash modulo the shard count in Python.
import hashlib
def shard_id(user_id: str, num_shards: int = 4) -> int:
"""Deterministically map a user_id to a shard index using MD5."""
digest = hashlib.md5(user_id.encode("utf-8")).hexdigest()
return int(digest[:8], 16) % num_shards
if __name__ == "__main__":
user_ids = ["alice", "bob", "carol", "d…How to Speed Up Column Lookups with DataFrame Index in Python
Use pandas set_index to make repeated column value lookups O(1)-style fast instead of scanning the whole DataFrame each time.
import pandas as pd
# Mock dataset with duplicate customer IDs
data = {"customer_id": [101, 102, 103, 101, 104, 102],
"order_amount": [250.0, 85.5, 300.0, 175.25, 420.0, 95.75]}
df = pd.DataFrame(data)
df = df.set_index("customer_id")
# Simulated lookup request
search_id = 102
# Fast index-based lookup (no…How to enforce a unique index constraint in Python
Mock a database unique index in Python that rejects duplicate rows based on one or more columns.
class MockIndex:
def __init__(self, columns):
self.columns = columns
self._values = set()
def insert(self, row):
key = tuple(row[col] for col in self.columns)
if key in self._values:
raise ValueError(f"Duplicate key {key} for columns {self.columns}")
self._v…Monitor Database Index Bloat in Python
Simulates index bloat checks for database tables using random ratio thresholds and reports alerts per index.
import random
import time
class IndexBloatMonitor:
def __init__(self, thresholds=(0.5, 0.8, 0.9)):
self.thresholds = thresholds
self.indices = {
"users_pk": 48.2,
"orders_created_idx": 124.7,
"products_name_idx": 15.3,
"payments_user_idx": 203.9,
…Simulate a GIN Index for JSONB in Python
Build a mock Generalized Inverted Index (GIN) that flattens JSON documents into key-value tokens for fast lookup queries, mimicking PostgreSQL JSONB indexing.
import json
import random
from collections import defaultdict
# Mock GIN (Generalized Inverted Index) for JSONB key-value pairs
class GINIndex:
def __init__(self):
self.posting_lists = defaultdict(list) # token -> list of doc_ids
def index(self, doc_id, json_obj):
"""Index a JSON documen…Snowflake ID Generator with Cluster Index Mock in Python
A thread-safe Snowflake ID generator mock that creates unique 64-bit IDs across simulated cluster nodes and maintains a sorted in-memory index for range queries.
import time
import threading
class SnowflakeIDGenerator:
def __init__(self, machine_id, datacenter_id):
self.machine_id = machine_id
self.datacenter_id = datacenter_id
self.sequence = 0
self.last_timestamp = -1
self.machine_bits = 5
self.datacenter_bits = 5
…Browse by section
Each section groups closely related Python snippets.
Database scaling & optimization — Python code examples
What you will find here
This page collects database scaling & optimization 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.