Big data & Spark
PySpark jobs, partitioning, batch processing, and large-dataset transform patterns.
Approximate Distinct Count in Python with HyperLogLog
Mock a large data stream and estimate the number of distinct items with a HyperLogLog-style probabilistic counter to save memory.
import random
import string
from collections import Counter
import math
class ApproxCountDistinct:
def __init__(self, num_buckets=16):
self.num_buckets = num_buckets
self.max_zeros = [0] * num_buckets
def _hash(self, item):
# Simple string hash to a 32-bit integer
h = …Bloom Filter Join Mock in Python
A mock hash join that uses a Bloom filter to pre-filter one table before performing an exact match, reducing the number of comparisons in large dataset joins.
import hashlib
import random
import string
class BloomFilter:
def __init__(self, size: int = 200, num_hashes: int = 3):
self.bits = [False] * size
self.size = size
self.num_hashes = num_hashes
def _hashes(self, item: str):
result = []
for seed in range(self.num_hashes…Delta Lake ACID Transaction Log Mock in Python
Simulates Delta Lake's transactional log with JSON files for atomic commits, versioned operations, and crash recovery
import json
import time
from pathlib import Path
class DeltaLog:
def __init__(self, path):
self.log_dir = Path(path)
self.log_dir.mkdir(parents=True, exist_ok=True)
self.version = 0
def _write_txn(self, action, payload):
txn = {
"version": self.version,
…How to Create a Mock Iceberg Snapshot Manifest in Python
Build a mock Iceberg snapshot manifest structure with metadata and data entries using Python dictionaries and JSON.
import json
from datetime import datetime, timezone
def create_mock_manifest(snapshot_id: int, file_paths: list[str]) -> dict:
"""Create a mock Iceberg snapshot manifest structure."""
manifest_file = {
"manifest_path": f"/warehouse/table/metadata/snap-{snapshot_id}-m0.avro",
"manifest_length"…How to Implement a Mock MapReduce for Word Count in Python
Simulates a MapReduce word count pipeline with mapper, shuffle, and reducer phases using Python dicts and standard library modules.
from collections import defaultdict
import re
def mapper(text):
"""Split text into words and emit (word, 1) pairs."""
words = re.findall(r'\b\w+\b', text.lower())
return [(word, 1) for word in words]
def reducer(pairs):
"""Group word-count pairs and sum counts."""
counts = defaultdict(int)
fo…How to Implement row_number Window Function in Python
This code implements a SQL-style ROW_NUMBER() window function in pure Python, partitioning rows by a set of columns and ranking them within each partition by an ordered set of columns.
from collections import defaultdict
import itertools
def row_number(rows, partition_by, order_by):
partitions = defaultdict(list)
for index, row in enumerate(rows):
key = tuple(row[col] for col in partition_by)
partitions[key].append((index, row))
result = []
for key in partitions:
…How to Mock a Catalyst Logical Plan in Python
Build a small Python class that mimics Spark Catalyst's logical plan tree for teaching or testing query optimizations.
from typing import Any, Dict, List, Optional
class CatalystLogicalPlan:
"""A minimal mock of Catalyst's logical plan for teaching purposes."""
def __init__(self, node_type: str, **kwargs: Any) -> None:
self.node_type = node_type
self.attributes: Dict[str, Any] = kwargs
self.child…How to Mock a Parquet partitionBy Sink in Python
Manually write a DataFrame to partitioned Parquet files, mimicking Spark's partitionBy sink behavior without Spark.
import pyarrow as pa
import pyarrow.parquet as pq
from pathlib import Path
import tempfile
import shutil
def mock_partition_by_sink(data, output_dir, partition_cols):
table = pa.Table.from_pandas(data)
schema = table.schema
unique_combos = table.select(partition_cols).to_pylist()
seen = set()
for…How to Simulate a MapReduce Mock with Combine Phase in Python
Simulates a MapReduce pipeline with a combiner that aggregates local counts per reducer to reduce network and compute overhead.
from collections import defaultdict
def map_phase(lines):
intermediate = defaultdict(list)
for line in lines:
for word in line.strip().lower().split():
intermediate[word].append(1)
return dict(intermediate)
def combine_phase(intermediate, num_reducers=3):
combined = defaultdict(li…Lazy Evaluation Transform Lineage Mock in Python
Build a mock lineage tracker for data transforms using lazy evaluation and function wrappers in Python.
import functools
def lazy_transform(pipeline):
"""Build a mock lineage tracker using lazy evaluation."""
lineage = []
def wrap(func):
@functools.wraps(func)
def wrapper(*args, **kwargs):
result = func(*args, **kwargs)
lineage.append({"transform": func.__name__, "a…Mock Predicate Pushdown in Python for Big Data Queries
Simulate predicate pushdown by applying filters at the storage layer before materializing rows, showing how big data engines optimize queries.
class Query:
def __init__(self, table, rows):
self.table = table
self.rows = rows
def filter(self, predicate):
return Query(
self.table,
[row for row in self.rows if all(predicate(row) for predicate in predicate)]
)
def filter_pushdown(self, predica…Mock RDD in Python: Simulate Spark RDD Lazy Transformations
Simulate Apache Spark RDD behavior in Python with lazy maps, filters, partitions, and a collect action.
import random
def mock_rdd(data, num_slices=2):
"""
A simple simulation of Spark RDD behavior with lazy evaluation,
transformations, and an action.
"""
class SimpleRDD:
def __init__(self, data, num_slices=2):
self.data = data
self.num_slices = num_slices
…Skew Join Salting Key in Python (Demo)
Demonstrates skew join salting by expanding a smaller side with salt keys and matching rows on the larger side via random salt assignment.
import random
def skew_join_salting_key(left_df, right_df, salt_range=4):
"""
Demonstrates skew join salting: expand the smaller side with salt keys,
then attach a salt key to each row on the larger side.
Returns a list of (left, right, salt) tuples.
"""
skewed_left = []
for row in left_d…Browse by section
Each section groups closely related Python snippets.
Big data & Spark — Python code examples
What you will find here
This page collects big data & spark 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.