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 Build a DAG Execution Stage Calculator in Python
Computes the execution stages of a directed acyclic graph (DAG) by grouping nodes that become ready simultaneously using topological sorting with Kahn's algorithm.
from collections import defaultdict, deque
def get_stages(edges):
"""Return list of stages, where each stage is a list of nodes
that become ready at the same time in a DAG."""
graph = defaultdict(list)
in_degree = defaultdict(int)
nodes = set()
for src, dst in edges:
graph[src].appen…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 a Streaming Watermark in Python
Mock structured streaming watermarks in Python to track late event times and compute a watermark for windowed processing.
from datetime import datetime, timedelta
import time
class StreamingWatermark:
"""Mock watermark tracker for structured streaming."""
def __init__(self, watermark_delay_seconds):
self.watermark_delay = timedelta(seconds=watermark_delay_seconds)
self.max_event_time = None
def observe_even…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 Spark Streaming Micro-Batches in Python
Simulate Spark's micro-batch streaming with a simple deque-based class that collects events over time and processes them in timed batches.
import time
from collections import deque
from datetime import datetime
class MicroBatchStream:
def __init__(self, batch_interval_sec=2):
self.batch_interval = batch_interval_sec
self.source = deque()
self.processed = []
def add_events(self, events):
self.source.extend(events…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 UDAF Aggregate Function in Python
This code provides a minimal mock of a User-Defined Aggregate Function (UDAF), simulating the initialize-update-merge-finalize lifecycle with a defaultdict counter.
from collections import defaultdict
class MockUDAF:
"""A minimal mock of a User-Defined Aggregate Function.
Simulates aggregate lifecycle: initialize, update per row,
and finalize the result.
"""
def __init__(self):
self._buffer = defaultdict(int)
def initialize(self):
"""Re…How to Mock and Test a Rate-Limited Source Stream in Python
Build a class that rate-limits emitted items using a sliding window and test it with a simulated stream in Python.
import time
from collections import deque
class RateLimitedSource:
def __init__(self, max_rate, window=1.0):
self.max_rate = max_rate
self.window = window
self._timestamps = deque()
def emit(self, item):
now = time.monotonic()
while self._timestamps and self._timestam…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…How to implement a tumbling window aggregation in Python
Build a mock tumbling window aggregator in Python that groups streaming events into fixed time intervals and computes count, sum, and average per window.
import time
from collections import deque
class TumblingWindow:
def __init__(self, duration_seconds):
self.duration = duration_seconds
self.buffer = deque()
self.window_start = None
def add(self, item):
current_time = time.time()
if self.window_start is None:
…How to use foreachBatch with a mock sink in PySpark
Demonstrates using Spark Structured Streaming's foreachBatch sink to capture and verify streaming batches by writing them into a custom mock sink object.
from pyspark.sql import SparkSession
from pyspark.sql.functions import col, lit
class MockSink:
def __init__(self):
self.batches = []
def write_batch(self, batch_df, batch_id):
# Collect batch data as list of dicts for verification
records = batch_df.collect()
self.batches…HyperLogLog Cardinality Estimation in Python
A small HyperLogLog implementation using MD5 hashing and 256 registers to estimate the number of unique items in a large stream with fixed memory.
import hashlib
import math
class HyperLogLog:
def __init__(self, b=8):
self.b = b
self.m = 1 << b
self.registers = [0] * self.m
self.alpha = 0.7213 / (1 + 1.079 / self.m)
def add(self, item):
h = int(hashlib.md5(str(item).encode()).hexdigest(), 16)
idx = h & (s…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…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.