Big data & Spark
PySpark jobs, partitioning, batch processing, and large-dataset transform patterns.
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 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 Compute-Collect Action Trigger in Python
Mock a compute-collect action trigger using Python's unittest.mock to simulate Spark-style job execution and assert trigger behavior.
Here's a Python code sample for the problem title "Action trigger compute collect mock":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 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 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:
…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…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
…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.